LLM/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2026-05-13 21:41:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: LLM:1.6.1
Branches Tags
LLM:master LLM:release/1.x LLM:v2/add-live-voice-chat LLM:debanjum/miscellaneous-v2-changes LLM:use-user-specified-chat-model-for-intermediate-steps LLM:pr/hjamet/1109 LLM:create-data-tracer LLM:evals/tmp-distill-trains-of-thought LLM:load-web-app-from-desktop-app LLM:use-structured-index-to-improve-kb-retrieval LLM:speed-up-khoj-docker-builds LLM:features/support-sqlite-as-db LLM:regenerate-edit-messages-on-web-app LLM:improve-agents-pane-on-home-screen LLM:use-turnstyle-ux-for-khoj-chat LLM:improve-doc-chunking-and-support-timely-embedings LLM:speed-up-embedding-model-app-load-when-not-connected-to-internet LLM:panchayat
LLM:2.0.0-beta.28 LLM:2.0.0-beta.27 LLM:2.0.0-beta.26 LLM:2.0.0-beta.25 LLM:2.0.0-beta.24 LLM:2.0.0-beta.23 LLM:2.0.0-beta.22 LLM:2.0.0-beta.21 LLM:2.0.0-beta.20 LLM:2.0.0-beta.19 LLM:2.0.0-beta.18 LLM:2.0.0-beta.17 LLM:2.0.0-beta.16 LLM:2.0.0-beta.15 LLM:2.0.0-beta.14 LLM:2.0.0-beta.13 LLM:2.0.0-beta.12 LLM:2.0.0-beta.11 LLM:2.0.0-beta.10 LLM:2.0.0-beta.9 LLM:2.0.0-beta.8 LLM:1.42.10 LLM:2.0.0-beta.7 LLM:2.0.0-beta.6 LLM:2.0.0-beta.5 LLM:2.0.0-beta.4 LLM:2.0.0-beta.3 LLM:2.0.0-beta.2 LLM:2.0.0-beta.1 LLM:1.42.9 LLM:1.42.8 LLM:1.42.7 LLM:1.42.6 LLM:1.42.5 LLM:1.42.4 LLM:1.42.3 LLM:1.42.2 LLM:1.42.1 LLM:1.42.0 LLM:1.41.0 LLM:1.40.0 LLM:1.39.0 LLM:1.38.0 LLM:1.37.2 LLM:1.37.1 LLM:1.37.0 LLM:1.36.6 LLM:1.36.5 LLM:1.36.4 LLM:1.36.3 LLM:1.36.2 LLM:1.36.1 LLM:1.36.0 LLM:1.35.3 LLM:1.35.2 LLM:1.35.1 LLM:1.35.0 LLM:1.34.0 LLM:1.33.2 LLM:1.33.1 LLM:1.33.0 LLM:1.32.2 LLM:1.32.1 LLM:1.32.0 LLM:1.31.0 LLM:1.30.10 LLM:1.30.9 LLM:1.30.8 LLM:1.30.7 LLM:1.30.6 LLM:1.30.5 LLM:1.30.4 LLM:1.30.3 LLM:1.30.2 LLM:1.30.1 LLM:1.30.0 LLM:1.29.1 LLM:1.29.0 LLM:1.28.3 LLM:1.28.2 LLM:1.28.1 LLM:1.28.0 LLM:1.27.1 LLM:1.27.0 LLM:1.26.4 LLM:1.26.3 LLM:1.26.2 LLM:1.26.1 LLM:1.26.0 LLM:1.25.0 LLM:1.24.1 LLM:1.24.0 LLM:1.23.3 LLM:1.23.2 LLM:1.23.1 LLM:1.23.0 LLM:1.22.3 LLM:1.22.2 LLM:1.22.1 LLM:1.22.0 LLM:1.21.6 LLM:1.21.5 LLM:1.21.4 LLM:1.21.3 LLM:1.21.2 LLM:1.21.1 LLM:1.21.0 LLM:1.20.4 LLM:1.20.3 LLM:1.20.2 LLM:1.20.1 LLM:1.20.0 LLM:1.17.0 LLM:1.16.0 LLM:1.15.0 LLM:1.14.0 LLM:1.13.0 LLM:1.12.1 LLM:1.12.0 LLM:1.11.2 LLM:1.11.1 LLM:1.11.0 LLM:1.10.2 LLM:1.10.1 LLM:1.10.0 LLM:1.9.0 LLM:1.8.0 LLM:1.7.0 LLM:1.6.2 LLM:1.6.1 LLM:1.6.0 LLM:1.5.1 LLM:1.5.0 LLM:1.4.0 LLM:1.3.0 LLM:1.2.1 LLM:1.2.0 LLM:1.1.0 LLM:1.0.1 LLM:1.0.0 LLM:0.14.0 LLM:0.13.0 LLM:0.12.3 LLM:0.12.2 LLM:0.12.1 LLM:rm LLM:0.12.0 LLM:0.11.4 LLM:0.11.3 LLM:0.11.2 LLM:0.11.1 LLM:0.11.0 LLM:0.10.1 LLM:0.10.0 LLM:0.9.0 LLM:0.8.2 LLM:0.8.1 LLM:0.8.0 LLM:0.7.1 LLM:0.7.0 LLM:0.6.2 LLM:0.6.1 LLM:0.6.0 LLM:0.5.0 LLM:0.4.0 LLM:0.3.0 LLM:0.2.6 LLM:0.2.5 LLM:0.2.1 LLM:v0.2.0 LLM:v0.1.9 LLM:v0.1.8 LLM:v0.1.7 LLM:v0.1.6 LLM:v0.1.5-alpha
...
compare: LLM:1.33.1
Branches Tags
LLM:master LLM:release/1.x LLM:v2/add-live-voice-chat LLM:debanjum/miscellaneous-v2-changes LLM:use-user-specified-chat-model-for-intermediate-steps LLM:pr/hjamet/1109 LLM:create-data-tracer LLM:evals/tmp-distill-trains-of-thought LLM:load-web-app-from-desktop-app LLM:use-structured-index-to-improve-kb-retrieval LLM:speed-up-khoj-docker-builds LLM:features/support-sqlite-as-db LLM:regenerate-edit-messages-on-web-app LLM:improve-agents-pane-on-home-screen LLM:use-turnstyle-ux-for-khoj-chat LLM:improve-doc-chunking-and-support-timely-embedings LLM:speed-up-embedding-model-app-load-when-not-connected-to-internet LLM:panchayat
LLM:2.0.0-beta.28 LLM:2.0.0-beta.27 LLM:2.0.0-beta.26 LLM:2.0.0-beta.25 LLM:2.0.0-beta.24 LLM:2.0.0-beta.23 LLM:2.0.0-beta.22 LLM:2.0.0-beta.21 LLM:2.0.0-beta.20 LLM:2.0.0-beta.19 LLM:2.0.0-beta.18 LLM:2.0.0-beta.17 LLM:2.0.0-beta.16 LLM:2.0.0-beta.15 LLM:2.0.0-beta.14 LLM:2.0.0-beta.13 LLM:2.0.0-beta.12 LLM:2.0.0-beta.11 LLM:2.0.0-beta.10 LLM:2.0.0-beta.9 LLM:2.0.0-beta.8 LLM:1.42.10 LLM:2.0.0-beta.7 LLM:2.0.0-beta.6 LLM:2.0.0-beta.5 LLM:2.0.0-beta.4 LLM:2.0.0-beta.3 LLM:2.0.0-beta.2 LLM:2.0.0-beta.1 LLM:1.42.9 LLM:1.42.8 LLM:1.42.7 LLM:1.42.6 LLM:1.42.5 LLM:1.42.4 LLM:1.42.3 LLM:1.42.2 LLM:1.42.1 LLM:1.42.0 LLM:1.41.0 LLM:1.40.0 LLM:1.39.0 LLM:1.38.0 LLM:1.37.2 LLM:1.37.1 LLM:1.37.0 LLM:1.36.6 LLM:1.36.5 LLM:1.36.4 LLM:1.36.3 LLM:1.36.2 LLM:1.36.1 LLM:1.36.0 LLM:1.35.3 LLM:1.35.2 LLM:1.35.1 LLM:1.35.0 LLM:1.34.0 LLM:1.33.2 LLM:1.33.1 LLM:1.33.0 LLM:1.32.2 LLM:1.32.1 LLM:1.32.0 LLM:1.31.0 LLM:1.30.10 LLM:1.30.9 LLM:1.30.8 LLM:1.30.7 LLM:1.30.6 LLM:1.30.5 LLM:1.30.4 LLM:1.30.3 LLM:1.30.2 LLM:1.30.1 LLM:1.30.0 LLM:1.29.1 LLM:1.29.0 LLM:1.28.3 LLM:1.28.2 LLM:1.28.1 LLM:1.28.0 LLM:1.27.1 LLM:1.27.0 LLM:1.26.4 LLM:1.26.3 LLM:1.26.2 LLM:1.26.1 LLM:1.26.0 LLM:1.25.0 LLM:1.24.1 LLM:1.24.0 LLM:1.23.3 LLM:1.23.2 LLM:1.23.1 LLM:1.23.0 LLM:1.22.3 LLM:1.22.2 LLM:1.22.1 LLM:1.22.0 LLM:1.21.6 LLM:1.21.5 LLM:1.21.4 LLM:1.21.3 LLM:1.21.2 LLM:1.21.1 LLM:1.21.0 LLM:1.20.4 LLM:1.20.3 LLM:1.20.2 LLM:1.20.1 LLM:1.20.0 LLM:1.17.0 LLM:1.16.0 LLM:1.15.0 LLM:1.14.0 LLM:1.13.0 LLM:1.12.1 LLM:1.12.0 LLM:1.11.2 LLM:1.11.1 LLM:1.11.0 LLM:1.10.2 LLM:1.10.1 LLM:1.10.0 LLM:1.9.0 LLM:1.8.0 LLM:1.7.0 LLM:1.6.2 LLM:1.6.1 LLM:1.6.0 LLM:1.5.1 LLM:1.5.0 LLM:1.4.0 LLM:1.3.0 LLM:1.2.1 LLM:1.2.0 LLM:1.1.0 LLM:1.0.1 LLM:1.0.0 LLM:0.14.0 LLM:0.13.0 LLM:0.12.3 LLM:0.12.2 LLM:0.12.1 LLM:rm LLM:0.12.0 LLM:0.11.4 LLM:0.11.3 LLM:0.11.2 LLM:0.11.1 LLM:0.11.0 LLM:0.10.1 LLM:0.10.0 LLM:0.9.0 LLM:0.8.2 LLM:0.8.1 LLM:0.8.0 LLM:0.7.1 LLM:0.7.0 LLM:0.6.2 LLM:0.6.1 LLM:0.6.0 LLM:0.5.0 LLM:0.4.0 LLM:0.3.0 LLM:0.2.6 LLM:0.2.5 LLM:0.2.1 LLM:v0.2.0 LLM:v0.1.9 LLM:v0.1.8 LLM:v0.1.7 LLM:v0.1.6 LLM:v0.1.5-alpha

1921 Commits
1.6.1 ... 1.33.1

Author SHA1 Message Date
sabaimran
25c1c1c591 Release Khoj version 1.33.1 2025-01-06 09:08:01 -08:00
sabaimran
689d9d8b3a Update formatting in admin.py and utils.py 2025-01-06 09:07:28 -08:00
thinker007
aa442c28eb Handle reporting chat estimated cost when some fields unavailable (#1026) 
Fix AttributeError: 'NoneType' object has no attribute 'model_extra'

* cost = chunk.usage.model_extra.get("estimated_cost", 0) if hasattr(chunk, "usage") and chunk.usage else 0  # Estimated costs returned by DeepInfra API
 2025-01-06 09:03:49 -08:00
sabaimran
4aed6f7e08 Add a link around the header khojlogotype to go home 2025-01-06 08:55:00 -08:00
Debanjum
266d274e21 Make automation should_notify check robust to non json mode chat models 
Use clean_json to handle automation should_notify check For gemini and
other chat models where enforcing json mode is problematic, not supported
 2025-01-06 20:16:32 +07:00
Debanjum
9a5e3583cf Remove bullet styling only from sidebar items on web app 
Previous fix had removed bullet styling from all components in web
app. This made chat messages on the web app lose bullet styling too.
 2025-01-06 20:15:42 +07:00
Debanjum
dc0bc5bcca Evaluate information retrieval quality using eval script 
- Encode article urls in filename indexed in Khoj KB
  Makes it easier for humans to compare, trace retrieval performance
  by looking at logs than using content hash (which was previously
  explored)
 2025-01-06 13:19:52 +07:00
Debanjum
daeba66c0d Optionally pass references used by agent for response to eval scorers 
This will allow the eval framework to evaluate retrieval quality too
 2025-01-06 13:19:52 +07:00
Debanjum
8231f4bb6e Return accuracy as decision to generalize across IR & standard scorers 2025-01-06 13:19:52 +07:00
sabaimran
eb9aadf72a Add an Obsidian README documentation for development 2025-01-05 19:06:27 -08:00
sabaimran
e89e49818b Merge pull request #1028 from ReallyVirtual/patch-1 
Update image_generation.md
 2025-01-05 13:53:00 -08:00
sabaimran
616cc189d1 Remove bullet points from li styling explicitly 2025-01-05 13:52:08 -08:00
sabaimran
a5705a5aa6 After agent prompt safe check is parsed as json, load it into a json object 2025-01-05 13:40:20 -08:00
Sohaib Athar
95a2387e9b Update image_generation.md 
Fixed typo
 2025-01-05 07:25:41 +05:00
sabaimran
756f4a2a66 Update regeneration logic to run for all entries now that we have a single search model ID 2025-01-03 15:16:10 -08:00
Debanjum
33f85b4a55 Fix title of Query Filters documentation 2025-01-01 18:56:16 +08:00
sabaimran
0ef787b57c Set waitBeforeSeconds to 0 2024-12-30 15:08:34 -08:00
Debanjum
90b4e03454 Pull out query filters as top level documentation page 
- Note perf eval from 2022
- Update links to query-filters in docs
- Fix links
- Update image model docs
 2024-12-30 14:35:05 -08:00
sabaimran
8f69eb949b Release Khoj version 1.33.0 2024-12-29 10:39:26 -08:00
Debanjum
1a43ca75f3 Update to latest jinja python package dependency 2024-12-27 01:44:41 -08:00
Debanjum
ca197ba9ba Improve Automation Flexibility and Automation Email Format (#1016) 
- Format AI response to send in automation email
- Let Khoj infer chat query based on user automation query
- Decide if automation emails should be sent based on response
  - Fix the `to_notify_or_not` decider AI
  - Ask reason before decision to improve to_notify decider AI
- Show error message on web app when fail to create/update automation
 2024-12-27 01:36:38 -08:00
Debanjum
90685ccbb0 Show error message if update automation via web app fails 2024-12-26 22:21:56 -08:00
Debanjum
c4bb92076e Convert async create automation api endpoints to sync 2024-12-26 21:59:55 -08:00
Debanjum
9674de400c Format AI response to send in automation email 
Previously we sent the AI response directly. This change post
processes the AI response with the awareness that it is to be sent to
the user as an email to improve rendering and quality of the emails.
 2024-12-26 21:04:50 -08:00
Debanjum
6d219dcc1d Switch to let Khoj infer chat query based on user automation query 
This tries to decouple the automation query from the chat query. So
the chat model doesn't have to know it is running in an automation
context or figure how to notify user or send automation response. It
just has to respond to the AI generated `query_to_run' corresponding
to the `scheduling_request` automation by the user.

For example, a `scheduling_request' of `notify me when X happens'
results in the automation calling the chat api with a `query_to_run`
like `tell me about X` and deciding if to notify based on information
gathered about X from the scheduled run. If these two are not
decoupled, the chat model may respond with how it can notify about X
instead of just asking about it.

Swap query_to_run with scheduling_request on the automation web page
 2024-12-26 21:04:50 -08:00
Debanjum
3600a9a4f3 Ask reason before decision to improve to_notify decider automation AI 
Previously it just gave a decision. This was hard to debug during
prompt tuning. Asking for reason before decision improves models
decision quality.
 2024-12-26 21:04:50 -08:00
Debanjum
dcc5073d16 Fix the to_notify decider automation chat actor. Add detailed logging 2024-12-26 21:04:50 -08:00
sabaimran
03b4667acb Merge pull request #1017 from khoj-ai/features/update-home-page 
- Rather than chunky generic cards, make the suggested actions more action oriented, around the problem a user might want to solve. Give them follow-up options. Design still in progress.
 2024-12-24 12:12:37 -08:00
sabaimran
5985ef4c7c Further improve prompts 2024-12-24 12:11:27 -08:00
sabaimran
012e0ef882 Add tooltip for file input ref. 2024-12-24 11:20:39 -08:00
sabaimran
a58b3b4a37 Remove some of the step one suggestions 2024-12-24 10:52:42 -08:00
sabaimran
cf78f426d3 Merge branch 'master' of github.com:khoj-ai/khoj into features/update-home-page 2024-12-24 09:52:06 -08:00
sabaimran
d27d291584 Merge pull request #1015 from khoj-ai/features/clean-up-authenticated-data 
- De facto, was being assumed everywhere if authenticatedData is null, that it's not logged in. This isn't true because the data can still be loading. Update the hook to send additional states.
- Bonus: Delete model picker code and a slew of unused imports.
 2024-12-24 09:51:39 -08:00
sabaimran
cd4cf4f9f6 Merge pull request #1014 from khoj-ai/features/improve-agent-management 
- Add support for seeing all steps of the agent modification flow via tabs at the top of the modal
- Separate knowledge base & tool selection into two separate parts
 2024-12-24 09:50:38 -08:00
sabaimran
3e6ba45cbe Merge pull request #1013 from khoj-ai/features/use-sidebar 
Use the [shadcn sidebar](https://ui.shadcn.com/docs/components/sidebar#sidebarmenusub) across Khoj and standardize how the side panel experience works across the app. This helps us generalize the code better, while re-using the same components. 

Deprecates current usage of the chat history side panel, replacing it with the new `appSidebar.tsx` component.

We'll eventually move out the `Manage Files` section and move it into a separate panel dedicated to chat-level controls.
 2024-12-24 09:50:09 -08:00
sabaimran
95fdbe13ae move all conversations button to bottom of side panel 2024-12-23 23:13:19 -08:00
sabaimran
d0256f267e Fix submit state for form with buttons sticky to button 2024-12-23 23:10:19 -08:00
Debanjum
0d5fc70aa3 Fix colors, title on create agent card 2024-12-23 20:01:56 -08:00
Debanjum
0b91383deb Make post oauth next url redirect more robust, handle q params better 2024-12-23 17:50:45 -08:00
Debanjum
17f8ba732d Autofocus on email input box when email sign-in selected on web app 2024-12-23 17:49:41 -08:00
sabaimran
fb111a944b Use disable_https flag instead of is_in_debug_mode to decide whether to redirect google auth request 2024-12-23 17:23:47 -08:00
sabaimran
3fd0c202ea Allow better spacing in the agent card and make the buttons sticky 2024-12-23 16:43:50 -08:00
sabaimran
c83709fdd1 Further clean up in home page initial cards experience 2024-12-22 18:11:19 -08:00
sabaimran
4c4f4401b1 Make suggestion cards a little more minimal 2024-12-22 11:54:27 -08:00
sabaimran
90b02b4cfe Merge branch 'features/clean-up-authenticated-data' of github.com:khoj-ai/khoj into features/update-home-page 2024-12-22 11:26:29 -08:00
sabaimran
798837378f Improve mobile friendliness and highlight missing necessary data 2024-12-22 11:02:50 -08:00
sabaimran
7032ccf130 Show create agent button when not logged in agents page 2024-12-22 10:01:15 -08:00
sabaimran
0fefbac89f Improve sidebar experience for not logged in state 2024-12-22 09:58:21 -08:00
sabaimran
60f80548a4 Remove unused span text 2024-12-22 09:21:40 -08:00
sabaimran
9f84f5dcc7 Give more breathing space to the sidebar footer 2024-12-22 09:18:05 -08:00
sabaimran
dc17272f70 Fix some spacing in the nav menu 2024-12-22 09:01:09 -08:00
sabaimran
45da6ec750 Separate the shorthand of each suggestion card from the prefilled text 2024-12-21 20:46:57 -08:00
sabaimran
bf405f50d7 Fix spacing of main content in the settings page 2024-12-21 20:46:21 -08:00
sabaimran
62dd4c55d4 Further improve UX of the suggestion cards 2024-12-21 20:10:54 -08:00
sabaimran
8c9c57e060 Merge branch 'features/clean-up-authenticated-data' of github.com:khoj-ai/khoj into features/update-home-page 2024-12-21 19:32:07 -08:00
sabaimran
8c6b4217ae Set width of chat layout to 100% 2024-12-21 19:29:37 -08:00
sabaimran
a17cc9db38 Fix handling 403 forbidden error from auth response 2024-12-21 19:19:35 -08:00
sabaimran
95826393e1 Update the home page suggestion cards 
- Rather than chunky generic cards, make the suggested actions more action oriented, around the problem a user might want to solve. Give them follow-up options. Design still in progress.
 2024-12-21 18:57:19 -08:00
Debanjum
8d129c4675 Bump default max prompt size for commercial chat models 2024-12-21 17:31:05 -08:00
Debanjum
37ae48d9cf Add support for OpenAI o1 model 
Needed to handle the current API limitations of the o1 model.
Specifically its inability to stream responses
 2024-12-21 17:25:32 -08:00
sabaimran
2c7c16d93e Fix conditional reference to is mobile width hook 2024-12-21 12:48:29 -08:00
sabaimran
e9dae4240e Clean up all references to authenticatedData 
- De facto, was being assumed everywhere if authenticatedData is null, that it's not logged in. This isn't true because the data can still be loading. Update the hook to send additional states.
- Bonus: Delete model picker code and a slew of unused imports.
 2024-12-21 08:45:43 -08:00
sabaimran
b1c5c5bcc9 Fix path to component library in shadcn sidebar 2024-12-20 15:48:57 -08:00
sabaimran
cc7fd1163f Use tabs to separate sections in the agent mod form 
- Add knowledge base as a separate section, apart from tools
- This makes it easier to navigate the different components quickly
 2024-12-20 14:41:15 -08:00
sabaimran
078753df30 Add chatwoot to the frame-src CSP 2024-12-20 13:33:48 -08:00
sabaimran
efe812e323 Add componets for tabs in agent page 2024-12-20 13:33:20 -08:00
sabaimran
ba792c02ba Improve share chat UI for alignment 2024-12-20 12:28:31 -08:00
sabaimran
7770caa793 Add side bar inset to home page. Simplify automations card. 2024-12-20 11:37:23 -08:00
sabaimran
b8a9dcd600 Improve mobile layout with sidebar inset and fix dark mode logo 2024-12-19 23:23:52 -08:00
sabaimran
b1880d9c9d Add side bar to search page 2024-12-19 22:46:50 -08:00
sabaimran
02c503e966 Further improve mobile layout with side panel 2024-12-19 22:00:32 -08:00
sabaimran
43331f7730 Remove unused css classes 2024-12-19 21:36:35 -08:00
sabaimran
b644bb8628 Further improve mobile friendliness 2024-12-19 21:34:04 -08:00
sabaimran
9d5480d886 Improve mobile friendlinses across chat and home pages. 2024-12-19 20:33:53 -08:00
sabaimran
68af10c805 Use the new shadcn sidebar for khoj nav and actions 
- Use the sidebar across all pages to quickly navigate through the app, access settings, and go to past chats
- Pending: mobile friendliness
 2024-12-19 20:10:03 -08:00
sabaimran
7eb15bf0a9 Update shadcn components 2024-12-19 14:33:36 -08:00
sabaimran
a4aeb9fdf3 Simplify the home page color scheme and overall design 2024-12-19 14:02:53 -08:00
Debanjum
0ae21e5628 Use icons, not text labels, for sidebar nav items on docs website 2024-12-17 20:49:09 -08:00
sabaimran
cafe1b0655 Remove error log line for payload inclusion 2024-12-17 19:48:22 -08:00
Debanjum
1e3f452d15 Handle sharing old conversation publically even if they have no slug 
New conversation have a slug, but older conversation may not. This
change allows those older conversations to still be shareable by using
a random uuid for constructing their url instead
 2024-12-17 19:44:36 -08:00
Debanjum
90b7ba51a4 Make agent prompt safety checker more forgiving and concise 
- Some of the instructions were duplicated (e.g illegal, harmful)
- Return format requested was inconsistent
- Safety prompt felt overtly prudish which lowered their utility.
  Make it laxer for now, add checks later if required
 2024-12-17 19:44:36 -08:00
sabaimran
bcee2ea01a Release Khoj version 1.32.2 2024-12-17 16:03:29 -08:00
sabaimran
92144c8102 Remove release step in todesktop flow, since we need to run releases manually now 
- Leaving it commented out for the time being so we can revisit automating this later
 2024-12-17 16:02:45 -08:00
sabaimran
f291884921 If not in debug mode, force google auth to use the https protocol 2024-12-17 15:44:18 -08:00
sabaimran
bcc1bc6854 Log the payload sent temporarily in order to help with debugging 2024-12-17 15:37:42 -08:00
sabaimran
7ca2553d17 Update login popup copy 2024-12-17 15:20:44 -08:00
sabaimran
ef99d8c28e Add more descriptive error logs when google auth token verification fails 2024-12-17 15:18:38 -08:00
Debanjum
60d55a83c4 Use khoj logo via url in readme to load in other locations like pypi 2024-12-17 14:00:53 -08:00
Debanjum
10bd56d2b9 Attest Khoj pypi package by upgrading pypi publish gh action 
- Print hash in CI to ease verifying ci built python package matches
  khoj package published on pypi
- Newer pypi publish github action should speed up workflow by ~30s
 2024-12-17 13:40:39 -08:00
sabaimran
2e80a1ce7c Release Khoj version 1.32.1 2024-12-17 13:28:00 -08:00
Debanjum
df15f00243 Tag docker images with latest tag in dockerize workflow on release 2024-12-17 13:18:51 -08:00
sabaimran
ded168dae3 Release Khoj version 1.32.0 2024-12-17 12:29:20 -08:00
sabaimran
f6abfcfa6b Use latest release version for pypi gh action to publish 2024-12-17 12:19:42 -08:00
Debanjum
c20364efcb Upgrade web app next.js, shadcn and other package dependencies 2024-12-17 11:15:22 -08:00
Debanjum
63d2c6f35a Allow research mode and other conversation commands in automations (#1011) 
Major
---
Previously we couldn't enable research mode or use other slash
commands in automated tasks.

This change separates determining if a chat query is triggered via
automated task from the (other) conversation commands to run the query
with.

This unlocks the ability to enable research mode in automations
apart from other variations like /image or /diagram etc.

Minor
---
- Clean the code to get data sources and output formats
- Have some examples shown on automations page run in research mode now
 2024-12-17 00:44:51 -08:00
sabaimran
3b050a33bb Include resend as a default dependency, rather than restricting to prod 2024-12-16 22:24:41 -08:00
sabaimran
741e9f56f9 Update admin button for getting login url to include user email 2024-12-16 22:16:05 -08:00
Debanjum
88aa8c377a Support online search with Searxng as zero config, self-hostable solution (#1010) 
This allows online search to work out of the box again 
for self-hosting users, as no auth/api key setup required.

Docker users do not need to change anything in their setup flow.
Direct installers can setup Searxng locally or use public instances if
they do not want to use any of the other providers (like Jina, Serper)

Resolves #749. Resolves #990
 2024-12-16 18:59:09 -08:00
sabaimran
7677bb14f8 Update docs home page 2024-12-16 18:48:42 -08:00
sabaimran
1bd0d46b3d Update the theme color used in our docs to match the theme in our emails 2024-12-16 18:42:50 -08:00
sabaimran
432e901087 Update the online search self-hosting instructions to reflect new setup 2024-12-16 18:37:20 -08:00
sabaimran
af2553a890 Remove the Searxng API key env variable for simplicity 2024-12-16 18:36:55 -08:00
sabaimran
19d80d190e Add latest tag to the khoj cloud description for prod 2024-12-16 17:56:12 -08:00
sabaimran
d62cc0d539 Merge branch 'master' of github.com:khoj-ai/khoj into support-online-search-via-searxng 2024-12-16 17:55:06 -08:00
sabaimran
6f3218f487 Merge pull request #1008 from khoj-ai/features/new-sign-in-page 
- Make it easier to quickly create the account without losing track of where you are
- Show some capabilities before you sign on
 2024-12-16 17:54:43 -08:00
sabaimran
753859fbe0 Make the docs and github buttons on the sign in email less prominent 2024-12-16 17:49:13 -08:00
sabaimran
20888d3930 Clarify some of the language in the sign in email 2024-12-16 17:47:12 -08:00
sabaimran
13e7455f56 Use lowercase c in click 2024-12-16 17:44:08 -08:00
sabaimran
d17a9ba4c8 Fix return data for expired code user 2024-12-16 17:33:53 -08:00
sabaimran
efb0b9f495 Gracefully handle error when user login code is expired 2024-12-16 16:47:54 -08:00
sabaimran
064f7e48ca Update various copy texts for OG metadata and such 2024-12-16 16:40:46 -08:00
sabaimran
28b8f9105d Remove parenthetical from email template 2024-12-16 13:40:41 -08:00
Debanjum
9d02978f6e Support online search with Searxng as turnkey, self-hostable solution 
This allows online search to work out of the box again for
self-hosting users, as no auth/api key setup required.

Docker users do not need to change anything in their setup flow.
Direct installers can setup searxng locally or use public instances if
they do not want to use any of the other providers (like Jina, Serper)

Resolves #749. Resolves #990
 2024-12-16 12:53:38 -08:00
Debanjum
9c64275dec Auto redirect requests to use HTTPS if server is using SSL certs 2024-12-16 12:53:38 -08:00
sabaimran
ae9750e58e Add rate limiting to OTP login attempts and update email template for conciseness 2024-12-16 11:59:45 -08:00
sabaimran
b7783357fa Decrease timeout limit for verification codes to 5 minutes 2024-12-16 09:07:34 -08:00
sabaimran
5d3da3340f Include email in verification API 2024-12-15 13:54:41 -08:00
sabaimran
8e3313156e Simplify the magic link email a little bit 2024-12-14 11:19:31 -08:00
sabaimran
6a56140360 Allow users to directly enter their unique code when logging in 
- Code automatically becomes invalid after 30 minutes
 2024-12-14 11:06:05 -08:00
sabaimran
c25174e8d4 Apply more finished styling to login features, make the pop-up mobile friendly 2024-12-14 09:46:19 -08:00
sabaimran
73c1fe6ae1 Add text overlay to caption the different assets 2024-12-13 13:45:31 -08:00
Debanjum
132f2c987a Make Khoj email sender configurable for all email variants 
The welcome, feedback and automation emails were still using the Khoj
domain, which wouldnt work for self-hosted users with their RESEND key

Resolves #1004
 2024-12-13 12:25:23 -08:00
sabaimran
f1fb4525c6 Remove old images 2024-12-13 11:31:14 -08:00
sabaimran
d5681ad1a2 Update image assets to sign up prompt 2024-12-13 11:30:14 -08:00
sabaimran
62545a9af3 Update package path for pypi ci export 2024-12-12 21:25:21 -08:00
sabaimran
e74e922cea Update file path of python installation 2024-12-12 16:50:32 -08:00
sabaimran
144f283a25 Maintain old login page for posterity and associated API 2024-12-12 16:23:44 -08:00
sabaimran
4697daeb1a Improve opengraph metadata across front-end pages 2024-12-12 15:56:43 -08:00
sabaimran
dfc150c442 Merge branch 'master' of github.com:khoj-ai/khoj into features/new-sign-in-page 2024-12-12 15:43:06 -08:00
sabaimran
ad3f8a33d1 Add a static login footer that prompts login, disable input box without auth 2024-12-12 14:57:52 -08:00
Debanjum
2db7a1ca6b Restart code sandbox on crash in eval github workflow (#1007) 
See
e3fed3750b
for corresponding change to use pm2 to auto-restart code sandbox
 2024-12-12 14:32:03 -08:00
Debanjum
12c976dcb2 Track usage costs from DeepInfra OpenAI compatible API 2024-12-12 14:20:34 -08:00
Debanjum
b0abec39d5 Use chat model name var name consistently and type openai chat utils 2024-12-12 14:20:34 -08:00
Debanjum
4915be0301 Fix initializing chat model names parameter after field rename in #1003 2024-12-12 14:20:33 -08:00
sabaimran
a7d0ed8670 Add carousel for navigating images in the sign up modal 2024-12-12 11:47:41 -08:00
Debanjum
9eb863e964 Restart code sandbox on crash in eval github workflow 2024-12-12 11:28:54 -08:00
Debanjum
01bc6d35dc Rename Chat Model Options table to Chat Model as short & readable (#1003) 
- Previous was incorrectly plural but was defining only a single model
- Rename chat model table field to name
- Update documentation
- Update references functions and variables to match new name
 2024-12-12 11:24:16 -08:00
sabaimran
943065b7b3 Remove dead dependencies and improve the google sign in button 2024-12-12 11:19:19 -08:00
sabaimran
41bb1e60d0 Use the LoginPrompt in the chat history side panel 2024-12-11 22:56:03 -08:00
sabaimran
b60b750555 Update the styling to align with Google branding via the sign in button 
- Disable the gsi client side code since it's being finnicky and inconsistent
 2024-12-11 22:49:11 -08:00
sabaimran
0f8b055b42 Improve padding for space, esp in mobile 2024-12-11 18:22:48 -08:00
sabaimran
142239d2c9 Add mobile friendliness and replace the login page redirects 2024-12-11 18:01:04 -08:00
sabaimran
de6ed2352a Break up the parts of the login dialog into smaller modules to extend for mobile 2024-12-11 17:18:43 -08:00
sabaimran
d35db99c6f Initial version of a carousel working for sign in with steps for email sign up 
- Google sign in is pending with the gsi client code. Will see if I can get that working
- Check in relevant image assets
 2024-12-11 16:54:06 -08:00
aditya218
9be26e1bd2 Fix documentation to point to local environment image_generation.md (#1005) 
Fix documentation to point to local environment.
 2024-12-11 16:12:25 -08:00
sabaimran
530b44cf56 Merge branch 'master' of github.com:khoj-ai/khoj into features/new-sign-in-page 2024-12-11 10:30:13 -08:00
Debanjum
fe09df66b7 Make code sandbox container url accessible to Khoj container in docker compose 2024-12-11 01:14:26 -08:00
Debanjum
59008ae90e Use buildx to create multi platform docker image 2024-12-11 00:21:29 -08:00
Debanjum
ec797bc6b8 Build docker imgs on native arch runners to avoid manifest list error 
This also avoids the need to use --amend and annotate steps when
creating the multi-arch docker images
 2024-12-10 23:16:36 -08:00
Debanjum
5f7b13df2d Fix new docker tags in workflow to not include forward slashes 2024-12-10 22:55:33 -08:00
Debanjum
ba6237b5c0 Fix to create multi-arch builds. Stop docker image overwrites in workflow 2024-12-10 21:08:17 -08:00
sabaimran
44ede26e67 Temporarily disable cloud arm builds while we disambiguate the build issues 2024-12-10 20:00:59 -08:00
Debanjum
33a5efaf4b Fix undefined variable exception during openai provider setup on init 
Resolves #1001
 2024-12-10 19:54:00 -08:00
sabaimran
e43341fdcc Release Khoj version 1.31.0 2024-12-10 19:41:31 -08:00
Debanjum
a757ecfd2b Put the generated assets message after the user query and fix prompt 2024-12-10 19:40:13 -08:00
Debanjum
40e4f2ec2e Reduce clutter in chat message ux on Obsidian 
- Move khoj message border to left like in web ui
- Remove user, sender emojis and name
- Ensure conversation title always at top of chat sessions view,
  even if no chat sessions loaded yet, instead of causing layout shift
  on chat sessions load
 2024-12-10 19:34:17 -08:00
sabaimran
1ec1eff57e Improve mobile header, reduce title bar padding and add conv title 2024-12-10 19:03:57 -08:00
sabaimran
321eeeaed7 Fix setting title of shared conversation, move shared button into the title pane 2024-12-10 18:19:46 -08:00
sabaimran
d7e5a76ace Add an icon in the input bar for research mode 2024-12-10 17:49:25 -08:00
sabaimran
01d000e570 Merge pull request #1002 from khoj-ai/features/improve-multiple-output-mode-generation 
Improve handling of multiple output modes

- Use the generated descriptions / inferred queries to supply context to the model about what it's created and give a richer response
- Stop sending the generated image in user message. This seemed to be confusing the model more than helping.
- Collect generated assets in a structured objects to provide model context. This seems to help it follow instructions and separate responsibility better
- Also, rename the open ai converse method to converse_openai to follow patterns with other providers
 2024-12-10 17:06:19 -08:00
sabaimran
2bb14c55a6 Merge branch 'master' of github.com:khoj-ai/khoj into features/improve-multiple-output-mode-generation 2024-12-10 16:56:36 -08:00
sabaimran
6c8007e23b Improve handling of multiple output modes 
- Use the generated descriptions / inferred queries to supply context to the model about what it's created and give a richer response
- Stop sending the generated image in user message. This seemed to be confusing the model more than helping.
- Also, rename the open ai converse method to converse_openai to follow patterns with other providers
 2024-12-10 16:54:21 -08:00
Debanjum
4bc5c1357a Upgrade server, documentation dependencies. Spell fix docker-compose.yml 2024-12-10 15:47:47 -08:00
Debanjum
f8957e52bf Keep chatml message content simple for wider compat unless attachments 
This allows for wider compatibility with chat models and openai proxy
ai model apis that expect message content to be string format, not
objects.
 2024-12-10 00:10:56 -08:00
sabaimran
4b4e0e20d4 Make the version number a badge, rather than an independent item in the nav dropdown 2024-12-09 14:45:26 -08:00
sabaimran
eb36492ba5 Update handling of images when included in the chat history with assistant message 2024-12-08 21:46:07 -08:00
Debanjum
b660c494bc Use recognizable DB model names to ease selection UX on Admin Panel 
Previously id were used (by default) for model display strings.
This made it hard to select chat model options, server chat settings
etc. in the admin panel dropdowns.

This change uses more recognizable names for the DB objects to ease
selection in dropdowns and display in general on the admin panel.
 2024-12-08 20:34:50 -08:00
Debanjum
d10dc9cfe1 Inform code tool AI only limited python packages are available to it 
Reduce code tool failing with module not found errors
 2024-12-08 20:34:50 -08:00
Debanjum
3fd8614a4b Only auto load available chat models from Ollama provider for now 
Allowing models from any openai proxy service makes it too unwieldy.
And a bunch of them do not even support this endpoint.
 2024-12-08 20:34:50 -08:00
sabaimran
2c934162d3 Add a data filter for privacy_level of agents 2024-12-08 19:55:57 -08:00
sabaimran
3b9f4c4356 Correct negative for running prod image locally 2024-12-08 19:55:35 -08:00
Debanjum
9dd3782f5c Rename OpenAIProcessorConversationConfig DB model to more apt AiModelApi (#998) 
* Rename OpenAIProcessorConversationConfig to more apt AiModelAPI

The DB model name had drifted from what it is being used for,
a general chat api provider that supports other chat api providers like
anthropic and google chat models apart from openai based chat models.

This change renames the DB model and updates the docs to remove this
confusion.

Using Ai Model Api we catch most use-cases including chat, stt, image generation etc.
 2024-12-08 18:02:29 -08:00
sabaimran
df66fb23ab Centralize definition of the content security policy and add in-app chat 
- in-app chat is meant for support requests and currently is only in the settings page, where users are most likely to go if confused IMO
 2024-12-08 17:57:27 -08:00
sabaimran
0b87c13f8d Add khoj_version to the settings menu 2024-12-08 17:55:56 -08:00
sabaimran
47a087c73b Fix chatwoot import issue by checking whether we're in an execution environment before loading the script 2024-12-08 17:16:20 -08:00
sabaimran
66f59c8d41 Add Chatwoot to documentation 
See repo: https://github.com/chatwoot/chatwoot
 2024-12-08 16:51:43 -08:00
sabaimran
6ed051d631 Merge pull request #994 from khoj-ai/features/update-desktop-app 
Simplify the desktop app

- Make the desktop app mainly a file-syncing client for users who have lots of documents that they need to share with Khoj. This is because the web app provides a fairly robust chat client which can be used by anyone on their computer.
- The chat client in the desktop app had significantly drifted from our current brand / them, and didn't provide enough value add to update. Later, we will make it easier to install the existing web app as a desktop PWA.
 2024-12-08 15:05:35 -08:00
sabaimran
05b3911080 Update some button titles and add descriptions for clarity 2024-12-08 14:29:12 -08:00
sabaimran
b78b92d6a0 Merge branch 'master' of github.com:khoj-ai/khoj into features/update-desktop-app 2024-12-08 14:20:20 -08:00
sabaimran
e3789aef49 Merge pull request #992 from khoj-ai/features/allow-multi-outputs-in-chat 
Currently, Khoj has terminal states with respect to what assets it outputs. We limit it to image, text, and excalidraw diagram. This limitation is unnecessary and provides undue constraints for creating more dynamic, diverse experiences. For instance, we may want the chat view to morph for document editing or generation, in which case having limited output modes would be a detriment.

This change allows us to emit generated assets and then continue on to more text generation in final response. It forces text response for all messages. It adds a new stream event, GENERATED_ASSETS, which holds content that the AI is emitting in response to the query.
 2024-12-08 14:19:05 -08:00
sabaimran
a2251f01eb Make result optional for code context, relevant when code execution was unsuccessful 2024-12-08 13:27:33 -08:00
sabaimran
9c403d24e1 Fix reference to directory in the eval workflow for starting terrarium 2024-12-08 13:03:05 -08:00
sabaimran
7cd2855146 Make attributes optional in the knowledge graph model 2024-12-08 12:23:17 -08:00
sabaimran
2af687d1c5 Allow snippetHighlighted to also be nullable 2024-12-08 11:51:24 -08:00
sabaimran
efa23a8ad8 Update validation requirements for online searches 2024-12-08 11:30:17 -08:00
sabaimran
6940c6379b Add sudo when running installations in order to install relevant packages 
add --legacy-peer-deps temporarily to see if it helps mitigate the issue
 2024-12-08 11:11:13 -08:00
sabaimran
4c4b7120c6 Use Khoj terrarium fork instead of building from official Cohere repo 2024-12-08 11:06:33 -08:00
sabaimran
a138845fea Merge branch 'master' of github.com:khoj-ai/khoj into features/allow-multi-outputs-in-chat 2024-12-08 10:57:16 -08:00
sabaimran
19832a3ed0 Add note to uncomment line when using the prod image 2024-12-05 18:16:01 -08:00
sabaimran
110c64ba27 Update the desktop instructions 2024-12-05 17:39:16 -08:00
Debanjum
65c5b163c9 Add khoj_lantern svg to web public assets for use by new admin panel 2024-12-05 10:57:18 -08:00
Debanjum
354dc12b3b Style the Admin Panel with a modern theme and Khoj branding (#999) 
Overview
- The default django admin panel UI looks pretty dated and didn't
  have any Khoj specific branding
- Used the Unfold Django admin panel theme for a modern look
- Used the Khoj logo and name in Admin panel title, headings, favicons

Details:
All models shown on Admin panel need to inherit from unfold's
ModelAdmin to get styling applied. So

- Make all models on Admin panel inherit from unfold's ModelAdmin
- Subclassed UserAdmin to inherit from unfold's ModelAdmin
- Deregistered the unused Auth Group model from the Admin panel
  We can add it back when its actually used. Avoid confusion for now
- Explicitly register DjangoJobExecution on admin panel and again make
  it inherit from the unfold.admin.ModelAdmin
 2024-12-04 23:53:43 -08:00
Matias Forbord
9cc79c0fb7 Fix broken doc links to query filters from emacs docs page (#1000) 
* docs: repair query filters link

* change docs link to be relative
 2024-12-04 23:52:27 -08:00
sabaimran
8953ac03ec Rename additional context for llm response to program execution context 2024-12-04 18:43:41 -08:00
sabaimran
886fe4a0c9 Merge branch 'master' of github.com:khoj-ai/khoj into features/allow-multi-outputs-in-chat 2024-12-03 21:37:00 -08:00
sabaimran
df5e34615a Fix processing of images field when construct chat messages 2024-12-03 21:26:55 -08:00
sabaimran
3552032827 Rename additional context to additional_context_for_llm_response 2024-12-03 21:23:15 -08:00
sabaimran
d507894546 Simplify the desktop app 
- Make the desktop app mainly a file-syncing client for users who have lots of documents that they need to share with Khoj. This is because the web app provides a fairly robust chat client which can be used by anyone on their computer.
- The chat client in the desktop app had significantly drifted from our current brand / them, and didn't provide enough value add to update. Later, we will make it easier to install the existing web app as a desktop PWA.
 2024-12-02 15:54:05 -08:00
Debanjum
9f7cb335c5 Create Android app for Khoj (#991) 
Use bubblewrap to publish the Khoj Progressive Web App (PWA) as a Trusted Web Activity (TWA) to the Android Play Store
 2024-12-02 15:45:04 -08:00
Debanjum
ee28d7f125 Fix Android Studio build warnings by using newer gradle, mavenCentral 2024-12-02 12:48:33 -08:00
Debanjum
5d6fb07066 Fix app icons, orientation. Improve name, id, description in webmanifest 
- Use bubblewrap generated splash screen, notification icons from
  1200x1200 high res khoj icon in assets.khoj.dev.
- Discard bubblewrap generated launcher icons.
- Fix orientation to respect phone orientation settings. "any" was not.
 2024-12-02 12:48:25 -08:00
Debanjum
147c8e9115 Release v3 with high-res splash screen. More details in web, app manifest 
- Add 512, 192 Khoj maskable icons to web app manifest for android rendering
- Add id, categories etc suggested by pwabuilder
- Use higher quality icon images for splash screen than what
  bubblewrap creates by default
 2024-12-02 11:28:35 -08:00
Debanjum
d333e10e64 Encode request params as utf-8 to fix multibyte char error in khoj.el 
Encode api key in header, POST request body and GET query param for
search as utf-8 to avoid the multibyte char in request issue when
making API calls from khoj.el to khoj server.

Resolves #935
 2024-12-02 02:00:14 -08:00
Debanjum
db29894038 Do not wrap filepath in Path to fix indexing markdown files on Windows (#993) 
### Issue
- Path with / are converted to \\ on Windows using the `Path' operator.
- The `markdown_to_entries' module was trying to normalize file paths with`Path'  for some reason.
  This would store the file paths in DB Entry differently than the file to entries map if Khoj ran on Windows.
  That'd result in a KeyError when trying to look up the entry file path from `file_to_text_map' in the `text_to_entries:update_embeddings()' function.

### Fix
- Removing the unnecessary OS dependent Path normalization in `markdown_to_entries' should keep the file path storage consistent across `file_to_text_map' var, `FileObjectAdaptor', `Entry' DB tables on Windows for Markdown files as well.

This issue will affect users hosting Khoj server on Windows and attempting to index markdown files.

Resolves #984
 2024-12-02 01:02:58 -08:00
Debanjum
47c926b0ff Add more typing to org|md_to_entries. Remove redundant f-string wraps 
- Add type hints to improve maintainability of stabilzed indexing code
- It shouldn't be necessary to wrap string variables in an f-string

This change aims to improve code quality. It should not affect
functionality.
 2024-12-01 23:02:52 -08:00
Debanjum
dffdd81345 Do not wrap filepath in Path to fix indexing markdown files on Windows 
Issue
- Path with / are converted to \\ on Windows using the Path operator.
- The markdown to entries method for some reason was doing this.
  This would store the file paths in DB entry differently than the file
  to entries map. Resulting in a KeyError when trying to look up the
  entry file path from file_to_text_map in the
  text_to_entries:update_embeddings() function.

Fix
- Removing the unnecessary OS dependendent Path normalization in
  markdown_to_entries should keep the file path storage consistent
  across file_to_text_map var, FileObjectAdaptor, Entry DB tables on
  Windows for Markdown files as well

This issue would only affect users hosting Khoj server on Windows and
attempting to index markdown files.

Resolves #984
 2024-12-01 23:00:31 -08:00
sabaimran
c87fce5930 Add a migration to use the new image storage format for past conversations 
- Added it to the Django migrations so that it auto-triggers when someone updates their server and starts it up again for the first time. This will require that they update their clients as well in order to view/consume image content.
- Remove server-side references in the code that allow to parse the text-to-image intent as it will no longer be necessary, given the chat logs will be migrated
 2024-12-01 18:35:31 -08:00
Debanjum
9e0a2c7a98 Restrict generated chat title to 200 chars limit allowed for chat slug 2024-11-30 19:12:03 -08:00
Debanjum
8b8e2be82d Only create subscription object when it does not exist for user 
This avoid unnecessarily throwing an internal server error when the
user tries to sign-up using multiple mechanisms (e.g first by email, then
by google oauth)
 2024-11-30 19:08:34 -08:00
Debanjum
fc6be543bd Improve GPQA eval prompt to imrpove parsing answer from Khoj response 2024-11-30 17:21:09 -08:00
sabaimran
00f48dc1e8 If in the new images format, show the response text in obsidian instead of the inferred query 2024-11-30 14:39:51 -08:00
sabaimran
224abd14e0 Only add the image_url to the constructed chat message if it is a url 2024-11-30 14:39:27 -08:00
sabaimran
991577aa17 Allow a None turnId to accommodate historic chat messages 2024-11-30 14:39:08 -08:00
sabaimran
a539761c49 Fix processing of excalidrawdiagram in json response chunking 2024-11-30 12:35:13 -08:00
sabaimran
dc4a9ee3e1 Ensure that the generated assets are maintained in the chat window after streaming is completed. 2024-11-30 12:31:20 -08:00
sabaimran
e3aee50cf3 Fix parsing of generated_asset response 2024-11-29 18:41:53 -08:00
sabaimran
2b32f0e80d Remove commented out code blocks 2024-11-29 18:11:50 -08:00
sabaimran
df855adc98 Update response handling in Obsidian to work with new format 2024-11-29 18:10:47 -08:00
sabaimran
512cf535e0 Collapse train of thought when completed during live stream 2024-11-29 18:10:35 -08:00
sabaimran
a0b00ce4a1 Don't include null attributes when filling in stored conversation metadata 
- Prompt adjustments to indicate to LLM what context it has
 2024-11-29 18:10:14 -08:00
sabaimran
c5329d76ba Merge branch 'master' of github.com:khoj-ai/khoj into features/allow-multi-outputs-in-chat 2024-11-29 14:12:03 -08:00
sabaimran
46f647d91d Improve image rendering for khoj generated images. FIx typing of stored excalidraw image. 2024-11-29 14:11:48 -08:00
Debanjum
fdf69b7049 Publish second version with new upload key 2024-11-28 22:04:10 -08:00
Debanjum
faf15072b6 Create first version of Khoj Android app from PWA using Bubblewrap 2024-11-28 22:04:10 -08:00
sabaimran
4f6d1211ba Fix additional context type in anthropic chat 2024-11-28 20:16:36 -08:00
sabaimran
6f408948d3 Fix typing of generated_fiels parameters 2024-11-28 20:15:10 -08:00
sabaimran
439b18c21f Release Khoj version 1.30.10 2024-11-28 19:43:06 -08:00
sabaimran
2dfd163430 Add more explicity run strategies in the runner matrix 2024-11-28 19:31:34 -08:00
sabaimran
80cd902c86 Since linux/amd64 images aren't being created, try setting a custom description on the image 
Refer to this GH documentation on working with multi arch images in the container registry:
https://docs.github.com/en/packages/working-with-a-github-packages-registry/working-with-the-container-registry#adding-a-description-to-multi-arch-images
 2024-11-28 19:14:06 -08:00
sabaimran
40d8a7a581 Release Khoj version 1.30.9 2024-11-28 18:45:50 -08:00
sabaimran
87aa653c7f Add additional steps in prod.Dockerfile to ensure dependencies are copied over 2024-11-28 18:37:08 -08:00
sabaimran
d91935c880 Initial commit of a functional but not yet elegant prototype for this concept 2024-11-28 17:28:23 -08:00
Debanjum
a552543f4f Use json5 to parse llm generated questions to query docs and web 
json5 is more forgiving, handles double quotes, newlines in raw json
string
 2024-11-28 14:35:34 -08:00
Debanjum
0a69af4f61 Update to latest ToDesktop runtime 2024-11-28 13:56:14 -08:00
Debanjum
1d0fe141dc Release Khoj version 1.30.8 2024-11-28 13:37:30 -08:00
Debanjum
29e801c381 Add MATH500 dataset to eval 
Evaluate simpler MATH500 responses with gemini 1.5 flash

This improves both the speed and cost of running this eval
 2024-11-28 12:48:25 -08:00
Debanjum
22aef9bf53 Add GPQA (diamond) dataset to eval 2024-11-28 12:48:25 -08:00
Debanjum
f1190ccf32 Improve parsing complex json strings returned by LLM (#989) 
- Improve escaping to load complex json objects
- Fallback to a more forgiving [json5](https://json5.org/) loader if `json.loads` cannot parse complex json str

This should reduce failures to pick research tool and run code by agent
 2024-11-28 11:01:39 -08:00
Debanjum
8c120a5139 Fallback to json5 loader if json.loads cannot parse complex json str 
JSON5 spec is more flexible, try to load using a fast json5 parser if
the stricter json.loads from the standard library can't load the
raw complex json string into a python dictionary/list
 2024-11-26 21:17:00 -08:00
Debanjum
70b7e7c73a Improve load of complex json objects. Use it to pick tool, run code 
Gemini doesn't work well when trying to output json objects. Using it
to output raw json strings with complex, multi-line structures
requires more intense clean-up of raw json string for parsing
 2024-11-26 17:37:57 -08:00
Debanjum
8cb0db0051 Fix llama-cpp-python install by pytest github workflow 
- Use pre-built wheels for torch and llama-cpp-python
- Install and link musl as it's used by llama-cpp-python pre-built
  wheel instead of glibc
- Join Install git and Install Dependencies steps in pytest workflow
  To remove unnecessary steps
 2024-11-26 02:04:36 -08:00
Debanjum
29315f44e7 Add assetlinks.json to link android app to app.khoj.dev domain 
Add sha cert of android upload, signing keys to open debug, prod apps
as TWA in fullscreen on android phones
 2024-11-26 01:57:54 -08:00
Debanjum
a97a45bf20 Align agent personality with recently updated khoj personality 
See update to Khoj personality in commit
6eb59464da
 2024-11-26 00:06:16 -08:00
Debanjum
e088fcbc7b Build for arm64 on arm64 runner. Parallelize arm64, x64 docker builds 
- Building arm64 image on an ubuntu arm64 runner reduces `yarn build'
  step time by 75% from 12mins to 3mins.
  - This is because no QEMU emulation for arm64 on x86 is required now
- Parallelizing x64 and arm64 platform builds halves build time on top
  - Revert to use standard ubuntu-latest runner as large x64 runner
    doesn't give much more speed improvements

This results an effective additional 50%-66% reduction in build time
on top of #987.

So a full dockerize workflow run now takes *10 mins* vs previous 35+mins.
This is a total of *72% improvement* in max dockerize run time.

Get additional speed improvements when docker layer cache hit.
 2024-11-24 23:18:55 -08:00
Debanjum
5723a3778e Speed up Docker image builds using multi-stage parallel pipelines (#987) 
## Objective
Improve build speed and size of khoj docker images

## Changes
### Improve docker image build speeds
  - Decouple web app and server build steps
  - Build the web app and server in parallel
  - Cache docker layers for reuse across dockerize github workflow runs
    - Split Docker build layers for improved cacheability (e.g separate `yarn install` and `yarn build` steps)
### Reduce size of khoj docker images 
  - Use an up-to-date `.dockerignore` to exclude unnecessary directories
  - Do not installing cuda python packages for cpu builds
### Improve web app builds
  - Use consistent mechanism to get fonts for web app
  - Make tailwind extensions production instead of dev dependencies
  - Make next.js create production builds for the web app (via `NODE_ENV=production` env var)
 2024-11-24 21:49:46 -08:00
Debanjum
4a5646c8da Cache docker layers, nextjs builds in dockerize github workflow 2024-11-24 21:06:22 -08:00
Debanjum
6a39651ad3 Standardize loading fonts locally across pages on web app 2024-11-24 20:41:15 -08:00
sabaimran
9368699b2c Migrate the pre-commit config 2024-11-24 14:54:26 -08:00
sabaimran
6eb59464da Add additional reinforcement to coax gemini into giving a minimum helpful response 2024-11-24 14:53:53 -08:00
sabaimran
15f062b34a Remove print statement for agent style map 2024-11-24 14:53:53 -08:00
sabaimran
d7e68a2d1b Wait for iplcodata to load before first message 
- Fix the console khoj ai ascii art
- Remove some not so good suggested prompt
 2024-11-24 14:53:53 -08:00
Debanjum
f51e0f7859 Make Next.js create production builds of web app for Docker images 2024-11-24 13:59:40 -08:00
Debanjum
710e00ad9e Make tailwind extensions prod, instead of dev, deps of web app 2024-11-24 13:59:40 -08:00
Debanjum
4b486ea5f6 Exclude unnecessary directories from final docker builds 2024-11-24 13:59:40 -08:00
Debanjum
78d8ca49ec Skip Nvidia GPU python packages during Server install in Dockerfiles 2024-11-24 13:59:39 -08:00
Debanjum
37887a175a Speed up Docker image builds using multi-stage parallel pipelines 
Decouple web app, server builds in parallel to speed up Docker
builds
 2024-11-24 12:48:30 -08:00
Debanjum
7c77d65d35 Improve logic to disable telemetry via KHOJ_TELEMETRY_DISABLE env var 
The newly added KHOJ_TELEMETRY_DISABLE env var knob to disable
telemetry should override old config mechanism when set
 2024-11-24 00:54:16 -08:00
sabaimran
2d683898c2 Release Khoj version 1.30.7 2024-11-23 22:51:10 -08:00
sabaimran
914ff994f7 Fix cost addition to chat_metadata 2024-11-23 22:50:45 -08:00
Debanjum
caaa127dcf Release Khoj version 1.30.6 2024-11-23 21:07:00 -08:00
Debanjum
57b8273002 Fix apt install for musl-dev in prod.Dockerfile 2024-11-23 21:06:09 -08:00
Debanjum
8f966b11ec Release Khoj version 1.30.5 2024-11-23 20:49:05 -08:00
Debanjum
498895a47d Fix libmusl error using pre-built llama-cpp-python wheel in prod Docker 2024-11-23 20:47:41 -08:00
Debanjum
e5b211a743 Release Khoj version 1.30.4 2024-11-23 19:48:21 -08:00
Debanjum
9848d89d03 Try build docker images with github high cpu, ram runner 2024-11-23 19:09:36 -08:00
Debanjum
04bb3d6f15 Fix libmusl error using pre-built llama-cpp-python wheel via Docker 
Seems like llama-cpp-python pre-built wheels need libmusl. Otherwise
you run into runtime errors on Khoj startup via Docker.
 2024-11-23 18:46:44 -08:00
Debanjum
8dd2122817 Set sample size to 200 for automated eval runs as well 2024-11-23 14:48:38 -08:00
Debanjum
c4ef31d86f Release Khoj version 1.30.3 2024-11-23 14:40:06 -08:00
Debanjum
15ae22bdcf Use pre-built llama-cpp-python wheel in Khoj docker images 
Reduces build time and resolves FileNotFoundError 'ninja' during
llama-cpp-python local build.
 2024-11-23 14:38:07 -08:00
sabaimran
4ac49ca90f Release Khoj version 1.30.2 2024-11-23 12:00:28 -08:00
sabaimran
eb1b21baaa Add a new sign in modal that is triggered from the login prompt screen, rather than redirecting user to another screen to sign in 2024-11-23 11:55:34 -08:00
Debanjum
5aa5cb1941 Add "New" section with latest updates to Readme 2024-11-23 01:36:50 -08:00
sabaimran
7f5bf35806 Disambiguate renewal_date type. Previously, being used as None, False, and Datetime in different places. 2024-11-22 12:06:20 -08:00
sabaimran
5e8c824ecc Improve the experience for finding past conversation 
- add a conversation title search filter, and an agents filter, for finding conversations
- in the chat session api, return relevant agent style data
 2024-11-22 12:03:01 -08:00
sabaimran
a761865724 Fix handling of customer.subscription.updated event to process new renewal end date 2024-11-22 12:03:01 -08:00
sabaimran
6a054d884b Add quicker/easier filtering on auth 2024-11-22 12:03:01 -08:00
Debanjum
b9a889ab69 Fix Khoj responses when code generated charts in response context 
The current fix should improve Khoj responses when charts in response
context. It truncates code context before sharing with response chat actors.

Previously Khoj would respond with it not being able to create chart
but than have a generated chart in it's response in default mode.

The truncate code context was added to research chat actor for
decision making but it wasn't added to conversation response
generation chat actors.

When khoj generated charts with code for its response, the images in
the context would exceed context window limits.

So the truncation logic to drop all past context, including chat
history, context gathered for current response.

This would result in chat response generator 'forgetting' all for the
current response when code generated images, charts in response context.
 2024-11-21 14:43:52 -08:00
Debanjum
5475a262d4 Move truncate code context func for reusability across modules 
It needs to be used across routers and processors. It being in
run_code tool makes it hard to be used in other chat provider contexts
due to circular dependency issues created by
send_message_to_model_wrapper func
 2024-11-21 14:27:39 -08:00
Debanjum
f434c3fab2 Fix toggling prompt tracer on/off in Khoj via PROMPTRACE_DIR env var 
Previous changes to depend on just the PROMPTRACE_DIR env var instead
of KHOJ_DEBUG or verbosity flag was partial/incomplete.

This fix adds all the changes required to only depend on the
PROMPTRACE_DIR env var to enable/disable prompt tracing in Khoj.
 2024-11-21 14:06:00 -08:00
Debanjum
4a40cf79c3 Add docs on how to cross-device access self-hosted khoj using tailscale 2024-11-21 11:07:18 -08:00
Debanjum
1f96c13f72 Enable starting khoj uvicorn server with ssl cert file, key for https 
Pass your domain cert files via the --sslcert, --sslkey cli args.
For example, to start khoj at https://example.com, you'd run command:

KHOJ_DOMAIN=example.com khoj --sslcert example.com.crt --sslkey
example.com.key --host example.com

This sets up ssl certs directly with khoj without requiring a
reverse proxy like nginx to serve khoj behind https endpoint for
simple setups. More complex setups should, of course, still use a
reverse proxy for efficient request processing
 2024-11-21 11:07:18 -08:00
sabaimran
9fea02f20f In telemetry, differentiate create_user google and email 2024-11-21 11:01:37 -08:00
sabaimran
9db885b5f7 Limit access to chat models to futurist users 2024-11-21 07:53:24 -08:00
sabaimran
7a00a07398 Add trailing slash to Ollama url in docs 2024-11-21 07:48:18 -08:00
sabaimran
3519dd76f0 Fix type of excalidraw image response 2024-11-20 19:01:13 -08:00
sabaimran
467de76fc1 Improve the image diagramming prompts and response parsing 2024-11-20 18:59:40 -08:00
Debanjum
50d8405981 Enable khoj to use terrarium code sandbox as tool in eval workflow 2024-11-20 14:19:27 -08:00
Debanjum
2203236e4c Update desktop app dependencies 2024-11-20 13:05:55 -08:00
Debanjum
409204917e Update documentation website dependencies 2024-11-20 13:05:32 -08:00
Debanjum
6f1adcfe67 Track Usage Metrics in Chat API. Track Running Cost, Accuracy in Evals (#985) 
- Track, return cost and usage metrics in chat api response
  Track input, output token usage and cost of interactions with 
  openai, anthropic and google chat models for each call to the khoj chat api
- Collect, display and store costs & accuracy of eval run currently in progress
  This provides more insight into eval runs during execution 
  instead of having to wait until the eval run completes.
 2024-11-20 12:59:44 -08:00
Debanjum
ffbd0ae3a5 Fix eval github workflow to run on releases, i.e on tags push 2024-11-20 12:57:42 -08:00
Debanjum
ed364fa90e Track running costs & accuracy of eval runs in progress 
Collect, display and store running costs & accuracy of eval run.

This provides more insight into eval runs during execution instead of
having to wait until the eval run completes.
 2024-11-20 12:40:51 -08:00
Debanjum
bbd24f1e98 Improve dropdown menus on web app setting page with scroll & min-width 
- Previously when settings list became long the dropdown height would
  overflow screen height. Now it's max height is clamped and  y-scroll
- Previously the dropdown content would take width of content. This
  would mean the menu could sometimes be less wide than the button. It
  felt strange. Now dropdown content is at least width of parent button
 2024-11-20 12:27:13 -08:00
Debanjum
c53c3db96b Track, return cost and usage metrics in chat api response 
- Track input, output token usage and cost for interactions
  via chat api with openai, anthropic and google chat models

- Get usage metadata from OpenAI using stream_options
- Handle openai proxies that do not support passing usage in response

- Add new usage, end response  events returned by chat api.
  - This can be optionally consumed by clients at a later point
  - Update streaming clients to mark message as completed after new
    end response event, not after end llm response event
- Ensure usage data from final response generation step is included
  - Pass usage data after llm response complete. This allows gathering
    token usage and cost for the final response generation step across
    streaming and non-streaming modes
 2024-11-20 12:17:58 -08:00
Debanjum
80df3bb8c4 Enable prompt tracing only when PROMPTRACE_DIR env var set 
Better to decouple prompt tracing from debug mode or verbosity level
and require explicit, independent config to enable prompt tracing
 2024-11-20 11:54:02 -08:00
Debanjum
9ab76ccaf1 Skip adding agent to chat metadata when chat unset to avoids null ref 2024-11-19 21:10:23 -08:00
Debanjum
4da0499cd7 Stream responses by openai's o1 model series, as api now supports it 
Previously o1 models did not support streaming responses via API. Now
they seem to do
 2024-11-19 21:10:23 -08:00
sabaimran
e5347dac8c Fix base image used for prod in docs 2024-11-19 15:51:27 -08:00
sabaimran
b943069577 Fix button text, and login url in self-hosted auth docs 2024-11-19 15:50:13 -08:00
sabaimran
3b5e6a9f4d Update authentication documentation 2024-11-19 15:45:47 -08:00
Debanjum
7bdc9590dd Fix handling sources, output in chat actor when is automated task 
Remove unnecessary ```python prefix removal. It isn't being triggered
in json deserialize path.
 2024-11-19 13:49:27 -08:00
Debanjum
0e7d611a80 Remove ```python codeblock prefix from raw json before deserialize 2024-11-19 12:53:52 -08:00
Debanjum
001c13ef43 Upgrade web app package dependencies 2024-11-19 12:53:52 -08:00
sabaimran
4f5c1eeded Update some of the open graph data for the documentation website 2024-11-19 11:14:46 -08:00
sabaimran
5134d49d71 Release Khoj version 1.30.1 2024-11-18 17:30:33 -08:00
sabaimran
8bdd0b26d3 And a connections clean up decorator to all scheduled tasks 2024-11-18 17:19:36 -08:00
Debanjum
817601872f Update default offline models enabled 2024-11-18 16:38:17 -08:00
Debanjum
45c623f95c Dedupe, organize chat actor, director tests 
- Move Chat actor tests that were previously in chat director tests file
- Dedupe online, offline io selector chat actor tests
 2024-11-18 16:10:50 -08:00
Debanjum
2a76c69d0d Run online, offine chat actor, director tests for any supported provider 
- Previously online chat actors, director tests only worked with openai.
  This change allows running them for any supported onlnie provider
  including Google, Anthropic and Openai.

- Enable online/offline chat actor, director in two ways:
  1. Explicitly setting KHOJ_TEST_CHAT_PROVIDER environment variable to
     google, anthropic, openai, offline
  2. Implicitly by the first API key found from openai, google or anthropic.

- Default offline chat provider to use Llama 3.1 3B for faster, lower
  compute test runs
 2024-11-18 15:11:37 -08:00
Debanjum
653127bf1d Improve data source, output mode selection 
- Set output mode to single string. Specify output schema in prompt
  - Both thesee should encourage model to select only 1 output mode
    instead of encouraging it in prompt too many times
  - Output schema should also improve schema following in general
- Standardize variable, func name of io selector for readability
- Fix chat actors to test the io selector chat actor
- Make chat actor return sources, output separately for better
  disambiguation, at least during tests, for now
 2024-11-18 15:11:37 -08:00
Debanjum
e3fd51d14b Pass user arg to create title from query in new automation flow 2024-11-18 12:58:10 -08:00
Debanjum
9e74de9b4f Improve serializing conversation JSON to print messages on console 
- Handle chatml message.content with non-json serializable data like
  WebP image binary data used by Gemini models
 2024-11-18 12:57:05 -08:00
sabaimran
3f70d2f685 Add more graceful exception handling when tool selection doesn't work 2024-11-18 09:34:49 -08:00
Debanjum
a2ccf6f59f Fix github workflow to start Khoj, connect to PG and upload results 
- Do not trigger tests to run in ci on update to evals
 2024-11-18 04:25:15 -08:00
Debanjum
7c0fd71bfd Add GitHub workflow to quiz Khoj across modes and specified evals (#982) 
- Evaluate khoj on random 200 questions from each of google frames and openai simpleqa benchmarks across *general*, *default* and *research* modes
- Run eval with Gemini 1.5 Flash as test giver and Gemini 1.5 Pro as test evaluator models
- Trigger eval workflow on release or manually
- Make dataset, khoj mode and sample size configurable when triggered via manual workflow
- Enable Web search, webpage read tools during evaluation
 2024-11-18 02:19:30 -08:00
sabaimran
f75085dc7a Release Khoj version 1.30.0 2024-11-17 21:36:22 -08:00
sabaimran
c72813ba67 Merge pull request #981 from rznzippy/bugfix/980/database-connections-leakage 
Fix database connections leakage (#980)
 2024-11-17 21:01:06 -08:00
sabaimran
7d50c6590d Merge pull request #977 from khoj-ai/features/improve-tool-selection 
- JSON extract from LLMs is pretty decent now, so get the input tools and output modes all in one go. It'll help the model think through the full cycle of what it wants to do to handle the request holistically.
- Make slight improvements to tool selection indicators
 2024-11-17 20:08:19 -08:00
sabaimran
282f47e0d6 Add Jina documentation to readme for self-hosting 2024-11-17 17:20:28 -08:00
Debanjum
48567fd468 Do not erase partial message when generation stopped via button on web app 
Previously, we'd replace the generated message with an error message
when message generation stopped via stop button on chat page of web app.
So the partially generated message (which could be useful) gets lost.

This change just stops generation, while keeping the generated
response so any useful information from the partially generated
message can be retrieved.
 2024-11-17 16:29:18 -08:00
Debanjum
285006d6c9 Sync chat models in Khoj with OpenAI proxies (e.g Ollama) on startup 
- Allows managing chat models in the OpenAI proxy service like Ollama.
- Removes need to manually add, remove chat models from Khoj Admin Panel
  for these OpenAI compatible API services when enabled.
- Khoj still mantains the chat models configs within Khoj, so they can
  be configured via the Khoj admin panel as usual.
 2024-11-17 15:34:36 -08:00
Debanjum
4a7f5d1abe Set API keys in docker-compose.yml to enable web search, scrape tools 2024-11-17 15:34:36 -08:00
Debanjum
d6eece63f4 Use Jina API Key of Jina web scraper if configured in DB 
Previously Jina search didn't API key. Now that it does need API key,
we should re-use the API key set in the Jina web scraper config,
otherwise fallback to using JINA_API_KEY from environment variable, if
either is present.

Resolves #978
 2024-11-17 15:34:14 -08:00
sabaimran
6531f24ca0 Further improvements for descriptions to LLM on modes, code, diagram, image. 2024-11-17 13:23:57 -08:00
sabaimran
0eba6ce315 When diagram generation fails, save to conversation log 
- Update tool name when choosing tools to execute
 2024-11-17 13:23:12 -08:00
sabaimran
7e662a05f8 Merge branch 'master' of github.com:khoj-ai/khoj into features/improve-tool-selection 2024-11-17 12:26:55 -08:00
Ilya Khrustalev
00b1af8f99 Fix database connections leakage (#980) 2024-11-17 19:15:05 +01:00
Debanjum
69ef6829c1 Simplify integrating Ollama, OpenAI proxies with Khoj on first run 
- Integrate with Ollama or other openai compatible APIs by simply
  setting `OPENAI_API_BASE' environment variable in docker-compose etc.
- Update docs on integrating with Ollama, openai proxies on first run
- Auto populate all chat models supported by openai compatible APIs
- Auto set vision enabled for all commercial models

- Minor
  - Add huggingface cache to khoj_models volume. This is where chat
  models and (now) sentence transformer models are stored by default
  - Reduce verbosity of yarn install of web app. Otherwise hit docker
  log size limit & stops showing remaining logs after web app install
  - Suggest `ollama pull <model_name>` to start it in background
 2024-11-17 02:08:20 -08:00
Debanjum
2366fa08b9 Update default vision supported & anthropic chat models on first run 
- Update to latest initialize with new claude 3.5 sonnet and haiku models
- Update to set vision enabled for google and anthropic models by
  default. Previously we didn't support but we've supported this for a
  month or two now
 2024-11-17 02:08:20 -08:00
Debanjum
23ab258d78 Improve user conversation config details on Admin panel 
Show user email and chat model that is associated with the user
conversation config
 2024-11-17 02:08:20 -08:00
Debanjum
41d9011a26 Move evaluation script into tests/evals directory 
This should give more space for eval scripts, results and readme
 2024-11-17 02:08:20 -08:00
Debanjum
d9d5884958 Enable evaluating Khoj on the OpenAI SimpleQA bench using eval script 
- Just load the raw csv from OpenAI bucket. Normalize it into FRAMES format
- Improve docstring for frames datasets as well
- Log the load dataset perf timer at info level
 2024-11-17 02:08:20 -08:00
Debanjum
eb5bc6d9eb Remove Talc search bench from Khoj eval script 2024-11-17 02:08:20 -08:00
Debanjum
fc45aceecf Delete unused favicon ico in old web app directory 2024-11-17 02:08:20 -08:00
Debanjum
a16fc3ade8 Only add /research prefix when no slash command in message on web app 
- Explictly adding a slash command is a higher priority intent than
  research mode being enabled in the background. Respect that for a
  more intuitive UX flow.

- Explicit slash commands do not currently work in research mode.
  You've to turn research mode off to use other slash commands. This
  is strange, unnecessary given intent priority is clear.
 2024-11-17 02:08:20 -08:00
sabaimran
a1b4587b34 Remove extract_images flag from PDF loader 2024-11-15 21:46:35 -08:00
sabaimran
15b4cec1e8 Add documentation for how to use the text to image model configs, reduce to Replicate 2024-11-15 15:26:14 -08:00
sabaimran
759873ec44 Add documentation for how to use the text to image model configs 2024-11-15 15:22:06 -08:00
sabaimran
c77dc84a68 Remove output_modes function reference in chat tests 2024-11-15 14:03:07 -08:00
sabaimran
e3f1ea9dee Improve tool, output mode selection process 
- JSON extract from LLMs is pretty decent now, so get the input tools and output modes all in one go. It'll help the model think through the full cycle of what it wants to do to handle the request holistically.
- Make slight improvements to tool selection indicators
 2024-11-15 13:53:53 -08:00
sabaimran
c1a5b32ebf Do not start server when importing the main.py file, unless gunicorn 
- Add more graceful shutdown when closing bg scheduler thread
 2024-11-14 17:36:51 -08:00
sabaimran
be3ee5ec9f Add cool new suggestion cards for math, diagramming 2024-11-14 17:36:51 -08:00
Debanjum
9fc44f1a7f Enable evaluation Khoj on the Talc Search Bench using Eval script 
- Just load the raw jsonl from Github and normalize it into FRAMES format
- Color printed accuracy in eval script to blue for readability
 2024-11-13 22:50:14 -08:00
Debanjum
8e009f48ce Show tool call error in next iteration. Allow rerun if model requests. 
Previously errors would get eaten up but the model wouldn't see
anything. And the model wouldn't be allowed re-run the same query-tool
combination in the next iteration.

This update should give it insight into why it didn't get a result. So
it can make an informed (hopefully better) decision on what to do next.
And re-run the previous query if appropriate.
 2024-11-13 22:50:14 -08:00
Debanjum
604da90fa8 Wrap try/catch around online search in research mode like other tools 
Previously when call to online search API etc. failed, it'd error out
of response to query in research mode. Khoj should skip tool use that
iteration but continue to try respond.
 2024-11-13 16:46:09 -08:00
Debanjum
8851b5f78a Standardize chat message truncation and serialization before print 
Previously chatml messages were just strings, now they can be list of
strings or list of dicts as well.

- Use json seriallization to manage their variations and truncate them
  before printing for context.
- Put logic in single function for use across chat models
 2024-11-13 16:30:17 -08:00
Debanjum
f4e37209a2 Improve error handling, display and configurability of eval script 
- Default to evaluation decision of None when either agent or
  evaluator llm fails. This fixes accuracy calculations on errors
- Fix showing color for decision True
- Enable arg flags to specify output results file paths
 2024-11-13 14:32:22 -08:00
Debanjum
15b0cfa3dd Improve structured message truncation in logger 
Previously chatml messages were just strings.
Since gemini, anthropic models always have messages as list of
strings, truncate those strings instead of the list of message content
 2024-11-13 14:32:22 -08:00
Debanjum
153ae8bea9 Cut binary, long output files from code result for context efficiency 
Removing binary data and truncating large data in output files
generated by code runs should improve speed and cost of research mode
runs with large or binary output files.

Previously binary data in code results was passed around in iteration
context during research mode. This made the context inefficient
because models have limited efficiency and reasoning capabilities over
b64 encoded image (and other binary) data and would hit context limits
leading to unnecessary truncation of other useful context

Also remove image data when logging output of code execution
 2024-11-13 14:32:22 -08:00
sabaimran
de34cc3987 Remove og image url with khoj documentation 2024-11-13 10:23:02 -08:00
sabaimran
4a1b1e8b9a Add support for interrupting messages after they've been sent. 2024-11-12 22:22:45 -08:00
sabaimran
d607ad7a27 Release Khoj version 1.29.1 2024-11-12 10:32:56 -08:00
sabaimran
8ec1764e42 Handle size calculation more gracefully for converted documents, depending on type 2024-11-12 02:00:29 -08:00
sabaimran
b6714c202f Increase the title character limit to 500 for conversations 2024-11-12 01:51:19 -08:00
sabaimran
f05e64cf8c Release Khoj version 1.29.0 2024-11-11 21:46:25 -08:00
sabaimran
47d3c8c235 Remove email query parameter from subscription patch api 2024-11-11 21:39:49 -08:00
sabaimran
d7027109a5 And null handling for response output_files in code output 2024-11-11 21:14:56 -08:00
sabaimran
d68243a3fb Revert clean_json logic temporarily. Eventually, we should do better validation here to extract markdown-formatted json. 2024-11-11 21:05:17 -08:00
sabaimran
1cab6c081f Add better error handling for diagram output, and fix chat history construct 
- Make the `clean_json` method more robust as well
 2024-11-11 20:44:19 -08:00
sabaimran
7bd2f83f97 Wrap test in suggestionCard 2024-11-11 20:12:46 -08:00
Debanjum
48862a8400 Enable Passing External Documents for Analysis in Code Sandbox (#960) 
- Allow passing user files as input into code sandbox for analysis
- Update prompt to give more example of complex, multi-line code
- Simplify logic for model. Run one program at a time, 
  instead of allowing model to run multiple programs in parallel
- Show Code generated charts and docs in Reference pane of web app and make them downloaded
 2024-11-11 19:37:17 -08:00
Debanjum
5078ac0ce2 Await on conversation save when generate conversation title via API 2024-11-11 19:17:39 -08:00
Debanjum
e1d0015248 Allow disabling Khoj telemetry via KHOJ_TELEMETRY_DISABLE env var 2024-11-11 19:17:39 -08:00
Debanjum
a52500d289 Show generated code artifacts before notes and online references 2024-11-11 18:00:22 -08:00
Debanjum
218eed83cd Show output file not code on hover. Remove reference card title border 2024-11-11 18:00:22 -08:00
Debanjum
b970cfd4b3 Align styling of reference panel card across code, docs, web results 
- Add a border below heading
- Show code snippet in pre block
- Overflow-x when reference side panel open to allow seeing whole text
  via x-scroll
- Align header, body position of reference cards with each other
- Only show filename in doc reference cards at message bottom.
  Show full file path in hover and reference side panel
 2024-11-11 18:00:22 -08:00
Debanjum
8e9f4262a9 Render code output files with code references in reference section 
- Improve rendering code reference with better icons, smaller text and
  different line clamps for better visibility
- Show code output files as sub card of code card in reference section
- Allow downloading files generated by code instead of rendering it in
  chat message directly
- Show executed code before online references in reference panel
 2024-11-11 18:00:22 -08:00
Debanjum
92c1efe6ee Fixes to render & save code context with non text based output modes 
- Fix to render code generated chart with images, excalidraw diagrams
- Fix to save code context to chat history in image, diagram output modes
- Fix bug in image markdown being wrapped twice in markdown syntax
- Render newline in code references shown on chat page of web app
  Previously newlines weren't getting rendered. This made the code
  executed by Khoj hard to read in references. This changes fixes that.

  `dangerouslySetInnerHTML' usage is justified as rendered code
  snippet is being sanitized by DOMPurify before rendering.
 2024-11-11 18:00:22 -08:00
Debanjum
af0215765c Decode code text output files from b64 to str to ease client processing 2024-11-11 18:00:22 -08:00
Debanjum
7b39f2014a Enable analysing user documents in code sandbox and other improvements 
- Run one program at a time, instead of allowing model to pass
  multiple programs to run in parallel to simplify logic for model
- Update prompt to give more example of complex, multi-line code
- Allow passing user files as input into code sandbox for analysis

- Log code execution timer at info level to evaluate execution latencies
  in production

- Type the generated code for easier processing by caller functions
 2024-11-11 17:59:37 -08:00
sabaimran
dc109559d4 Research mode gray when off, colored when on 2024-11-11 16:35:07 -08:00
sabaimran
cdda9c2e73 Improve text wrapping for attached files and preview context 
For the research mode toggle, make it not fill when it's off
 2024-11-11 13:32:10 -08:00
sabaimran
dd36303bb7 Fix sending file attachments in save_to_conversation method 
- When files attached but upload fails, don't update the state variables
- Make removing null characters in pdf extraction more space efficient
 2024-11-11 12:53:06 -08:00
Debanjum
ba2471dc02 Do not CRUD on entries, files & conversations in DB for null user (#958) 
Increase defense-in-depth by reducing paths to create, read, update or delete entries, files and conversations in DB when user is unset.
 2024-11-11 12:47:22 -08:00
Debanjum
536fe994be Remove unused db adapter methods, like for fact checker data store 2024-11-11 12:22:34 -08:00
Debanjum
10bca6fa8f Convert required user param check into decorator. Use with more adapters 2024-11-11 12:22:32 -08:00
Debanjum
ff5c10c221 Do not CRUD on entries, files & conversations in DB for null user 
Increase defense-in-depth by reducing paths to create, read, update or
delete entries, files and conversations in DB when user is unset.
 2024-11-11 12:20:07 -08:00
sabaimran
27fa39353e Make custom agent creation flow available to everyone 
- For private agents, add guardrails to prevent against any misuse or violation of terms of service.
 2024-11-11 11:54:59 -08:00
sabaimran
b563f46a2e Merge pull request #957 from khoj-ai/features/include-full-file-in-convo-with-filter 
Support including file attachments in the chat message

Now that models have much larger context windows, we can reasonably include full texts of certain files in the messages. Do this when an explicit file filter is set in a conversation. Do so in a separate user message in order to mitigate any confusion in the operation.

Pipe the relevant attached_files context through all methods calling into models.

This breaks certain prior behaviors. We will no longer automatically be processing/generating embeddings on the backend and adding documents to the "brain". You'll have to go to settings and go through the upload documents flow there in order to add docs to the brain (i.e., have search include them during question / response).
 2024-11-11 11:34:42 -08:00
sabaimran
2bb2ff27a4 Rename attached_files to query_files. Update relevant backend and client-side code. 2024-11-11 11:21:26 -08:00
sabaimran
47937d5148 Merge branch 'features/include-full-file-in-convo-with-filter' of github.com:khoj-ai/khoj into features/include-full-file-in-convo-with-filter 2024-11-11 09:34:08 -08:00
sabaimran
ae4eb96d48 Consolidate file name to icon mapping 2024-11-11 09:34:04 -08:00
Debanjum
7954f39633 Use accept param to file input to indicate supported file types in web app 
Remove unused total size calculations in chat input
 2024-11-11 04:06:17 -08:00
Debanjum
4223b355dc Use python stdlib methods to write pdf, docx to temp files for loaders 
Use python standard method tempfile.NamedTemporaryFile to write,
delete temporary files safely.
 2024-11-11 03:24:50 -08:00
Debanjum
fd15fc1e59 Move construct chat history back to it's original position in file 
Keep function where it original was allows tracking diffs and change
history more easily
 2024-11-11 03:24:50 -08:00
Debanjum
35d6c792e4 Show snippet of truncated messages in debug logs to avoid log flooding 2024-11-11 02:30:38 -08:00
sabaimran
8805e731fd Merge branch 'master' of github.com:khoj-ai/khoj into features/include-full-file-in-convo-with-filter 2024-11-10 19:24:11 -08:00
sabaimran
a5e2b9e745 Exit early when running an automation if the conversation for the automation does not exist. 2024-11-10 19:22:21 -08:00
sabaimran
55200be4fa Apply agent color fill to the toggle both in off and on states 2024-11-10 19:16:43 -08:00
Debanjum
7468f6a6ed Deduplicate online references returned by chat API to clients 
This will ensure only unique online references are shown in all
clients.

The duplication issue was exacerbated in research mode as even with
different online search queries, you can get previously seen results.

This change does a global deduplication across all online results seen
across research iterations before returning them in client reponse.
 2024-11-10 16:10:32 -08:00
Debanjum
137687ee49 Deduplicate searches in normal mode & across research iterations 
- Deduplicate online, doc search queries across research iterations.
  This avoids running previously run online, doc searches again and
  dedupes online, doc context seen by model to generate response.
- Deduplicate online search queries generated by chat model for each
  user query.
- Do not pass online, docs, code context separately when generate
  response in research mode. These are already collected in the meta
  research passed with the user query
- Improve formatting of context passed to generate research response
  - Use xml tags to delimit context. Pass per iteration queries in each
    iteration result
  - Put user query before meta research results in user message passed
    for generating response

This deduplications will improve speed, cost & quality of research mode
 2024-11-10 16:10:32 -08:00
Debanjum
306f7a2132 Show error in picking next tool to researcher llm in next iteration 
Previously the whole research mode response would fail if the pick
next tool call to chat model failed. Now instead of it completely
failing, the researcher actor is told to try again in next iteration.

This allows for a more graceful degradation in answering a research
question even if a (few?) calls to the chat model fail.
 2024-11-10 14:52:02 -08:00
Debanjum
eb492f3025 Only keep webpage content requested, even if Jina API gets more data 
Jina search API returns content of all webpages in search results.
Previously code wouldn't remove content beyond max_webpages_to_read
limit set. Now, webpage content in organic results aree explicitly
removed beyond the requested max_webpage_to_read limit.

This should align behavior of online results from Jina with other
online search providers. And restrict llm context to a reasonable size
when using Jina for online search.
 2024-11-10 14:51:16 -08:00
Debanjum
8ef7892c5e Exclude non-dictionary doc context from chat history sent to chat models 
This fixes chat with old chat sessions. Fixes issue with old Whatsapp
users can't chat with Khoj because chat history doc context was
stored as a list earlier
 2024-11-10 14:51:16 -08:00
Debanjum
d892ab3174 Fix handling of command rate limit and improve rate limit messages 
Command rate limit wouldn't be shown to user as server wouldn't be
able to handle HTTP exception in the middle of streaming.

Catch exception and render it as LLM response message instead for
visibility into command rate limiting to user on client

Log rate limmit messages for all rate limit events on server as info
messages

Convert exception messages into first person responses by Khoj to
prevent breaking the third wall and provide more details on wht
happened and possible ways to resolve them.
 2024-11-10 14:51:16 -08:00
Debanjum
80ee35b9b1 Wrap messages in web, obsidian UI to stay within screen when long links 
Wrap long links etc. in chat messages and train of thought lists on
web app app and obsidian plugin by breaking them into newlines by word
 2024-11-10 14:49:51 -08:00
Debanjum
f967bdf702 Show correct example index being currently processed in frames eval 
Previously the batch start index wasn't being passed so all batches
started in parallel were showing the same processing example index

This change doesn't impact the evaluation itself, just the index shown
of the example currently being evaluated
 2024-11-10 14:49:51 -08:00
Debanjum
84a8088c2b Only evaluate non-empty responses to reduce eval script latency, cost 
Empty responses by Khoj will always be an incorrect response, so no
need to make call to an evaluator agent to check that
 2024-11-10 14:49:51 -08:00
sabaimran
170d959feb Handle offline messages differently, as they don't respond well to the structured messages 2024-11-09 19:52:46 -08:00
sabaimran
2c543bedd7 Add typing to the constructed messages listed 2024-11-09 19:40:27 -08:00
sabaimran
79b15e4594 Only add images when they're present and vision enabled 2024-11-09 19:37:30 -08:00
sabaimran
bd55028115 Fix randint import from random when creating filenames for tmp 2024-11-09 19:17:18 -08:00
sabaimran
92b6b3ef7b Add attached files to latest structured message in chat ml format 2024-11-09 19:17:00 -08:00
sabaimran
835fa80a4b Allow docx conversion in the chatFunction.ts 2024-11-09 18:51:00 -08:00
sabaimran
459318be13 And random suffixes to decreases any clash probability when writing tmp files to disc 2024-11-09 18:46:34 -08:00
sabaimran
dbf0c26247 Remove _summary_ description in function descriptions 2024-11-09 18:42:42 -08:00
sabaimran
e5ac076fc4 Move construct_chat_history method back to conversation.utils.py 2024-11-09 18:27:46 -08:00
sabaimran
bc95a99fb4 Make tracer the last input parameter for all the relevant chat helper methods 2024-11-09 18:22:46 -08:00
sabaimran
ceb29eae74 Add phone number verification and remove telemetry update call from place where authentication middleware isn't yet installed (in the middleware itself). 2024-11-09 12:25:36 -08:00
sabaimran
3badb27744 Remove stored uploaded files after they're processed. 2024-11-08 23:28:02 -08:00
sabaimran
78630603f4 Delete the fact checker application 2024-11-08 17:27:42 -08:00
sabaimran
807687a0ac Automatically generate titles for conversations from history 2024-11-08 16:02:34 -08:00
sabaimran
7159b0b735 Enforce limits on file size when converting to text 2024-11-08 15:27:28 -08:00
sabaimran
4695174149 Add support for file preview in the chat input area (before message sent) 2024-11-08 15:12:48 -08:00
sabaimran
ad46b0e718 Label pages when extract text from pdf, docs content. Fix scroll area in doc preview. 2024-11-08 14:53:20 -08:00
sabaimran
ee062d1c48 Fix parsing for PDFs via content indexing API 2024-11-07 18:17:29 -08:00
sabaimran
623a97a9ee Merge branch 'master' of github.com:khoj-ai/khoj into features/include-full-file-in-convo-with-filter 2024-11-07 17:18:23 -08:00
sabaimran
33498d876b Simplify the share chat page. Don't need it to maintain its own conversation history 
- When chatting on a shared page, fork and redirect to a new conversation page
 2024-11-07 17:14:11 -08:00
sabaimran
4b8be55958 Convert UUID to string when forking a conversation 2024-11-07 17:13:04 -08:00
sabaimran
9bbe27fe36 Set default value of attached files to empty list 2024-11-07 17:12:45 -08:00
sabaimran
3a51996f64 Process attached files in the chat history and add them to the chat message 2024-11-07 16:06:58 -08:00
sabaimran
a89160e2f7 Add support for converting an attached doc and chatting with it 
- Document is first converted in the chatinputarea, then sent to the chat component. From there, it's sent in the chat API body and then processed by the backend
- We couldn't directly use a UploadFile type in the backend API because we'd have to convert the api type to a multipart form. This would require other client side migrations without uniform benefit, which is why we do it in this two-phase process. This also gives us capacity to repurpose the moe generic interface down the road.
 2024-11-07 16:06:37 -08:00
sabaimran
e521853895 Remove unnecessary console.log statements 2024-11-07 16:03:31 -08:00
sabaimran
92c3b9c502 Add function to get an icon from a file type 2024-11-07 16:02:53 -08:00
sabaimran
140c67f6b5 Remove focus ring from the text area component 2024-11-07 16:02:02 -08:00
sabaimran
b8ed98530f Accept attached files in the chat API 
- weave through all subsequent subcalls to models, where relevant, and save to conversation log
 2024-11-07 16:01:48 -08:00
sabaimran
ecc81e06a7 Add separate methods for docx and pdf files to just convert files to raw text, before further processing 2024-11-07 16:01:08 -08:00
sabaimran
394035136d Add an api that gets a document, and converts it to just text 2024-11-07 16:00:10 -08:00
sabaimran
3b1e8462cd Include attach files in calls to extract questions 2024-11-07 15:59:15 -08:00
sabaimran
de73cbc610 Add support for relaying attached files through backend calls to models 2024-11-07 15:58:52 -08:00
Debanjum
4cad96ded6 Add Script to Evaluate Khoj on Google's FRAMES benchmark (#955) 
- Why
We need better, automated evals to measure performance shifts of Khoj
across prompt, model and capability changes.

Google's FRAMES benchmark evaluates multi-step retrieval and reasoning
capabilities of AI agents. It's a good starter benchmark to evaluate Khoj.

- Details
This PR adds an eval script to evaluate Khoj responses on the the FRAMES
benchmark prompts against the ground truth provided by it.

Script allows configuring sample size, batch size, sampling queries from the
eval dataset.

Gemini is used as an LLM Judge to auto grade Khoj responses vs ground truth 
data from the benchmark.
 2024-11-06 17:52:01 -08:00
Debanjum
8679294bed Remove need to set server chat settings from use openai proxies docs 
This was previously required, but now it's only usefuly for more
advanced settings, not typical for self-hosting users.

With recent updates, the user's selected chat model is used for both
Khoj's train of thought and response. This makes it easy to
switch your preferred chat model directly from the user settings
page and not have to update this in the admin panel as well.

Reflect these code changse in the docs, by removing the unnecessary
step for self-hosted users to create a server chat setting when using
an OpenAI proxy service like Ollama, LiteLLM etc.
 2024-11-05 17:10:53 -08:00
Debanjum
05a93fcbed v-align attach, send buttons with chat input text area on web app 
Otherwise, those buttons look off-center when images are attached to
the chat input area
 2024-11-05 17:10:53 -08:00
sabaimran
a0480d5f6c use fill weight for the toggle right (enabled state) for research mode 2024-11-04 22:01:09 -08:00
sabaimran
dc26da0a12 Add uploaded files in the conversation file filter for a new convo 2024-11-04 22:00:47 -08:00
Debanjum
b51ee644aa Fix escaping filename when normalizing in org node parser 2024-11-04 20:24:57 -08:00
Debanjum
5724d16a6f Fix passing images to anthropic chat models to extract questions 2024-11-04 20:24:57 -08:00
sabaimran
cf0bcec0e7 Revert SKIP_TESTS flag in offline chat director tests 2024-11-04 19:06:54 -08:00
sabaimran
1f372bf2b1 Update file summarization unit tests now that multiple files are allowed 2024-11-04 17:45:54 -08:00
sabaimran
7543360210 Merge branch 'master' of github.com:khoj-ai/khoj into features/include-full-file-in-convo-with-filter 2024-11-04 16:55:48 -08:00
sabaimran
b6145df3be Handle file retrieval when agent is None 2024-11-04 16:55:22 -08:00
sabaimran
3dc9139cee Add additional handling for when file_object comes back empty 2024-11-04 16:53:07 -08:00
sabaimran
a27b8d3e54 Remove summarize condition for only 1 file filter 2024-11-04 16:51:37 -08:00
sabaimran
362bdebd02 Add methods for reading full files by name and including context 
Now that models have much larger context windows, we can reasonably include full texts of certain files in the messages. Do this when an explicit file filter is set in a conversation. Do so in a separate user message in order to mitigate any confusion in the operation.

Pipe the relevant attached_files context through all methods calling into models.

We'll want to limit the file sizes for which this is used and provide more helpful UI indicators that this sort of behavior is taking place.
 2024-11-04 16:37:13 -08:00
sabaimran
e3ca52b7cb Use .get() to get text accompanying image url, instead of subindexing 2024-11-04 16:09:16 -08:00
sabaimran
1e89baca7b Deprecate the UserSearchModelConfig and remove all references 
- The server has moved to a model of standardization for the embeddings generation workflow. Remove references to the support for differentiated models.
- The migration script fo ra new model needs to be updated to accommodate full regeneration.
 2024-11-04 12:24:41 -08:00
Debanjum
1ccbf72752 Use logger instead of print to track eval 2024-11-04 00:40:26 -08:00
sabaimran
99c1d2831a Release Khoj version 1.28.3 2024-11-02 12:23:11 -07:00
sabaimran
075b4ecf15 Call subscription_to_state with sync_to_async wrapper when getting user subscription state 
- This is needed in case the renewal_date is not set and we need to reset it for the user
 2024-11-02 12:22:35 -07:00
sabaimran
ec44cbe1e7 Release Khoj version 1.28.2 2024-11-02 07:53:51 -07:00
Debanjum
791eb205f6 Run prompt batches in parallel for faster eval runs 2024-11-02 04:58:03 -07:00
Debanjum
96904e0769 Add script to evaluate khoj on Google's FRAMES benchmark 
Google's FRAMES benchmark evaluates multi-step retrieval and reasoning
capabilities of an agent.

The script uses Gemini as an LLM Judge to evaluate Khoj responses to
the FRAMES benchmark prompts against the ground truth provided by it.
 2024-11-02 04:57:42 -07:00
Debanjum
31b5fde163 Only enable prompt tracer if git python is installed 2024-11-02 02:07:02 -07:00
sabaimran
5b18dc96e0 Release Khoj version 1.28.1 2024-11-01 22:51:51 -07:00
sabaimran
8d1b1bc78e Move the git python dependency into top level dependencies 2024-11-01 22:51:00 -07:00
Debanjum
e85dd59295 Release Khoj version 1.28.0 2024-11-01 19:06:59 -07:00
Debanjum
1f79a10541 Fix link to code execution feature in docs 2024-11-01 18:22:21 -07:00
Debanjum
cff8e02b60 Research Mode [Part 2]: Improve Prompts, Edit Chat Messages. Set LLM Seed for Reproducibility (#954) 
- Improve chat actors and their prompts for research mode.
- Add documentation to enable the code tool when self-hosting Khoj
- Edit Chat Messages
  - Store Turn Id in each chat message. 
  - Expose API to delete chat message.
  - Expose delete chat message button to turn delete chat message from web app
- Set LLM Generation Seed for Reproducible Debugging and Testing
  - Setting seed for LLM generation is supported by Llama.cpp and OpenAI models. 
    This can (somewhat) restrain LLM output
  - Getting fixed responses for fixed inputs helps test, debug longer reasoning chains like used in advanced reasoning
 2024-11-01 18:16:42 -07:00
Debanjum
14e453039d Add prompt tracing, agent personality to infer webpage urls chat actor 2024-11-01 18:12:50 -07:00
Debanjum
ab321dc518 Expect query before tool in response to give think space in research prompt 2024-11-01 17:51:41 -07:00
Debanjum
1a83bbcc94 Clean API chat router. Move FeedbackData response type to router helper 2024-11-01 17:51:41 -07:00
sabaimran
e6eb87bbb5 Merge branch 'improve-debug-reasoning-and-other-misc-fixes' of github.com:khoj-ai/khoj into improve-debug-reasoning-and-other-misc-fixes 2024-11-01 16:48:39 -07:00
sabaimran
a213b593e8 Limit the number of urls the webscraper can extract for scraping 2024-11-01 16:48:36 -07:00
sabaimran
327fcb8f62 create defiltered query after conversation command is extracted 2024-11-01 16:48:03 -07:00
sabaimran
b79a9ec36d Clarify description of the code evaluation environment: not for document creation 2024-11-01 16:47:27 -07:00
Debanjum
9c7b36dc69 Use standard per minute rate limits across user types 2024-11-01 16:16:06 -07:00
Debanjum
ac21b10dd5 Simplify logic to get default search model. Remove unused import 2024-11-01 15:14:00 -07:00
sabaimran
2b35790165 Merge branch 'master' of github.com:khoj-ai/khoj into improve-debug-reasoning-and-other-misc-fixes 2024-11-01 14:51:26 -07:00
Debanjum
22f3ed3f5d Research Mode: Give Khoj the ability to perform more advanced reasoning (#952) 
## Overview
Khoj can now go into research mode and use a python code interpreter. These are experimental features that are being released early for feedback and testing.

- Research mode allows Khoj to dynamically select the tools it needs to best answer the question. It is also allowed more iterations to get to a satisfactory answer. Its more dynamic train of thought is shown to improve visibility into its thinking.
- Adding ability for Khoj to use a python code interpreter is an adjacent capability. It can help Khoj do some data analysis and generate charts for you. A sandboxed python to run code is provided using [cohere-terrarium](https://github.com/cohere-ai/cohere-terrarium?tab=readme-ov-file), [pyodide](https://pyodide.org/).

## Analysis
Research mode (significantly?) improves Khoj's information retrieval for more complex queries requiring multi-step lookups but takes longer to run. It can research for longer, requiring less back-n-forth with the user to find an answer.

Research mode gives most gains when used with more advanced chat models (like o1, 4o, new claude sonnet and gemini-pro-002). Smaller models improve their response quality but tend to get into repetitive loops more often. 

## Next Steps
- Get community feedback on research mode. What works, what fails, what is confusing, what'd be cool to have.
- Tune Khoj's capabilities for longer autonomous runs and to generalize across a larger range of model sizes

## Miscellaneous Improvements
- Khoj's train of thought is saved and shown for all messages, not just the latest one
- Render charts generated by Khoj and code running using the code tool on the web app
- Align chat input color to currently selected agent color
 2024-11-01 14:46:29 -07:00
sabaimran
baa939f4ce When running code, strip any code delimiters. Disable application json type specification in Gemini request. 2024-11-01 13:47:39 -07:00
sabaimran
8fd2fe162f Determine if research mode is enabled by checking the conversation commands and 'linting' them in the selection phase 2024-11-01 13:12:34 -07:00
sabaimran
cead1598b9 Don't reset research mode after completing research execution 2024-11-01 13:00:11 -07:00
Debanjum
c1c779a7ef Do not yaml format raw code results in context for LLM. It's confusing 2024-11-01 12:45:26 -07:00
sabaimran
b3dad1f393 Standardize rate limits to 1/6 ratio 2024-11-01 12:21:09 -07:00
sabaimran
23a49b6b95 Add documentation for python code execution capability 2024-11-01 12:14:33 -07:00
Debanjum
cd75151431 Do not allow auto selecting research mode as tool for now. 
You are required to manually turning it on. This takes longer and
should be a high intent activity initiated by user
 2024-11-01 12:07:52 -07:00
Debanjum
0b0cfb35e6 Simplify in research mode check in api_chat. 
- Dedent code for readability
- Use better name for in research mode check
- Continue to remove inferred summarize command when multiple files in
  file filter even when not in research mode
- Continue to show select information source train of thought.
  It was removed by mistake earlier
 2024-11-01 12:07:08 -07:00
sabaimran
ffa7f95559 Add template for a code sandbox to the docker-compose configuration 2024-11-01 11:50:58 -07:00
Debanjum
73750ef286 Merge branch 'master' into features/advanced-reasoning 2024-11-01 11:42:01 -07:00
sabaimran
1fc280db35 Handle case where infer_webpage_url returns no valid urls 2024-11-01 11:41:32 -07:00
Debanjum
1c920273dd Add Prompt Tracer to Visualize, Analyze and Debug Khoj's Train of Thought (#951) 
## Overview
Use git to capture prompt traces of khoj's train of thought. View, analyze and debug them using your favorite git client (e.g vscode, magit).

- Each commit captures an interaction with an LLM
  The commit writes the query, response and system message each to a separate file in the repo.
  The commit message captures the chat model, Khoj version and other metadata
- Each conversation turn can have multiple interactions with an LLM (e.g Khoj's train of thought)
- Each new conversation turn forks from and merges back into its conversation branch
- Each new conversation branches from the user branch
- Each new user branches from root commit on the main branch

## Usage
1. Set `KHOJ_DEBUG=true` or start khoj in very verbose mode with `khoj -vv` to turn on prompt tracing
2. Chat with Khoj as usual 
3. Open the promptrace git repo to view the generated prompt traces using your favorite git porcelain. 
   The Khoj prompt trace git repo is created at `/tmp/khoj_promptrace` by default. You can configure the prompt trace directory by setting the `PROMPTRACE_DIR`environment variable.

## Implementation
- Add utility functions to capture prompt traces using git (via `gitpython`)
- Make each model provider in Khoj commit their LLM interactions with promptrace
- Weave chat metadata from chat API through all chat actors and commit it to the prompt trace
 2024-11-01 11:33:54 -07:00
sabaimran
33d36ee58c Add experimental notice to research mode tooltip 2024-11-01 11:00:27 -07:00
sabaimran
0145b2a366 Set usage limits on the research mode 2024-11-01 10:29:33 -07:00
sabaimran
3ea94ac972 Only include inferred-queries in chat history when present 2024-10-31 22:01:41 -07:00
sabaimran
149cbe1019 Use bottom anchor for the commandbar popover 2024-10-31 20:40:38 -07:00
sabaimran
21858acccc Remove conversation command always in query, filter out inferred queries that were not with selected tool when going through tool selection iterations 2024-10-31 20:27:38 -07:00
sabaimran
19241805ee Merge branch 'master' of github.com:khoj-ai/khoj into improve-debug-reasoning-and-other-misc-fixes 2024-10-31 18:20:23 -07:00
Debanjum
302bd51d17 Improve online chat actor prompt for research and normal mode 
- Match the online query generator prompt to match the formatting of
  extract questions
- Separate iteration results by newline
- Improve webpage and online tool descriptions
 2024-10-31 18:17:12 -07:00
Debanjum
52163fe299 Improve research planner prompt to reduce looping 2024-10-31 18:17:01 -07:00
sabaimran
7ebf999688 Merge branch 'master' of github.com:khoj-ai/khoj into features/advanced-reasoning 2024-10-31 18:15:13 -07:00
sabaimran
159ea44883 Remove frame references in the diagramming prompts 2024-10-31 18:14:51 -07:00
Debanjum
89597aefe9 Json dump contents in prompt tracer to make structure discernable 2024-10-31 18:08:42 -07:00
Debanjum
5b15176e20 Only add /research prefix in research mode if not already in user query 2024-10-31 18:08:42 -07:00
sabaimran
559601dd0a Do not exit if/else loop in research loop when notes not found 2024-10-31 13:51:10 -07:00
sabaimran
a13760640c Only show trash can when turnId is present 2024-10-31 13:19:16 -07:00
sabaimran
8d1ecb9bd8 Add optional brew steps for docker install 2024-10-31 12:41:53 -07:00
Debanjum
adca6cbe9d Merge branch 'master' into add-prompt-tracer-for-observability 2024-10-31 02:28:34 -07:00
Debanjum
e17dc9f7b5 Put train of thought ui before Khoj response on web app 2024-10-31 02:24:53 -07:00
Debanjum
e8e6ead39f Fix deleting new messages generated after conversation load 2024-10-30 20:56:38 -07:00
Debanjum
cb90abc660 Resolve train of thought component needs unique key id error on web app 2024-10-30 14:00:21 -07:00
Debanjum
ca5a6831b6 Add ability to delete messages from the web app 2024-10-30 14:00:21 -07:00
Debanjum
ba15686682 Store turn id with each chat message. Expose API to delete chat turn 
Each chat turn is a user query, khoj response message pair
 2024-10-30 14:00:21 -07:00
Debanjum
f64f5b3b6e Handle add/delete file filter operation on non-existent conversation 2024-10-30 14:00:21 -07:00
Debanjum
b3a63017b5 Support setting seed for reproducible LLM response generation 
Anthropic models do not support seed. But offline, gemini and openai
models do. Use these to debug and test Khoj via KHOJ_LLM_SEED env var
 2024-10-30 14:00:21 -07:00
Debanjum
d44e68ba01 Improve handling embedding model config from admin interface 
- Allow server to start if loading embedding model fails with an error.
  This allows fixing the embedding model config via admin panel.

  Previously server failed to start if embedding model was configured
  incorrectly. This prevented fixing the model config via admin panel.

- Convert boolean string in config json to actual booleans when passed
  via admin panel as json before passing to model, query configs

- Only create default model if no search model configured by admin.
  Return first created search model if its been configured by admin.
 2024-10-30 14:00:21 -07:00
Debanjum
358a6ce95d Defer turning cursor color to selected agents color for later 
Capability exists but idea needs to be investigated further
 2024-10-30 14:00:21 -07:00
Debanjum
2ac840e3f2 Make cursor in chat input take on selected agent color 2024-10-30 14:00:21 -07:00
Debanjum
1448b8b3fc Use 3rd person for user in research prompt to reduce person confusion 
Models were getting a bit confused about who is search for who's
information. Using third person to explicitly call out on who's behalf
these searches are running seems to perform better across
models (gemini's, gpt etc.), even if the role of the message is user.
 2024-10-30 13:49:48 -07:00
Debanjum
b8c6989677 Separate example from actual question in extract question prompt 2024-10-30 13:49:48 -07:00
Debanjum
86ffd7a7a2 Handle \n, dedupe json cleaning into single function for reusability 
Use placeholder for newline in json object values until json parsed
and values extracted. This is useful when research mode models outputs
multi-line codeblocks in queries etc.
 2024-10-30 13:49:48 -07:00
Debanjum
83ca820abe Encourage Anthropic models to output json object using { prefill 
Anthropic API doesn't have ability to enforce response with valid json
object, unlike all the other model types.

While the model will usually adhere to json output instructions.

This step is meant to more strongly encourage it to just output json
object when response_type of json_object is requested.
 2024-10-30 13:49:48 -07:00
Debanjum
dc8e89b5de Pass tool AIs iteration history as chat history for better context 
Separate conversation history with user from the conversation history
between the tool AIs and the researcher AI.

Tools AIs don't need top level conversation history, that context is
meant for the researcher AI.

The invoked tool AIs need previous attempts at using the tool in this
research runs iteration history to better tune their next run.

Or at least that is the hypothesis to break the models looping.
 2024-10-30 13:49:48 -07:00
Debanjum
d865994062 Rename code tool arg previous_iteration_history' to context' 2024-10-30 13:49:48 -07:00
Debanjum
06aeca2670 Make researcher, docs search AIs ask more diverse retrieval questions 
Models weren't generating a diverse enough set of questions. They'd do
minor variations on the original query. What is required is asking
queries from a bunch of different lenses to retrieve the requisite
information.

This prompt updates shows the AIs the breadth of questions to by
example and instruction. Seem like performance improved based on vibes
 2024-10-30 13:49:48 -07:00
Debanjum
01881dc7a2 Revert "Make extract question prompt in 1st person wrt user as its a user message" 
This reverts commit 6d3602798aa1b95a30c557576fd4f93ddef2ae76.
 2024-10-30 13:49:48 -07:00
Debanjum
3e695df198 Make extract question prompt in 1st person wrt user as its a user message 
Divide Example from Actual chat history section in prompt
 2024-10-30 13:49:48 -07:00
Debanjum
a3751d6a04 Make extract relevant information system prompt work for any document 
Previously it was too strongly tuned for extracting information from
only webpages. This shouldn't be necessary
 2024-10-30 13:49:48 -07:00
Debanjum
a39e747d07 Improve passing user name in pick next research tool prompt 2024-10-30 13:49:48 -07:00
Debanjum
deff512baa Improve research mode prompts to reduce looping, increase webpage reads 2024-10-30 13:49:48 -07:00
Debanjum
d3184ae39a Simplify storing and displaying document results in research mode 
- Mention count of notes and files disovered
- Store query associated with each compiled reference retrieved for
  easier referencing
 2024-10-30 13:49:48 -07:00
Debanjum
8bd94bf855 Do not use a message branch if no msg id provided to prompt tracer 2024-10-30 13:49:48 -07:00
sabaimran
b63fbc5345 Add a simple badget to the dropdown menu that shows subscription status 2024-10-30 13:00:16 -07:00
sabaimran
82f3d79064 Merge branch 'master' of github.com:khoj-ai/khoj into features/advanced-reasoning 2024-10-30 11:32:10 -07:00
sabaimran
2b2564257e Handle subscription case where it's set to trial, but renewal_date is not set. set the renewal_date for LENGTH_OF_FREE_TRIAL days from subscription creation. 2024-10-30 11:05:31 -07:00
Debanjum
9935d4db0b Do not use a message branch if no msg id provided to prompt tracer 2024-10-28 17:50:27 -07:00
Debanjum
d184498038 Pass context in separate message from user query to research chat actor 2024-10-28 15:37:28 -07:00
Debanjum
d75ce4a9e3 Format online, notes, code context with YAML to be legibile for LLM 2024-10-28 15:37:28 -07:00
sabaimran
5bea0c705b Use break-words in the train of thought for better formatting 2024-10-28 15:36:06 -07:00
sabaimran
1f1b182461 Automatically carry over research mode from home page to chat 
- Improve mobile friendliness with new research mode toggle, since chat input area is now taking up more space
- Remove clunky title from the suggestion card
- Fix fk lookup error for agent.creator
 2024-10-28 15:29:24 -07:00
sabaimran
ebaed53069 Merge branch 'master' of github.com:khoj-ai/khoj into features/advanced-reasoning 2024-10-28 12:39:00 -07:00
sabaimran
889dbd738a Add keyword diagram to diagram output mode description 2024-10-28 12:20:46 -07:00
Debanjum
50ffd7f199 Merge branch 'master' into features/advanced-reasoning 2024-10-28 04:10:59 -07:00
Debanjum
a5d0ca6e1c Use selected agent color to theme the chat input area on home page 2024-10-28 03:47:40 -07:00
Debanjum
aad7528d1b Render slash commands popup below chat input text area on home page 2024-10-28 02:06:04 -07:00
Debanjum
3e17ab438a Separate notes, online context from user message sent to chat models (#950) 
Overview
---
- Put context into separate user message before sending to chat model.
  This should improve model response quality and truncation logic in code
- Pass online context from chat history to chat model for response.
  This should improve response speed when previous online context can be reused
- Improve format of notes, online context passed to chat models in prompt.
  This should improve model response quality

Details
---
The document, online search context are now passed as separate user
messages to chat model, instead of being added to the final user message.

This will improve
- Models ability to differentiate data from user query.
  That should improve response quality and reduce prompt injection
  probability
- Make truncation logic simpler and more robust
  When context window hit, can simply pop messages to auto truncate
  context in order of context, user, assistant message for each
  conversation turn in history until reach current user query

  The complex, brittle logic to extract user query from context in
  last user message isn't required.
 2024-10-28 02:03:18 -07:00
Debanjum
8ddd70f3a9 Put context into separate message before sending to offline chat model 
Align context passed to offline chat model with other chat models

- Pass context in separate message for better separation between user
  query and the shared context
- Pass filename in context
- Add online results for webpage conversation command
 2024-10-28 00:22:21 -07:00
Debanjum
ee0789eb3d Mark context messages with user role as context role isn't being used 
Context role was added to allow change message truncation order based
on context role as well.

Revert it for now since currently this is not currently being done.
 2024-10-28 00:04:14 -07:00
Debanjum
4e39088f5b Make agent name in home page carousel not text wrap on mobile 2024-10-27 23:03:53 -07:00
Debanjum
94074b7007 Focus chat input on toggle research mode. v-align it with send button 2024-10-27 22:54:55 -07:00
sabaimran
a691ce4aa6 Batch entries into smaller groups to process 2024-10-27 20:43:41 -07:00
sabaimran
2924909692 Add a research mode toggle to the chat input area 2024-10-27 16:37:40 -07:00
sabaimran
68499e253b Auto-collapse train of thought, show after chat response in history 2024-10-27 15:48:13 -07:00
sabaimran
101ea6efb1 Add research mode as a slash command, remove from default path 2024-10-27 15:47:44 -07:00
sabaimran
0bd78791ca Let user exit from command mode with esc, click out, etc. 2024-10-27 15:01:49 -07:00
sabaimran
a121d67b10 Persist the train of thought in the conversation history 2024-10-26 23:46:15 -07:00
sabaimran
9e8ac7f89e Fix input/output mismatches in the /summarize command 2024-10-26 16:37:58 -07:00
sabaimran
e4285941d1 Use the advanced chat model if the user is subscribed 2024-10-26 16:00:54 -07:00
sabaimran
33e48aa27e Merge branch 'add-prompt-tracer-for-observability' of github.com:khoj-ai/khoj into features/advanced-reasoning 2024-10-26 14:09:00 -07:00
sabaimran
fd71a4b086 Add better exception handling in the prompt trace logic, use default value from parameters 2024-10-26 14:08:00 -07:00
Debanjum
3e5b5ec122 Encourage model to read webpages more often after online search 
Previously model would rarely read webpages after webpage search. Need
the model to webpages more regularly for deeper research and to stop
getting stuck in repetitive online search loops
 2024-10-26 10:49:09 -07:00
Debanjum
bf96d81943 Format online results as YAML to pass it in more readable form to model 
Previous passing of online results as json dump in prompts was less
readable for humans, and I'm guessing less readable for
models (trained on human data) as well?
 2024-10-26 10:49:09 -07:00
Debanjum
3e97ebf0c7 Unescape special characters in prompt traces for better readability 2024-10-26 10:49:09 -07:00
Debanjum
8af9dc3ee1 Unescape special characters in prompt traces for better readability 2024-10-26 10:45:42 -07:00
Debanjum Singh Solanky
0f3927e810 Send gathered references to client after code results calculated 2024-10-26 05:59:10 -07:00
Debanjum Singh Solanky
f04f871a72 Merge branch 'add-prompt-tracer-for-observability' of github.com:khoj-ai/khoj into features/advanced-reasoning 
- Start from this branches src/khoj/routers/api_chat.py
    Add tracer to all old and new chat actors that don't have it set
    when they are called.
  - Update the new chat actors like apick next tool etc to use tracer too
 2024-10-26 05:56:13 -07:00
Debanjum Singh Solanky
ddc6ccde2d Merge branch 'master' into features/advanced-reasoning 
- Conflicts:
  Combine both sides of the conflict in all 3 files below
  - src/khoj/processor/conversation/utils.py
  - src/khoj/routers/helpers.py
  - src/khoj/utils/helpers.py
 2024-10-26 05:15:51 -07:00
Debanjum Singh Solanky
ea0712424b Commit conversation traces using user, chat, message branch hierarchy 
- Message train of thought forks and merges from its conversation branch
- Conversation branches from user branch
- User branches from root commit on the main branch

- Weave chat tracer metadata from api endpoint through all chat actors
  and commit it to the prompt trace
 2024-10-26 05:08:47 -07:00
Debanjum Singh Solanky
a3022b7556 Allow Offline Chat model calling functions to save conversation traces 2024-10-26 05:08:47 -07:00
Debanjum Singh Solanky
eb6424f14d Allow Anthropic API calling functions to save conversation traces 2024-10-26 05:08:47 -07:00
Debanjum Singh Solanky
6fcd6a5659 Allow Gemini API calling functions to save conversation traces 2024-10-26 05:08:47 -07:00
Debanjum Singh Solanky
384f394336 Allow OpenAI API calling functions to save conversation traces 2024-10-26 04:59:21 -07:00
Debanjum Singh Solanky
10c8fd3b2a Save conversation traces to git for visualization 2024-10-26 04:59:19 -07:00
sabaimran
7e0a692d16 Release Khoj version 1.27.1 2024-10-25 15:23:07 -07:00
sabaimran
b257fa1884 Add a None check before doing a DT comparison when getting subscription type 2024-10-25 15:22:48 -07:00
sabaimran
0f6f282c30 Release Khoj version 1.27.0 2024-10-25 14:11:14 -07:00
sabaimran
479e156168 Add to the ConversationCommand.Image description to LLM 2024-10-25 09:14:32 -07:00
sabaimran
a11b5293fb Add uploaded images to research mode, code slash command, include code references 2024-10-24 23:56:24 -07:00
sabaimran
5acf40c440 Clean up summarization code paths 
Use assumption of summarization response being a str
 2024-10-24 23:56:24 -07:00
sabaimran
12b32a3d04 Resolve merge conflicts 2024-10-24 23:43:55 -07:00
Debanjum
adee5a3e20 Give Vision to Anthropic models in Khoj (#948) 
### Major
- Give Vision to Anthropic models in Khoj

### Minor
- Reuse logic to format messages for chat with anthropic models
- Make the get image from url function more versatile and reusable
- Encourage output mode chat actor to output only json and nothing else
 2024-10-24 18:02:38 -07:00
Debanjum Singh Solanky
01d740debd Return typed image from image_with_url function for readability 2024-10-24 17:58:46 -07:00
Debanjum Singh Solanky
37317e321d Dedupe user location passed in image, diagram generation prompts 2024-10-24 01:03:29 -07:00
Debanjum Singh Solanky
2a32836d1a Log more descriptive error when image gen fails with Replicate 2024-10-24 01:03:29 -07:00
sabaimran
30f9225021 Merge branch 'master' of github.com:khoj-ai/khoj into features/advanced-reasoning 2024-10-23 19:15:51 -07:00
sabaimran
5120597d4e Remove user customized search model (#946) 
- Use a single standard search model across the server. There's diminishing benefits for having multiple user-customizable search models. 
- We may want to add server-level customization for specific tasks
- Store the search model used to generate a given entry on the `Entry` object
- Remove user-facing APIs and view
- Add a management command for migrating the default search model on the server

In a future PR (after running the migration), we'll also remove the `UserSearchModelConfig`
 2024-10-23 17:38:37 -07:00
Debanjum Singh Solanky
8d588e0765 Encourage output mode chat actor to output only json and nothing else 
Latest claude model wanted to say more than just give the json output.
The updated prompt encourages the model to ouput just json. This is
similar to what is already being done for other prompts
 2024-10-23 17:19:21 -07:00
Debanjum Singh Solanky
abad5348a0 Give Vision to Anthropic models in Khoj 2024-10-23 17:19:21 -07:00
Debanjum Singh Solanky
6fd50a5956 Reuse logic to format messages for chat with anthropic models 2024-10-23 17:19:21 -07:00
Debanjum Singh Solanky
82eac5a043 Make the get image from url function more versatile and reusable 
It was previously added under the google utils. Now it can be used by
other conversation processors as well.

The updated function
- can get both base64 encoded and PIL formatted images from url
- will return the media type of the image as well in response
 2024-10-23 17:19:20 -07:00
sabaimran
f3ce47b445 Create explicit flow to enable the free trial (#944) 
* Create explicit flow to enable the free trial

The current design is confusing. It obfuscates the fact that the user is on a free trial. This design will make the opt-in explicit and more intuitive.

* Use the Subscription Type enum instead of hardcoded strings everywhere

* Use length of free trial in the frontend code as well
 2024-10-23 15:29:23 -07:00
Debanjum Singh Solanky
bc059eeb0b Merge branch 'master' into put-retrieved-context-in-separate-chatml-message 2024-10-23 12:55:18 -07:00
Debanjum Singh Solanky
3b978b9b67 Fix chat history construction when generating chatml msgs with context 2024-10-23 12:55:12 -07:00
sabaimran
c5e91c346a Fix Docker desktop link for Linux 2024-10-23 11:24:54 -07:00
Debanjum Singh Solanky
9f2c02d9f7 Chat with the default agent by default from web app home 
Had temporarily updated the default selected agent to last used.
Revert for now as
1. The previous logic was buggy. It didn't select the default agent
   even when the last used agent was the default agent. Which would
   require more work.
2. It maybe too early anyway to set the default agent to last used.
 2024-10-23 03:43:57 -07:00
Debanjum Singh Solanky
218946edda Fix copying message with user images on web app 
Adding div elements to message to render degraded text copied to
clipboard for messages with user uploaded images.

This change fixes that by separating message to render from message
for clipboard. It ensures differently formatted forms of the user
images are added to the two to allow proper rendering while still
having decently formatted text copied to clipboard
 2024-10-23 03:41:25 -07:00
Debanjum Singh Solanky
7d9a06c8ab Merge branch 'master' into put-retrieved-context-in-separate-chatml-message 2024-10-23 00:13:38 -07:00
sabaimran
7c29af9745 Add link to self-hosted admin page and add docs for building front-end assets. Close #901 2024-10-22 22:42:27 -07:00
Debanjum Singh Solanky
2a50694089 Allow typing multi-line queries from a phone with Enter key 
Add newline instead of sending message when hit Enter key on mobile
displays. As on phones shift key doesn't exist and send button is easily
clickable.

Limit hitting Enter key to send message to computers = larger display
= expected to have full fledged keyboards.
 2024-10-22 21:20:22 -07:00
Debanjum Singh Solanky
a134cd835c Focus on chat input area to enter text after file uploads on web app 2024-10-22 21:19:17 -07:00
Debanjum
c81e708833 Show all agents, smart sorted, in carousel on home screen of web app (#943) 
## Overview
Allow quickly selecting, switching agents from agents pane on home page of web app

## Details
- Show all agents in carousel on home screen agent pane of web app
- Smart Sort
  1. Pin default agent as first for ease of access
  2. Show used agents by MRU for ease of access
  3. Shuffle unused agents for discoverability
- Select most recently used agent to chat with by default
- Push smart sort logic down to API
  - Common logic can be reused across clients
  - Agent sort was previously done in web app
- Focus on chat input on agent select
- Double click agent on home page to open edit agent card on agents page
 2024-10-22 21:18:17 -07:00
Debanjum Singh Solanky
750fbce0c2 Merge branch 'master' into improve-agent-pane-on-home-screen 2024-10-22 20:05:29 -07:00
Debanjum Singh Solanky
3be505db48 Only show type of error when image generation fails to clients 
Rather than showing raw error message from the underlying service as it
could contain sensitive information
 2024-10-22 20:03:20 -07:00
Debanjum
c6f3253ebd Chat with Multiple Images. Support Vision with Gemini (#942) 
## Overview
- Add vision support for Gemini models in Khoj
- Allow sharing multiple images as part of user query from the web app
- Handle multiple images shared in query to chat API
 2024-10-22 19:59:18 -07:00
Debanjum Singh Solanky
b3fff43542 Sanitize user attached images. Constrain chat input width on home page 
Set max combined images size to 20mb to allow multiple photos to be shared
 2024-10-22 19:42:40 -07:00
Debanjum Singh Solanky
6c393800cc Merge branch 'master' into multi-image-chat-and-vision-for-gemini 2024-10-22 18:38:49 -07:00
Debanjum Singh Solanky
91bbd19333 Close the agent detail hover card when scroll on agent pane 2024-10-22 18:03:17 -07:00
Debanjum Singh Solanky
110c67f083 Improve agent pill, detail card styling. Handle null chatInputRef 
- Remove border from agent detail hover card on home page
- Do not wrap long agent names in agent pills on home page
- Handle scenario where chatInputRef is null
 2024-10-22 18:03:17 -07:00
Debanjum Singh Solanky
aca8bef024 Only use recent chat sessions for agent MRU. Handle null agent chats 2024-10-22 17:46:45 -07:00
sabaimran
0dad4212fa Generate dynamic diagrams (via Excalidraw) (#940) 
Add support for generating dynamic diagrams in flow with Excalidraw (https://github.com/excalidraw/excalidraw). This happens in three steps:
1. Default information collection & intent determination step.
2. Improving the overall guidance of the prompt for generating a JSON, Excalidraw-compatible declaration.
3. Generation of the diagram to output to the final UI.

Add support in the web UI.
 2024-10-22 16:13:46 -07:00
sabaimran
1e993d561b Release Khoj version 1.26.4 2024-10-22 13:50:08 -07:00
Debanjum Singh Solanky
e8fb79a369 Rate limit the count and total size of images shared via API 2024-10-22 04:37:54 -07:00
Debanjum Singh Solanky
39a613d3bc Fix up openai chat actor tests 2024-10-22 03:09:36 -07:00
Debanjum Singh Solanky
0847fb0102 Pass online context from chat history to chat model for response 
Previously only notes context from chat history was included.
This change includes online context from chat history for model to use
for response generation.

This can reduce need for online lookups by reusing previous online
context for faster responses. But will increase overall response time
when not reusing past online context, as faster context buildup per
conversation.

Unsure if inclusion of context is preferrable. If not, both notes and
online context should be removed.
 2024-10-22 03:09:36 -07:00
Debanjum Singh Solanky
0c52a1169a Put context into separate user message before sending to chat model 
The document, online search context are now passed as separate user
messages to chat model, instead of being added to the final user message.

This will improve

- Models ability to differentiate data from user query.
  That should improve response quality and reduce prompt injection
  probability

- Make truncation logic simpler and more robust
  When context window hit, can simply pop messages to auto truncate
  context in order of context, user, assistant message for each
  conversation turn in history until reach current user query

  The complex, brittle logic to extract user query from context in
  last user message isn't required.

Marking the context message with assistant role doesn't translate well
across chat models. E.g
- Gemini can't handle consecutive messages by role = model well
- Claude will merge consecutive messages by same role. In current
  message ordering the context message will result get merged into the
  previous assistant response. And if move context message after user
  query. The truncation logic will have to hop and skip while doing
  deletions
- GPT seems to handle consecutive roles of any type fine

Using context role = user generalizes better across chat models for
now and aligns with previous behavior.
 2024-10-22 03:09:36 -07:00
Debanjum Singh Solanky
7ac241b766 Improve format of notes, online context passed to chat models in prompt 
Improve separation of note snippets and show its origin file in notes
prompt to have more readable, contextualized text shared with model.

Previously the references dict was being directly passed as a string.
The documents don't look well formatted and are less intelligible.

- Passing file path along with notes snippets will help contextualize
  the notes better.
- Better formatting should help with making notes more readable by the
  chat model.
 2024-10-22 03:09:36 -07:00
sabaimran
892040972f Replace user_id with server_id in telemetry 2024-10-21 20:47:52 -07:00
sabaimran
db959a504d Fix the version of pymupdf to avert build errors 2024-10-21 12:56:51 -07:00
sabaimran
21e69b506d Release Khoj version 1.26.3 2024-10-21 08:19:05 -07:00
Debanjum Singh Solanky
9b554feb91 Show agent details card on hover on agent pill on web app home page 
- Double click on agent to open edit agent card
- Focus on chat input pane when agent selected/clicked
  for quick, smooth agent switch and message flow
- Hover on agent to see agent detail card on non-mobile displays
  - Use debounce to only show when hover on card for a bit
 2024-10-21 00:08:01 -07:00
Debanjum Singh Solanky
220ff1df62 Set chatInputArea forward ref from parent components for control 2024-10-21 00:02:48 -07:00
Debanjum Singh Solanky
54b92eaf73 Extract isUserSubscribed check from Agents page to make it resusable 2024-10-20 23:31:48 -07:00
Debanjum Singh Solanky
bdbe8f003e Move agent details and edit card out into reusable components on web app 2024-10-20 23:31:47 -07:00
sabaimran
ad197be70c Fix PDFs unit test, skip OCR 2024-10-20 22:25:41 -07:00
sabaimran
59fec37943 Improve agents management, and limit agents view to private and official agents 
- Default to None for the input_tools and output_modes so that they can be managed in the admin panel
- Hold off on showing off all Public Agents until we have a better experience for user profiles etc.
 2024-10-20 22:24:51 -07:00
sabaimran
a979457442 Add unit tests for agents 
- Add permutations of testing for with, without knowledge base. Private, public, different users.
 2024-10-20 20:04:50 -07:00
sabaimran
fc70f25583 Release Khoj version 1.26.2 2024-10-20 18:03:36 -07:00
sabaimran
046de57571 Improve error handling when documents not searched with stack trace 
- Stop extract OCR content from PDFs
- Only use agent knowledge base when user not provided
 2024-10-20 18:03:14 -07:00
sabaimran
2b68d61fef Release Khoj version 1.26.1 2024-10-20 16:21:51 -07:00
Debanjum Singh Solanky
5fca41cc29 Show agents sorted by mru, Select mru agent by default on web app 
Have get agents API return agents ordered intelligently
- Put the default agent first
- Sort used agents by most recently chatted with agent for ease of access
- Randomly shuffle the remaining unused agents for discoverability
 2024-10-20 15:21:25 -07:00
Debanjum Singh Solanky
a6bfdbdbfe Show all agents in carousel on home screen agent pane of web app 
This change wraps the agent pane in a scroll area with all agents shown.
It allows selecting an agent to chat with directly from the home
screen without breaking flow and having to jump to the agents page.

The previous flow was not convenient to quickly and consistently start
chat with one of your standard agents.

This was because a random subet of agents were shown on the home page.
To start chat with an agent not shown on home screen load you had to
open the agents page and initiate the conversation from there.
 2024-10-20 15:21:25 -07:00
Debanjum Singh Solanky
9ffd726799 Allow making sync api requests with body from khoj.el 2024-10-20 15:16:40 -07:00
Debanjum Singh Solanky
ac51920859 Start conversation with Agents from within Emacs 
Exposes a transient switch with available agents as selectable options
in the Khoj chat sub-menu.

Currently shows agent slugs instead of agent names as options. This
isn't the cleanest but gets the job done for now.

Only new conversations with a different agent can be started. Existing
conversations will continue with the original agent it was created with.
The ability to switch the conversation's agent doesn't exist on the
server yet.
 2024-10-20 15:16:40 -07:00
Debanjum Singh Solanky
7646ac6779 Style user attached images as carousel on chat input area of web app 2024-10-20 00:40:08 -07:00
sabaimran
5d5bea6a5f Ensure images are reset after messages processed 2024-10-19 22:02:06 -07:00
sabaimran
1ad6e1749f Move window redirect to after relevant data is dropped in localStorage on the homage page 
One limitation of this methodology is that localStorage has a limit in how much data it can take. Should add more graceful error handling here as well.
 2024-10-19 20:36:13 -07:00
sabaimran
cb6b3ec1e9 Improve mode description given to LLM when determining how to respond. 
Currently experiencing difficulty instruction following when an image is shared. It's more likely to try and output an image. Update to make a clearer distinction.
 2024-10-19 20:35:32 -07:00
sabaimran
545259e308 Remove unused icons in chatInputArea 2024-10-19 16:54:21 -07:00
Debanjum Singh Solanky
3cc1426edf Style user attached images with fixed height, in a single row on web app 2024-10-19 16:48:36 -07:00
Debanjum Singh Solanky
58a331227d Display the attached images inside the chat input area on the web app 
- Put the attached images display div inside the same parent div as
  the text area
- Keep the attachment, microphone/send message buttons aligned with
  the text area. So the attached images just show up at the top of the
  text area but everything else stays at the same horizontal height as
  before.

- This improves the UX by
  - Ensuring that the attached images do not obscure the agents pane
    above the chat input area
  - The attached images visually look like they are inside the actual
    input area, rather than floating above it. So the visual aligns
    with the semantics
 2024-10-19 16:29:45 -07:00
Debanjum Singh Solanky
3e39fac455 Add vision support for Gemini models in Khoj 2024-10-19 15:47:03 -07:00
Debanjum Singh Solanky
0d6a54c10f Allow sharing multiple images as part of user query from the web app 
Previously the web app only expected a single image to be shared by
the user as part of their query.

This change allows sharing multiple images from the web app.

Closes #921
 2024-10-19 15:47:03 -07:00
Debanjum Singh Solanky
e2abc1a257 Handle multiple images shared in query to chat API 
Previously Khoj could respond to a single shared image at a time.

This changes updates the chat API to accept multiple images shared by
the user and send it to the appropriate chat actors including the
openai response generation chat actor for getting an image aware
response
 2024-10-19 14:53:33 -07:00
Debanjum Singh Solanky
d55cba8627 Pass user query for chat response when document lookup fails 
Recent changes made Khoj try respond even when document lookup fails.
This change missed handling downstream effects of a failed document
lookup, as the defiltered_query was null and so the text response
didn't have the user query to respond to.

This code initializes defiltered_query to original user query to
handle that.

Also response_type wasn't being passed via
send_message_to_model_wrapper_sync unlike in the async scenario
 2024-10-19 14:32:19 -07:00
Debanjum Singh Solanky
a4e6e1d5e8 Share webp images from web, desktop, obsidian app to chat with 2024-10-19 14:32:17 -07:00
sabaimran
dbd9a945b0 Re-evaluate agent private/public filtering after authenticateddata is retrieved. Update selectedAgent check logic to reflect. 2024-10-18 09:31:56 -07:00
Debanjum Singh Solanky
35015e720e Release Khoj version 1.26.0 2024-10-17 18:25:53 -07:00
Debanjum Singh Solanky
f0dcfe4777 Explicitly ask Gemini models to format their response with markdown 
Otherwise it can get confused by the format of the passed context (e.g
respond in org-mode if context contains org-mode notes)
 2024-10-17 18:12:47 -07:00
Debanjum
7fb4c2939d Make Chat and Online Search Resilient and Faster (#936) 
## Overview
### New
- Support using Firecrawl(https://firecrawl.dev) to read web pages
- Add, switch and re-prioritize web page reader(s) to use via the admin panel

### Speed
- Improve response speed by aggregating web page read, extract queries to run only once for each web page

### Response Resilience
- Fallback through enabled web page readers until web page read
- Enable reading web pages on the internal network for self-hosted Khoj running in anonymous mode
- Try respond even if web search, web page read fails during chat
- Try respond even if document search via inference endpoint fails

### Fix
- Return data sources to use if exception in data source chat actor

## Details
### Configure web page readers to use
 - Only the web scraper set in Server Chat Settings via the Django admin panel, if set
 - Otherwise use the web scrapers added via the Django admin panel (in order of priority), if set
 - Otherwise, use all the web scrapers enabled by settings API keys via environment variables (e.g `FIRECRAWL_API_KEY', `JINA_API_KEY' env vars set), if set
 - Otherwise, use Jina to web scrape if no scrapers explicitly defined
 
For self-hosted setups running in anonymous-mode, the ability to directly read webpages is also enabled by default. This is especially useful for reading webpages in your internal network that the other web page readers will not be able to access.

### Aggregate webpage extract queries to run once for each distinct web page

Previously, we'd run separate webpage read and extract relevant
content pipes for each distinct (query, url) pair.

Now we aggregate all queries for each url to extract information from
and run the webpage read and extract relevant content pipes once for
each distinct URL.

Even though the webpage content extraction pipes were previously being
run in parallel. They increased the response time by
1. adding more ~duplicate context for the response generation step to read
2. being more susceptible to variability in web page read latency of the parallel jobs

The aggregated retrieval of context for all queries for a given
webpage could result in some hit to context quality. But it should
improve and reduce variability in response time, quality and costs. 

This should especially help with speed and quality of online search 
for offline or low context chat models.
 2024-10-17 17:57:44 -07:00
Debanjum Singh Solanky
2c20f49bc5 Return enabled scrapers as WebScraper objects for more ergonomic code 2024-10-17 17:44:09 -07:00
Debanjum Singh Solanky
0db52786ed Make web scraper priority configurable via admin panel 
- Simplifies changing order in which web scrapers are invoked to read
  web page by just changing their priority number on the admin panel.
  Previously you'd have to delete/, re-add the scrapers to change
  their priority.

- Add help text for each scraper field to ease admin setup experience

- Friendlier env var to use Firecrawl's LLM to extract content

- Remove use of separate friendly name for scraper types.
  Reuse actual name and just make actual name better
 2024-10-17 17:42:42 -07:00
Debanjum Singh Solanky
20b6f0c2f4 Access internal links directly via a simple get request 
The other webpage scrapers will not work for internal webpages. Try
access those urls directly if they are visible to the Khoj server over
the network.

Only enable this by default for self-hosted, single user setups.
Otherwise ability to scan internal network would be a liability!

For use-cases where it makes sense, the Khoj server admin can
explicitly add the direct webpage scraper via the admin panel
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
d94abba2dc Fallback through enabled scrapers to reduce web page read failures 
- Set up scrapers via API keys, explicitly adding them via admin panel
  or enabling only a single scraper to use via server chat settings.

- Use validation to ensure only valid scrapers added via admin panel
  Example API key is present for scrapers that require it etc.

- Modularize the read webpage functions to take api key, url as args
  Removes dependence on constants loaded in online_search. Functions
  are now mostly self contained

- Improve ability to read webpages by using the speed, success rate of
  different scrapers. Optimal configuration needs to be discovered
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
11c64791aa Allow changing perf timer log level. Info log time for webpage read 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
c841abe13f Change webpage scraper to use via server admin panel 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
e47922e53a Aggregate webpage extract queries to run once for each distinct webpage 
This should reduce webpage read and response generation time.

Previously, we'd run separate webpage read and extract relevant
content pipes for each distinct (query, url) pair.

Now we aggregate all queries for each url to extract information from
and run the webpage read and extract relevant content pipes once for
each distinct url.

Even though the webpage content extraction pipes were previously being
in parallel. They increased response time by
1. adding more context for the response generation chat actor to
   respond from
2. and by being more susceptible to page read and extract latencies of
   the parallel jobs

The aggregated retrieval of context for all queries for a given
webpage could result in some hit to context quality. But it should
improve and reduce variability in response time, quality and costs.
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
98f99fa6f8 Allow using Firecrawl to extract web page content 
Set the FIRECRAWL_TO_EXTRACT environment variable to true to have
Firecrawl scrape and extract content from webpage using their LLM

This could be faster, not sure about quality as LLM used is obfuscated
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
993fd7cd2b Support using Firecrawl to read webpages 
Firecrawl is open-source, self-hostable with a default hosted service
provided, similar to Jina.ai. So it can be
1. Self-hosted as part of a private Khoj cloud deployment
2. Used directly by getting an API key from the Firecrawl.dev service

This is as an alternative to Olostep and Jina.ai for reading webpages.
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
731ea3779e Return data sources to use if exception in data source chat actor 
Previously no value was returned if an exception got triggered when
collecting information sources to search.
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
a932564169 Try respond even if web search, webpage read fails during chat 
Khoj shouldn't refuse to respond to user if web lookups fail.
It should transparently mention that online search etc. failed.
But try respond as best as it can without those references

This change ensures a response to the users query is attempted even
when web info retrieval fails.
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
1b04b801c6 Try respond even if document search via inference endpoint fails 
The huggingface endpoint can be flaky. Khoj shouldn't refuse to
respond to user if document search fails.
It should transparently mention that document lookup failed.
But try respond as best as it can without the document references

This changes provides graceful failover when inference endpoint
requests fail either when encoding query or reranking retrieved docs
 2024-10-17 17:40:49 -07:00
Debanjum Singh Solanky
9affeb9e85 Fix to log the client app calling the chat API 
- Remove unused subscribed variable from the chat API
- Unexpectedly dropped client app logging when migrated API chat to do
  advanced streaming in july
 2024-10-17 15:24:43 -07:00
Debanjum Singh Solanky
c6c48cfc18 Fix arg to generate_summary_from_file and type of this_iteration 2024-10-17 13:38:48 -07:00
Debanjum Singh Solanky
884fe42602 Allow automation as an output mode supported by custom agents 2024-10-17 11:58:52 -07:00
Debanjum Singh Solanky
c5e19b37ef Use Khoj icons. Add automation & improve agent text on web login page 2024-10-17 11:58:52 -07:00
Debanjum Singh Solanky
42acc324dc Handle correctly setting file filters as array when API call fails 
- Only set addedFiles to selectedFiles when selectedFiles is an array
- Only set seleectedFiles, addedFiles to API response json when
  response succeeded. Previously we set it to response json
  on errors as well. This made the variables into json objects instead
  of arrays on API call failure
- Check if selectedFiles, addedFiles are arrays before running
  operations on them. Previously the addedFiles.includes was where the
  code would fail
 2024-10-17 11:58:52 -07:00
Debanjum Singh Solanky
7ebfc24a96 Upgrade Django version used by Khoj server 2024-10-17 11:58:52 -07:00
Debanjum Singh Solanky
ea59dde4a0 Upgrade documentation website dependencies 2024-10-17 11:58:52 -07:00
sabaimran
07ab8ab931 Update handling of gemini response with new API changes. Per documentation: 
finish_reason (google.ai.generativelanguage_v1beta.types.Candidate.FinishReason):
            Optional. Output only. The reason why the
            model stopped generating tokens.
            If empty, the model has not stopped generating
            the tokens.
 2024-10-17 09:00:01 -07:00
Rehan Daphedar
27835628e6 Fix typo in docs for error 400 fix when self-hosting (#938) 2024-10-16 23:15:43 -07:00
Debanjum Singh Solanky
19c65fb82b Show user uuid field in django admin panel 2024-10-15 17:59:12 -07:00
Debanjum Singh Solanky
6c5b362551 Remove deprecated GET chat API endpoint 2024-10-15 15:13:09 -07:00
Debanjum Singh Solanky
931c56182e Fix default chat model to use user model if no server chat model set 
- Advanced chat model should also fallback to user chat model if set
- Get conversation config should falback to user chat model if set

These assume no server chat model settings is configured
 2024-10-15 15:13:09 -07:00
Debanjum Singh Solanky
feb6d65ef8 Merge branch 'master' into features/advanced-reasoning 2024-10-15 09:37:56 -07:00
Debanjum Singh Solanky
336c6c3689 Show tool to use decision for next iteration in train of thought 2024-10-15 01:12:18 -07:00
Debanjum Singh Solanky
81fb65fa0a Return data sources to use if exception in data source chat actor 
Previously no value was returned if an exception got triggered when
collecting information sources to search.
 2024-10-14 18:20:20 -07:00
Debanjum Singh Solanky
3c93f07b3f Try respond even if web search, webpage read fails during chat 
Khoj shouldn't refuse to respond to user if web lookups fail.
It should transparently mention that online search etc. failed.
But try respond as best as it can without those references

This change ensures a response to the users query is attempted even
when web info retrieval fails.
 2024-10-14 18:13:26 -07:00
Debanjum Singh Solanky
07ab7ebf07 Try respond even if document search via inference endpoint fails 
The huggingface endpoint can be flaky. Khoj shouldn't refuse to
respond to user if document search fails.
It should transparently mention that document lookup failed.
But try respond as best as it can without the document references

This changes provides graceful failover when inference endpoint
requests fail either when encoding query or reranking retrieved docs
 2024-10-14 18:13:26 -07:00
Debanjum Singh Solanky
d6206aa80c Remove deprecated GET chat API endpoint 2024-10-14 18:13:26 -07:00
Debanjum Singh Solanky
263eee4351 Fix default chat model to use user model if no server chat model set 
- Advanced chat model should also fallback to user chat model if set
- Get conversation config should falback to user chat model if set

These assume no server chat model settings is configured
 2024-10-14 18:13:26 -07:00
sabaimran
81aa1b5589 Update some edge cases and usability of create agent flow 
- Use the slug to determine which agent to PATCH
- Make the agent creation form multi-step to streamline the process
 2024-10-14 14:07:31 -07:00
Debanjum Singh Solanky
abcd11cfc0 Merge branch 'master' into features/advanced-reasoning 2024-10-13 03:06:23 -07:00
Debanjum Singh Solanky
9356e66b94 Fix default chat model to use user model if no server chat model set 
- Advanced chat model should also fallback to user chat model if set
- Get conversation config should falback to user chat model if set

These assume no server chat model settings is configured
 2024-10-13 03:02:29 -07:00
Debanjum Singh Solanky
9314f0a398 Fix default chat configs to use user model if no server chat model set 
Post merge cleanup in advanced reasoning to fallback to user chat
model if no server chat model defined for advanced and default
 2024-10-13 02:59:10 -07:00
Debanjum Singh Solanky
8ff13e4cf6 Update readme. Mention new capabilities 2024-10-13 01:30:53 -07:00
Debanjum Singh Solanky
a2200466b7 Merge branch 'master' into features/advanced-reasoning 2024-10-12 21:01:22 -07:00
Debanjum
c66c571396 Simplify switching chat model when self-hosting (#934) 
# Overview
- Default to use user chat models for train of thought when no server chat settings created by admins
- Default to not create server chat settings on first run

# Details
This change simplifies switching chat models for self-hosted setups 
by just changing the chat model on the user settings page.

It falls back to use the user chat model for train of thought 
if server chat settings have not been created on the admin panel.

Server chat settings, when set, controls the chat model used 
for Khoj's train of thought and the default user chat model.

Previously a self-hosted user had to update
1. the server chat settings in the admin panel and
2. their own user chat model in the user settings panel

to completely switch to a different chat model 
for both train of thought & response generation respectively

You can still set server chat settings via the admin panel 
to use a different chat model for train of thought vs response generation. 
But this is only useful for advanced, multi-user setups.
 2024-10-12 19:58:05 -07:00
Debanjum Singh Solanky
90888a1099 Log when new user created via magic link or whatsapp as well 2024-10-12 19:56:01 -07:00
Debanjum Singh Solanky
8222c6629d Remove unused subscribed argument to read_webpage function 2024-10-12 10:45:39 -07:00
Debanjum Singh Solanky
9daaae0fdb Render inline any image files output by code in message 
Update regex to also include any links to code generated images that
aren't explicitly meant to be displayed inline. This allows folks to
download the image (unlike the fake link that doesn't work created by
model)
 2024-10-12 10:34:57 -07:00
Debanjum Singh Solanky
20d495c43a Update the iterative chat director prompt to generalize across chat models 
These prompts work across o1 and standard openai model. Works with
anthropic and google models as well
 2024-10-12 10:34:57 -07:00
sabaimran
eb4d598d0f Eliminate the drawer component from the Agents view 2024-10-10 20:40:59 -07:00
sabaimran
0a1c3e4f41 Release Khoj version 1.25.0 2024-10-10 18:07:30 -07:00
sabaimran
01a58b71a5 Skip image, code generation if in research mode 2024-10-10 18:06:29 -07:00
Debanjum Singh Solanky
1b13d069f5 Pass data collected from various sources to code tool in normal flow too 2024-10-10 05:19:27 -07:00
Debanjum Singh Solanky
f462d34547 Render images files output by code interpreter in message on web app 2024-10-10 05:17:53 -07:00
Debanjum Singh Solanky
564491e164 Extract date filters quoted with non-ascii quotes in query 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
6a8fd9bf33 Reorder embeddings search arguments based on argument importance 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
0eacc0b2b0 Use consistent name for user, planner to not miss current user query 
Previously Khoj would start answering the previous query. This maybe
because the prompt uses User for prompt in chat history but was using
Q for current user prompt.
 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
284c8c331b Increase default max iterations for research chat director to 5 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
1e390325d2 Let research chat director decide which webpage to read, if any 
Make webpages to read automatically on search_online configurable via
a argument.

Set it to default to 1, so other callers of the function
are unaffected.

But iterative chat director can still decide which, if
any, webpages to read based on the online search it performs
 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
5a699a52d2 Improve webpage summarization prompt to better extract links, excerpts 
This change allows the iterative director to dive deeper into its
research as the data extracted contains relevant links from the webpage

Previous summarization prompt didn't extract relevant links from the
webpage which limited further explorations from webpages
 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
61df1d5db8 Pass previous iteration results to code interpreter chat actors 
This improves the code interpreter chat actors abilitiy to generate
code with data collected during the previous iterations
 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
9e7025b330 Set python interpret sandbox url via environment variable 2024-10-10 04:45:00 -07:00
Debanjum Singh Solanky
2dc5804571 Extract defilter query into conversation utils for reuse 2024-10-10 04:45:00 -07:00
sabaimran
e69a8382f2 Add a code icon for code-related train of thought 2024-10-09 23:56:57 -07:00
sabaimran
536422a40c Include code snippets in the reference panel 2024-10-09 23:54:11 -07:00
Debanjum Singh Solanky
8d33c764b7 Allow iterative chat director to use python interpreter as a tool 2024-10-09 23:38:20 -07:00
Debanjum Singh Solanky
b373073f47 Show executed code in web app chat message references 2024-10-09 22:13:18 -07:00
Debanjum Singh Solanky
a98f97ed5e Refactor Run Code tool into separate module and modularize code functions 
Move construct_chat_history and ChatEvent enum into conversation.utils
and move send_message_to_model_wrapper to conversation.helper to
modularize code. And start thinning out the bloated routers.helper

- conversation.util components are shared functions that conversation
  child packages can use.
- conversation.helper components can't be imported by conversation
  packages but it can use these child packages

This division allows better modularity while avoiding circular
import dependencies
 2024-10-09 22:13:17 -07:00
Debanjum Singh Solanky
8044733201 Give Khoj ability to run python code as a tool triggered via chat API 
Create python code executing chat actor
- The chat actor generate python code within sandbox constraints
- Run the generated python code in the cohere terrarium, pyodide
  based sandbox accessible at sandbox url
 2024-10-09 21:37:22 -07:00
Debanjum Singh Solanky
4d33239af6 Improve prompts for the iterative chat director 2024-10-09 21:23:18 -07:00
Debanjum Singh Solanky
6ad85e2275 Fix to continue showing retrieved documents in train of thought 2024-10-09 21:20:22 -07:00
sabaimran
a6f6e4f418 Fix notes references and passage of user query in the chat flow 2024-10-09 20:34:20 -07:00
Debanjum Singh Solanky
ec248efd31 Allow iterative chat director to do notes search 2024-10-09 19:04:59 -07:00
Debanjum Singh Solanky
a6905a9f0c Pass background context to iterating chat director 2024-10-09 19:04:59 -07:00
sabaimran
028b6e6379 Fix yield for scraping direct web page 2024-10-09 18:14:08 -07:00
sabaimran
717d9da8d8 Handle when summarize result is not present, rename variable in for loop from query 2024-10-09 17:57:08 -07:00
sabaimran
03544efde2 Ignore typing of the result dict for online, web page scrape 2024-10-09 17:48:24 -07:00
sabaimran
ab81b01fcb Fix typing of direct_web_pages and remove the deprecated chat API 2024-10-09 17:46:28 -07:00
sabaimran
5b8d663cf1 Add intermediate summarization of results when planning with o1 2024-10-09 17:40:56 -07:00
sabaimran
7b288a1179 Clean up the function planning prompt a little bit 2024-10-09 16:59:20 -07:00
sabaimran
f71e4969d3 Skip summarize while it's broken, and snip some other parts of the workflow while under construction 2024-10-09 16:40:06 -07:00
sabaimran
f7e6f99a32 add typing for extract document references 2024-10-09 16:05:34 -07:00
sabaimran
6960fb097c update types of prev iterations response 2024-10-09 16:04:39 -07:00
sabaimran
4978360852 Fix type of previous_iterations 2024-10-09 16:02:41 -07:00
sabaimran
46ef205a75 Add additional type annotations for compiled_references et al 2024-10-09 16:01:52 -07:00
sabaimran
4fbaef10e9 Correct usage of the summarize function 2024-10-09 15:58:05 -07:00
sabaimran
c91678078d Correct the usage of query passed to summarize function 2024-10-09 15:55:55 -07:00
sabaimran
f867d5ed72 Working prototype of meta-level chain of reasoning and execution 
- Create a more dynamic reasoning agent that can evaluate information and understand what it doesn't know, making moves to get that information
- Lots of hacks and code that needs to be reversed later on before submission
 2024-10-09 15:54:25 -07:00
Debanjum
00546c1a63 Fix link to llama-cpp-python setup docs 2024-10-09 01:30:33 -07:00
Debanjum Singh Solanky
05fb0f14d3 Use user chat models for train of thought when no server chat settings 
Update chat actors to use user's chat model for train of thought. This
requires passing the user info as argument to all the chat actors.

Whether the user is subscribed or not can be inferred from the user
info being passed, so it doesn't need to be passed as a separate
argument to chat actor functions

Let send_message_to_model function infer chat model instead of passing
it as an argument from some chat actors. Better if this logic can be
done in a single place.
 2024-10-09 00:07:08 -07:00
Debanjum Singh Solanky
ec0c79217f Do not set server chat settings on first run 
Server chat settings can be set for advanced self-hosted or multi-user
cloud setups. They are not necessary anymore as we fallback to use the
users chat model for train of thought now
 2024-10-09 00:07:08 -07:00
Debanjum Singh Solanky
a9009ea774 Default to use user chat model if server chat settings not defined 
Fallback to use user chat model for train of thought if server chat
settings not defined.

This simplifies switching chat models for single-user, self-hosted
setups by just changing the chat model on the user settings page.

Server chat settings, when set, controls the default user chat model
and the chat model that is used for Khoj's train of thought.

Previously a self-hosted user had to update both the server chat
settings in the admin panel and their own user chat model in the user
settings panel to explicitly switch to a different chat model (i.e to
switch to a new model for both train of thought & response generation)

You can still set server chat settings to use a different chat
model for train of thought and response generation. But this is only
necessary for advanced self-hosted or cloud hosted setups of Khoj.
 2024-10-09 00:07:08 -07:00
Debanjum Singh Solanky
9a056383e0 Reduce size of start chat and edit buttons on agent card in web app 2024-10-09 00:00:32 -07:00
Debanjum Singh Solanky
dc7f22f76c Mention no. of docs in agents knowledge base in its badge hover text 2024-10-08 23:51:00 -07:00
Debanjum Singh Solanky
13fb22f7e7 Update agent form data shown in edit card after save operaton on web app 
Previously you had to refresh the page to see the updated data on
reopening the agents edit card after a save operation.

Now you see the latest saved agent data on reopening the agents edit
card. This should avoid confusion on whether the data was saved
correctly
 2024-10-08 23:26:04 -07:00
Debanjum Singh Solanky
dd770cf1b9 Start chat with public and protected agents when shared via link 2024-10-08 22:10:07 -07:00
Debanjum Singh Solanky
80212c50fd Use default agent in others chats with an agent if agent made private 
If a public or protected agent is made private. Other users who were
having conversation with that agent will have to carry on their
conversation using default agent instead
 2024-10-08 22:08:38 -07:00
Debanjum Singh Solanky
d628f89ce9 Prefetch agents related database models 2024-10-08 21:59:15 -07:00
Debanjum Singh Solanky
8de67c5d4d Fallback to use general command if no tool selected by agent 2024-10-08 19:48:02 -07:00
Debanjum Singh Solanky
b80c4bcfdd Improve agent command descriptions 2024-10-08 19:47:51 -07:00
Debanjum Singh Solanky
67d0e59eac Pass chat history to the summarize chat actor 2024-10-08 18:44:52 -07:00
Debanjum Singh Solanky
7e3090060b Encourage Gemini to output more verbose responses 2024-10-08 18:41:43 -07:00
Debanjum Singh Solanky
bbbdba3093 Time embedding model load for better visibility into app startup time 
Loading the embeddings model, even locally seems to be taking much
longer. Use timer to track visibility into embedding, cross-encoder
model load times
 2024-10-08 18:41:43 -07:00
Debanjum Singh Solanky
516472a8d5 Switch default tokenizer to tiktoken as more widely used 
The tiktoken BPE based tokenizers seem more widely used these days.

Fallback to gpt-4o tiktoken tokenizer to count tokens for context
stuffing
 2024-10-08 18:41:43 -07:00
Debanjum Singh Solanky
2b8f7f3efb Reuse a single func to format conversation for Gemini 
This deduplicates code and prevents logic from deviating across gemini
chat actors
 2024-10-08 18:41:42 -07:00
Debanjum Singh Solanky
452e360175 Do not use max prompt size to limit Gemini max output tokens 
We should start disambiguating the the max input from output size. Max
prompt size should only be used for the max input context to an LLM.

If required max_output_tokens should be set as a separate new field
 2024-10-08 15:30:08 -07:00
Debanjum Singh Solanky
bdc36fec5d Remove unnecessary whitespace indent from personality context 2024-10-08 15:30:08 -07:00
sabaimran
3daa3c003d When tool selection is not done successfully with an agent, return all agent tools as options 2024-10-08 15:03:58 -07:00
sabaimran
ad716ca58d Delete associated entries with an agent when it is deleted 2024-10-08 15:00:21 -07:00
sabaimran
f7fc6dbdc8 Limit agent creation and modification to subscribed users 2024-10-08 14:59:57 -07:00
sabaimran
c7638a783e Dynamically update added files when upload in agent creation 2024-10-07 21:54:11 -07:00
sabaimran
e10a0571ff Only check the prompt safety if the agent is not private 2024-10-07 21:42:14 -07:00
sabaimran
f700d5bddb Add summarization capability with agent knowledge base 2024-10-07 21:20:23 -07:00
sabaimran
df3dc33e96 Show reference icon and domain side by side 2024-10-07 20:28:48 -07:00
sabaimran
59e55f981f Reset agent to default when continuing with deceased agent 2024-10-07 20:28:33 -07:00
sabaimran
874776024a Handle chat history rendering when agent is deceased 2024-10-07 20:28:10 -07:00
sabaimran
f232c2b059 Allow user to chat with agent knowledge base if general mode 2024-10-07 19:55:33 -07:00
sabaimran
c00654ae58 Update default agent settings 2024-10-07 18:11:24 -07:00
sabaimran
3d0e183bea Add more log lines when encountering rate limiting 2024-10-07 14:36:12 -07:00
sabaimran
e4a8a69bc8 Add a subtle check mark when the copy button is selected 2024-10-07 09:41:03 -07:00
sabaimran
405c047c0c Include agent personality through subtasks and support custom agents (#916) 
Currently, the personality of the agent is only included in the final response that it returns to the user. Historically, this was because models were quite bad at navigating the additional context of personality, and there was a bias towards having more control over certain operations (e.g., tool selection, question extraction).

Going forward, it should be more approachable to have prompts included in the sub tasks that Khoj runs in order to response to a given query. Make this possible in this PR. This also sets us up for agent creation becoming available soon.

Create custom agents in #928

Agents are useful insofar as you can personalize them to fulfill specific subtasks you need to accomplish. In this PR, we add support for using custom agents that can be configured with a custom system prompt (aka persona) and knowledge base (from your own indexed documents). Once created, private agents can be accessible only to the creator, and protected agents can be accessible via a direct link.

Custom tool selection for agents in #930

Expose the functionality to select which tools a given agent has access to. By default, they have all. Can limit both information sources and output modes.
Add new tools to the agent modification form
 2024-10-07 00:21:55 -07:00
sabaimran
c0193744f5 Update readme.md 2024-10-06 12:26:53 -07:00
sabaimran
d4ffeca90a Fix notion indexing with manually set token 2024-10-05 09:13:16 -07:00
sabaimran
29a422b6bc Remove the single dollar sign delimeters from katex rendering 2024-10-04 12:24:19 -07:00
Debanjum Singh Solanky
e217cb5840 Suggest notification type automation on Automation page of web app 2024-10-03 16:36:23 -07:00
Debanjum Singh Solanky
f626b34436 Update automation docs with screenshots 2024-10-03 16:36:05 -07:00
sabaimran
27c7e54695 Release Khoj version 1.24.1 2024-10-03 13:21:10 -07:00
Debanjum
4a1cb50da3 Make Online Search Location Aware (#929) 
## Overview
Add user country code as context for doing online search with serper.dev API.
This should find more user relevant results from online searches by Khoj

## Details
### Major
- Default to using system clock to infer user timezone on js clients
- Infer country from timezone when only timezone received by chat API
- Localize online search results to user country when location available

### Minor
- Add `__str__` func to `LocationData` class to deduplicate location string generation
 2024-10-03 12:33:47 -07:00
sabaimran
cb4052e333 Bump up rate limit for subscribed users and add an option to create new conversation in the POST request 2024-10-03 12:31:58 -07:00
sabaimran
7a5cd06162 Improve the login page (#931) 
* Init version of improved login page
* Use split screen view, add a gradient
 2024-10-02 14:26:46 -07:00
Debanjum Singh Solanky
591c582eeb Fix list references in use openai proxy docs 2024-09-30 23:21:33 -07:00
Debanjum Singh Solanky
852662f946 Use requestAnimationFrame for synced scroll on chat in web app 
Make all the scroll actions just use requestAnimationFrame instead of
setTimeout. It better aligns with browser rendering loop, so better
for UX changes than setTimeout
 2024-09-30 23:21:10 -07:00
sabaimran
57b4f844b7 Fail app start if initalization fails 2024-09-30 17:30:06 -07:00
Debanjum Singh Solanky
04aef362e2 Default to using system clock to infer user timezone on js clients 
Using system clock to infer user timezone on clients makes Khoj
more robust to provide location aware responses.

Previously only ip based location was used to infer timezone via API.
This didn't provide any decent fallback when calls to ipapi failed or
Khoj was being run in offline mode
 2024-09-30 07:08:12 -07:00
Debanjum Singh Solanky
344f3c60ba Infer country from timezone when only tz received by chat API 
Timezone is easier to infer using clients system clock. This can be
used to infer user country name, country code, even if ip based
location cannot be inferred.

This makes using location data to contextualize Khoj's responses more
robust. For example, online search results are retrieved for user's
country, even if call to ipapi.co for ip based location fails
 2024-09-30 07:08:11 -07:00
Debanjum Singh Solanky
1fed842fcc Localize online search results to user country when location available 
Get country code to server chat api from i.p location check on clients.
Use country code to get country specific online search results via Serper.dev API
 2024-09-30 07:08:11 -07:00
Debanjum Singh Solanky
eb86f6fc42 Add __str__ func to LocationData class to dedupe location string gen 
Previously the location string from location data was being generated
wherever it was being used.

By adding a __str__ representation to LocationData class, we can
dedupe and simplify the code to get the location string
 2024-09-30 07:08:11 -07:00
sabaimran
1dfc89e79f Store conversation ID for new conversations as a string, not UUID 2024-09-29 18:07:08 -07:00
sabaimran
d92a349292 Improve image generation tool description 2024-09-29 16:20:25 -07:00
Debanjum Singh Solanky
d21a4e73a0 Update docs to use new variables to sync files, directories from khoj.el 2024-09-29 14:03:06 -07:00
Debanjum Singh Solanky
d66a0ccfaa Update client setup docs with instructions for self-hosting users 
Resolves #808
 2024-09-29 13:58:02 -07:00
Debanjum Singh Solanky
dd44933515 Release Khoj version 1.24.0 2024-09-29 04:56:11 -07:00
Debanjum Singh Solanky
1e8ce52d98 Reduce size of Khoj Docker images by removing layers and caches 
- Align Dockerfile and prod.Dockerfile code
- Reduce Docker image size by 25% by reducing Docker layers and
  removing package caches
 2024-09-29 04:06:35 -07:00
Debanjum Singh Solanky
9b10b3e7a1 Remove unused langchain openai server dependency 2024-09-29 04:06:35 -07:00
Debanjum Singh Solanky
e767b6eba3 Update Documentation with flags to enable GPU on Khoj pip install 
- Use tabs for GPU/CPU type khoj being install on
- Update CMAKE flags to use to install Khoj with correct GPU support
  Previous flags used DLLAMA, this has been updated to use DGGML now
  in llama.cpp
 2024-09-29 04:06:35 -07:00
sabaimran
63a2b5b3c4 Remove tools cache in dockerize.yml workflow 2024-09-29 00:27:37 -07:00
Debanjum Singh Solanky
936bc64b82 Render images to take full width of chat message div 
Remove unnecessary "Inferred Query" heading prefix to image generation prompt
used by Khoj. The inferred query in chat message has a heading of it's
own, so avoid two headings for the image prompt
 2024-09-28 23:45:56 -07:00
Debanjum Singh Solanky
4efa7d4464 Upgrade the Next.js web app package dependency 2024-09-28 23:45:56 -07:00
Debanjum Singh Solanky
b3cb417796 Fix spelling of Manage Context in Side Panel of Web App 2024-09-28 23:45:56 -07:00
sabaimran
676ff5fa69 Fix setting title on new conversations, add the action menu 2024-09-28 23:43:27 -07:00
Shantanu Sakpal
65d5e03f7f Reduce tooltip popup delay duration for Create Agent button on Web app (#926) 
The problem was the tool tip was visible on hover, but it was slow, so before the tool tip popped up, the user would click on the button and this stopped the tool tip from popping up.

So i reduced the popup delay to 10ms. now as soon as user hovers over the button, they will see that its a feature coming soon!
 2024-09-28 23:01:40 -07:00
Shantanu Sakpal
be8de1a1bd Only Auto Scroll when at Page Bottom and Add Button to Scroll to Page Bottom on Web App (#923) 
Improve Scrolling on Chat page of Web app

- Details
  1. Only auto scroll Khoj's streamed response when scroll is near bottom of page
      Allows scrolling to other messages in conversation while Khoj is formulating and streaming its response
  2. Add button to scroll to bottom of the chat page
  3. Scroll to most recent conversation turn on conversation first load
      It's a better default to anchor to most recent conversation turn (i.e most recent user message)
  4. Smooth scroll when Khoj's chat response is streamed
      Previously the scroll would jitter during response streaming
  5. Anchor scroll position when fetch and render older messages in conversation
      Allow users to keep their scroll position when older messages are fetched from server and rendered

Resolves #758
 2024-09-28 22:54:34 -07:00
sabaimran
06777e1660 Convert the default conversation id to a uuid, plus other fixes (#918) 
* Update the conversation_id primary key field to be a uuid

- update associated API endpoints
- this is to improve the overall application health, by obfuscating some information about the internal database
- conversation_id type is now implicitly a string, rather than an int
- ensure automations are also migrated in place, such that the conversation_ids they're pointing to are now mapped to the new IDs

* Update client-side API calls to correctly query with a string field

* Allow modifying of conversation properties from the chat title

* Improve drag and drop file experience for chat input area

* Use a phosphor icon for the copy to clipboard experience for code snippets

* Update conversation_id parameter to be a str type

* If django_apscheduler is not in the environment, skip the migration script

* Fix create automation flow by storing conversation id as string

The new UUID used for conversation id can't be directly serialized.
Convert to string for serializing it for later execution

---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
 2024-09-24 14:12:50 -07:00
Debanjum Singh Solanky
0c936cecc0 Release Khoj version 1.23.3 2024-09-24 12:44:09 -07:00
Debanjum Singh Solanky
61c6e742d5 Truncate chat context to max tokens for offline, openai chat actors too 2024-09-24 12:42:32 -07:00
sabaimran
e306e6ca94 Fix file paths used for pypi wheel building 2024-09-22 12:42:08 -07:00
Debanjum
f00e0e6080 Improve Khoj First Run, Docker Setup and Documentation (#919) 
## Improve
- Intelligently initialize a decent default set of chat model options
- Create non-interactive mode. Auto set default server configuration on first run via Docker

## Fix
- Make RapidOCR dependency optional as flaky requirements causing docker build failures
- Set default openai text to image model correctly during initialization

## Details
Improve initialization flow during first run to remove need to configure Khoj:

- Set Google, Anthropic Chat models too
  Previously only Offline, Openai chat models could be set during init

- Add multiple chat models for each LLM provider
  Interactively set a comma separated list of models for each provider

- Auto add default chat models for each provider in non-interactive
  model if the `{OPENAI,GEMINI,ANTHROPIC}_API_KEY' env var is set
  - Used when server run via Docker as user input cannot be processed to configure server during first run

- Do not ask for `max_tokens', `tokenizer' for offline models during
  initialization. Use better defaults inferred in code instead

- Explicitly set default chat model to use
  If unset, it implicitly defaults to using the first chat model.
  Make it explicit to reduce this confusion

Resolves #882
 2024-09-21 14:15:45 -07:00
Debanjum Singh Solanky
a6c0b43539 Upgrade documentation package dependencies 2024-09-21 14:06:40 -07:00
Debanjum Singh Solanky
2033f5168e Modularize chat models initialization with a reusable function 
The chat model initialize interaction flow is fairly similar across
the chat model providers.

This should simplify adding new chat model providers and reduce
chances of bugs in the interactive chat model initialization flow.
 2024-09-21 14:06:40 -07:00
Debanjum Singh Solanky
26c39576df Add Documentation for the settings on the Khoj Admin Panel 
This is an initial pass to add documentation for all the knobs
available on the Khoj Admin panel.

It should shed some light onto what each admin setting is for and how
they can be customized when self hosting.

Resolves #831
 2024-09-21 14:06:40 -07:00
Debanjum Singh Solanky
730e5608bb Improve Self Hosting Docs. Better Docker, Remote Access Setup Instructions 
- Improve Self Hosting Docker Instructions
  - Ask to Install Docker Desktop to not require separate
    docker-compose install and unify the instruction across OS
  - To Self Host on Windows, ask to use Docker Desktop with WSL2 backend

- Use nested Tab grouping to split Docker vs Pip Self Host Instructions

- Reduce Self Host Setup Steps in Documentation after code simplification
  - First run now avoids need to configure Khoj via admin panel
  - So move the chat model config steps into optional post setup
    config section

- Improve Instructions to Configure chat models on First Run

- Compress configuring chat model providers into a Tab Group

- Add Documentation for Remote Access under Advanced Self Hosting
 2024-09-21 14:06:17 -07:00
Debanjum Singh Solanky
91c76d4152 Intelligently initialize a decent default set of chat model options 
Given the LLM landscape is rapidly changing, providing a good default
set of options should help reduce decision fatigue to get started

Improve initialization flow during first run
- Set Google, Anthropic Chat models too
  Previously only Offline, Openai chat models could be set during init

- Add multiple chat models for each LLM provider
  Interactively set a comma separated list of models for each provider

- Auto add default chat models for each provider in non-interactive
  model if the {OPENAI,GEMINI,ANTHROPIC}_API_KEY env var is set

- Do not ask for max_tokens, tokenizer for offline models during
  initialization. Use better defaults inferred in code instead

- Explicitly set default chat model to use
  If unset, it implicitly defaults to using the first chat model.
  Make it explicit to reduce this confusion

Resolves #882
 2024-09-19 20:32:08 -07:00
Debanjum Singh Solanky
f177723711 Add default server configuration on first run in non-interactive mode 
This should configure Khoj with decent default configurations via
Docker and avoid needing to configure Khoj via admin page to start
using dockerized Khoj

Update default max prompt size set during khoj initialization
as online chat model are cheaper and offline chat models have larger
context now
 2024-09-19 15:12:55 -07:00
Debanjum Singh Solanky
020167c7cf Set default openai text to image model correctly during initialization 
Speech to text model was previously being set to the text to image
model previously!
 2024-09-19 15:11:34 -07:00
Debanjum Singh Solanky
077b88bafa Make RapidOCR dependency optional as flaky requirements 
RapidOCR depends on OpenCV which by default requires a bunch of GUI
paramters. This system package dependency set (like libgl1) is flaky

Making the RapidOCR dependency optional should allow khoj to be more
resilient to setup/dependency failures

Trade-off is that OCR for documents may not always be available and
it'll require looking at server logs to find out when this happens
 2024-09-19 15:10:31 -07:00
sabaimran
0a568244fd Revert "Convert conversationId int to string before making api request to bulk update file filters" 
This reverts commit c9665fb20b.

Revert "Fix handling for new conversation in agents page"

This reverts commit 3466f04992.

Revert "Add a unique_id field for identifiying conversations (#914)"

This reverts commit ece2ec2d90.
 2024-09-18 20:36:57 -07:00
Debanjum Singh Solanky
bb2bd77a64 Send chat message to Khoj web app via url query param 
- This allows triggering khoj chat from the browser addressbar
- So now if you add Khoj to your browser bookmark with
  - URL: https://app.khoj.dev/?q=%s
  - Keyword: khoj

- Then you can type "khoj what is the news today" to trigger Khoj to
  quickly respond to your query. This avoids having to open the Khoj web
  app before asking your question
 2024-09-17 21:50:47 -07:00
Debanjum Singh Solanky
ecdbcd815e Simplify code to remove json codeblock from AI response string 2024-09-17 21:50:47 -07:00
sabaimran
e457720e8a Improve the email templates and better align with new branding 2024-09-17 11:18:25 -07:00
sabaimran
c9665fb20b Convert conversationId int to string before making api request to bulk update file filters 2024-09-16 15:45:23 -07:00
sabaimran
3466f04992 Fix handling for new conversation in agents page 2024-09-16 15:04:49 -07:00
sabaimran
ece2ec2d90 Add a unique_id field for identifiying conversations (#914) 
* Add a unique_id field to the conversation object

- This helps us keep track of the unique identity of the conversation without expose the internal id
- Create three staged migrations in order to first add the field, then add unique values to pre-fill, and then set the unique constraint. Without this, it tries to initialize all the existing conversations with the same ID.

* Parse and utilize the unique_id field in the query parameters of the front-end view

- Handle the unique_id field when creating a new conversation from the home page
- Parse the id field with a lightweight parameter called v in the chat page
- Share page should not be affected, as it uses the public slug

* Fix suggested card category
 2024-09-16 12:19:16 -07:00
sabaimran
e6bc7a2ba2 Fix links to log in email templates 2024-09-15 19:14:19 -07:00
Debanjum Singh Solanky
79980feb7b Release Khoj version 1.23.2 2024-09-15 03:07:26 -07:00
Debanjum Singh Solanky
575ff103cf Frame chat response error on web app in a more conversational form 
Also indicate hitting dislike on the message should be enough to
convey the issue to the developers.
 2024-09-15 03:00:49 -07:00
Debanjum Singh Solanky
893ae60a6a Improve handling of harmful categorized responses by Gemini 
Previously Khoj would stop in the middle of response generation when
the safety filters got triggered at default thresholds. This was
confusing as it felt like a service error, not expected behavior.

Going forward Khoj will
- Only block responding to high confidence harmful content detected by
  Gemini's safety filters instead of using the default safety settings
- Show an explanatory, conversational response (w/ harm category)
  when response is terminated due to Gemini's safety filters
 2024-09-15 02:17:54 -07:00
sabaimran
ec1f87a896 Release Khoj version 1.23.1 2024-09-12 22:46:39 -07:00
sabaimran
2a4416d223 Use prefetch_related for the openai_config when retrieving all chatmodeloptions async 2024-09-12 22:45:43 -07:00
sabaimran
253ca92203 Release Khoj version 1.23.0 2024-09-12 20:25:29 -07:00
Debanjum Singh Solanky
178b78f87b Show debug log, not warning when use default tokenizer for context stuffing 2024-09-12 20:21:01 -07:00
Debanjum
f173188dcf Support using image generation models like Flux via Replicate (#909) 
- Support using image generation models like Flux via Replicate
- Modularize the image generation code
- Make generate better image prompt chat actor add composition details
- Generate vivid images with DALLE-3
 2024-09-12 20:19:46 -07:00
Debanjum Singh Solanky
75d3b34452 Extract image generation code into new image processor for modularity 2024-09-12 20:01:32 -07:00
Debanjum Singh Solanky
84051d7d89 Make generate better image prompt chat actor add composition details 2024-09-12 19:58:57 -07:00
Debanjum Singh Solanky
ed12f45a26 Generate vivid images with DALLE-3 
It's apparently the default setting in chatgpt app according to the
openai cookbook at https://cookbook.openai.com/articles/what_is_new_with_dalle_3#examples-and-prompts
 2024-09-12 19:58:57 -07:00
Debanjum Singh Solanky
1b82aea753 Support using image generation models like Flux via Replicate 
Enables using any image generation model on Replicate's Predictions
API endpoints.

The server admin just needs to add text-to-image model on the
server/admin panel in organization/model_name format and input their
Replicate API key with it

Create db migration (including merge)
 2024-09-12 19:58:56 -07:00
Brian Kanya
1d512b4986 Use environment variable to set sender email of auth link emails (#907) 
Set sender email using `RESEND_EMAIL` environment variable for magic link sent via Resend API for authentication . It was previously hard-coded. This prevented hosting Khoj on other domains. 

Resolves #908
 2024-09-12 18:48:11 -07:00
Debanjum
26ca3df605 Support OpenAI's new O1 Model Series (#912) 
- Major
   - The new O1 series doesn't seem to support streaming, response_format enforcement, 
      stop words or temperature currently. 
   - Remove any markdown json codeblock in chat actors expecting json responses

- Minor
   - Override block display styling of links by Katex in chat messages
 2024-09-12 18:42:51 -07:00
Debanjum Singh Solanky
0685a79748 Remove any markdown json codeblock in chat actors expecting json responses 
Strip any json md codeblock wrapper if exists before processing
response by output mode, extract questions chat actor. This is similar
to what is already being done by other chat actors

Useful for succesfully interpreting json output in chat actors when
using non (json) schema enforceable models like o1 and gemma-2

Use conversation helper function to centralize the json md codeblock
removal code
 2024-09-12 18:26:15 -07:00
Debanjum Singh Solanky
6e660d11c9 Override block display styling of links by Katex in chat messages 
This happens sometimes when LLM respons contains [\[1\]] kind of links
as reference. Both markdown-it and katex apply styling.

Katex's span uses display: block which makes the rendering of these
references take up a whole line by themselves.

Override block styling of spans within an `a' element to prevent such
chat message styling issues
 2024-09-12 18:22:46 -07:00
Debanjum Singh Solanky
272eae5d66 Add support for the newly released OpenAI O1 model series for preview 
The O1 series doesn't seem to support streaming, stop words or
temperature, response_format currently.
 2024-09-12 18:22:46 -07:00
Alexander Matyasko
9570933506 Support Google's Gemini model series (#902) 
* Add functions to chat with Google's gemini model series
  * Gracefully close thread when there's an exception in the gemini llm thread
* Use enums for verifying the chat model option type
* Add a migration to add the gemini chat model type to the db model
* Fix chat model selection verification and math prompt tuning
* Fix extract questions method with gemini. Enforce json response in extract questions.
* Add standard stop sequence for Gemini chat response generation

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
 2024-09-12 18:17:55 -07:00
Debanjum Singh Solanky
42b727e926 Revert additional logging enabled to debug automation failures in prod 
Additional logging was enabled to debug automation failures in
production since migration chat API to use POST request method (from
earlier GET).

Redirect from http to https was default to use GET instead of POST
method to call /api/chat on redirect. This has been resolved now
 2024-09-12 17:56:54 -07:00
sabaimran
14a495cbb5 Release Khoj version 1.22.3 2024-09-12 12:39:04 -07:00
sabaimran
91cee2eaa8 Handle redirects when scheduling chats from automations 2024-09-12 11:36:47 -07:00
sabaimran
4555969d38 Add additional log lines 2024-09-12 10:50:36 -07:00
sabaimran
12897a9a62 Update link to gif demo in README to pull from GitHub 2024-09-11 20:09:26 -07:00
sabaimran
9310f88537 Add quadratic equation gif to docs 2024-09-11 20:07:57 -07:00
sabaimran
d042a055cf Update the demo and simplify the readme 2024-09-11 20:03:48 -07:00
sabaimran
4d3224657f Update the documentation with swanky new demo videos 2024-09-11 19:57:10 -07:00
Debanjum Singh Solanky
2cc4a0769e Release Khoj version 1.22.2 2024-09-11 18:39:24 -07:00
Debanjum Singh Solanky
7f186be742 Fix json payload passed by automations to the new POST chat API 2024-09-11 18:35:31 -07:00
sabaimran
5038d15574 Route to config_page, not to deprecated notion_config_page, on notion callback API 2024-09-11 18:30:23 -07:00
Debanjum Singh Solanky
b61d825cbc Sanitize user attached image in chat message input pane of web app 2024-09-11 18:02:33 -07:00
Debanjum Singh Solanky
de60ad7da6 Update automations to call new POST chat API endpoint 2024-09-11 17:28:40 -07:00
Debanjum Singh Solanky
055ead550c Update desktop shortcut, web app factchecker to use new POST chat API 2024-09-11 17:28:32 -07:00
Debanjum Singh Solanky
bc2e889d72 Update chat director, client tests to call chat API using new POST method 2024-09-11 17:28:06 -07:00
Debanjum Singh Solanky
3f51af9a96 Keep the GET chat API endpoint for a bit before deprecating it 
This is to avoid breaking non-updated Khoj clients
 2024-09-11 16:50:10 -07:00
Debanjum Singh Solanky
241b9009ba Update OpenAI chat actor tests to handle more questions being extracted 2024-09-11 16:16:55 -07:00
Debanjum Singh Solanky
03befc9b12 Use consistent user attached image placeholder text for chat actors 
Get information sources and get output mode don't actually see the
images. They just get placeholder text to indicate that the user
attached an image to their message for context
 2024-09-11 16:16:55 -07:00
Debanjum Singh Solanky
04363a504c Prompt Whisper to know "Khoj" term for speech to text transcription 2024-09-11 16:16:55 -07:00
Debanjum Singh Solanky
3dcc8695b2 Improve vertical alignment of lists in chat messages on web app 
- Make train of thought icons to be top aligned, next to the
  their intermediate step heading
- Add margin bottom to ordered, unordered lists in chat message,
  similar to how it is already added for paragraphs
 2024-09-11 16:16:55 -07:00
Debanjum Singh Solanky
179357b28a Default to gpt-4o-mini as online chat model 2024-09-11 16:16:55 -07:00
sabaimran
ae74c6ca55 Release Khoj version 1.22.1 2024-09-11 13:03:53 -07:00
sabaimran
cd5db277f3 Fix sync to async issue when getting all valid vision configs 2024-09-11 12:57:54 -07:00
sabaimran
9b12290c17 Release Khoj version 1.22.0 2024-09-11 11:21:02 -07:00
sabaimran
2932d305b0 Simplify redundant logic for constructing structured messages with image url 2024-09-10 21:09:43 -07:00
sabaimran
07e2c49a7a Set default temperature to 0.7 in the extract_questions method 2024-09-10 21:09:21 -07:00
sabaimran
8d40fc0aef Limit vision_enabled image formatting to OpenAI APIs and send vision to extract_questions query 2024-09-10 20:08:14 -07:00
Debanjum Singh Solanky
aa31d041f3 Style list html elements by default on web app to improve readability 
Previously list styling was turned off for some reason in Next.js
 2024-09-10 17:45:04 -07:00
Debanjum Singh Solanky
d81a050d73 Update documentation package dependencies 2024-09-10 14:18:56 -07:00
Debanjum Singh Solanky
7614718204 Build Khoj cloud docker image for arm64 architecture too 2024-09-10 13:57:09 -07:00
Debanjum Singh Solanky
596db603e0 Pass query params to chat API in POST body instead of URL query string 
Closes #899, #678
 2024-09-10 13:57:03 -07:00
Debanjum Singh Solanky
fc6345e246 Simplify setImagePath for upload from chat input area of web app 2024-09-10 09:18:54 -07:00
Raghav Tirumale
549686a7a4 Add Vision Support (#889) 
# Summary of Changes
* New UI to show preview of image uploads
* ChatML message changes to support gpt-4o vision based responses on images
* AWS S3 image uploads for persistent image context in conversations
* Database changes to have `vision_enabled` option in server admin panel while configuring models
* Render previously uploaded images in the chat history, show uploaded images for pending msgs
* Pass the uploaded_image_url through to subqueries
* Allow image to render upon first message from the homepage
* Add rendering support for images to shared chat as well
* Fix some UI/functionality bugs in the share page
* Convert user attached images for chat to webp format before upload
* Use placeholder to attached image for data source, response mode actors
* Update all clients to call /api/chat as a POST instead of GET request
* Fix copying chat messages with images to clipboard

TLDR; Add vision support for openai models on Khoj via the web UI!

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
 2024-09-09 15:22:18 -07:00
Debanjum Singh Solanky
b553bba1d8 Release Khoj version 1.21.6 2024-09-09 14:55:36 -07:00
sabaimran
223d310ea2 CTA in welcome email 2024-09-09 14:33:27 -07:00
Debanjum Singh Solanky
5dea9ef323 Add selected OS tab to url in documentation to ease link sharing 2024-09-09 10:40:53 -07:00
Debanjum Singh Solanky
87c52dfd02 Update Documentation project dependencies 
Stop wrapping Tabs in explicit mdx-code-blocks as build after upgrade
throws error
 2024-09-09 10:40:53 -07:00
Debanjum Singh Solanky
7941b12d50 Toggle speak, send buttons based on chat input text entered on Desktop 2024-09-09 10:40:53 -07:00
Debanjum Singh Solanky
b5f6550de2 Move link to source code from Nav pane to About page on Desktop app 2024-09-09 10:40:53 -07:00
Debanjum Singh Solanky
77b44f6db0 Update Desktop app dependencies 2024-09-09 10:40:53 -07:00
Debanjum Singh Solanky
303d8ed64e Update Obsidian plugin package dependencies 2024-09-09 10:40:53 -07:00
Debanjum Singh Solanky
72fbbc092c Upgrade Django, FastAPI, Uvicorn packages 
- Update Django to 5.0.8
- Update Uvicorn to 0.30.6
- Update FastAPI minimum versions to 0.110.0
 2024-09-09 10:40:53 -07:00
sabaimran
8e6b9afeb7 Add an automation for research paper summaries 2024-09-08 11:50:49 -07:00
Debanjum
05c169bb37 Set File Types to Sync from Obsidian via Khoj Plugin Settings Page (#904) 
Limit file types to sync with Khoj from Obsidian to:
- Avoid hitting per user index-able data limits, especially for folks on the Khoj cloud free tier. E.g by excluding images in Obsidian vault from being synced
- Improve context used by Khoj to generate responses
 2024-09-05 22:40:30 -07:00
Husain007
4e8ead66a8 Fix URL to web, desktop settings pages on Desktop application (#903) 
Update web and desktop settings URLs on desktop application from previous 'config' path to new 'settings' path
 2024-09-05 14:47:43 -07:00
Debanjum Singh Solanky
bc26cf8b2f Only show updated index notice on success in Obsidian plugin 
Previously it'd show indexing success notice on error and success
 2024-09-04 17:52:32 -07:00
Debanjum Singh Solanky
cb425a073d Use rich text error to better guide when exceed data sync limits in Obsidian 
When user exceeds data sync limits. Show error notice with
- Link to web app settings page to upgrade subscription
- Link to Khoj plugin settings in Obsidian to configure file types to
  sync from vault to Khoj
 2024-09-04 17:52:32 -07:00
Debanjum Singh Solanky
19efc83455 Set File Types to Sync from Obsidian via Khoj Plugin Settings Page 
Useful to limit file types to sync with Khoj. Avoids hitting indexed
data limits, especially for users on the Khoj cloud free tier

Closes #893
 2024-09-04 16:09:56 -07:00
sabaimran
7216a06f5f Release Khoj version 1.21.5 2024-09-03 21:58:00 -07:00
sabaimran
895f1c8e9e Gracefully close thread when there's an exception in the anthropic llm thread. Include full stack traces. 2024-09-03 13:16:51 -07:00
sabaimran
17901406aa Gracefully close thread when there's an exception in the openai llm thread. Closes #894. 2024-09-03 13:16:51 -07:00
sabaimran
6ed68b574b Merge pull request #898 from lvnilesh/patch-1 
Handles deprecation of version reference
 2024-09-03 12:53:44 -07:00
sabaimran
912cc0074a Use nonlocal for conversation_id when running the event_generator 2024-09-03 11:55:06 -07:00
sabaimran
591f5a522c Release Khoj version 1.21.4 2024-09-02 17:45:39 -07:00
sabaimran
9306a0bb2c Prefetch the settings and openai_config of a texttoimagemodelconfig 2024-09-02 17:35:21 -07:00
sabaimran
132eac0f51 Merge pull request #897 from khoj-ai/features/increase-rate-limits 
Increase rate limits for data indexing
 2024-08-25 23:39:30 -07:00
LV Nilesh
77cc1cd42f Update docker-compose.yml 
Handles deprecation of version reference
 2024-08-25 17:05:47 -07:00
sabaimran
977001b801 Reduce the test data packet size 2024-08-25 16:14:32 -07:00
sabaimran
6eb06e8626 Downgrade rate limit to 200MB 2024-08-25 15:26:27 -07:00
sabaimran
439a2680fd Increase rate limits for data indexing 2024-08-25 15:09:30 -07:00
sabaimran
af4e9988c4 Merge pull request #896 from khoj-ai/features/add-support-for-custom-confidence 
Add support for custom search model-specific thresholds
 2024-08-24 20:32:41 -07:00
sabaimran
4b77325f63 Default to infinite distance when using the search API 2024-08-24 19:57:49 -07:00
sabaimran
e919d28f1c Add support for custom search model-specific thresholds 2024-08-24 19:28:26 -07:00
sabaimran
fa4d808a5f Encode uri components when sending automations data to the server 2024-08-24 18:45:50 -07:00
sabaimran
387b7c7887 Release Khoj version 1.21.3 2024-08-23 11:15:15 -07:00
sabaimran
7b8b3a66ae Revert django version to previous patch 2024-08-23 11:12:41 -07:00
Debanjum Singh Solanky
5927ca8032 Properly close chat stream iterator even if response generation fails 
Previously chat stream iterator wasn't closed when response streaming
for offline chat model threw an exception.

This would require restarting the application. Now application doesn't
hang even if current response generation fails with exception
 2024-08-23 02:06:26 -07:00
Debanjum Singh Solanky
bdb81260ac Update docs to mention using Llama 3.1 and 20K max prompt size for it 
Update stale credits to better reflect bigger open source dependencies
 2024-08-22 20:27:58 -07:00
Debanjum Singh Solanky
238bc11a50 Fix, improve openai chat actor, director tests & online search prompt 2024-08-22 19:09:33 -07:00
Debanjum Singh Solanky
9986c183ea Default to gpt-4o-mini instead of gpt-3.5-turbo in tests, func args 
GPT-4o-mini is cheaper, smarter and can hold more context than
GPT-3.5-turbo. In production, we also default to gpt-4o-mini, so makes
sense to upgrade defaults and tests to work with it
 2024-08-22 19:04:49 -07:00
Debanjum Singh Solanky
8a4c20d59a Enforce json response by offline models when requested by chat actors 
- Background
  Llama.cpp allows enforcing response as json object similar to OpenAI
  API. Pass expected response format to offline chat models as well.

- Overview
  Enforce json output to improve intermediate step performance by
  offline chat models. This is especially helpful when working with
  smaller models like Phi-3.5-mini and Gemma-2 2B, that do not
  consistently respond with structured output, even when requested

- Details
  Enforce json response by extract questions, infer output offline
  chat actors
  - Convert prompts to output json objects when offline chat models
    extract document search questions or infer output mode
  - Make llama.cpp enforce response as json object

- Result
  - Improve all intermediate steps by offline chat actors via json
    response enforcement
  - Avoid the manual, ad-hoc and flaky output schema enforcement and
    simplify the code
 2024-08-22 18:07:44 -07:00
Debanjum Singh Solanky
ab7fb5117c Release Khoj version 1.21.2 2024-08-20 12:38:54 -07:00
Debanjum Singh Solanky
de24ffcf0d Upgrade Axios, a desktop app dependency, to version 1.7.4 2024-08-20 12:32:36 -07:00
Debanjum Singh Solanky
a60baa55fb Upgrade Django, a Khoj server dependency, to version 5.0.8 2024-08-20 12:32:00 -07:00
sabaimran
1ac8de6c3a Release Khoj version 1.21.1 2024-08-20 11:55:34 -07:00
Debanjum Singh Solanky
5d59acd1f4 Stop pushing deprecated khoj-assistant package to pypi 
- Also skip uploading package version to it already exists on pypi
  This happens when a release is new khoj tagged release is created
 2024-08-20 11:43:02 -07:00
sabaimran
f6ce2fd432 Handle end of chunk logic in openai stream processor 2024-08-20 10:50:09 -07:00
sabaimran
029775420c Release Khoj version 1.21.0 2024-08-20 10:01:56 -07:00
sabaimran
4808ce778a Merge pull request #892 from khoj-ai/upgrade-offline-chat-models-support 
Upgrade offline chat model support. Default to Llama 3.1
 2024-08-20 11:51:20 -05:00
Debanjum Singh Solanky
58c8068079 Upgrade default offline chat model to llama 3.1 2024-08-20 09:28:56 -07:00
sabaimran
2d9dd81e76 Re-add authenticated decorator to api_chat.py /chat endpoint 2024-08-19 05:37:18 -05:00
sabaimran
2c5350329a Remove the hashes from titles in found relevant notes 2024-08-18 22:31:15 -05:00
Debanjum Singh Solanky
acdc3f9470 Unwrap any json in md code block, when parsing chat actor responses 
This is a more robust way to extract json output requested from
gemma-2 (2B, 9B) models which tend to return json in md codeblocks.

Other models should remain unaffected by this change.

Also removed request to not wrap json in codeblocks from prompts. As
code is doing the unwrapping automatically now, when present
 2024-08-16 14:16:29 -05:00
Debanjum Singh Solanky
ca45fce8ac Break long links in train of thought to stay within chat page width 2024-08-16 14:16:29 -05:00
sabaimran
c0316a6b5d Enable free tier users to have unlimited chats with the default chat model (#886) 
- Allow free tier users to have unlimited chats with default chat model. It'll only be rate-limited and at the same rate as subscribed users
- In the server chat settings, replace the concept of default/summarizer models with default/advanced chat models. Use the advanced models as a default for subscribed users.
- For each `ChatModelOption' configuration, allow the admin to specify a separate value of `max_tokens' for subscribed users. This allows server admins to configure different max token limits for unsubscribed and subscribed users
- Show error message in web app when hit rate limit or other server errors
 2024-08-16 12:14:44 -07:00
Debanjum
8dad9362e7 Improve search model config display for admin (#887) from aam-at/feature/improve_search_model_config_admin 
Currently, the search model config display for admins only shows the id of the search model config, which is not very informative. 

The changes enhances the admin console by displaying the name of the search model config (name), as well as the bi-encoder model (bi_encoder) and cross-encoder model (cross_encoder) along the id.
 2024-08-16 07:33:55 -07:00
Debanjum
2b1482d2b4 Fix indexing content from Emacs #883 from aam-at/bugfix/fix_emacs_if 
Previously `force' was passed as a query param to the single indexing API. After the recent API updates, it is meant to select the API method to use (PATCH vs PATCH). Converting `force' argument to a bool fixes implementing this new behavior
 2024-08-16 07:32:46 -07:00
Debanjum
0b568e204e Add model_config for cross-encoder model (#885) from aam-at/feature/crossencoder_model_config 
Add `model_config' for the cross-encoder model, so the server admin can use models which require the `trust_remote_code' argument to run locally
 2024-08-16 07:32:19 -07:00
Debanjum
39e566ba91 Improve Document, Online Search to Answer Vague or Meta Questions (#870) 
- Major
  - Improve doc search actor performance on vague, random or meta questions
  - Pass user's name to document and online search actors prompts

- Minor
  - Fix and improve openai chat actor tests
  - Remove unused max tokns arg to extract qs func of doc search actor
 2024-08-16 06:46:13 -07:00
Debanjum Singh Solanky
27ad9b1302 Remove unused max tokns arg to extract qs func of doc search actor 2024-08-13 12:53:39 +05:30
Debanjum Singh Solanky
f75606d7f5 Improve doc search actor performance on vague, random or meta questions 
- Issue
  Previously the doc search actor wouldn't extract good search queries
  to run on user's documents for broad, vague questions.

- Fix
  The updated extract questions prompt shows and tells the doc search
  actor on how to deal with such questions

  The doc search actor's temperature was also increased to support more
  creative/random questions. The previous temp of 0 was meant to
  encourage structured json output. But now with json mode, a low temp is
  not necessary to get json output
 2024-08-13 12:53:39 +05:30
Debanjum Singh Solanky
3675938df6 Support passing temperature to offline chat model chat actors 
- Use temperature of 0 by default for extract questions offline chat
  actor
- Use temperature of 0.2 for send_message_to_model_offline (this is
  the default temperature set by llama.cpp)
 2024-08-13 12:53:00 +05:30
Shantanu Sakpal
b5bcce7f85 Cycle through chat history in chat input on Obsidian (#861) 
* Add ability to cycle through the chat history in the chat input on Obsidian (similar to terminal history navigation)
* Add mod key shortcut to cycle through chat history in chat input
* Add shortcut help text in chat input placeholder

---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
 2024-08-12 23:55:25 -07:00
srikary12
05c0aa3882 Support exclusion file filters (#826) 
### Overview
Support exclude file filter in user search queries

### Details
- All of the exclude file filter terms need to be satisfied
- Any one of the include file filter terms should be satisfied

### Example
- **Search Query**: *what happened yesterday? -file:"tasks.org" -file:"work.md" file:"diary.org" file:"journal.org*
- **Behavior**: Query will try find relevant notes in any of `journal.org` or `diary.org` and not in `tasks.org` and not in `work.md`

### Details
* Add support for exclusion file filters
* Translate file filter to valid Django DB entry filter regex
* Exclude all files when multiple exclude file filter in query

Previously we were applying an "Or" filter, which would exclude any
file mentioned in a query with multiple exclude file filter.

This is not what we naturally mean when we ask excluding a file in a query

* Rename, rearrange, deduplicate and add file filter tests

Closes #728
---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
 2024-08-12 05:41:54 -07:00
Alexander Matyasko
2d9bf14ecb Improve search model config display for admin 2024-08-11 19:13:25 +08:00
Debanjum Singh Solanky
7815e02dd4 Release Khoj version 1.20.4 2024-08-11 16:00:13 +05:30
Debanjum Singh Solanky
d951e36945 Update khoj.el package description, it had gone stale 2024-08-11 15:52:46 +05:30
Debanjum Singh Solanky
16b31c3e35 Refresh automation data shown by edit automation card after update 
Previously required the automation page to be refreshed to see updates
to the automation in the edit automation card. This would be seen when
user tries to edit an automation multiple times (without a page refresh)
 2024-08-11 15:52:46 +05:30
Debanjum Singh Solanky
f2f37ae444 Fix creating, editing automations that start weekly on Sunday 2024-08-11 15:52:46 +05:30
Debanjum Singh Solanky
ec9add9a51 Fix automation edit cards height. Scroll when card longer than screen 2024-08-11 15:52:46 +05:30
sabaimran
d99f03e4f3 If the list of choices in a chunk is empty, continue in openai response 2024-08-11 15:30:09 +05:30
Alexander Matyasko
f16b0f628b Fix true/false evaluation in Emacs to prevent unintended index re-indexing 
Previously, the code incorrectly treated all non-nil values as true, leading to
the index being re-indexed with the force flag whenever the user selected to
update the index.
 2024-08-11 17:24:11 +08:00
Alexander Matyasko
0e9e9648e6 Fix emacs if syntax 2024-08-11 17:24:11 +08:00
sabaimran
6f94a076f7 Add conversation_id parameter to the create_automation method 2024-08-11 10:45:13 +05:30
sabaimran
acb825f4f5 Bug fixes for automations 
- Pass the new conversation id as kwarg for the scheduled_chat function
- For edit automations, re-use the original conversation id
- Parse images correctly for image automations
 2024-08-11 10:41:43 +05:30
Debanjum Singh Solanky
5075d13902 Give visual feedback when interact with chat message feedback buttons 
- Use color to provide visual feedback when hover, click on feedback
  buttons
- Use color to provide visual feedback when hover on speech, copy
  buttons click
- Add cooldown period before being able to send feedback on that message again.
  Avoids inadvertent multiple consecutive clicks on feedback buttons
 2024-08-10 20:09:52 +05:30
Debanjum Singh Solanky
b3c6c8c84b Add OpenGraph metadata to web app pages for improve social share links 2024-08-10 18:14:05 +05:30
Debanjum Singh Solanky
fc411091c8 Add apple favicon, load favicons for each web app page from assets folder 2024-08-10 18:14:05 +05:30
Debanjum Singh Solanky
a7623e64fa Move Khoj webmanifest, assets to new web app public directory 2024-08-10 18:14:04 +05:30
sabaimran
af1d4b9ba4 Remove the premium requirement for speech for now 2024-08-10 14:10:12 +05:30
sabaimran
1d581464e6 Filter out any undefined agents when rendering the home page 2024-08-10 13:33:55 +05:30
sabaimran
acf1c14122 Release Khoj version 1.20.3 2024-08-09 18:11:11 +05:30
sabaimran
7d3a25f8c0 Handle processing case for the schedule leader process lock when it's empty 2024-08-09 16:37:06 +05:30
sabaimran
faf3584acd Fix automations edit button 2024-08-09 14:21:11 +05:30
sabaimran
5ef198a5b2 Improve default background color styling for inputs 2024-08-08 18:08:05 +05:30
sabaimran
c08b9e89f0 Update test_db_lock with new function name 2024-08-08 13:03:01 +05:30
sabaimran
64b2073e63 In the time-based job for managing the schedule leader, and logic to create a new lock when the current one is expired. 2024-08-08 12:42:59 +05:30
sabaimran
7ee0d9067d Fix apostrophe issue in copy text when commandempty in settings page 2024-08-08 11:41:10 +05:30
sabaimran
f28693c8c7 create a useismobilewidth method for standardized mobile view detection. 2024-08-07 21:04:44 +05:30
sabaimran
2943bed5d4 Update category colors 2024-08-07 18:51:31 +05:30
sabaimran
37afa3411f Improve the file upload experience in the settings page 2024-08-07 18:51:20 +05:30
sabaimran
1ee21f5150 Add support for showing files outside of conversation view and linking people to manage files in settings 2024-08-07 18:50:53 +05:30
sabaimran
93f4ceabc1 Add drag/drop file upload support to the chat input area 2024-08-07 18:50:19 +05:30
sabaimran
370ebdee24 Standardized the mobile width calculation 2024-08-07 18:49:06 +05:30
sabaimran
52fed6023f Overlay the side panel on top of other content 2024-08-07 18:46:06 +05:30
Alexander Matyasko
823f8d58bb Add model_config for crossencoder model 
Add model_config for crossencoder model, so the user can use models
which require trust_remote_code.
 2024-08-07 18:00:12 +08:00
sabaimran
09b71846be Remove favicon.ico as it's interfering with favicon rendering in the home page 2024-08-07 11:53:25 +05:30
Debanjum Singh Solanky
167ef000f4 Fix chat API for non-streaming mode json response 2024-08-06 19:27:54 +05:30
sabaimran
00ee4c2697 Release Khoj version 1.20.2 2024-08-06 16:16:33 +05:30
sabaimran
d4a8ff0683 Support workflow dispatch events for running the pypi.yml job 2024-08-06 15:55:39 +05:30
sabaimran
ccccb8e7e6 Just ignore the static directory outputting by django's static collection 2024-08-06 15:51:54 +05:30
sabaimran
c4be3b43e5 Add the compiled folder to the list of directories to look through for static templates 2024-08-06 14:50:44 +05:30
sabaimran
265d2a79be Remove duplicate assets from being included in the pypi output 2024-08-06 13:51:37 +05:30
sabaimran
24d0fdb262 Fix directory referenceds in pypi.yml configuration for compiled folder 2024-08-06 13:38:34 +05:30
sabaimran
23b1b36f8c Fix directory referenceds in pypi.yml configuration for compiled folder 2024-08-06 13:31:42 +05:30
sabaimran
81c75e1024 Fix static file folder path for the pypi build 
- Since the .gitignore will ignore any of the assets in the src/ folder when building the package wheel, we need to output the static assets to another folder just for the python pypi package. Use /compiled for this.
 2024-08-06 13:24:26 +05:30
sabaimran
694f551625 Fix mkdir step when copying generated files 2024-08-06 10:17:56 +05:30
sabaimran
7607abc726 Release Khoj version 1.20.1 2024-08-06 10:05:41 +05:30
sabaimran
e9f9d92989 Try to manually copy the built files into where the src directory should be for the pypi build 2024-08-06 10:05:06 +05:30
Debanjum
c23688e2de Fixes and Improvements Post Spring UX Release (#880) 
- Auto focus on email input on login screen for smoother login experience
- Use file icon associated with search page results. Improve search bar
- Show logged in user's email in nav menu for context
- Use previous icons with eyes for search, agents and automations items in nav menu
 2024-08-05 14:32:31 -07:00
Debanjum Singh Solanky
a4388c5e65 Use custom Khoj Icons for Search, Agents & Automation in Nav Menu 
- Update agents, automations, search svg icons
 2024-08-06 02:55:29 +05:30
sabaimran
e9d6899fc2 Change the way the export is created for the pypi package in order to transfer static files out of the tmp shell 2024-08-05 22:46:54 +05:30
sabaimran
b17577c138 Fix configuration for default voice model settings 2024-08-05 19:57:21 +05:30
Debanjum Singh Solanky
ec106d743d Use file icon associated with search page results. Improve search bar 2024-08-05 19:24:39 +05:30
Debanjum Singh Solanky
4258392fc7 Auto focus on email input on login screen for smoother login experience 2024-08-05 19:24:16 +05:30
Debanjum Singh Solanky
020a956c89 Show user email address on settings menu for logged in account context 2024-08-05 19:19:47 +05:30
sabaimran
998d08f155 Fix logic for deletion to automatically re-render the side pane 2024-08-05 18:07:20 +05:30
sabaimran
20d95dc45e Add the favicon.ico file to the public directory of app.khoj.dev 2024-08-05 18:04:03 +05:30
sabaimran
1eab6c8590 Add additional icons for agents, pencil line and chalkboard 2024-08-05 17:23:29 +05:30
sabaimran
bafda233e2 Add standlone khoj_domain for allowed_hosts 2024-08-05 17:11:37 +05:30
Debanjum Singh Solanky
e412ed3bcb Release Khoj version 1.20.0 2024-08-05 16:25:21 +05:30
Debanjum Singh Solanky
9f785dbafe Format web app package.json using prettier 2024-08-05 16:23:31 +05:30
Debanjum Singh Solanky
7d3a208f8b Update bump version script to bump new next.js web app version too 2024-08-05 16:20:47 +05:30
sabaimran
2a63439b16 Merge pull request #879 from khoj-ai/features/migrate-to-spring-ui 
Migrate all existing pages except login to the new spring ui
 2024-08-05 03:45:02 -07:00
sabaimran
b7ed32f455 Merge branch 'master' of github.com:khoj-ai/khoj into features/migrate-to-spring-ui 2024-08-05 16:12:46 +05:30
sabaimran
7e6b611a19 Fix typo for Obsidian 2024-08-05 15:55:06 +05:30
sabaimran
34d54c75f7 Lint new changes again 2024-08-05 15:54:50 +05:30
Debanjum Singh Solanky
7cb14ff07a Add dev setup script. Run prettier on web app pre-commit 2024-08-05 15:49:31 +05:30
sabaimran
91047d1619 Use a png for the windows desktop icon 2024-08-05 15:29:30 +05:30
sabaimran
1151d14466 Add a separate windows object in the todesktop configuration 2024-08-05 14:27:56 +05:30
sabaimran
c56072aa7b Update todesktop runtime and use the icns file for the todesktop configuration 2024-08-05 14:19:38 +05:30
sabaimran
484b0aa96b Use the newer, simpler favicon across desktop and documentation. Update the macos icon set 2024-08-05 14:06:04 +05:30
sabaimran
1b35a3b16e Fix link to login in the nav menu 2024-08-05 12:32:19 +05:30
sabaimran
5a5bbe3852 Remove deprecate views, assets 2024-08-05 12:31:47 +05:30
sabaimran
c61b289bd1 Migrate all existing pages except login to the new spring ui 2024-08-05 12:17:56 +05:30
sabaimran
f835e330b8 Fix selection of icons, colors, add examples for personal finance 2024-08-05 12:08:18 +05:30
sabaimran
af6a70c9fb Fix fuschia spelling in the colorutils file as well 2024-08-05 11:51:45 +05:30
sabaimran
e0775446c9 fix spelling of fuschia :( 2024-08-05 11:50:11 +05:30
sabaimran
de1cd8c264 Clean up some of the suggestions code, improve randomness of cards' 2024-08-05 11:19:50 +05:30
sabaimran
37e261ff93 Show connected icon when files or notion is indexed 2024-08-05 10:33:18 +05:30
sabaimran
8bc28fb11d Merge pull request #878 from khoj-ai/features/big-upgrade-chat-ux 
Spring UI: Modernize UX for normie development
 2024-08-04 21:32:18 -07:00
sabaimran
22cfedcaff In the chat history side panel, order conversations by updated time 2024-08-05 09:48:00 +05:30
sabaimran
8220dc6115 Include the updated_at datetime when returning a conversation session 2024-08-05 09:47:13 +05:30
Debanjum Singh Solanky
e296d387e1 Clean duplicate title shown in reference snippets of hierarchical docs 
Hierarchical documents like org-mode, markdown have their ancestry
shown in first line. Remove it to show cleaner, deduplicated reference
text from org-mode, markdown files
 2024-08-05 04:59:06 +05:30
Debanjum Singh Solanky
95c2a52775 Show file icons in references for first party supported document types 
Add org, markdown, pdf, word, icon and default file icons to simplify
identifying file type used as reference for generating chat response
 2024-08-05 04:59:06 +05:30
Debanjum Singh Solanky
18a973b666 Fix name of Khoj logo component file in web app 2024-08-05 04:59:06 +05:30
Debanjum Singh Solanky
842036688d Format next.js web app with prettier 2024-08-05 04:59:06 +05:30
Debanjum Singh Solanky
41bdd6d6d9 Throw warning on prettier formatting issues in web app 2024-08-05 03:58:20 +05:30
Debanjum Singh Solanky
1cdfa8087c Update Khoj tagline to "Your Second Brain" 2024-08-05 02:27:05 +05:30
Debanjum Singh Solanky
46f928165c Fix deep linking to settings page cards from docs 2024-08-05 02:27:05 +05:30
sabaimran
f7840782a4 Fix broken rendering of math equations via katex 2024-08-05 00:20:43 +05:30
Debanjum Singh Solanky
b803ed19d3 Add simplified, cleaner khoj logo images to web app static dir 2024-08-04 23:40:21 +05:30
sabaimran
69c3635ce7 Merge pull request #877 from khoj-ai/features/fit-and-finish-new-ux 
Fit and finish updates for the new UX
 2024-08-04 10:26:33 -07:00
Debanjum Singh Solanky
51e56e17ee Align padding of agent pills to home screen chat input on small screens 2024-08-04 21:57:54 +05:30
Debanjum Singh Solanky
b744dffefd Align voice message button with send chat message button style 2024-08-04 21:04:38 +05:30
Debanjum Singh Solanky
70f670dcf7 Show send button when text in chat input else voice message button 
Utilize chat footer space more efficiently. This is especially useful
on small screens

- Send button is anyway only enabled when there is text in chat input
- Otherwise voice message button is better to show by default
 2024-08-04 19:25:49 +05:30
Debanjum Singh Solanky
c627527a6f Reorder automation card actions buttons. Put Delete action last 2024-08-04 19:01:11 +05:30
Debanjum Singh Solanky
c7b67a978e Align agents and automation page structure, widths and spacings 
- Remove invalid call to styles.main
- Remove unnecessary top padding above side pane to keep side pane at
  consistent position across web app
- Use same pageLayout styles and styling structure on agent like
  automation
- Vertically center automation section and page title on it's row
- Fix applying flex vs grid with tailwind
 2024-08-04 19:01:11 +05:30
Debanjum Singh Solanky
60af173c4a Improve responsive spacing of chat page footer buttons 
- Remove x axis footer padding on small screens to preserve space,
  keep equal spacing between footer items
- Add 1rem margin to buttons to not have overlap in boundary
- Add 1rem y-axis padding to chat footer to not have focus boundary
  leave the footer boundary on smaller screens
 2024-08-04 19:01:10 +05:30
sabaimran
4f2fcc82f0 Make the input area only rounded on the top corners when in mobile view 
- Create better styling for the input area buttons, resizing in mobile and creating more even height with a more minimal send button
 2024-08-04 18:28:33 +05:30
sabaimran
322fb34d4b Add top padding to the automations header to align it with the agents page 2024-08-04 12:27:37 +05:30
sabaimran
3e1e4a1857 Move the clients section back to the bottom 2024-08-04 11:32:22 +05:30
Debanjum Singh Solanky
caf5c3d74c Link to Khoj manifest in home page metadata to support PWA install 
Installing Khoj as PWA was supported in previous web UX as well. This
just adds link to the existing webmanifest to continue support for
installing Khoj as PWA with new web UX
 2024-08-04 05:06:38 +05:30
Debanjum Singh Solanky
692058bbdd Fix time of day calculation logic 
Previously between 00:00 - 04:00 it'd trigger afternoon insteead of
evening
 2024-08-04 04:53:50 +05:30
Debanjum Singh Solanky
015c155582 Simplify structure of chat page to match other pages 2024-08-04 04:43:55 +05:30
Debanjum Singh Solanky
bf71e472c4 Load static assets from Khoj server in dev environment 2024-08-04 04:25:48 +05:30
Debanjum Singh Solanky
f38c072f07 Update chat session title in side pane to new title after rename 
Previously the rename wasn't updating the chat session title. We'd
have to refresh the page or side pane to get latest chat session names
after rename action.
 2024-08-04 04:25:48 +05:30
Debanjum Singh Solanky
2f7a8698a0 Fix width and equalize spacing between buttons in chat footer 
Previously the footer's right border wasn't visible on small screens
due to usage of w-full

Use mr-1 on send button instead of px-1 on chat input parent to
eualize chat footer buttons spacing
 2024-08-04 04:25:48 +05:30
Debanjum Singh Solanky
5541bc09c8 Prefix Khoj page breadcrumbs to chat page title for orientation 
Allows tab search by looking at standard prefix. Still allows
page title based identification of different Khoj chat sessions
 2024-08-04 04:25:48 +05:30
Debanjum Singh Solanky
6a9865ace7 Only show API keys card in non anon mode 
- Show informative toast messages on copy, delete of API keys
- Onle show API keys card in non anonymous mode. API keys aren't
  required (and is disabled on server side) in anon mode. Not showing
  card at all in anon mode reduces chance of unnecessary confusion
 2024-08-04 04:25:45 +05:30
Debanjum Singh Solanky
f28208d35b Only show chat sessions uptil last month in side pane 
- Reduce chat title size
 2024-08-04 01:52:08 +05:30
sabaimran
75559a55aa only show search if logged in. update agents icon 2024-08-03 23:23:03 +05:30
sabaimran
185dcb61f7 Update the settings page to better match the design 2024-08-03 20:49:19 +05:30
sabaimran
3e74d383fe Strip quotes from the response mode llm response 2024-08-03 17:33:20 +05:30
sabaimran
87e97e40f4 Resolve various warnings during export 2024-08-03 17:33:04 +05:30
sabaimran
5a75f2c00f Use filled icons when side panel is open 2024-08-03 15:42:49 +05:30
sabaimran
e6260a7bb6 Improve oadding for h9me page chat iput area and inc margin on api keys 2024-08-03 15:33:33 +05:30
Debanjum Singh Solanky
7a8a9fc807 Auto focus cursor on search input when open search page 2024-08-03 13:52:36 +05:30
Debanjum Singh Solanky
30304ccc56 Fix session drawer to fit title, action triple-dot in width on mobile 2024-08-03 13:52:36 +05:30
Debanjum Singh Solanky
5b17fa5dda Set home, chat page height so footer, header visible w/o scroll on phone 
Set dynamic view height of page to 100%
 2024-08-03 13:52:36 +05:30
sabaimran
687a881ad2 Remove the agents header in the loading view 2024-08-03 13:44:56 +05:30
sabaimran
0db630a123 image cards should be /image, not /paint 2024-08-03 13:44:31 +05:30
sabaimran
261f62e353 Fix automations mobile view by using a wrapper component that chooses a dialog or a drawer 2024-08-03 13:44:17 +05:30
sabaimran
4ce17acd00 Set greeting message to longer text in default view. Only show two agents in mobile 2024-08-03 12:14:58 +05:30
sabaimran
6c35ee4960 Revert height of the side panel on the home page 2024-08-03 11:59:07 +05:30
Debanjum Singh Solanky
e66adf60c5 Have the home and chat page take full height, reduce greeting top space 2024-08-03 11:54:12 +05:30
Debanjum Singh Solanky
cf8745ef78 Improve structure of chat footer on mobile to put agents above input 2024-08-03 11:31:57 +05:30
Debanjum Singh Solanky
529ffdb7e3 Make Title, Chat Footer Icons larger to ease click, tap on Mobile 2024-08-03 11:23:29 +05:30
Debanjum Singh Solanky
8d1c5226ec Remove unnecessary debug logs 2024-08-03 09:55:31 +05:30
sabaimran
f136214290 Improve the nav menu in the not logged in experience 2024-08-03 09:44:04 +05:30
sabaimran
f9606ce9b7 Merge branch 'features/fit-and-finish-new-ux' of github.com:khoj-ai/khoj into features/fit-and-finish-new-ux 2024-08-03 09:34:04 +05:30
Debanjum Singh Solanky
d8fe677933 Prevent overflow on Search page by search results 2024-08-03 07:07:35 +05:30
Debanjum Singh Solanky
f3765a20b9 Improve content alignment on automation page for small screens 
- Left align email, location, timezone pills on small screens
- Indent user enabled automations to improve delineation between
  sections
 2024-08-03 07:05:15 +05:30
Debanjum Singh Solanky
a6e1b2c7cb Style nav menu button and expand nav menu item click area to full-width 
Style profile pircture button on nav menu
 - Use primary colored ring around subscribed user profile on nav menu
 - Use gray colored ring around non-subscribed user profile on nav menu
 - Use upper case initial as profile pic for user with no profile pic

- Click anywhere on nav menu item to trigger action
  Previously the actual clickable area was smaller than the width of
  the nav menu item
 2024-08-03 05:43:24 +05:30
Debanjum Singh Solanky
eed9e401a2 Improve alignment of title bar elements 2024-08-03 04:11:58 +05:30
sabaimran
f188396395 Prompt to login when authenticated, click on suggestion card 
- Improve styling for the side panel when not logged in
 2024-08-03 01:42:32 +05:30
sabaimran
9c5ff1699a Use new nav menu alignment in the settings page 2024-08-03 01:42:32 +05:30
sabaimran
b1d3979ed9 Fix navmenu in settings, share/chat pages 2024-08-03 01:42:21 +05:30
sabaimran
5f8b76c8f2 Fix layout/styling of the factchecker app 2024-08-03 01:07:59 +05:30
sabaimran
1bb746aaed Adjust spacing when side panel is opened 2024-08-03 01:07:59 +05:30
sabaimran
07b3bdf181 Update nav menu styling to include everything in one header 
- Move the nav menu into the chat history side panel component, so that they both show up on one line
- Update all pages to use it with the new formatting
- in mobile, present the sidebar button, home button, and profile button evenly centered in the middle
 2024-08-03 01:07:55 +05:30
Debanjum Singh Solanky
e62888659f Only show greeting once userConfig is fetched from server 
- Pass userConfig from Home as prop to chatBodyData component with
  loading state
- Pass loading state of userConfig to allow components to handle
  rendering dependent elements once it is loaded
 2024-08-02 20:25:09 +05:30
Debanjum Singh Solanky
0adee07d40 Update home page greetings to use user name, when available 2024-08-02 20:25:09 +05:30
sabaimran
bbe7491f2f Prompt to login when authenticated, click on suggestion card 
- Improve styling for the side panel when not logged in
 2024-08-02 20:12:18 +05:30
sabaimran
d48a789442 Use new nav menu alignment in the settings page 2024-08-02 19:44:30 +05:30
sabaimran
e6014e89bf Fix navmenu in settings page 2024-08-02 19:28:59 +05:30
sabaimran
1509c536f9 Fix layout/styling of the factchecker app 2024-08-02 19:06:01 +05:30
sabaimran
0d8cdee60a Adjust spacing when side panel is opened 2024-08-02 17:49:50 +05:30
sabaimran
d3c07a098d Update nav menu styling to include everything in one header 
- Move the nav menu into the chat history side panel component, so that they both show up on one line
- Update all pages to use it with the new formatting
- in mobile, present the sidebar button, home button, and profile button evenly centered in the middle
 2024-08-02 17:46:13 +05:30
sabaimran
5a8ea884a9 Use new HTTP stream format within the new UX 
Use updated format for HTTP streamed responses from the Khoj server in the new chat UX
Remove references to the websocket connected field, as websocket use has been deprecated
 2024-08-02 02:35:10 -07:00
Debanjum Singh Solanky
02b46a1784 Render references after chat response is streamed for smoother render 
Otherwise the Khoj's chat response is filling up in between the
streamed message and already rendered references section at the bottom
of the message

Define OnlineContext type to simplify typing online context param
across other interfaces and functions
 2024-08-02 14:11:34 +05:30
Debanjum Singh Solanky
a733e5c1d4 Remove unused handleCompiledReferences chat functions 2024-08-02 13:18:55 +05:30
Debanjum Singh Solanky
7858aff2e2 Trigger welcomeConsole only once on chat, shared chat page load 2024-08-02 13:18:01 +05:30
Debanjum Singh Solanky
cab0957fd3 Just show Khoj logo on title bar on small screens 
Continue to show logo + text on larger screens
 2024-08-02 13:18:01 +05:30
Debanjum Singh Solanky
3f607b3978 Add icons, improve description of home, chat & search page metadata 2024-08-02 13:18:01 +05:30
Debanjum Singh Solanky
4f783b911c Update DOMPurify imports correctly to resolve compilation warnings 2024-08-02 13:18:01 +05:30
sabaimran
4492017b96 Move processmessagechunk file into a common chat function 2024-08-02 12:31:43 +05:30
sabaimran
13dee7d89e Remove status update for understanding query 2024-08-01 19:22:21 +05:30
sabaimran
6babd5c0ce Merge pull request #876 from khoj-ai/features/use-intl-phone-input-settings 
Use international phone number input and verify whatsapp flow
 2024-08-01 04:52:02 -07:00
sabaimran
1b2cad2a2c Use af in the default state and configure the phone number input styling 2024-08-01 17:04:57 +05:30
sabaimran
723b37955a Disable input for phone number only if its pending verification 2024-08-01 16:45:38 +05:30
sabaimran
84dd1b57fe Use an intl phone input number field and fix the whole verification flow 
- There were some state mismatches in configuring a whatsapp number. This commit fixes those issues and uses an external library for phone number validation
 2024-08-01 16:44:17 +05:30
sabaimran
ed16914ac3 Remove deprecated fields and fix erroneous export in settings page 2024-08-01 14:45:54 +05:30
sabaimran
7941f4d54d Remove references to deprecated setupwebsocket function 2024-08-01 14:43:17 +05:30
sabaimran
db93ac5d4b Merge branch 'features/big-upgrade-chat-ux' of github.com:khoj-ai/khoj into features/use-new-sse-in-new-chat-ux 2024-08-01 14:41:50 +05:30
sabaimran
fd0e0405af Fix logic for setting and sending the initial chat message from the home page 
- Load agents only once when the page loads, rather than triggering constant re-renders
 2024-08-01 13:53:16 +05:30
sabaimran
9a43622cef Remove usages of the websocketconnected variable 2024-08-01 13:14:23 +05:30
sabaimran
bfeb64b48f Migrate the shared chat page to also use the new SSE streaming format 2024-08-01 13:14:09 +05:30
sabaimran
833553c3a3 Move conversation commands selection earlier to include in telemetry collected 2024-08-01 12:52:41 +05:30
sabaimran
dbbcf2564f Remove the usage of emojis in the incremental status updates 2024-08-01 12:52:05 +05:30
sabaimran
cd85a51980 Ingest new format for server sent events within the HTTP streamed response 
- Note that the SSR for next doesn't support rendering on the client-side, so it'll only update it one big chunk
- Fix unique key error in the chatmessage history for incoming messages
- Remove websocket value usage in the chat history side panel
- Remove other websocket code from the chat page
 2024-08-01 12:50:43 +05:30
Debanjum
60870a7a3e Create Settings Page in new Web App (#872) 
- Details
  - Add Profile Client, Content Sections
  - Make Multi Step Cards for Whatsapp, Files, Notion Integrations
  - Align Settings page with new Baraabar UX
 2024-07-30 06:59:42 -07:00
Debanjum Singh Solanky
32ce564b7c Remove unused Files Connect button and setup Github content card 2024-07-30 18:55:14 +05:30
Debanjum Singh Solanky
ecb873c488 Only allow search model to be updated without being subscribed 
Do not make fetch request to server if user is not subscribed
 2024-07-30 18:50:57 +05:30
Debanjum Singh Solanky
f58cff5bcc Increase rate limit in the api/content vs deprecated indexer API 2024-07-30 16:09:26 +05:30
Debanjum Singh Solanky
f0bb6883f8 Improve Delete experience on Files Card in Settings Page 
Improve placeholder text for notion API key and Whatsapp
number (mention country code required)
 2024-07-30 15:25:14 +05:30
sabaimran
b1eb564706 remove the optional pydantic typing from the files param 2024-07-30 15:25:14 +05:30
sabaimran
4a7efdc552 Use patch in place of put in the indexer API call, ensure that files are not being required in the indexer path 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
ffbf57292c Create synced files management modal on the settings page 
Use a Command Dialog to allow easier filtering of files to view
without having to leave the settings page
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
ccc46a09b5 Add new API to batch delete a list of files by filename 
- Rearrange DELETE content API definitions order to go from more
  specific to more general
- Create batched file deletion DB adapter
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
9d86cb57ac Build UX to Connect and Manage Notion Integration via Settings Page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
7ee179ee1f Return user's Notion token in API call for detailed user settings 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
00a908ae12 Move subscription card to Profile settings section. Remove Billing section 
- Why
  Profile section and billing section looked too empty (1 card each).
  Combining them makes the setting page look more complete. Shows
  subscription options early on
- Details
  - Made Futurist text orange
  - Made Unsubscribe a down button instead of cloud slash
  - Updated toast title to subscription
  - Improve Futurist trial title and description
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
058c902dc7 Delete unused npm package-lock.json as Web app uses yarn.lock instead 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
b8c9b3ffa3 Reduce padding height of input area on new home page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
8a447107dd Set user name on clicking Save button on settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
44e0b20202 Align Content, Client & Billing settings sections with new designs 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
51e83bcc26 Improve responsive behavior of settings cards 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
efcad4996d Add phone number verification for Whatsapp to new settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
48548684c0 Add card to connect Whatsapp to Khoj on settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
8ec90f194f Add title icons for each content section card on settings page 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
60cdf61737 Create billing section for managing subscription on settings page 
- Replicate behavior on current settings.html page
- Improve text for each subscription state to make it more informative, fun
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
2e165a0e0a Create client API keys section on settings page 
- Add table shadcn component to use in API keys settings section
- In dev mode, route requests to auth to khoj server at localhost:42110
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
00fa4fa0fa Save model on selecting model in dropdown. No extra save action reqd 
- Remove now unnecessary button to Save in Card with dropdown
- Use toast to show success, failure (not working)
- Rename language to search, Move it to features section. Add icon to
  the card
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
13292fc4ca Add icons to card headings 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
a5a06da3fc Use Dropdown component for model options. Make cards more responsive 
- Ensure model name doesn't stretch or shrink dropdown width from
  parent card width
- Ensure buttons flex wrap on smaller displays
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
ade2f6f5d1 Rename selected voice model in get config API response for consistency 
- Update references in new and old web client settings
- Arrange new client settings props and add header comments similar to
- config response for code readability
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
b3253562a5 Dynamically set Content cards buttons based on already setup or not 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
7e8e80f29e Create config page using tailwind, shadcn components, styling 
- Include side pane but with only the account info in it
- Replicate styling of the old config page
 2024-07-30 15:25:14 +05:30
Debanjum Singh Solanky
88007d7552 Get user config in the new web client from the new user config APIs 2024-07-30 15:25:14 +05:30
sabaimran
a6339bb973 Add mroe card suggestions and simplify color selection for suggestion cards 2024-07-29 19:11:39 +05:30
sabaimran
551630f0f1 Code clean-up and some fit and finish 
- Add a lot more suggestions cards, improve mobile rendering of suggestion cards, improve alignment of chat input, shift message when starts recording voice, remove dead code
 2024-07-28 15:19:36 +05:30
sabaimran
413255ddc7 Add closing tag to whatsapp qr code image 2024-07-28 13:50:38 +05:30
sabaimran
41eb85c933 Update the docs for whatsapp to include the QR code 2024-07-28 13:43:50 +05:30
sabaimran
1a1d9c7257 Merge branch 'master' of github.com:khoj-ai/khoj into features/big-upgrade-chat-ux 2024-07-27 14:18:05 +05:30
Raghav Tirumale
1685c60e3c Nav Menu Upgrades and Minor UX Improvements (#869) 
* Converted navigation menu into a dropdown menu
* Moved collapsed side panel menu icons into top row
* Auto refresh when conversation is deleted to update side panel and route back to main page if deletion is on current conversation
* Highlight the current conversation in the side panel
* Dynamic homepage messages with current day and time of day.
* `colorutils` upgraded to have more expansive tailwind color options and dynamic class name generation.
* Converted create agent button alert into shadcn `ToolTip`
* Colored lines and icons for agents in chat window
* Cleaned up border styling in dark mode
* fixed three dot menu in side panel to be more easier to click
* Add the KhojLogo import in the nav menu and use a default user profile icon when not authenticated
* Get rid of custom --box-shadow CSS variable
* Pass the agent metadat through the chat body data in order to style the send button
* Add login to the unauthenticated login view, redirecto to home if conversation history not loaded
* Set a max height for the input text area
* Simplify tailwind class names

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-07-27 14:12:00 +05:30
Debanjum
8503d7a07b Split Configure API into Content, Model API paths (#857) 
## Major: Breaking Changes
- Move API endpoints under /configure/<type>/model to /api/model/<type>
- Move API endpoints under /api/configure/content/ to /api/content/
- Accept file deletion requests by clients during sync
- Split /api/v1/index/update into /api/content PUT, PATCH API endpoints

## Minor: Create New API Endpoint
- Create API endpoints to get user content configurations

Related: #852
 2024-07-26 23:48:41 -07:00
Debanjum Singh Solanky
878cc023a0 Fix and improve openai chat actor tests 
- Use new form of passing doc references to now passing chat actor
  test
- Fix message list generation from conversation logs provided
  Strangely the parent conversation_log gets passed down to
  message_to_log func when the kwarg is not explicitly specified
 2024-07-26 23:53:47 +05:30
Debanjum Singh Solanky
a47a54f207 Pass user name to document and online search actors prompts 
This should improve the quality of personal information extraction
from document and online sources. The user name is only used when it
is set
 2024-07-26 23:53:17 +05:30
sabaimran
e86143dbb0 Merge pull request #867 from khoj-ai/features/search-page-v2 
Update the search page
 2024-07-26 08:08:04 -07:00
sabaimran
eb5af38f33 Release Khoj version 1.17.0 2024-07-26 20:14:45 +05:30
Raghav Tirumale
5dcac18ba5 New Agents Page User Interface (#866) 
Changes for new agents page
- Modernized agent cards
- Responsive design to support mobile users
- Button for users to create their own agents (coming soon)
- Optimized to use tailwind and icon utils
- Side panel added for quick access to conversations
 2024-07-26 20:12:31 +05:30
Debanjum Singh Solanky
3daef910c0 Remove stale comment from api content 2024-07-26 20:05:35 +05:30
sabaimran
44d34f9090 Update the unit test for the subscribed user 2024-07-26 19:59:01 +05:30
sabaimran
377f7668c5 Merge pull request #858 from khoj-ai/use-sse-instead-of-websocket 
Use Single HTTP API for Robust, Generalizable Chat Streaming
 2024-07-26 07:11:54 -07:00
sabaimran
6607e666dc Increase rate limit for data upload packet size in indexer.py 2024-07-26 19:35:32 +05:30
Debanjum Singh Solanky
778c571288 Use enum to track chat stream event types in chat api router 2024-07-26 00:19:43 +05:30
sabaimran
7482797605 Add some better default states for no files found, prompt to search. Add link to search in the file search compnoent in side panel 2024-07-25 13:00:28 +05:30
sabaimran
662dffea3b Press enter to search 2024-07-24 19:28:38 +05:30
sabaimran
19cd607c96 Style the see content button correctly 2024-07-24 18:28:23 +05:30
sabaimran
75a370cc06 Implement focus mode to click into full text of the note 2024-07-24 18:00:33 +05:30
sabaimran
5adbfe14ab Add a search page that just renders truncated results when you click search 2024-07-24 17:43:19 +05:30
sabaimran
52db15706d Remove unused styling 2024-07-24 17:42:36 +05:30
sabaimran
cfe7a1068e Update the navmenu title if prop is updated and undefined 2024-07-24 17:41:31 +05:30
Debanjum Singh Solanky
ebe92ef16d Do not send references twice in streamed image response 
Remove unused image content to reduce response payload size.
References are collated, sent separately
 2024-07-24 17:18:14 +05:30
Debanjum Singh Solanky
37b8fc5577 Extract events even when http chunk contains partial or mutiple events 
Previous logic was more brittle to break with simple unbalanced
'{' or '}' string present in the event data. This method of trying to
identify valid json obj was fairly brittle. It only allowed json
objects or processed event as raw strings.

Now we buffer chunk until we see our unicode magic delimiter and only
then process it.

This is much less likely to break based on event data and the
delimiter is more tunable if we want to reduce rendering breakage
likelihood further
 2024-07-24 17:17:39 +05:30
sabaimran
4d30e5b158 Fix indexing error for notion, expecting image and docx in dict 2024-07-24 16:58:31 +05:30
sabaimran
694bedc25b Add support for text to speech and speech to text (#863) 
- Add support for text to speech, speech to text. Add loading and responsive indicators to reflect state.
- When streaming for speech to text, show incremental transcription in the message input field
- When streaming text to speech, and a pause button in the chat message to allow user to stop playback
 2024-07-24 14:36:40 +05:30
Raghav Tirumale
3e4325edab Upgrade: New Home Screen for Khoj (#860) 
* V1 of the new automations page
Implemented:
- Shareable
- Editable
- Suggested Cards
- Create new cards
- added side panel new conversation button
- Implement mobile-friendly view for homepage
- Fix issue of new conversations being created when selected agent is changed
- Improve center of the homepage experience
- Fix showing agent during first chat experience
- dark mode gradient updates

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-07-24 13:16:19 +05:30
Debanjum Singh Solanky
70201e8db8 Log total, ttft chat response time on start, end llm_response events 
- Deduplicate code to collect chat telemetry by relying on
  end_llm_response event
- Log time to first token and total chat response time for latency
  analysis of Khoj as an agent. Not just the latency of the LLM
- Remove duplicate timer in the image generation path
 2024-07-23 23:21:12 +05:30
Debanjum Singh Solanky
b36a7833a6 Remove the old mechanism of streaming compiled references 
Do not need response generator to stuff compiled references in chat
stream using "### compiled references:" separator.

References are now sent to clients as structured json while streaming
 2024-07-23 19:53:51 +05:30
Debanjum Singh Solanky
eb4e12d3c5 s/online_context/onlineContext chat API response field for consistency 
This will align the name of the online context field returned by
current chat message and chat history
 2024-07-23 19:50:43 +05:30
Debanjum
498fe2458c Support Gemma 2 Model Family for Offline Chat (#855) 
## Overview
- Gemma 2 is a new open model family by Google. They've released a 9B, 29B param model. A 2B model is also expected.
- It performs really well on the Chatbot arena and shows good performance when testing within Khoj as well.
- Llama.cpp support for Gemma 2 architecture seems to have stabilized
- If Gemma 2 performs well in further testing, it can be made the default offline chat model for Khoj
  - Once the 2B param model is released, the model size to download can be automatically chosen based on (V)RAM available

## Major
- Support Gemma 2 for Offline Chat
- Improve and fix chat model prompts for better, consistent context

## Minor
- Fix and improve offline chat actor, director tests
- Improve offline chat truncation to consider chat message delimiter tokens
 2024-07-23 06:57:02 -07:00
Debanjum Singh Solanky
0277d16daf Share desktop chat streaming utility funcs across chat, shortcut views 
Null check menu, menuContainer to avoid errors on Khoj mini
 2024-07-23 19:16:33 +05:30
Debanjum Singh Solanky
e439a6ddac Use async/await in web client chat stream instead of promises 
Align streaming logic across web, desktop and obsidian clients
 2024-07-23 18:17:47 +05:30
Debanjum Singh Solanky
fafc467173 Put loading spinner at bottom of chat message in web client 2024-07-23 18:17:47 +05:30
Debanjum Singh Solanky
fc33162ec6 Use new chat streaming API to show Khoj train of thought in Desktop app 
Show loading spinner at end of current message
 2024-07-23 18:17:47 +05:30
Debanjum Singh Solanky
c5ad172616 Keep loading animation at message end & reduce lists padding in Obsidian 
Previously loading animation would be at top of message. Moving it to
bottom is more intuitve and easier to track.

Remove white-space: pre from list elements. It was adding too much y
axis padding to chat messages (and train of thought)
 2024-07-23 17:56:03 +05:30
Debanjum Singh Solanky
54b4203683 Update chat API client tests to mix testing of batch and streaming mode 2024-07-23 17:56:03 +05:30
Debanjum Singh Solanky
3f5f418d0e Use new chat streaming API to show Khoj train of thought in Obsidian client 2024-07-23 17:56:03 +05:30
Debanjum Singh Solanky
8303b09129 Convert snake case to camel case in chat view of obsidian plugin 2024-07-23 15:29:12 +05:30
Debanjum Singh Solanky
b224d7ffad Simplify get_conversation_by_user DB adapter code 2024-07-23 14:51:11 +05:30
Debanjum Singh Solanky
daec439d52 Replace old chat router with new chat router with advanced streaming 
- Details
  Only return notes refs, online refs, inferred queries and generated
  response in non-streaming mode. Do not return train of throught and
  other status messages

  Incorporate missing logic from old chat API router into new one.

- Motivation
  So we can halve chat API code by getting rid of the duplicate logic
  for the websocket router

  The deduplicated code:
  - Avoids inadvertant logic drift between the 2 routers
  - Improves dev velocity
 2024-07-23 14:51:11 +05:30
Debanjum Singh Solanky
2d4b284218 Simplify streaming chat function in web client 2024-07-23 14:38:55 +05:30
Debanjum Singh Solanky
6b9550238f Simplify advanced streaming chat API, align params with normal chat API 2024-07-22 22:51:24 +05:30
Debanjum Singh Solanky
b8d3e3669a Stream Status Messages via Streaming Response from server to web client 
- Overview
Use simpler HTTP Streaming Response to send status messages, alongside
response and references from server to clients via API.

Update web client to use the streamed response to show train of thought,
stream response and render references.

- Motivation
This should allow other Khoj clients to pass auth headers and recieve
Khoj's train of thought messages from server over simple HTTP
streaming API.

It'll also eventually deduplicate chat logic across /websocket and
/chat API endpoints and help maintainability and dev velocity

- Details
  - Pass references as a separate streaming message type for simpler
    parsing. Remove passing "### compiled references" altogether once
    the original /api/chat API is deprecated/merged with the new one
    and clients have been updated to consume the references using this
    new mechanism
  - Save message to conversation even if client disconnects. This is
    done by not breaking out of the async iterator that is sending the
    llm response. As the save conversation is called at the end of the
    iteration
  - Handle parsing chunked json responses as a valid json on client.
    This requires additional logic on client side but makes the client
    more robust to server chunking json response such that each chunk
    isn't itself necessarily a valid json.
 2024-07-22 15:41:21 +05:30
Debanjum Singh Solanky
91fe41106e Convert Websocket into Server Side Event (SSE) API endpoint 
- Convert functions in SSE API path into async generators using yields
- Validate image generation, online, notes lookup and general paths of
  chat request are handled fine by the web client and server API
 2024-07-21 14:20:22 +05:30
sabaimran
9cf52bb7e4 Update automations UX for more consistency (#856) 
* Update the automations UI to be a more suitable color distribution based on new designs

* Use accented colors for the metadata, update dark mode colors

* Update form to use icons as well and render more pretty inline form labels
 2024-07-21 12:22:23 +05:30
sabaimran
e694c82343 Fix Docker build issues with yarn / next /node (#859) 
* Rollback node version being installed from nodesource to node 20
 2024-07-19 19:11:29 +05:30
sabaimran
1af9dbb083 Switch node/yarn install steps to use more native installation patterns 2024-07-19 17:10:08 +05:30
sabaimran
6d5ca5a3e1 yarn clean cache before build 2024-07-19 16:06:38 +05:30
sabaimran
7f0d1bd414 Add verbose logs when outputing yarn install steps 2024-07-19 15:48:43 +05:30
sabaimran
7426a4f819 Prefetch related agent when retrieving the conversation for performance improvements 2024-07-19 14:43:30 +05:30
Debanjum Singh Solanky
07f36fa95a Update new web interface with update calls to /content, /model APIs 2024-07-19 12:23:22 +05:30
Debanjum Singh Solanky
f03525f431 Add back /api/configure as /api/settings API endpoint 
It had been removed during the /api/configure/content to /api/content
API migration before
 2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
3832ef0236 Move API endpoints under /api/configure/phone/ to /api/phone/ 
Pull out /api/configure/phone API endpoints into /api/phone for
more concise and sufficiently explanatory API path

Refactor Flow
1. Rename /api/configure/phone -> /api/phone
 2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
1197266912 Move API endpoints under /configure/<type>/model to /api/model/<type> 
Now the API to configure all the AI models is under /api/models.
This provides better organization and API hierarchy. The /configure
url segment was redundant.

- Rename POST /api/phone to PATCH /api/phone
- Rename GET /api/configure to GET /api/settings

Refactor Flow
1. Move out POST /user/name to main api.py
2. Rename /api/configure/<type>/model -> /api/model/<type>
3. Rename @api_configure to @api_mode
4. Rename file api_config.py to api_model.py
 2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
469a1cb6a2 Move API endpoints under /api/configure/content/ to /api/content/ 
Pull out /api/configure/content API endpoints into /api/content to
allow for more logical organization of API path hierarchy

This should make the url more succinct and API request intent more
understandable by using existing HTTP method semantics along with the
path.

The /configure URL path segment was either
- redundant (e.g POST /configure/notion) or
- incorrect (e.g GET /configure/files)

Some example of naming improvements:
- GET /configure/types -> GET /content/types
- GET /configure/files -> GET /content/files
- DELETE /configure/files -> DELETE /content/files

This should also align, merge better the the content indexing API
triggered via PUT, PATCH /content

Refactor Flow
1. Rename /api/configure/types -> /api/content/types
2. Rename /api/configure -> /api
3. Move /api/content to api_content from under api_config
 2024-07-19 05:40:34 +05:30
Debanjum Singh Solanky
bba4e0b529 Accept file deletion requests by clients during sync 
- Remove unused full_corpus boolean. The full_corpus=False code path
  wasn't being used (accept for in a test)
- The full_corpus=True code path used was ignoring file deletion
  requests sent by clients during sync. Unclear why this was done
- Added unit test to prevent regression and show file deletion by
  clients during sync not ignored now
 2024-07-19 04:53:01 +05:30
Debanjum Singh Solanky
5923b6d89e Split /api/v1/index/update into /api/content PUT, PATCH API endpoints 
- This utilizes PUT, PATCH HTTP method semantics to remove need for
  the "regenerate" query param and "/update" url suffix
- This should make the url more succinct and API request intent more
  understandable by using existing HTTP method semantics
 2024-07-19 01:45:53 +05:30
Debanjum Singh Solanky
e9f86e320b Fix and improve offline chat actor, director tests 
- Use updated references schema with compiled key
- Enable director tests that are now expected to pass and that do pass
  (with Gemma 2 at least)
 2024-07-18 03:43:09 +05:30
Debanjum Singh Solanky
b0ee78586c Improve offline chat truncation to consider message separator tokens 2024-07-18 03:43:09 +05:30
Debanjum Singh Solanky
6f46e6afc6 Improve and fix chat model prompts for better, consistent context 
- Add day of week to system prompt of openai, anthropic, offline chat models
- Pass more context to offline chat system prompt to
  - ask follow-up questions
  - know where to find information about khoj (itself)
- Fix output mode selection prompt. Log error if model does not select
  valid option from list of valid output modes provided
- Use consistent names for question, answers passed to
  extract_questions_offline prompt

- Log which model extracts question, what the offline chat model sees
  as context. Similar to debug log shown for openai models
 2024-07-18 03:43:09 +05:30
Debanjum Singh Solanky
53eabe0c06 Support Gemma 2 for Offline Chat 
- Pass system message as the first user chat message as Gemma 2
  doesn't support system messages
- Use gemma-2 chat format
- Pass chat model name to generic, extract questions chat actors
  Used to figure out chat template to use for model
  For generic chat actor argument was anyway available but not being
  passed, which is confusing
 2024-07-18 03:09:38 +05:30
Debanjum Singh Solanky
65dade4838 Create API endpoints to get user content configurations 
This is to be used by the new Next.js web client
 2024-07-17 13:41:14 +05:30
Debanjum
2ab8fb78b1 Migrate the PyPI package to use project name: khoj (#853) 
### Changes
- Deprecate [khoj-assistant](https://pypi.org/project/khoj-assistant) pypi package. Use more accurate and succinct pypi project name, [khoj](https://pypi.org/project/khoj)
- Update references to use `khoj` pypi package in docs and code
- Update pypi workflow to publish to both khoj, khoj-assistant for now
- Update stale python 3.9 support mentioned in our pyproject
   Can't support python 3.9 as depend on [Django 5.0.7](https://pypi.org/project/Django/5.0.7/) which needs python >=3.10

### Verify
- Updated `pypi.yml` github workflow publishes to both (new) [khoj](https://pypi.org/project/khoj/1.16.1.dev16/), (old) [khoj-assistant](https://pypi.org/project/khoj-assistant/1.16.1.dev16/) pypi projects
- Can install Khoj python package with `pip install khoj`
 2024-07-17 01:05:51 -07:00
Debanjum
bf815e4463 Refactor Config API and Settings pages for Reuse and Consistency (#852) 
### Major
- Reuse get config data logic across config pages on web client
- Make config api endpoint urls and response fields consistent
- Rename API path /api/config to /api/configure
- Move Web, Desktop client settings page to be under `/settings` from the previous `/config` url path

### Minor
- Pass isMobileWidth prop to SidePanel via chat share interface
- Turn prettier off instead of throwing error for now
- Do no explicitly add line-clamp plugin as it's in Tailwind by default
 2024-07-17 01:03:06 -07:00
Debanjum Singh Solanky
a1c362a4f7 Expose web, desktop settings page under /settings, not /configure 
- Update references to the settings page to use new url across docs
  and code
- Rename desktop and web settings page to settigns.html instead of
  config[ure].html
 2024-07-17 13:17:29 +05:30
Debanjum Singh Solanky
b015b0e83d Arrange config API detailed response fields to improve readability 
There are a lot of fields being returned. Group returned fields and
add comment header to each Group for readability
 2024-07-17 13:17:28 +05:30
Debanjum Singh Solanky
71ebf31a54 Make config API detailed response fields more intuitive, consistent 
- Use name, id for every [search|chat|voice|pain]_model_option
- Rename current_model_state field to more intuitive enabled_content_source
- Update references to the update fields in config.html
 2024-07-17 12:41:01 +05:30
Debanjum Singh Solanky
30d60aaae9 Add, fix Khoj Docker container labels 2024-07-17 10:41:17 +05:30
Debanjum Singh Solanky
583fa3c188 Migrate the pypi package to khoj project name. Update references 
- Deprecate khoj-assistant pypi package. Use more accurate and
  succinct pypi project name, khoj
- Update references to sye khoj pypi package in docs and code instead
  of the legacy khoj-assistant pypi package
- Update pypi workflow to publish to both khoj, khoj-assistant for now
- Update stale python 3.9 support mentioned in our pyproject. Can't
  support python 3.9 as depend on latest django which support >=3.10
 2024-07-17 10:41:16 +05:30
Debanjum Singh Solanky
7316e6b9d3 Pass isMobileWidth prop to SidePanel via chat share interface 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
4759c4ac96 Turn prettier off instead of throwing error for now 
Until web interface code is reformatted with prettier
 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
466ef3f8f1 Do no explicitly add line-clamp plugin as it's in Tailwind by default 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
59000a47cb Move Desktop config page to /configure from /config url path 
Update references to point to page at /configure instead of /config
 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
a5c16ad600 Move Web client config page to /configure from /config url path 
Update docs, clients and error messages to point to /configure
instead of /config
 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
de15a7a3fc Rename API path /api/config to /api/configure 
- Update clients calling /api/config to call /api/configure instead
 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
dd31936746 Make config api endpoint urls consistent 
- Consistently use /content/ for data. Remove content-source from path
- Remove unnecessary /data/ prefix for API endpoints under /config
 2024-07-16 16:13:27 +05:30
Debanjum Singh Solanky
e8176b41ef Reuse get config data logic across config pages on web client 
- Put logic to get config data, detailed or basic into router helpers module
- Use the get config func across the config pages on web clients

- Put configure content and get_notion_auth_url funcs in router helper
  module to avoid circular import
 2024-07-16 16:13:27 +05:30
sabaimran
1a5405e24c Fix interpretation of day of week in automation form 2024-07-16 10:12:30 +05:30
sabaimran
c837f3779e Update the agents page with new UX (#850) 
- Use icons/colors for setting the styling of agents
- Update automations page to use the shadcn cards: https://github.com/shadcn-ui/ui
 2024-07-16 10:10:55 +05:30
sabaimran
1c6ed9bc6d Migrate the existing automations page to use React (#849) 
Migrates the Automations page to React, mostly keeping the overall design consistent with organization. Use component library, with some changes in color. Add easier management with straightforward form and editing experience.
Use system preference for determining dark mode if not explicitly set.
 2024-07-15 21:42:33 +05:30
Debanjum
c7764c7470 Fix, Improve Behavior, Styling of Chat View on Web (#851) 
### Behavior
- Close chat sessions side panel on click open a chat session
- Show agent profile card with description when hover on agent in chat view
- Show action bar on last chat message without hover
- Show chat message action buttons without hover on mobile interfaces
- Show chat message timestamp on hover in chat view
- Show text descriptions of chat message action buttons on hover
- Render inline png, webp images generated by Khoj in chat view

### Fixes
- Do not render references with broken links in chat view
- Fix closing side panel on mobile when click open a chat session
- Only open side panel as drawer in mobile view
- Constrain chat messages to stay within view port across screen sizes

### Styling: Spacing, Sizing, Mobile Friendly
- Make Khoj icon appropriately sized and side panel arrow bold
- Conversations list should resize to take max space on side panel
- Make loading message, styling configurable. Do not show agent when no data
- Improve Train of Thought icons spacing and loading circle
- Improve mobile friendly styling of chat session side panel
- Improve styling of chat input, references UI across screen sizes
- Center cursor in chat input. See upto 2 lines for multi-line context

### Miscellaneous
- Add code formatter for web interface with prettier
 2024-07-15 08:39:14 -07:00
Debanjum Singh Solanky
6c630bc6c3 Constrain chat messages to stay in view port across screen sizes 
- Constrain chat messages max width to view port across screen sizes
- Wrap references on smaller screens, use tailwind, not js to apply styling
 2024-07-15 21:00:50 +05:30
sabaimran
9a5bf4c701 Fix rendering of teaser reference panel in mobile width 2024-07-15 19:40:55 +05:30
sabaimran
2e9275c0f3 Remove side panel padding in desktop view. Fix width in mobile view 2024-07-15 19:33:12 +05:30
Debanjum Singh Solanky
ba0ba6b59f Merge branch 'features/big-upgrade-chat-ux' of github.com:khoj-ai/khoj into document-styling-on-chat-ux 2024-07-15 10:42:56 +05:30
Debanjum
23f61d49e0 Support syncing, searching images from Obsidian plugin (#847) 
- Sync images from Obsidian vault with Khoj server now that Khoj can OCR images
- Support rendering images returned by Khoj search modal
 2024-07-14 20:41:39 -07:00
Debanjum Singh Solanky
6f8f846086 Standardize code format for web interface with prettier 
Use husky, lint-staged to run prettier pre-commit
 2024-07-15 00:34:54 +05:30
sabaimran
06dce4729b Make most major changes for an updated chat UI (#843) 
- Updated references panel
- Use subtle coloring for chat cards
- Chat streaming with train of thought
- Side panel with limited sessions, expandable
- Manage conversation file filters easily from the side panel
- Updated nav menu, easily go to agents/automations/profile
- Upload data from the chat UI (on click attachment icon)
- Slash command pop-up menu, scrollable and selectable
- Dark mode-enabled
- Mostly mobile friendly
 2024-07-14 23:18:06 +05:30
Debanjum Singh Solanky
6dd90931e8 Fix closing side panel on mobile when click open a chat session 2024-07-14 22:54:49 +05:30
Debanjum Singh Solanky
47b754c07b Only open side panel as drawer in mobile view 2024-07-14 14:08:41 +05:30
Debanjum Singh Solanky
b47f30ad77 Make Khoj icon appropriately sized and side panel arrow bold 2024-07-14 14:06:36 +05:30
Debanjum Singh Solanky
e6b21144e2 Conversations list should resize to take max space on side panel 2024-07-14 13:49:36 +05:30
Debanjum Singh Solanky
c2bf405489 Make loading message, styling configurable. Do not show agent when no data 
- Pass Loading message, class name via props to both inline and normal
  loading spinners
- Pass loading conversation message to loading spinner when chat
  history is being fetched
 2024-07-14 13:00:36 +05:30
Debanjum Singh Solanky
63719747cb Show agent profile card with description when hover on agent in chat view 
- Create profile card componennt. Use it for agent profile card
- Pass agent persona from khoj server via API
- Put link to agent profile page in the hover card to make it 2 clicks
  away. Othewise inadvertent clicks on agent in chat view lead away to
  agent page
- Use tailwind line-clamp extension to clamp card to first two lines
 2024-07-14 12:20:11 +05:30
Debanjum Singh Solanky
dbbd4b9777 Show action bar on last chat message without hover 2024-07-14 10:32:31 +05:30
Debanjum Singh Solanky
a0f38e079f Improve Train of Thought icons spacing and loading circle 2024-07-14 09:35:15 +05:30
Debanjum Singh Solanky
e9567741eb Improve mobile friendly styling of chat session side panel 2024-07-14 00:57:08 +05:30
Debanjum Singh Solanky
b26a6e25d1 Show chat message action buttons without hover on mobile interfaces 
This is because hover maybe hard to do on mobile devices
 2024-07-14 00:54:23 +05:30
Debanjum Singh Solanky
f69f9e3523 Close chat sessions side panel on click open a chat session 2024-07-14 00:53:16 +05:30
Debanjum Singh Solanky
d51011314f Improve styling of chat input, references UI across screen sizes 
Use tailwind screen breakpoints shorthand instead of js to apply
different styling for different screen sizes
 2024-07-13 20:45:34 +05:30
Debanjum Singh Solanky
2668e42e7f Center cursor in chat input. See upto 2 lines for multi-line context 
- Reuse class name when get slash command icons
- Previous chat input styling didn't have the cursor centered in the
  chat input text area. But it did allow seeing multi line chat inputs
  for context
 2024-07-13 02:51:29 +05:30
Debanjum Singh Solanky
aeaebfb515 Show chat message timestamp on hover in chat view 2024-07-13 02:51:19 +05:30
Debanjum Singh Solanky
e00c6b486e Add hover text descriptions of action buttons on chat message in web view 2024-07-12 15:40:51 +05:30
Debanjum Singh Solanky
5fccccfdff Do not render references with broken links in chat view 2024-07-12 15:14:11 +05:30
Debanjum Singh Solanky
b98a0cfe1b Render inline png, webp images generated by Khoj in chat view 
Add spacing between chat message paragraphs
 2024-07-12 15:13:19 +05:30
sabaimran
3e7e73ddd6 Switch from using dynamic routes to static routes and extracting slug from URL manually. See https://github.com/vercel/next.js/discussions/64660 for limitations with static export / dynamic routes 2024-07-11 23:06:27 +05:30
sabaimran
bea0aa5445 Improve the logged out share experience 2024-07-11 20:11:21 +05:30
Debanjum Singh Solanky
02658ad4fd Upgrade Django version 2024-07-11 16:35:10 +05:30
Debanjum Singh Solanky
cbae8b68fb Add DB migration from making bi_encode configs optional in #834 2024-07-11 16:33:31 +05:30
Debanjum Singh Solanky
3a75838196 Add Keyboard shortcuts to navigate in Khoj Desktop 2024-07-11 16:29:53 +05:30
Debanjum Singh Solanky
6c1861b319 Improve the prompt to generate images with DALLE3 and SD3 
- Major
  - Ask for prompt in prose
  - Remove seed from SD3 image generation to improve diversity of output
    for a given prompt
    Otherwise for conversations with similar sounding
    prompts, the images would be almost exactly the same. This maybe
    another indicator of SD3's inability to capture detailed
    instructions
  - Consistently use "prompt" wording instead of "query" in improved
    image generation prompts.
    Previously a mix of those terms were being used, which could confuse
    the chat model

- Minor
  - Add day of week to prompt
  - Remove 2-5 sentence limit on instructions to SD3. It seems to be
    able to follow longer instructions just with less fidelity than
    DALLE. And the 2-5 sentence instruction limit wasn't being adhered to
  - Improve ability to edit, improve the image based on follow-up
    instructions by the user
  - Align prompts for DALLE and SD3. Only difference is to wrap text to
    be rendered in quotes for SD3. This improves it's ability to render
    requested text. DALLE cannot render text as well or consistently
 2024-07-11 16:29:53 +05:30
Debanjum Singh Solanky
21fe1a917b Support syncing, searching images from Obsidian plugin 2024-07-11 16:22:31 +05:30
sabaimran
6f1d799759 Modularize code and implemenet share experience 2024-07-10 23:08:16 +05:30
sabaimran
1b4a51f4a2 Remove print statement for debugging timestamps 2024-07-10 14:54:22 +05:30
sabaimran
0369eb6e0e Fix timestamp bug for pending message and expand CSP for thumbnails 2024-07-10 14:53:31 +05:30
sabaimran
375685530f Add content security policy to the chat page 2024-07-10 11:18:41 +05:30
sabaimran
c5cfd0f2cf Remove unused slash command-related useeffect hook 2024-07-10 10:03:58 +05:30
sabaimran
e1a5c17775 Add DOMPurify for rendering md text. Add a easter egg in the console 2024-07-10 10:03:08 +05:30
sabaimran
e358723baa Fix image rendering and unique key for pending message? 2024-07-09 21:55:54 +05:30
sabaimran
c8c5d50b1a Improve command bar slash experience 2024-07-09 21:39:13 +05:30
sabaimran
c25bf97831 Update hover styling for see all button 2024-07-09 20:55:54 +05:30
sabaimran
23b71b0dff Remove shadow from the slash command bar 2024-07-09 20:52:38 +05:30
sabaimran
998e2aec30 Update dark mode, fix chat message time stamp, fix rendering for new message 2024-07-09 20:50:20 +05:30
sabaimran
0c6b6de09e Revert web client route chat page rendering logic 2024-07-09 19:47:04 +05:30
sabaimran
cc22e1b013 Add pop-up module for the slash commands 2024-07-09 19:46:17 +05:30
sabaimran
5b69252337 Add hover effects for chat messages 2024-07-09 14:56:57 +05:30
sabaimran
a0e9530fa4 Merge branch 'master' of github.com:khoj-ai/khoj into features/chat-ui-updates-big 2024-07-09 12:57:50 +05:30
sabaimran
260aa61818 Remove tests for python3.9 2024-07-09 12:28:11 +05:30
sabaimran
4471c1e37f Apply mitigations for piling up open connections 
- Because we're using a FastAPI api framework with a Django ORM, we're running into some interesting conditions around connection pooling and clean-up. We're ending up with a large pile-up of open, stale connections to the DB recurringly when the server has been running for a while. To mitigate this problem, given starlette and django run in different python threads, add a middleware that will go and call the connection clean up method in each of the threads.
 2024-07-09 12:22:58 +05:30
sabaimran
609e7ee19c Fix width of side panel 2024-07-09 12:02:01 +05:30
Debanjum
0b1b262512 Add system dependencies required by RapidOCR to fix Khoj Docker image (#842) 
- Issue
The Khoj docker build would fail with `ImportError: libGL.so.1: cannot open shared object file: No such file or directory`. This was required by the Khoj RapidOCR python package dependency. 

- Fix
A minimal set of system packages have been added to resolve this issue.
 2024-07-08 22:16:16 +05:30
kxnarak
43413cd21f add dependencies required by the RapidOCR python package 2024-07-08 18:26:19 +05:30
sabaimran
bf4c2f219e Merge branch 'master' of github.com:khoj-ai/khoj into features/chat-ui-updates-big 2024-07-08 17:00:42 +05:30
sabaimran
037e157648 Fix a variety of links 2024-07-08 16:49:13 +05:30
sabaimran
6b80bb3f37 Add a demo for the khoj mini application, minor updates to other pages, remove out of date demos page 2024-07-08 16:33:47 +05:30
Debanjum Singh Solanky
9e31ebff93 Release Khoj version 1.16.0 2024-07-07 18:26:10 +05:30
Debanjum Singh Solanky
54132efd67 Fix Khoj Obsidian plugin build 2024-07-07 18:26:10 +05:30
Debanjum Singh Solanky
510d9b3a29 Add short keys to open chat menu, new chat, search from Obsidian pane 2024-07-07 17:57:17 +05:30
Debanjum Singh Solanky
3e0c882e27 Transcribe only when keyboard shortcut or button pressed in Obsidian 
- Transcribe on holding Ctrl+s keyboard shortcut
- Transcribe on holding the transcribe button pressed via mouse too
- Make the transcribe button robust to inadvertent touches by using timeout
- Do not transcribe, trigger auto-send on silences. Silence detection
  is super rudimentary, just blocks standard emanations by whisper
  when no speech
 2024-07-07 17:57:17 +05:30
sabaimran
0eb000c3ea Add health checks for the django ORM 2024-07-07 16:11:28 +05:30
sabaimran
6f8a65c529 References, mobile friendly chat sessions and file filter 2024-07-07 15:42:29 +05:30
Debanjum Singh Solanky
a31cd0dec1 Fix async batch delete of indexed entries 2024-07-06 22:45:26 +05:30
Debanjum
08b379c2ab Fix, Improve Indexing, Deleting Files (#840) 
### Fix
- Fix degrade in speed when indexing large files
- Resolve org-mode indexing bug by splitting current section only once by heading
- Improve summarization by fixing formatting of text in indexed files

### Improve
- Improve scaling user, admin flows to delete all entries for a user
 2024-07-06 19:52:42 +05:30
Debanjum Singh Solanky
4a471979eb Upgrade sentence-transformer package to version 3.0.1 
Add einops dependency for some sentence transformer models like the
nomic-embed
 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
d693baccbc Make it optional to set the encoder, cross-encoder configs via admin UI 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
1baebb8d0e Identify markdown headings by any whitespace character after ^#+ 
Previously only markdown headings with space characters after # would
be considered a heading. So ^##\t wouldn't be considered a valid heading
 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
010486fb36 Split current section once by heading to resolve org-mode indexing bug 
- Split once by heading (=first_non_empty) to extract current section body
  Otherwise child headings with same prefix as current heading will
  cause the section split to go into infinite loop
- Also add check to prevent getting into recursive loop while trying
  to split entry into sub sections
 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
6a135b1ed7 Fix degrade in speed of indexing large files. Improve summarization 
Adding files to the DB for summarization was slow, buggy in two ways:
- We were updating same text of modified files in DB = no of chunks
  per file times

- The `" ".join(file_content)' code was breaking each character in the
  file content by a space. This formats the original file content
  incorrectly before storing in the DB

Because this code ran in the main file indexing path, it was slowing down
file indexing. Knowledge bases with larger files were impacted more strongly
 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
e6ffb6b52c Improve scaling user flow to delete all entries 
- Delete entries by batch to improve efficiency of query at scale
- Share code to delete all user entries between it's async, sync methods
- Add indicator to show when files being deleted on web config page
 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
1ab59865b5 Improve scaling admin flow to delete all entries for user 2024-07-06 19:35:59 +05:30
Debanjum
05138cbd0a Use DOM Scripting, Add CSP to Web config pages. Disable CSP in Obsidian plugin (#834) 
- Add CSP to web config pages. Load phone no. validation js, css from S3
- Construct config page elements on Web via DOM scripting
- Disable CSP in Khoj Obsidian as it interferes with Obsidian functionality

- Other miscellaneous voice message level improvements (rate limit, listening animation)
 2024-07-06 19:30:09 +05:30
Debanjum Singh Solanky
9bdb48807b Ratelimit text to speech model. Validate share chat url domain 
- Do not log auth error message on server when Resend setup as Magic
  links for sign-in are now supported
 2024-07-06 12:53:19 +05:30
Debanjum Singh Solanky
b334db0fca Add CSP to web config pages. Load phone no validation js, css from S3 2024-07-06 12:48:28 +05:30
Debanjum Singh Solanky
2f034f807a Construct config page elements on Web via DOM scripting. 
Minimize isage of innerHTML to prevent DOM clobbering and unintended
escape by user Input
 2024-07-06 12:48:28 +05:30
Debanjum Singh Solanky
69c9e8cc08 Disable CSP in Khoj Obsidian as it interferes with Obsidian functionality 
The Khoj CSP interferes with other Obsidian features and plugins as
CSP is applied page wide.

For now chat message sanitization via Dompurify should suffice.

Enable CSP when can scope it to only the Khoj Obsidian plugin.
 2024-07-05 16:10:08 +05:30
Debanjum Singh Solanky
a353d883a0 Make it optional to set the encoder, cross-encoder configs via admin UI 
Upgrade sentence-transformer, add einops dependency for some sentence
transformer models like nomic
 2024-07-05 16:09:30 +05:30
Debanjum Singh Solanky
6d59ad7fc9 Add listening circle animation to speak button in Obsidian plugin 
Use icon active focus as color of animation button
 2024-07-05 14:00:53 +05:30
sabaimran
aec44a0b89 Add dark mode toggle! And improve experience for train of thought 2024-07-04 18:29:21 +05:30
Debanjum Singh Solanky
516af86575 Fix add, remove of the text to speech loader element in Obsidian 2024-07-04 17:38:45 +05:30
sabaimran
465ef0b772 Add a loading experience when waiting for khoj response 2024-07-04 13:49:51 +05:30
Debanjum Singh Solanky
814aca6d69 Skip summarize when not triggered via slash cmd and can't summarize 
Maybe better to fallback to non-summarize behavior if summarize intent
is just inferred but we can't actually summarize because the single
file added to conversation isn't satisfied
 2024-07-04 13:31:00 +05:30
Debanjum
4446de00d3 Enable Voice, Keyboard Shortcuts in Khoj Obsidian Plugin (#837) 
- Simplify quick jump between Khoj side pane and main editor view using keyboard shortcuts
- Enable voice chat in Obsidian to make interactions with Khoj more seamless
 2024-07-04 13:28:29 +05:30
sabaimran
5ea8b16f84 Fix missing method error 2024-07-04 12:08:22 +05:30
sabaimran
d61bddf56c Fix retrieving image model by prefetching the openai config in the async method 2024-07-04 11:58:33 +05:30
sabaimran
a129b017b9 Fix image generation on server -- use default config when not set by user 2024-07-04 09:13:23 +05:30
sabaimran
34118078bf kill the emojis 2024-07-04 00:30:21 +05:30
sabaimran
d5ba916978 Working example of streaming, intersection observer, other UI updates 2024-07-04 00:30:01 +05:30
sabaimran
78d1a29bc1 Finish up filte filter side panel menu 2024-07-02 23:32:36 +05:30
sabaimran
6fa2dbc042 Do not use the custom configured max prompt size to send message to anthropic 2024-07-02 21:59:06 +05:30
sabaimran
8a6722ba97 Add basic implementation for chat side panel components 2024-07-02 21:56:43 +05:30
Debanjum Singh Solanky
afcfc60637 Merge DB migrations post merge of SD3 via API support PR 2024-07-02 17:54:58 +05:30
Debanjum
c015eeb5dd Improve Online Search: Parallelize Search, Use Jina Reader API by default (#832) 
- Overview
  Khoj wil be able to do online search out of the box, even for self-hosted users
  - Default to Jina search, reader API when no Serper.dev, Olostep API keys
  - Run online searches in parallel to process multiple queries faster

- Details
  - Jina provides a [reader API](https://github.com/jina-ai/reader) for online search and web page reading
     It requires no API key. This provides a good default to enable 
     online search for self-hosted readers requiring no additional setup. 

  - Jina search API also returns webpage contents with the results, so
     just use those directly when Jina Search API used instead of
     trying to read webpages separately. The extract relevant content from
     webpage step using a chat model is still used from the
    `read_webpage_and_extract_content' func in this case.

  - Parse search results from Jina search API into same format as
     Serper.dev for accurate rendering of online references by clients

  - Run online searches in parallel with AsyncIO to process multiple queries faster
 2024-07-02 17:44:51 +05:30
Debanjum
826c3dc9cc Enable using Stable Diffusion 3 for Image Generation via API (#830) 
- Support Stable Diffusion 3 via API
  Server Admin needs to setup model similar to DALLE-3 via Django Admin Panel
- Use shorter prompt generator to prompt SD3 to create better images
- Allow users to set paint model to use from web client config page
 2024-07-02 17:28:50 +05:30
Debanjum Singh Solanky
d5ceff2691 Update tests and documentation with Jina reader API usage and info 
Update offline, openai chat actor, director tests to not require
Serper to run the online command tests

Update documentation for self-hosted online search to mention no setup
is required by default. But improvements can be made by using
Serper.dev or Olostep
 2024-07-02 17:19:09 +05:30
Debanjum Singh Solanky
553beae848 No need to set OpenAI API key from environment variable explicitly 
It is unnecessary as the OpenAI client automatically tries to use API
key from OPENAI_API_KEY env var when the api_key field is unset
 2024-07-02 17:19:09 +05:30
Debanjum Singh Solanky
a038e4911b Default to Jina search, reader API when no Serper.dev, Olostep API keys 
Jina AI provides a search and webpage reader API that doesn't require
an API key. This provides a good default to enable online search for
self-hosted readers requiring no additional setup.

Jina search API also returns webpage contents with the results, so
just use those directly when Jina Search API used instead of
trying to read webpages separately. The extract relvant content from
webpage step using a chat model is still used from the
`read_webpage_and_extract_content' func in this case.

Parse search results from Jina search API into same format as
Serper.dev for accurate rendering of online references by clients
 2024-07-02 17:19:08 +05:30
Debanjum Singh Solanky
ff44734774 Run online searches in parallel to process multiple queries faster 2024-07-02 17:19:08 +05:30
sabaimran
0ee7cc8c47 Change overall architecure of how information is flowing for better statefulness 2024-07-02 12:39:54 +05:30
sabaimran
541ce04ebc Checkpoint: Updated sidebar panel with new components 
- Add non-functional UI elements for chat, references, feedback buttons, rename/share session, mic, attachment, websocket connection
 2024-07-02 11:18:50 +05:30
Raghav Tirumale
8eccd8a5e4 Support Indexing Images via OCR (#823) 
- Added support for uploading .jpeg, .jpg, and .png files to Khoj from Web, Desktop app
- Updating indexer to generate raw text and entries using RapidOCR
- Details
  * added support for indexing images via ocr
  * fixed pyproject.toml
  * Update src/khoj/processor/content/images/image_to_entries.py
     Co-authored-by: Debanjum <debanjum@gmail.com>
  * Update src/khoj/processor/content/images/image_to_entries.py
     Co-authored-by: Debanjum <debanjum@gmail.com>
  * removed redudant try except blocks
  * updated desktop js file to support image formats
  * added tests for jpg and png
  * Fix processing for image to entries files
  * Update unit tests with working image indexer
  * Change png test from version verificaition to open-cv verification

---------

Co-authored-by: Debanjum <debanjum@gmail.com>
Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-07-01 06:00:00 -07:00
Debanjum Singh Solanky
cffc14a46a Trigger voice chat via keyboard shortcut in Khoj side pane 
Quickly trigger voice chat from Khoj side pane using Keyboard shortcuts
 2024-07-01 18:06:09 +05:30
Debanjum Singh Solanky
3723904512 Toggle jump between Khoj side pane & previous editor via cmd, kbd shortcut 
Improve quick navigation to, from Khoj side pane using Keyboard
shortcut or Obsidian command
 2024-07-01 18:05:59 +05:30
Debanjum Singh Solanky
fbb95ca342 Put cursor on chat input when focus on chat view in Obsidian 
This should improve fluidity of keyboard interactions with Khoj on
Obsidian.

Open Khoj chat view via keybinding or command pallete and ask
question using only the keyboard, with no mouse clicks required
 2024-07-01 18:05:55 +05:30
Debanjum Singh Solanky
093e276908 Enable Voice chat in Khoj Obsidian plugin 
- Automatically carry out voice chats with Khoj from within Obsidian
  When send voice message, Khoj will auto respond with voice as well
- Listen to past Khoj messages as speech
- Add circular loading spinner to use while message is being converted
  to speech
 2024-07-01 18:02:28 +05:30
sabaimran
c83b8f2768 Allow just one worker to be the background schedule leader (#836) 
* Add a leader election mechanism to circumvent runtime issues for multiple schedulers

- Reduce the load on the DB and risk of issues on the service side by limiting the execution environment to one elected leader at a given time. This one is responsible for managing all of the execution of the jobs, though all workers are capable of adding and removing jobs

* Set a max duration for the schedule leader position (12 hrs), add some error if automation not added successfully
 2024-06-28 13:13:25 +05:30
sabaimran
80fe5ce182 Fix user not authenticated interpretation error 2024-06-27 21:13:54 +05:30
Raghav Tirumale
24a0d8b073 Add OS Level Shortcut Window for Quick Access to Khoj Desktop (#815) 
* rough sketch of desktop shortcuts. many bugs to fix still

* working MVP of desktop shortcut khoj

* UI fixes

* UI improvements for editable shortcut message

* major rendering fix to prevent clipboard text from getting lost

* UI improvements and bug fixes

* UI upgrades: custom top bar, edit sent message and color matching

* removed debug javascript file

* font reverted to Noto Sans

* cleaning up the code and removing diffs

* UX fixes

* cleaning up unused methods from html

* front end for button to send user back to main window to continue conversation

* UX fix for window and continue conversation support added

* migrated common js functions into chatutils.js

* Fix window closing issue in macos by

1. Use a helper function to determine if the window is open by seeing if there's a browser window with shortcut.html loaded
2. Use the  event listener on the window to handle teardown

* removed extra comment and renamed continue convo button

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-06-27 07:20:13 -07:00
sabaimran
870d9ecdbf Add a fact checker feature with updated styling (#835) 
- Add an experimental feature used for fact-checking falsifiable statements with customizable models. See attached screenshot for example. Once you input a statement that needs to be fact-checked, Khoj goes on a research spree to verify or refute it.
- Integrate frontend libraries for [Tailwind](https://tailwindcss.com/) and [ShadCN](https://ui.shadcn.com/) for easier UI development. Update corresponding styling for some existing UI components. 
- Add component for model selection 
- Add backend support for sharing arbitrary packets of data that will be consumed by specific front-end views in shareable scenarios
 2024-06-27 18:45:38 +05:30
sabaimran
3b7a9358c3 Add our first view via Next.js for Agents (#817) 
Initialize our migration to use Next.js for front-end views via Agents. This includes setup for getting authenticated users, reading in available agents, setting up a pop-up modal when you're clicking on an agent, and allowing users to start new conversations with agents.

Best attempt at an in-place migration, though there are some noticeable differences.

Also adds view for chat that are not being used, but in experimental phase.
 2024-06-27 13:56:16 +05:30
Debanjum Singh Solanky
afbeee9e82 Rename copy-button to more general chat-action-button in Obsidian client 
- Use 4 space indent of activateView function in pane_view component
 2024-06-26 18:09:23 +05:30
sabaimran
8c12a69570 Fix issue in anthropic chat when khoj message becomes top message 
This is because Anthropic requires the first message in the chat history to be from the user.
 2024-06-26 12:59:34 +05:30
Debanjum Singh Solanky
4f89319b40 Release Khoj version 1.15.0 2024-06-26 10:38:16 +05:30
Debanjum Singh Solanky
bbfd320ed4 Use Yarn instead of NPM to bump Desktop, Obsidian client versions 2024-06-26 10:37:58 +05:30
Debanjum Singh Solanky
c793d8a69e Add Validation logic to save PaintModel. Use API key from Paint Model 
Rename Paint Model, Adapters to TextToImage for consistency
 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
1acf969c6e Do not require OpenAI to generate image as local chat + sd3 works now 
Previously the text_to_image helper would only trigger the image
generation flow if OpenAI client was setup. This is not required
anymore as offline chat model + sd3 API works. So remove that check
 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
2c4bf91a61 Allow user to set paint model to use from web client config page 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
eb09aba747 Remove quotes wrapping the prompt from being passed to image gen model 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
fdd4c02461 Use shorter prompt generator to prompt SD3 to create better images 2024-06-26 10:16:26 +05:30
Debanjum Singh Solanky
eda33e092f Enable using Stable Diffusion 3 for Image Generation via API 2024-06-26 10:16:26 +05:30
Debanjum
a25689fabf Use user theme in Obsidian for Khoj plugin styling (#825) 
Makes the Khoj chat in the Obsidian plugin adapt better to the user theme, making it feel more seamless, and helps with dark mode compatibility
 2024-06-26 10:14:17 +05:30
Debanjum Singh Solanky
cfe46fd9f5 Add Border Color instead of BG Color for Chat Message in Obsidian 2024-06-26 08:11:04 +05:30
sabaimran
fb818ead60 Use active bg instead of code background for khoj response 2024-06-26 08:05:13 +05:30
sabaimran
a4b2552540 Update conversation session selection menu to use Obsidian theme colors as well 2024-06-26 08:05:13 +05:30
sabaimran
da5b07e913 Remove custom styling on the reference buttons 2024-06-26 08:05:13 +05:30
sabaimran
c4a1ae9375 Make the Khoj Obsidian plugin more user theme friendly 
Use the CSS variables from the theme for the Khoj UI components
 2024-06-26 08:04:17 +05:30
Debanjum Singh Solanky
d6fe5d9a63 Pass current component as arg to markdown renderer in chat view 
This doesn't work on search modal, but hopefully will get resolved
once we migrate search into a view from a modal
 2024-06-24 16:12:20 +05:30
Debanjum Singh Solanky
0d04018622 Install pydantic with optional email validator package 
Otherwise Khoj fails on startup. Not sure why, must be new changes to
pydantic?
 2024-06-24 16:12:20 +05:30
Debanjum Singh Solanky
6f280b1ccc Split setup of specific OpenAI API proxies into separate doc pages 2024-06-24 16:12:20 +05:30
Debanjum Singh Solanky
68e7c297e0 Add Advanced Self Hosting Section, Improve Self Hosting, OpenAI Proxy Docs 
- Add instructions for self-hosted users with info, warning boxes to
  avoid, fix common issues when setting up Khoj server
- Create new Advanced Self Hosting section
  - Extract Advanced Self-Hosting Sections from the Advanced Page and
    move them to separate Pages under Advanced Self Hosting section
- Improve OpenAI Proxy Docs
  - Put Ollama setup as a section under OpenAI API Proxy page instead
    of a separate page
  - Add Section to use Khoj with chat model from LM Studio
  - Update LiteLLM docs to use chat model from LM Studio
 2024-06-24 16:12:20 +05:30
Debanjum Singh Solanky
732332a3c5 Spell fix s/e.g/e.g./ across code, tests and docs 2024-06-24 15:24:45 +05:30
Debanjum Singh Solanky
8fc7f980aa Revert KHOJ_DOMAIN to only support single domain. 
Multiple domain support didn't generalize to other portions where it
is used
 2024-06-24 15:24:45 +05:30
sabaimran
4110e71e84 Add info in the documentation about text to speech 2024-06-24 12:46:33 +05:30
sabaimran
939811e9b5 Fix conversation look up logic 2024-06-24 09:10:03 +05:30
Debanjum Singh Solanky
a4d88612c1 Just use yarn for package version locking. Remove npm package lock 2024-06-23 16:06:20 +05:30
Debanjum Singh Solanky
55be90cdd2 Sanitize user input fields on Automations page of web client 
Use Dompurify to sanitize user input
 2024-06-23 14:14:47 +05:30
Debanjum Singh Solanky
1c7a562880 Generate automation cards via DOM scripting 2024-06-23 13:22:38 +05:30
Debanjum Singh Solanky
57a36967bf Run Obsidian version script in bump_version.sh to write to versions.json 
This handles updates from manifest.json minAppVersion field to the
versions.json file.

The minAppVersion field is for the minimum Obsidian app version
supported by a Khoj plugin version
 2024-06-23 08:18:55 +05:30
Debanjum Singh Solanky
c7c32a7467 Improve online chat reference extraction in Khoj.el Emacs package 
- Handle online references with no title
- Improve handling references which are arrays instead of lists
 2024-06-23 08:13:36 +05:30
Debanjum Singh Solanky
9d33d8c0fa Upgrade typescript eslint dev dependency of Khoj Obsidian plugin 2024-06-23 07:36:49 +05:30
Debanjum
a94062469a Automatically Find Similar Notes on Emacs in Background (#827) 
Khoj will find and display notes similar to the current entry in the side pane when
1. find similar is open in side pane and
2. cursor has moved to a new entry

### Major
- Find similar notes to current note at cursor automatically in background
- Only show headings of search result and increase default results count

### Minor
- Pass absolute path of file to index from khoj.el emacs client
- Update help message to only show the smaller set of new keybindings
- Fix edge cases in loading some chat sessions
 2024-06-23 07:36:11 +05:30
sabaimran
38090b2553 In dockerize.yml file, revert the added configuration 2024-06-22 21:11:25 +05:30
sabaimran
a53178cab9 Add developer support for using next.js to serve generated static files (#814) 
To improve the developer experience for front-end development, we're migrating to Next.js. In order to do this migration page-by-page, we're using static site generation via Next.js. This also helps us avoid making cross site requests from front-end to back-end for the time being, while giving a ramp to separating out server and client if needed for scale down the road.

Dev instructions for using the next.js setup are in the added README.

This adds scaffolding for including the built files in the python package as well as the docker images. Docker setup has been tested locally. In order to verify the build is working as expected, we can navigate to the {khoj_host}:42110/experimental and verify that the experiment page comes up.

This setup works with serving static files included in the src/interface/web folder from the Django app. The key bit for understanding the setup is in the yarn export command in package.json.
 2024-06-22 20:12:41 +05:30
Debanjum Singh Solanky
59edb99f04 Simplify, improve bump version development script 
- Just use in-built `npm version' command to update desktop, obsidian version
- Upgrade by major, minor or patch version using new -t flag in script
  E.g bump_version -t minor
 2024-06-22 18:19:38 +05:30
Debanjum Singh Solanky
abd6f58aee Upgrade Desktop app package dependencies 2024-06-22 17:38:52 +05:30
Debanjum Singh Solanky
f413dc62cd Upgrade Obsidian plugin dependencies. Add package lock file for it 
Add it to bump_version script as well.
 2024-06-22 17:38:52 +05:30
Debanjum Singh Solanky
1d7d51a7ab Upgrade Documentation packages 2024-06-22 17:38:48 +05:30
Debanjum Singh Solanky
22f6db0a6b Upgrade RapidOCR and enable for Python 3.12. Fix PDF OCR test 2024-06-22 16:01:55 +05:30
Debanjum Singh Solanky
55a23eae25 Upgrade pillow to fix pytest workflow failure 2024-06-22 15:17:43 +05:30
Debanjum Singh Solanky
7e277e9381 Fix getting file-toggle-button element in chat of web app 2024-06-21 15:54:38 +05:30
Debanjum Singh Solanky
fa7b40ab86 Automatically respond with Voice if subscribed user sent Voice message 2024-06-21 15:53:01 +05:30
Debanjum Singh Solanky
5e5fe4b7af Improve font size, spacing of conversation session on desktop app 2024-06-21 12:25:35 +05:30
sabaimran
d3c0111121 Include base URL when using openai api config in extract questions. Close #831 2024-06-21 12:18:50 +05:30
sabaimran
b9966eb3d4 Add support for text to speech in chat responses (#821) 
* Enable speech to text responses in khoj chat

- Current issue: reads out all the markdown formatting, plus waits for the whole result to be streamed before playing it

* Extract content from markdown-formatted text

* Add a loader for while you're waiting for Khoj's response

* Add user configuration option for chat model options, allow server side configuration for option list

* Join up APIs, views, admin pages to allow configuring custom voice models
 2024-06-21 11:30:28 +05:30
Debanjum Singh Solanky
427575e958 Improve khoj chat new, delete session flows 
When create new conversation session, automatically request query. As
that is expected next action after creating new session

Pass session-id to khoj-chat to allow reuse from
create-new-conversation func

When delete conversation session, do not call load chat session.
Unnecessary action.

Use thread-last to improve code flow in new, delete conversation funcs
 2024-06-21 10:54:59 +05:30
Debanjum Singh Solanky
59032a06d5 Improve defaults when extracting fields from online reference in khoj.el 2024-06-21 10:54:59 +05:30
Debanjum Singh Solanky
9262aea7a5 Fix comments, func calls based on melpazoid, checkdoc, package-lint 2024-06-21 10:54:59 +05:30
sabaimran
ff26b19d2b Add a migration for allowing the docx field in the entries file type 2024-06-21 09:47:49 +05:30
sabaimran
3cfe5aabe5 Add support for magic link email sign-in (#820) 
* Add magic link email sign-in option

* Adding backend routes and model changes to keep state of email verification code and status

* Test and fix end to end email verification flow

* Add documentation for how to use the magic link sign-in when self-hosting Khoj

* Add magic link sign in to public conversation page
 2024-06-20 13:32:58 +05:30
Debanjum Singh Solanky
0afe66ac39 Restore cursor to original window after opening Khoj side pane 
Previously the cursor would move to the Khoj side pane on opening it.
This would break user's flow, especially when find similar triggers
automatically

New behavior maintains smoother update of auto find similar without
disrupting user browsing
 2024-06-20 12:50:13 +05:30
Debanjum Singh Solanky
afe91a2633 Only show headings of search result and increase total count returned 
Previously it would show complete result body this would make the
result width variable and hard to track all the returned results

Showing just heading makes it easier to track
 2024-06-20 12:50:13 +05:30
Debanjum Singh Solanky
2b12a5514e Find similar notes to current note at cursor automatically in background 
- Call find similar on current element if point has moved to new
  element
- Delete the first result from find-similar search results as that'll
  be the current note (which is trivially most similar to itself)
- Determine find-similar based text formating at the rendering layer
  rather than at the top level find-similar func
 2024-06-20 12:50:13 +05:30
Raghav Tirumale
093eb473cb Add Documentation for the /summarize Command (#822) 
* added documentation for the /summarize command

* Add a hint for natural language usage

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-06-20 12:08:01 +05:30
Raghav Tirumale
bd3b590153 Support Indexing Docx Files (#801) 
* Add support for indexing docx files and associated unit tests

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-06-20 11:18:01 +05:30
Debanjum Singh Solanky
d042e073cc Pass absolute path of file to index from khoj.el emacs client 2024-06-20 00:26:18 +05:30
Debanjum Singh Solanky
d23f2849d4 Update help message to only show the smaller set of new keybindings 2024-06-20 00:26:18 +05:30
Raghav Tirumale
d4e5c95711 Add Ability to Summarize Documents (#800) 
* Uses entire file text and summarizer model to generate document summary.
* Uses the contents of the user's query to create a tailored summary.
* Integrates with File Filters #788 for a better UX.
 2024-06-18 19:31:07 +05:30
Debanjum Singh Solanky
677d49d438 Release Khoj version 1.14.0 2024-06-18 17:13:46 +05:30
Debanjum Singh Solanky
2930b57c78 Use hashed value to improve deduplication of search results on server 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
6814dadd21 Fix opening Web, Desktop setup links on first run from Desktop app 
Previous version failed to open the setup links
 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
632f55a9e8 Do not default to rerank if device has GPU 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
f1120f24a1 Use solarized light css styling to highlight code in chat messages 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
d8a5a01cea Pass multiple allowed Khoj domains via KHOJ_DOMAIN env var 
To add multiple allowed Khoj domains pass them as a comma separated
list of domains via the KHOJ_DOMAIN environment variable

Resolve comment in issue #662
 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
4daf16e5f9 Only redirect to next url relative to current domain 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
86a3505d89 Remove image HTML elements from non whitelisted sources in Obsidian chat 
Given img src enforcement via CSP required loosening. Soft enforce it
via a regex replace of img HTML elements if the src isn't from the
whitelisted set of source prefixes.

Currently allowed source prefixes are
- app: for local images
- data: for inline generated images
- https://generated.khoj.dev: for cloud generated images
 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
c7d825bddb Sanitize markdown in Obsidian after conversion to HTML too 
- Create and use a function to convert markdown to sanitized html
- Remove unused Latex delimiter handling as Katex isn't used in
  Khoj chat on Obsidian
 2024-06-18 17:04:25 +05:30
Debanjum Singh Solanky
08c3aa496d Loosen CSP in Obsidian to load images, sync and allow Obsidian domain 2024-06-18 17:04:25 +05:30
sabaimran
327045be43 Make some basic updates to the chat documentation. Inc. conversation file filters, new screenshot 2024-06-18 12:14:59 +05:30
sabaimran
76e1bed8f9 Update Obsidian documentation 2024-06-18 08:22:10 +05:30
sabaimran
a57e1e7a14 Fix langchain, tenacity versions 2024-06-17 14:52:11 +05:30
sabaimran
ce9c14f894 Fix more packages related to langchain in the pyproject.toml 2024-06-17 14:38:05 +05:30
sabaimran
ba0187798a Get converastion id before retrieving relevant notes in non-socket code 2024-06-17 14:26:06 +05:30
Debanjum
d2d9f4888e Upgrade Khoj Emacs UX (#812) 
- Open Khoj in Emacs Side pane
   Open Khoj chat, search in right pane to allow for ambient engagement
- Improve Khoj Chat
  - Show online references used for chat
  - Make chat API call async to not block user interactions
  - Fix loading chat history, references in khoj.el chat buffer
- Improve Khoj Search, Find Similar functions
   - Make calls to Khoj search API async to not block user interactions
- Support Conversation Sessions
  - Create transient menu to open, create, delete conversation sessions from the Khoj Emacs client
 2024-06-16 10:39:48 +05:30
Debanjum Singh Solanky
fe36adb7b9 Remove short keys to switch content type during search to avoid conflict 
- C-x o to switch to search org content conflicts with switch buffer shortkey
  This is more apparent in the async search scenario as it prevents
  perform other actions while async search is in progress

- Also switching content type wouldn't scale to all the content types
  Khoj will support without causing more conflicting keybinding
 2024-06-15 17:31:19 +05:30
Debanjum Singh Solanky
2a84524d19 Make khoj.el search, similar API calls async to not block user interactions 2024-06-15 17:30:58 +05:30
Debanjum Singh Solanky
c6b95f8776 Handle rendering messages using the old reference schema in khoj.el 
Previously references were a list instead of a map
 2024-06-15 17:30:58 +05:30
Debanjum Singh Solanky
db056c896d Delete old conversation sessions from the chat menu in Khoj Emacs 2024-06-15 17:30:58 +05:30
Debanjum Singh Solanky
e3d995a74f Extract select conversation session logic into func for reusability 2024-06-15 17:30:38 +05:30
Debanjum Singh Solanky
e15dc23bbe Improve logic to create vs reuse window for khoj side pane logic 
Khoj side pane occupies a vertically split bottom right side pane.
If the bottom right window is not a vertical split, create a new
vertical split pane for khoj, otherwise reuse the existing window
 2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
055e5e8d26 Create new conversation from the chat menu in Khoj Emacs 2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
c33954cd93 Fix loading an empty chat session in Emacs 2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
e21c0648ae Create, use reusable function to call Khoj API from elisp 2024-06-15 16:37:41 +05:30
Debanjum Singh Solanky
7bcb49b6e7 Support conversation sessions in the Khoj Emacs client 
Add option in khoj main transient menu option to open menu to
- switch between existing conversations
 2024-06-15 13:13:20 +05:30
Debanjum Singh Solanky
df9c5ff263 Show online references used for chat response as footnotes in Emacs 
Previously online references used weren't being shown
 2024-06-15 13:13:19 +05:30
sabaimran
82f37971c5 Fix broken link in automations.md 2024-06-14 16:22:27 +05:30
sabaimran
25d8cdd9cd Misc fixes: 
- Fix getting file filters for not found conversations
- Allow iamge rendering in automation emails
- Fix nearest 15th minute calculation in automations creation
 2024-06-14 16:20:22 +05:30
sabaimran
971f1cd897 Add basic page about automations 2024-06-14 15:52:30 +05:30
sabaimran
17bce930ba Add a documentation page for keyboard shortcuts 2024-06-14 14:30:31 +05:30
Raghav Tirumale
35715096f4 UX Improvement: Keyboard Shortcuts for Recent Messages (#804) 
* added keyboard shortcuts to access old queries
 2024-06-14 12:45:09 +05:30
sabaimran
2dcfb3c2f0 Fix bug for drag and drop single file 2024-06-14 12:01:10 +05:30
sabaimran
7e4a61f2ac Disable rate limiting if billing is not enabled 2024-06-12 21:39:02 +05:30
Debanjum Singh Solanky
385057f09e Make khoj.el chat API call async to not block user interactions 2024-06-12 21:04:48 +05:30
sabaimran
45e725ac9c Use the summarizer model for generating improved image prompts 2024-06-12 17:41:12 +05:30
Raghav Tirumale
673d0d367c Fix: Adding Support for Uploading Multiple Files (#803) 
* added support for uploading multiple files at a time.

* optimized multiple file upload to use a batch upload

* allowing files to upload even if there is one unsupported file
 2024-06-12 15:51:35 +05:30
Debanjum Singh Solanky
906ebee075 Open Khoj chat, search in right pane to allow for ambient engagement 
See the currently active window in context while doing chat, search
or find similar operations in a side pane.

This is similar to how we've moved Khoj on Obsidian into the side pane
as well
 2024-06-09 23:32:34 +05:30
Debanjum Singh Solanky
cd4baa3fa5 Fix loading chat history, references in khoj.el chat buffer 2024-06-09 18:34:00 +05:30
Debanjum
6afbd8032e Improve Intermediate Steps in Formulating Chat Response (#799) 
# Major
- Disambiguate Text output mode to disambiguate from Default data source lookup
- Fix showing headings in intermediate step in generating chat response
- Remove "Path" prefix from org ancestor heading in compiled entry

# Minor
- Fix OpenAI chat actor, director unit tests
 2024-06-09 07:55:01 +05:30
Debanjum Singh Solanky
f440ddbe1d Fix openai chat actor, director tests 
- Update test ChatModelOptions setup since update to it's schema
- Fix stale function calls using their updated signatures
 2024-06-09 07:24:47 +05:30
sabaimran
2e209ab28b Handle case where conversation does not (yet) exist 2024-06-08 16:22:12 +05:30
sabaimran
849c38c0a4 Add support for managing audiences for new users 2024-06-08 15:51:17 +05:30
sabaimran
06a47ee457 Add language-specific syntax highlighting via highlight.js (#802) 
* Add language-specific syntax highlighting via highlight.js

- Add highlight.js to our assets CDN for fast load and compliance with the CSP
- See other stylesheets options here: https://cdnjs.com/libraries/highlight.js

* Bonus: set min-height to prevent increasing length of the sessions pane

* Fix references rendering and add highlight.js in public conversation
 2024-06-08 15:17:09 +05:30
Debanjum Singh Solanky
5f2442450c Update truncation test to reduce flakyness in cloud tests 
Removed dependency on faker, factory for the truncation tests as that
seems to be the point of flakiness
 2024-06-07 19:42:48 +05:30
sabaimran
dbb06466bf Minor fit/finish updates to the file filter experience 2024-06-07 15:05:00 +05:30
sabaimran
58a02f06ea Fix multilingual font rendering (#797) 
* Fix multilingual font rendering; fallback to an Arabic language font which contains more Asian characters. Close #756

* Tune font-sizes and styling to accomodate new fonts with old sizing

- Move connection-status styling out from inline html into css block
- Remove start typing chat-input height jitter
- align new-conversation button, text
- use relative font sizes instead of absolute font sizes in most places

---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
 2024-06-07 11:53:47 +05:30
Raghav Tirumale
ba16afd3c2 New Feature: Adding File Filtering to Conversations (#788) 
* UI update for file filtered conversations
* Interactive file menu #UI to add/remove files on each conversation as references.
* Backend changes implemented to load selected file filters from a conversation into the querying process.
---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-06-07 10:53:37 +05:30
Debanjum Singh Solanky
f91cdf8e18 Fix showing headings in intermediate step in generating chat response 2024-06-06 16:52:23 +05:30
Debanjum Singh Solanky
18f7e6e7ed Remove "Path" prefix from org ancestor heading in compiled entry 2024-06-06 16:51:26 +05:30
sabaimran
8d701ebe22 Add fedCM to accommodate google migration (#798) 
- See migration guidelines here: https://developers.google.com/identity/gsi/web/guides/fedcm-migration#fedcm_flag
 2024-06-06 14:23:16 +05:30
Debanjum Singh Solanky
dd2225b1aa Use Text output mode to disambiguate from Default data source lookup 
Previously if default output was selected by Khoj, we'd end up doing
an documents search as well, even when Khoj selected internet or
general data source to lookup.

This update disambiguates the default information mode from the text
output mode. To avoid doing documents search when not deemed necessary
by Khoj
 2024-06-06 11:56:48 +05:30
Debanjum Singh Solanky
a1e4f4bde7 Gracefully skip indexing when empty list of docs provided 
Improve error message when fail to index content
 2024-06-05 19:39:15 +05:30
Debanjum Singh Solanky
21987f60c7 Use `-difference' to get files to delete. Make batch size defcustom 
Improve docstrings to align with `checkdoc' requirement for all args
being mentioned
 2024-06-05 19:39:15 +05:30
Debanjum
bfacd65971 Batch upload files for indexing from the Emacs client (#735) from yuzhou721/master 
Encode filenames and batch file uploads to improve sending content to index from the Emacs client
 2024-06-05 19:31:06 +05:30
sabaimran
a9c383e62c Use an ASGI application, rather than WSGI 
- ASGI should be the preferred application, as our codebase runs a lot of async code
 2024-06-05 09:25:08 +05:30
sabaimran
0816cec4bc Manually close old db connections periodically 2024-06-04 22:19:47 +05:30
sabaimran
acfdc8da77 Explicitly set the connection age to 0 in the django settings. Seems to be some strange behavior with async gunicorn + django db 2024-06-04 20:31:51 +05:30
Debanjum Singh Solanky
85a343363b Release Khoj version 1.13.0 2024-06-04 11:57:44 +05:30
Debanjum
1dfd6d7391 Merge pull request from GHSA-h2q2-vch3-72qm 
Add CSP and sanitize chat messages in Obsidian, Desktop, Web apps
 2024-06-04 11:29:21 +05:30
Debanjum Singh Solanky
b757ba664f Sanitize chat messages to render in Obsidian, Desktop, Web apps 
Use DOMPurify to escape any unsafe HTML in chat message before adding
it to DOM via innerHTML updates to a HTML element
 2024-06-04 10:53:30 +05:30
Debanjum Singh Solanky
9f80c2ab76 Enforce Content-Security-Policy (CSP) in Obsidian, Desktop, Web apps 
Prevent XSS attacks by enforcing Content-Security-Policy (CSP) in apps.
Do not allow loading images, other assets from untrusted domains.

- Only allow loading assets from trusted domains
  like 'self', khoj.dev, ipapi for geolocation, google (fonts, img)
  - images from khoj domain, google (for profile pic)
  - assets from khoj domain
  - Do not allow iframe src
  - Allow unsafe-inline script and styles for now as markdown-it escapes html
    in user, khoj chat

- Add hostURL to CSP of the Desktop, Obsidian apps
  Given web client is served by khoj server, it doesn't need to
  explicitly allow for khoj.dev domain. So if user self-hosting, it'll
  automatically allow the domain in the CSP (via 'self')

  Whereas the Obsidian, Desktop clients allow configure the server URL.
  Note *switching server URL breaks CSP until app is reloaded*
 2024-06-04 10:53:30 +05:30
Debanjum Singh Solanky
179c70dba8 Upgrade Khoj llama-cpp, django and jinja dependencies 2024-06-04 09:05:53 +05:30
Debanjum Singh Solanky
bbcdb8413d Add null checks, fix build errors in Khoj plugin on newer Obsidian 2024-06-03 18:03:11 +05:30
Debanjum Singh Solanky
d8ace4d34c Highlight the agents, automation tab when active on the web app 2024-06-03 16:57:03 +05:30
sabaimran
4679f07336 Clean up some of the design of agents, inspired by dicussion #792 2024-06-03 12:52:07 +05:30
Debanjum Singh Solanky
8cdab5f31a Update slash command UX in chat UI of desktop app to match web app 
Make commands in popup menu on typing slash in chat input selectable
 2024-06-02 17:27:37 +05:30
Debanjum Singh Solanky
7828bd6f2e Hide command popup & focus on chatInput on selecting command in web app 
Style command popup cursor and add highlight to indicate using slash
command
 2024-06-02 17:27:37 +05:30
Debanjum
cf8c9c2a3d Serve image assets from Khoj domain, not directly from S3 bucket (#734) 
- Serve generated images from Khoj domain instead of directly from AWS S3
- Rename assets URL from Khoj S3 bucket to assets.khoj.dev
 2024-06-02 17:24:35 +05:30
sabaimran
5bb3689562 Do not stream responses in the scheduled_chat response 2024-06-02 11:31:15 +05:30
sabaimran
5132b01ab1 Remove intent_type from telemetry update in api_chat 2024-06-02 10:21:38 +05:30
Raghav Tirumale
a3934b3aaa Improved Command Menu and Help Command (#774) 
* The command menu (triggered by "/") now has a clickable list of possible commands, that automatically fill into the chat when pressed.
* The `/help` command now searches `khoj.dev` pages to provide useful assistance to the user.

---------

Co-authored-by: raghavt3 <raghavt3@illinois.edu>
Co-authored-by: sabaimran <65192171+sabaimran@users.noreply.github.com>
 2024-06-01 22:33:31 +05:30
sabaimran
6d10f98498 Add additional lines for KHOJ_NO_HTTPS and KHOJ_DOMAIN in the docker-compose 2024-06-01 21:48:43 +05:30
sabaimran
841cbff249 Add documentation for setting up google auth in self-hosted khoj. Closes #771 2024-06-01 21:38:21 +05:30
sabaimran
89178bcebd Fix formatting issues for task email in mobile 2024-06-01 14:19:12 +05:30
Debanjum
b499b3fe2a Upgrade Khoj Obsidian: Chat from Side Pane, Stream Intermediate Steps, Copy Message to Clipboard (#736) 
### Details
- **Chat with Khoj from right pane on Obsidian**
  - Modal was too ephemeral, couldn't have it open for reference, quick jump to Khoj chat
- **Stream intermediate steps taken by Khoj** for generating response to the chat pane
  Gives more transparency into Khoj 'thinking' process, e.g internet, notes searches performed, documents read etc. 
  The feedback allows us to tune our messages to elicit better responses by Khoj
- Add ability to **copy message to clipboard, paste chat messages directly into current file**
- Jump to **Search**, **Find Similar** functions from navigation bar on the Khoj Obsidian side pane
- Improve spacing, use consistent colors in chat message references and buttons

Resolves #789, #754
 2024-06-01 13:29:21 +05:30
sabaimran
8b9c26c468 Remove unused method 2024-06-01 12:54:43 +05:30
sabaimran
5ec641837a Allow automations to be shareable (#790) 
* Updating the API / UI to support sharing of automations
* Allow people to see the automations even when not logged in, and add an overlay effect
* Handle unauthenticated users taking actions
* Support showing pre-filled automation details on the config automations page
* Redirect user to login if they try to add an automation while unauthenticated
 2024-06-01 12:44:49 +05:30
Debanjum Singh Solanky
7d7d4cf5c3 Make new chat message text selectable in Obsidian side pane 
Resolves #789
 2024-06-01 11:01:39 +05:30
Debanjum Singh Solanky
7fb7f200b3 Fix rendering text in chat messages with bulleted lists 
Improves #789
 2024-06-01 10:51:22 +05:30
Debanjum Singh Solanky
7a93599fe8 Merge branch 'master' into upgrade-khoj-on-obsidian 
- Conflicts:
  - src/khoj/interface/web/chat.html
    Use our changes with feedback button changes from master
 2024-06-01 10:07:43 +05:30
Debanjum Singh Solanky
92bab9fa61 Get Conversation session action buttons out from under the three dot menu 2024-05-31 20:11:00 +05:30
Debanjum Singh Solanky
7fa42daf89 Render action buttons for new Khoj chat responses in Obsidian 
- Dedupe the code to add action buttons to chat messages
- Update the renderIncrementalMessage function to also add the action
  buttons to newly generated chat messages by Khoj
 2024-05-31 20:11:00 +05:30
Debanjum Singh Solanky
2d010db83f Toggle chat session view on clicking the Obsidian chat sessions button 2024-05-31 20:11:00 +05:30
Debanjum Singh Solanky
275d4877a6 Fix loading spinner visibility by using contrasting background color 
Fix code formating of Khoj chat view in Obsidian
 2024-05-31 20:09:24 +05:30
sabaimran
2667ef4544 Refresh the conversation from the db in the websocket flow 2024-05-31 16:15:56 +05:30
sabaimran
fd07abbfc8 Decrease the life of one connection 2024-05-31 15:39:15 +05:30
Debanjum
3090b84252 Disable Minutely Recurrence for Automations (#781) 
* Disable automation recurrence at minute level frequency

* Set a max lifetime for django's connections to the db

* Disable any automation that has a non-numeric first digit (i.e., recuring on the minute level)

* Re-enable automations

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-05-31 12:50:19 +05:30
sabaimran
5dca48d9fc Fix setting of conn_max_age variable 2024-05-31 11:07:13 +05:30
sabaimran
76f941f4e5 Revert email from from to sender again in resend API. keeps switching? 2024-05-31 10:30:18 +05:30
sabaimran
b27f59b12b Remove all unused code related to websockets 2024-05-30 11:39:04 +05:30
sabaimran
4b3d3fe7ea /s/sender/from in resend calls 2024-05-30 08:43:46 +05:30
sabaimran
2076543e32 Disable AP Scheduler while performing maintenance 2024-05-30 08:02:59 +05:30
sabaimran
4aac84e1c1 Pin rsesend verison in pyproject.toml 2024-05-30 07:05:11 +05:30
Debanjum Singh Solanky
7823ef09dc Simplify conditional code. Improve logs to track conversion progress 2024-05-29 17:50:07 +05:30
Debanjum Singh Solanky
215db8cab3 Reduce log level of noisy process lock logs 2024-05-29 13:14:44 +05:30
Debanjum Singh Solanky
7b18919564 Tag external links to open in a separate window on the Desktop app 
Previously clicking inline links would open the URL directly in the
Desktop app. This was strange and it didn't provide any way to go back
to Khoj desktop app UI from the opened link
 2024-05-29 10:12:50 +05:30
Debanjum Singh Solanky
c957a6cb43 Delete unused base_processor_integration html file from web interface 2024-05-29 08:30:13 +05:30
sabaimran
7dd72c1d25 Fix trailing whitespace issue in development.mdx 2024-05-29 04:36:46 +05:30
sabaimran
cb33fb67fe Remove the automations-related dead code in the web config 2024-05-29 04:22:45 +05:30
Debanjum Singh Solanky
15c5873c20 Provide more context in docs for self-hosting Khoj on Windows 2024-05-28 20:56:26 +05:30
Debanjum Singh Solanky
7594401461 Fix expand chat reference animation in web, desktop, obsidian clients 2024-05-28 20:56:26 +05:30
Debanjum Singh Solanky
1ea7675fc9 View, switch chat sessions from Obsidian chat pane 2024-05-28 20:33:39 +05:30
Debanjum Singh Solanky
e86899eec4 Click on referenced notes by Khoj chat to open it in Obsidian vault 
Allow opening Khoj chat references in Obsidian vault if the reference
is a heading or file in the current Obsidian vault
 2024-05-28 10:16:40 +05:30
Debanjum
39faae68c0 Merge pull request #768 from MythicalCow/documentation/windows-development-fixes 
Documentation Fixes for Development Page
 2024-05-28 00:26:15 +05:30
Raghav Tirumale
4a8920f9a4 formatting fix 2024-05-27 12:52:08 -05:00
Raghav Tirumale
9a11a3cd63 Added installation notes for windows users and added postgres setup instructions. 2024-05-27 12:49:52 -05:00
Desmond
70fea6c6b6 fix: delete file request 2024-05-27 14:46:26 +08:00
sabaimran
607534021b Add a link to github in the settings menu, improve styling 2024-05-27 11:39:30 +05:30
Desmond
3f49b5a4ab fix: emacs tests 2024-05-27 10:42:09 +08:00
sabaimran
b97ca9d19d Skip using max_tokens as input to the extract questions step, as that's not used for max_output 2024-05-27 01:23:54 +05:30
sabaimran
9ebf3a4d80 Improve the admin experience, add more metadata to the list_display 
- Don't propagate max_tokens to the openai chat completion method. the max for the newer models is fixed at 4096 max output. The token limit is just used for input
 2024-05-27 00:49:20 +05:30
sabaimran
01cdc54ad0 Add support for Anthropic models (#760) 
* Add support for chatting with Anthropic's suite of models

- Had to use a custom class because there was enough nuance with how the anthropic SDK works that it would be better to simply separate out the logic. The extract questions flow needed modification of the system prompt in order to work as intended with the haiku model
 2024-05-26 22:50:34 +05:30
Debanjum Singh Solanky
0f796a79ec Extract function to get link to entry in Obsidian vault for reuse 2024-05-26 18:03:15 +05:30
Debanjum Singh Solanky
e24ca9ec28 Pass file path of each doc reference in references returned by API 
- Pass file path of reference along with the compiled reference in
  list of references returned by chat API converts
- Update the structure of references from list of strings to list of
  dictionary (containing 'compiled' and 'file' keys)
- Pull out the compiled reference from the new references data struct
  wherever it was is being used
 2024-05-26 18:02:11 +05:30
Debanjum Singh Solanky
ba330712f8 Fix to always pass online results in chat API response 2024-05-26 13:56:55 +05:30
Debanjum Singh Solanky
38d8d2bb56 Show online references used to generate response in Obsidian chat view 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
f495d338eb Modularize render message with references func in web based clients 
Simplify, reuse, standardize code to render messages with references
in the obsidian, web and desktop clients. Specifically:

- Reuse function to create reference section, dedupe code
- Create reusable function to generate image markdown
- Simplify logic to render message with references
 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
14a2006c76 Stream steps taken to generate response in Obsidian chat pane 
- Setup websocket using Khoj web app as reference.
- Moved the geolocating code to chat view out from the general pane
  view
- Use loading spinner from web instead of the thinking emoji
 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
afcd22d30c Improve spacing, colors of chat message references and buttons 
Works better with dark modes. References have more spacing and adhere
to background color of the chat message itself
 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
bd4931e70b Add ability to paste chat messages directly into current file 
It'll replace any highlighted text with the chat message or if not
text is highlighted, it'll insert the chat message at the last cursor
position in the active file
 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
032ad3b521 Add ability to copy messages to clipboard from Obsidian Khoj chat 2024-05-26 13:55:22 +05:30
Debanjum Singh Solanky
57f1c53214 Create Nav bar for Obsidian pane. Use abstract View class for reuse 
- Jump to chat, show similar actions from nav menu of Khoj side pane
  - Add chat, search icons from web, desktop app
  - Use lucide icon for find similar (for now)
  - Match proportions of find similar icon to khoj other icons via css, js

- Use KhojPaneView abstract class to allow reuse of common functionality like
  - Creating the nav bar header in side pane views
  - Loading geo-location data for chat context
  This should make creating new views easier
 2024-05-26 13:55:22 +05:30
sabaimran
e2922968d6 Move some gifs to the assets s3 bucket and add instructions for Ollama, shareable conversations 2024-05-25 01:08:20 +05:30
sabaimran
e23c803cee Release Khoj version 1.12.1 2024-05-24 21:42:03 +05:30
sabaimran
0308699849 Use links from assets.khoj.dev to render images in the automations page 2024-05-24 20:18:02 +05:30
sabaimran
3f9c20a399 Make it easier to manage server-level chat settings (#729) 
* Add support for server-wide model settings fix web page reading results returning logic
 2024-05-24 20:15:18 +05:30
sabaimran
cbbbe2da9a Add a schedule picker and automations preview func (#747) 
* Update suggested automations
* add a schedule picker when creating an automation
* Create a new conversation in flow of the automation scheduling in order to send a preview and deliver more consistent results
* Start adding in scaffolding to manually trigger a test job for an automation
* Add support for manually triggering automations for testing
* Schedule automation asynchronously
* Update styling of the preview button
* Improve admin lookup experience and prevent jobs from being scheduled to run every minute of everyday
* Ignore mypy issues on job info short description
 2024-05-24 19:42:47 +05:30
Ikko Eltociear Ashimine
ac3e5089a2 docs: update typo in desktop.md (#744) 
reponses -> responses
 2024-05-24 03:52:03 +05:30
Md. Shahnewaz Siddique
3af06a3d5a Updated installation instructions for windows, linux in readme (#741) 2024-05-24 03:51:25 +05:30
sabaimran
4511c6ae7c Fix bug in chat feedback flow - user message not included during live chat 2024-05-21 14:55:39 -05:00
Desmond
a3c6045328 Merge remote-tracking branch 'origin/master' 2024-05-21 21:55:53 +08:00
Desmond
b0630c1a98 Simplify partition 2024-05-21 21:52:01 +08:00
sabaimran
0b7910d4af Pin th elangchain-community version explicitly 2024-05-21 05:26:17 -05:00
Raghav Tirumale
d57772f9e7 Add Feedback Buttons on Chat (#721) 
### Description and Rationale for Changes
This feature includes thumbs up and thumbs down buttons on Khoj's chat responses that provide automated feedback. When a thumbs up/down button is clicked, the code sends an email to team@khoj.dev with the following:
* user query
* khoj's response
* whether the sentiment of the user was good or bad. 

This is critical in improving Khoj's nondeterministic LLM model for a better user experience.
### List of Changes
* new endpoint in `api_chat.py` (/feedback) that can be used to trigger mail sending).
* thumbs up and thumbs down buttons implemented in `chat.html`
* new function in `routers/email.py` to handle feedback email sending via resend
* `feedback.html` template for a formatted email with the feedback.

---------

Co-authored-by: mythicalcow <mythicalcow@linux.myguest.virtualbox.org>
Co-authored-by: sabaimran <narmiabas@gmail.com>
 2024-05-20 16:29:08 -05:00
Debanjum
f941948d11 Merge pull request #738 from joshavant/patch-1 
Improve telemetry.md disabling instructions in docs
 2024-05-17 21:43:42 +05:30
Josh Avant
37ad1d5397 Update telemetry.md disabling instructions 2024-05-15 15:18:00 -05:00
sabaimran
7feaf34702 Fix capitalization, update suggeted prompt 2024-05-10 02:36:13 -07:00
sabaimran
b545aceb47 Use a simpler example for the sample automation and put schedule on top of instructions 2024-05-09 13:53:19 -07:00
sabaimran
2b8e5a86cc Update version for resent library in pyproject.toml 2024-05-09 13:43:27 -07:00
sabaimran
7ae00832bd Rname from parameter to sender in resend call 2024-05-09 13:29:39 -07:00
sabaimran
fbd76f8ebe Improve the UX of automations (#737) 
* Improve the automations UX

- Add suggested jobs to elimiinate some of the cold start problem
- Make each of the tasks cards that are clickable/editable

* Hide suggested automations that have already been added

* Add a footer and reapply styling when a save action is taken on a card
 2024-05-09 01:29:48 -07:00
sabaimran
70d0ee4310 Only remove the process lock from a process that created it 2024-05-08 10:14:52 -07:00
Desmond Deng
20303feb3a Merge branch 'khoj-ai:master' into master 2024-05-08 13:46:34 +08:00
Desmond
150cd18bf3 Update batch-size 2024-05-08 13:44:22 +08:00
Desmond
192cd53003 Batch send of index files 2024-05-08 13:38:40 +08:00
sabaimran
a50deb2762 Add better handling for empty responses 2024-05-07 11:49:33 -07:00
sabaimran
4aed6bd274 Add an admin view for subscriptions 2024-05-07 11:48:52 -07:00
sabaimran
77626d28d1 Include stack trace when automation is not successfully craeted 2024-05-07 06:52:41 -07:00
sabaimran
0c8c565ab0 Don't include the whole stack trace for an integrity error 2024-05-07 06:48:18 -07:00
Debanjum Singh Solanky
0a1a6cd041 Get detailed user info in Obsidian from the new v1/user API 
Previously we were just getting user email from the /health API
Instead store the retrieved user info in the user settings
 2024-05-07 04:37:26 +08:00
Debanjum Singh Solanky
f8f9d066db Focus on input field, scroll to latest message on opening chat pane 
Previously scroll and chat input focus weren't applied as view hadn't
been rendered yet
 2024-05-07 04:37:26 +08:00
Debanjum Singh Solanky
9f65e8de98 Open Khoj Chat as a Pane instead of a Modal 
- Allows having it open on the side as you traverse your Obsidian notes
- Allow faster time to response, having responses visible for context
- Enables ambient interactions
 2024-05-07 04:37:26 +08:00
sabaimran
9ae828cf11 Use asssets.khoj.dev for loading math katex rendering 2024-05-07 01:43:46 +08:00
sabaimran
cf0b7628d0 Add the url scheme to the public share url 2024-05-06 21:37:49 +08:00
sabaimran
f6aaecb04f Fix construction method for public share conversation URL 2024-05-06 08:32:51 +05:30
sabaimran
14c9bea663 Make conversations optionally shareable (#712) 
* Make conversations optionally shareable

- Shared conversations are viewable by anyone, without a login wall
- Can share a conversation from the three dot menu
- Add a new model for Public Conversation
- The rationale for a separate model is that public and private conversations have different assumptions. Separating them reduces some of the code specificity on our server-side code and allows us for easier interpretation and stricter security. Separating the data model makes it harder to accidentally view something that was meant to be private
- Add a new, read-only view for public conversations
 2024-05-05 23:16:04 +05:30
Debanjum Singh Solanky
80cbaca935 Serve generated images from Khoj domain instead of directly from S3 
Use CNAME to forward requests from the khoj subdomain to the
equivalent S3 bucket
 2024-05-04 20:07:10 +05:30
Debanjum Singh Solanky
425496844b Rename assets URL from Khoj S3 bucket to assets.khoj.dev 
Server khoj assets from khoj domain
 2024-05-04 20:07:10 +05:30
sabaimran
88daa841fd Rename process lock migration and add a reverse migration step 2024-05-04 20:05:00 +05:30
sabaimran
509a8a412c Throw an error if trying to create a process lock that already exists. Names should be unique 2024-05-04 19:03:53 +05:30
sabaimran
7100614de5 Add support for rendering math equations in the web view (#733) 
- Add parsing logic for LaTeX-format math equations in the web chat
- Add placeholder delimiters when converting the markdown to HTML in order to avoid removing the escaped characters
- Add the `<!DOCTYPE html>` specification to the page
 2024-05-04 15:59:17 +05:30
Debanjum Singh Solanky
d9b3482b1a Show error when required fields to create automation are not set 2024-05-04 11:17:30 +05:30
Debanjum Singh Solanky
91a5643c5c Use Preview label for Automate feature. Prefix mailto: link to contact 2024-05-04 10:59:17 +05:30
Debanjum Singh Solanky
fd2328ab40 Do not hard code base url of path to automation icon in chat message 2024-05-04 10:59:07 +05:30
sabaimran
a38f3227e2 Revert domain in task task send emails 2024-05-03 15:27:27 +05:30
sabaimran
a1263951e9 Use mail to in email contact link 2024-05-03 12:16:56 +05:30
sabaimran
7c9847fe48 Increase jitter to 60 2024-05-03 11:38:22 +05:30
sabaimran
737ebfd521 Make improvements to online search prompts and use a custom domain for automations emails 2024-05-03 10:47:42 +05:30
sabaimran
42e9504ba8 Use a different function for getting last run time, avoid async/sync issues 2024-05-02 12:13:45 +05:30
sabaimran
9e8491b814 Add experimental disclaimers to the automations 2024-05-02 11:40:37 +05:30
sabaimran
c418449311 Add additional robustness in verifying job execution parameters at run time 2024-05-02 11:13:04 +05:30
sabaimran
690e9d8ed3 Collapse the reminders after they're successfully scheduled 2024-05-02 09:55:04 +05:30
sabaimran
6b648ee3ad Add experimental disclaimer in the automation page 2024-05-02 09:21:27 +05:30
sabaimran
f4fbc91515 Remove the exclamation point from the email 2024-05-01 19:01:51 +05:30
sabaimran
bddd1d0fcb Quip, smart reminders 2024-05-01 16:39:07 +05:30
sabaimran
bc8b92a77d Release Khoj version 1.12.0 2024-05-01 16:30:48 +05:30
sabaimran
9d02c354dd Merge pull request #732 from khoj-ai/fit-and-finish/schedule-tasks 
Fixes and improves for scheduled tasks
 2024-05-01 03:16:09 -07:00
sabaimran
b499851097 Use the cleaned query as the reference query in the email notification 2024-05-01 15:33:11 +05:30
sabaimran
f24495e0e6 Fix time zone used in query history. Closes #694 2024-05-01 15:31:48 +05:30
sabaimran
7fd57d737e Adjustments to improve overall styling of config page, email template 2024-05-01 14:19:47 +05:30
sabaimran
28578310d1 Add log line when sending a task-related email 2024-05-01 13:56:02 +05:30
sabaimran
a86f95117e Add the subject generation prompt and helper method 2024-05-01 13:55:32 +05:30
sabaimran
c30ba2e551 Set subject dynamically when creating new tasks, and make some minor improvments to the automations UI 2024-05-01 13:54:59 +05:30
sabaimran
d1b2037676 Shutdown the scheduler when the application is exiting 2024-05-01 13:53:34 +05:30
Debanjum
10f623154e Enable Creating Automations from Khoj (#731) 
## Support Scheduling Automations (#695) 
   1. Detect when user intends to schedule a task, aka reminder
      - Support new `reminder` output mode to the response type chat actor
      - Show examples of selecting the reminder output mode to the response type chat actor
   2. Extract schedule time (as cron timestring) and inferred query to run from user message
   3. Use APScheduler to call chat with inferred query at scheduled time

## Make Automations Persistent (#714) 
  - Make scheduled jobs persistent and work in multiple worker setups
  - Add new operation Scheduled Job to Operation enum of ProcessLock

## Add UX to Configure Scheduled Tasks (#715)
  - Add section in settings page to view, delete your scheduled tasks
  - Add API endpoints to get and delete user scheduled tasks

## Make Automations more Robust. Improve UX (#718)
  - Decouple Task Run from User Notification
  - Make Scheduling more Robust
    - Use JSON mode to get parse-able output from chat model
    - Make timezone calculation programmatic on server instead of asking chat model
    - Use django-apscheduler to handle apscheduler and django interfacing
  - Improve automation UX. Move it out into separate top level page
    - Allow creating, modifying automations from the automations page
    - Infer cron from natural language client side to avoid roundtrip
 2024-05-01 11:08:19 +05:30
Debanjum Singh Solanky
89a8dbb81a Fix edit job API. Use user timezone, pass all reqd. params to automation 
- Pass user and calling_url to the scheduled chat too when modifying
  params of automation
- Update to use user timezone even when update job via API
- Move timezone string to timezone object calculation into the
  schedule automation method
 2024-05-01 10:29:49 +05:30
Debanjum Singh Solanky
19c5af3ebc Handle natural language to cron translation error on web client 2024-05-01 09:10:18 +05:30
Debanjum Singh Solanky
70ee9ddf91 Merge migrations from main with feature branch 2024-05-01 09:10:18 +05:30
Debanjum Singh Solanky
8f28f6cc1e Remove now unused location data from being passed to automation funcs 2024-05-01 08:48:16 +05:30
Debanjum Singh Solanky
815966cb25 Unify, modularize DB adapters to get automation metadata by user further 2024-05-01 08:47:50 +05:30
Debanjum Singh Solanky
21bdf45d6f Add link to Automate page in nav pane of the web app 2024-05-01 08:47:50 +05:30
Debanjum Singh Solanky
bd5008136a Move automations into independent page. Allow direct automation 
- Previously it was a section in the settings page. Move it to
  independent, top-level page to improve visibility of feature

- Calculate crontime from natural language on web client before
  sending it to to server for saving new/updated schedule to disk.
  - Avoids round-trip of call to chat model

- Convert POST /api/automation API endpoint into a direct request for
  automation with query_to_run, subject and schedule provided via the
  automation page. This allows more granular control to create automation
  - Make the POST automations endpoint more robust; runs validation
    checks, normalizes parameters
 2024-05-01 08:47:48 +05:30
Debanjum Singh Solanky
cbc8a02179 Make, use func for constructing the automation created response 
- Dedupe logic across http, ws chat API endpoints
- Reduces size of already too long http, ws chat API endpoint funcs
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
c52ed333fa Make content, cards on config pages occupy the whole middle column 
- Make the config page content use  the same top level 3-column layout
  as the khoj-header-wrapper
  This ensures the content is aligned with heading pane width
- Let cards and other settings sections scale to the width of their
  grid element. This utilizes more of the screen space and does it
  consistently across the different settings pages
 2024-05-01 08:30:10 +05:30
sabaimran
ad4145e48c Fix unique has for job id 2024-05-01 08:30:10 +05:30
sabaimran
311d58e1ed Ensure the automated_task command is removed from the prepended query 2024-05-01 08:30:10 +05:30
sabaimran
eb65532386 Use Django ap scheduler in place of the sqlalchemy one 2024-05-01 08:30:10 +05:30
sabaimran
06213ea814 Fix token retrieval when executing the job and name async job approriately 2024-05-01 08:30:10 +05:30
sabaimran
ca8a7d8368 Revert sync -> aync in send welcome email method 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
6936875a82 Use DB adapter to unify logic to get, delete automation by auth user 
To use place with logic to get, view, delete (and edit soon) automations
by (authenticated) user, instead of scattered across code
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
1238cadd31 Allow editting query-to-run from the automation config section 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
cb2b1dccc5 Add icon for Automation feature. Replace old icons for delete, new 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
23f2057868 Allow creating automations from automation settings section in web ui 
- Create new POST API endpoint to create automations
- Use it in the settings page on the web interface to create
  new automations

This simplified managing automations from the setting page by allowing
both delete and create from the same page
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
2f9241b5a3 Rename scheduled task to automations across code and UX 
- Fix query, subject parameters passed to email template
- Show 12 hour scheduled time in automation created chat message
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
230d160602 Improve rendering task scheduled settings view and message 
- Render crontime string in natural language in message & settings UI
- Show more fields in tasks web config UI
- Add link to the tasks settings page in task scheduled chat response
- Improve task variables names
  Rename executing_query to query_to_run. scheduling_query to
  scheduling_request
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
d341b1efe8 Store, retrieve task metadata from the job name field 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
ae10ff4a5f Create create_scheduled_task func to dedupe logic across ws, http APIs 
Previously, both the websocket and http endpoint were implementing
the same logic. This was becoming too unwieldy
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
8dfa0bf047 Simplify task scheduler prompt. No timezone conversion. Infer subject 
- Make timezone aware scheduling programmatic, instead of asking the
  chat model to do the conversion. This removes the need for
  scratchpad and may let smaller models handle the task as well
- Make chat model infer subject for email. This should make the
  notification email more readable
- Improve email by using subject in email subject, task heading. Move
  query to email final paragraph, which is where task metadata  should
  go
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
2c563ad280 Use hash of query in process lock id to standardize id format 
- Using inferred_query directly was brittle (like previous job id)
- And process lock id had a limited size, so wouldn't work for larger
  inferred query strings
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
3ce06a938c Render scheduled task response as html to improve readability in email 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
c17dbbeb92 Render next run time in user timezone in config, chat UIs 
- Pass timezone string from ipapi to khoj via clients
  - Pass this data from web, desktop and obsidian clients to server
- Use user tz to render next run time of scheduled task in user tz
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
6736551ba3 Improve scheduled task text rendered in UI 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
0e01362469 Merge DB migrations from master with those from scheduled task feature 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
a5ed4f2af2 Send email to share results of scheduled task 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
69775b6d6e Add /task command. Use it to disable scheduling tasks from tasks 
This takes the load of the task scheduling chat actor / prompt from
having to artifically differentiate query to create scheduled task
from a scheduled task run.
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
22289a0002 Improve task scheduling by using json mode and agent scratchpad 
- The task scheduling actor was having trouble calculating the
  timezone. Giving the actor a scratchpad to improve correctness by
  thinking step by step
- Add more examples to reduce chances of the inferred query looping to
  create another reminder instead of running the query and sharing
  results with user
- Improve task scheduling chat actor test with more tests and
  by ensuring unexpected words not present in response
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
7f5981594c Only notify when scheduled task results satisfy user's requirements 
There's a difference between running a scheduled task and notifying
the user about the results of running the scheduled task.

Decide to notify the user only when the results of running the
scheduled task satisfy the user's requirements.

Use sync version of send_message_to_model_wrapper for scheduled tasks
 2024-05-01 08:30:10 +05:30
Debanjum Singh Solanky
7e084ef1e0 Improve job id. Fix refreshing list of jobs on delete from config page 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
a1e5195c8b Save separate user message time from Khoj response time in chat logs 
Previously user message time was being stored the same as Khoj
response time in conversation logs.
 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
5133b6e73b Minor improvements to styling the config page 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
648f1a5c71 Suffix chat response element vars with "El" in chat.html of web, desktop apps 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
98d0ffecf1 Add section in settings page to view, delete your scheduled tasks 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
423d61796d Add API endpoints to get and delete user scheduled tasks 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
af0972c539 Make scheduled jobs persistent and work in multiple worker setups 
- Store scheduled job state in Postgres so job schedules persist
  across app restarts
- Use Process Locks to only allow single worker to process a given job
  type. This prevents duplicating job runs across all workers
 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
fcf878e1f3 Add new operation Scheduled Job to Operation enum of ProcessLock 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
c28d7d3414 Add basic chat actor test to infer scheduled queries 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
c11742f443 Add chat actor to schedule run query for user at specified times 
- Detect when user intends to schedule a task, aka reminder
  Add new output mode: reminder. Add example of selecting the reminder
  output mode
- Extract schedule time (as cron timestring) and inferred query to run
  from user message
- Use APScheduler to call chat with inferred query at scheduled time
- Handle reminder scheduling from both websocket and http chat requests

- Support constructing scheduled task using chat history as context
  Pass chat history to scheduled query generator for improved context
  for scheduled task generation
 2024-05-01 08:28:59 +05:30
Debanjum Singh Solanky
9e068fad4f Handle null ref, when refresh conversation from db in websocket chat 2024-04-30 14:19:07 +05:30
sabaimran
37879a7850 Release Khoj version 1.11.2 2024-04-30 13:31:06 +05:30
sabaimran
93b41170d1 Refresh the conversation log from the db before addressing the next query 2024-04-30 13:27:51 +05:30
Debanjum Singh Solanky
f1545d2b2f Add, fix help link, improve title style in web ui config pages 
- Align title text with icon better in all config cards
- Fix help link to github setup docs
- Fix help link to notion setup docs
 2024-04-30 05:50:08 +05:30
Debanjum Singh Solanky
e6da0f9a8c Fix response type of delete client tokens API endpoint 
Previously the make delete API response failed, after deleting token.
Required a page refresh to see that the API token was actually gone.

This was happening because the response type of the delete token API
endpoint isn't a string, so it failed FastAPI response validation
checks.
 2024-04-30 02:46:52 +05:30
sabaimran
0f4c3518d3 Allow session cookies to be stored with a lax policy for some localhost scenarios 2024-04-29 15:48:45 +05:30
sabaimran
5beedc9734 Use Secure proxy ssl header only if no https 2024-04-29 15:33:21 +05:30
sabaimran
408f4780ce Add and update documentation for setting up khoj with an openai proxy server or offline llm 2024-04-27 20:16:32 +05:30
sabaimran
12258f02d7 Release Khoj version 1.11.1 2024-04-27 18:42:24 +05:30
sabaimran
2047b0c973 Support customization of the OpenAI base url in admin settings (#725) 
- Allow self-hosted users to customize their open ai base url. This allows you to easily use a proxy service and extend support for other models.
- This also includes a migration that associates any existing openai chat model configuration with an openai processor configuration
- Make changing model a paid/subscriber feature
- Removes usage of langchain's OpenAI wrapper for better control over parsing input/output
 2024-04-27 18:24:35 +05:30
sabaimran
49834e3b00 Add a hero image for the og:image meta tag 2024-04-27 17:07:21 +05:30
sabaimran
138f12f957 Fix indentation and revert first run message link styling to all links 2024-04-27 09:56:58 +05:30
Debanjum Singh Solanky
4395ed8065 Improve extract_questions func. Set message role to user, not assistant 
Previous behavior of passing message with role = "assistant was
reducing instruction following quality of the model
 2024-04-26 11:55:22 +05:30
Debanjum Singh Solanky
346499f12c Fix, improve args being passed to chat_completion args 
- Allow passing completion args through completion_with_backoff
- Pass model_kwargs in a separate arg to simplify this
- Pass model in `model_name' kwarg from the send_message_to_model func
  `model_name' kwarg is used by langchain, not `model' kwarg
 2024-04-26 11:55:22 +05:30
sabaimran
d8f2eac6e0 Release Khoj version 1.11.0 2024-04-25 17:24:59 +05:30
Debanjum Singh Solanky
1842017393 Skip trying to index deleted files, folders from Desktop app 
Previously app would crash on startup if desktop app was told to
index a file that had been deleted afterwards
 2024-04-25 15:23:05 +05:30
Debanjum
17a06f152c Support Llama 3 and Improve Offline Chat Actors (#724) 
- Add support for Llama 3 in Khoj offline mode
- Make chat actors generate valid json with more local models
- Fix offline chat actor tests
 2024-04-25 14:00:56 +05:30
Debanjum
220e5516ab Make Search Models More Configurable. Upgrade Default Cross-Encoder (#722) 
- Upgrade default cross-encoder to mixedbread ai's mxbai-rerank-xsmall
- Support more embedding models by making query, docs encoding configurable
 2024-04-25 13:55:49 +05:30
Debanjum Singh Solanky
cf08eaf786 Add comments explaining each field in the search model config in DB 2024-04-25 13:54:13 +05:30
Debanjum
4ee5ac7c20 Fix Chat UI and Indexing on Desktop App (#723) 
- Make valid file extension checking case insensitive on Desktop app
- Skip indexing non-existent folders on Desktop app
- Pass auth headers to fix lazy load of chat messages on Desktop app
- Set chat-message height to height of content in web, desktop
 2024-04-24 18:49:03 +05:30
Debanjum Singh Solanky
89ef23de50 Upgrade gunicorn and make it only a production dependency 2024-04-24 11:28:55 +05:30
Debanjum Singh Solanky
799efb5974 Create DB migration to add new fields and change default cross-encoder 2024-04-24 09:50:34 +05:30
Debanjum Singh Solanky
ec41482324 Upgrade default cross-encoder to mixedbread ai's mxbai-rerank-xsmall 
Previous cross-encoder model was a few years old, newer models should
have improved in quality. Model size increases by 50% compared to
previous for better performance, at least on benchmarks
 2024-04-24 09:50:09 +05:30
Debanjum Singh Solanky
7eaf9367fe Support more embedding models by making query, docs encoding configurable 
Most newer, better embeddings models add a query, docs prefix when
encoding. Previously Khoj admins couldn't configure these, so it
wasn't possible to use these newer models.

This change allows configuring the kwargs passed to the query, docs
encoders by updating the search config in the database.
 2024-04-24 09:49:17 +05:30
Debanjum Singh Solanky
f2db8d7d99 Fix offline chat actor tests 
Do not check for original q in extracted questions. Since this was
removed in a previous commit
 2024-04-24 09:40:00 +05:30
Debanjum Singh Solanky
4f7237b158 Make chat actors generate valid json with more local models 
Improve tool, online search, webpage links, docs search chat actor
prompts. Ensure works with hermes-2-pro and llama-3.

Be more specific about generating JSON and not saying anything else.
 2024-04-24 09:40:00 +05:30
Debanjum Singh Solanky
a2e4e4bede Add support for Llama 3 in Khoj offline mode 
- Improve extract question prompts to explicitly request JSON list
- Use llama-3 chat format if HF repo_id mentions llama-3. The
  llama-cpp-python logic for detecting when to use llama-3 chat format
  isn't robust enough currently
 2024-04-24 09:40:00 +05:30
Debanjum Singh Solanky
8e77b3dc82 Fix infer_max_tokens func when configured_max_tokens is set to None 2024-04-24 09:36:29 +05:30
Debanjum Singh Solanky
8196ab62f9 Make valid file extension checking case insensitive on Desktop app 2024-04-24 09:35:20 +05:30
Debanjum Singh Solanky
5def14e3bb Skip indexing non-existent folders on Desktop app 2024-04-24 09:35:20 +05:30
Debanjum Singh Solanky
cd05f262a6 Pass auth headers to fix lazy load of chat messages on Desktop app 2024-04-24 09:35:20 +05:30
Debanjum Singh Solanky
4d5d3e6433 Set chat-message height to height of content in web, desktop 
In some cases, especially with image generation requests, this was
causing the chat messages to overlap in the chat UI
 2024-04-24 09:35:20 +05:30
sabaimran
60658a8037 Get rid of enable flag for the offline chat processor config 
- Default, assume that offline chat is enabled if there is an offline chat model option configured
 2024-04-23 23:08:29 +05:30
sabaimran
ac474fce38 Ensure that the tokenizer and max prompt size are used the wrapper method 2024-04-23 21:22:23 +05:30
Olatoyan George
ad59180fb8 Added indication in the desktop UI for back-end connectivity (#711) 
* Changed the styling of the link that takes a user to the settings page into a button
* added an indicator that shows if a user is connected to the server or not
* made a class name more descriptive and also made the text in first run message more intuitive
* changed the command to install dependencies in the README.md
* changed the class name of the first run message text to be more descriptive
* added icons in the desktop UI that shows if a file is synced successfully or not
* made the link class name in the homepage more descriptive
* fixed the hover issue on status box in the chat header pane
* fixed hovering issue on status box on macOS
 2024-04-23 16:43:48 +05:30
Debanjum
419b044ac5 Use set, inferred max token limits wherever chat models are used (#713) 
- User configured max tokens limits weren't being passed to
  `send_message_to_model_wrapper'
- One of the load offline model code paths wasn't reachable. Remove it
  to simplify code
- When max prompt size isn't set infer max tokens based on free VRAM
  on machine
- Use min of app configured max tokens, vram based max tokens and
  model context window
 2024-04-23 16:42:35 +05:30
AjaySDwivedi1
abf6f963ea Replaced reinitialize and save all button to a sync button in config.… (#701) 
Replaced reinitialize and save all button to a sync button in config
 2024-04-23 16:42:11 +05:30
Debanjum Singh Solanky
c39c4e4ec4 Improve prompt for online search query generation chat actor 
- Allow searching github, pypi for information about Khoj
- Enable creating multiple search queries by rewording prompt
 2024-04-22 01:32:11 +05:30
Debanjum Singh Solanky
175169c156 Use set, inferred max token limits wherever chat models are used 
- User configured max tokens limits weren't being passed to
  `send_message_to_model_wrapper'
- One of the load offline model code paths wasn't reachable. Remove it
  to simplify code
- When max prompt size isn't set infer max tokens based on free VRAM
  on machine
- Use min of app configured max tokens, vram based max tokens and
  model context window
 2024-04-20 11:23:28 +05:30
Debanjum Singh Solanky
002cd14a65 Only let agent use online search tool if connected to it 2024-04-20 11:19:48 +05:30
Debanjum Singh Solanky
75c9ebbc54 Only show uvicorn debug logs at higher verbosity levels 
Don't automatically show the uvicorn logs when in_debug_mode, only
show on at least verbosity = 2, i.e when start khoj with -vv flag
 2024-04-20 11:18:01 +05:30
sabaimran
c6d668bacf Bump gunicorn workers per server up to 2 2024-04-18 11:32:51 +05:30
sabaimran
c9a8abafa4 Merge pull request #710 from khoj-ai/add-run-with-process-lock-and-fix-edge-cases 
Extract run with process lock logic into func. Use it to re-index content
 2024-04-17 01:29:02 -07:00
sabaimran
6de4a4873a Fix image-related client unit test 2024-04-17 13:28:48 +05:30
sabaimran
3132430737 Add tests for the db lock 2024-04-17 13:22:41 +05:30
sabaimran
d11354f9c8 Remove additional references to image content config 2024-04-17 13:00:50 +05:30
sabaimran
105dbf49e4 Fix max_duration_in_seconds for the update_embeddings job 2024-04-17 13:00:18 +05:30
Debanjum Singh Solanky
8e0bae894d Extract run with process lock logic into func. Use for content reindexing 2024-04-17 12:31:19 +05:30
Debanjum Singh Solanky
e9f608174b Fix access to Khoj admin panel from non HTTPS custom domains 
To access the Khoj admin panel from a non HTTPS custom domain the
`KHOJ_NO_SSL' and `KHOJ_DOMAIN' env vars need to be explictly set.

See the updated setup docs for details.

Resolves #662
 2024-04-17 03:20:05 +05:30
sabaimran
46210695b6 pin version of huggingface hub explicitly to ensure relevant constants are present. Closes #708 2024-04-17 01:09:36 +05:30
sabaimran
b0059654c9 Do not create an import error if the resend module is not available 2024-04-17 01:00:22 +05:30
sabaimran
f04ead7c37 Remove seting up log line for configuring image search 2024-04-17 00:45:39 +05:30
sabaimran
0208688801 Increase factor for n_ctx reduciton to 2e6 2024-04-17 00:41:36 +05:30
Debanjum Singh Solanky
1f2ffce85b Copy chat message with it's markdown formatting in Web, Desktop apps 2024-04-16 22:10:34 +05:30
sabaimran
91c8b137f1 Add a database lock for jobs that shouldn't be run by multiple workers (#706) 
* Add a database lock for jobs that shouldn't be run by multiple workers

* Import relevant functions from utils.helpers
 2024-04-16 21:29:27 +05:30
sabaimran
adb2e8cc5f Check if n is populated before making a comparison 2024-04-16 02:05:58 +05:30
Debanjum Singh Solanky
6707ccc463 Check before updating "chat" key in meta_log in chat history API endpoint 2024-04-15 21:06:47 +05:30
Debanjum Singh Solanky
4e7812fe55 Use Django management cmd to update inline images in DB to/from WebP/PNG 
This provides Khoj server admins more control on migrating their S3
images to WebP format from PNG
 2024-04-15 20:19:49 +05:30
Debanjum Singh Solanky
7fab8d6586 Only use chat messages count in history API endpoint when set by client 2024-04-15 19:12:57 +05:30
Debanjum
6b3ef61dd2 Improve Chat Page Load Perf, Offline Chat Perf and Miscellaneous Fixes (#703) 
### Store Generated Images as WebP 
- 78bac4ae Add migration script to convert PNG to WebP references in database
- c6e84436 Update clients to support rendering webp images inline
- d21f22ff Store Khoj generated images as webp instead of png for faster loading

### Lazy Fetch Chat Messages to Improve Time, Data to First Render
This is especially helpful for long conversations with lots of images
- 128829c4 Render latest msgs on chat session load. Fetch, render rest as they near viewport
- 9e558577 Support getting latest N chat messages via chat history API

### Intelligently set Context Window of Offline Chat to Improve Performance
- 4977b551 Use offline chat prompt config to set context window of loaded chat model

### Fixes
- 148923c1 Fix to raise error on hitting rate limit during Github indexing
- b8bc6bee Always remove loading animation on Desktop app if can't login to server
- 38250705 Fix `get_user_photo` to only return photo, not user name from DB

### Miscellaneous Improvements
- 689202e0 Update recommended CMAKE flag to enable using CUDA on linux in Docs
- b820daf3 Makes logs less noisy
 2024-04-15 18:34:29 +05:30
Debanjum Singh Solanky
a352940dfd Use Django management command to update images URL in DB to WebP 
This provides Khoj server admins more control on migrating their S3
images to WebP format from PNG
 2024-04-15 17:53:41 +05:30
Debanjum Singh Solanky
7d8e8eb0cf Use Enum to type text-to-image intent of Khoj chat response 2024-04-15 17:53:40 +05:30
Debanjum Singh Solanky
128829c477 Show latest msgs on chat session load. Fetch rest as they near viewport 
- Reduces time to first render when loading long chat sessions
- Limits size of first page load, when loading long chat sessions

These performance improvements are maximally felt for large chat
sessions with lots of images generated by Khoj

Updated web and desktop app to support these changes for now
 2024-04-15 16:10:56 +05:30
Debanjum Singh Solanky
9e5585776c Support getting latest N chat messages via chat history API 
Get latest N if N > 0, else return all messages except latest N from
the conversation
 2024-04-15 15:32:32 +05:30
Debanjum Singh Solanky
e5ff85f6fb Start fetching khoj css before icons to reduce time with no styling 
This should reduce frequency of page load jitter when icons are loaded
before style is applied
 2024-04-15 15:32:32 +05:30
Debanjum Singh Solanky
d5de59d411 Do not assume results key present in notion content when indexing 2024-04-15 08:02:20 +05:30
Debanjum Singh Solanky
4977b55106 Use offline chat prompt config to set context window of loaded chat model 
Previously you couldn't configure the n_ctx of the loaded offline chat
model. This made it hard to use good offline chat model (which these
days also have larger context) on machines with lower VRAM
 2024-04-14 02:35:36 +05:30
Debanjum Singh Solanky
689202e00e Update recommended CMAKE flag to enable using CUDA on linux in Docs 2024-04-14 02:35:27 +05:30
Debanjum Singh Solanky
148923c13a Fix to raise error on hitting rate limit during Github indexing 2024-04-13 22:09:13 +05:30
sabaimran
f24d71c71c Improve the agents UX (#702) 
- Make the chat buttons look more clickable
- Show agent name in new conversation message
- Add an icon to the CTA to send agent a message
 2024-04-13 20:11:37 +05:30
Debanjum Singh Solanky
78bac4ae05 Add migration script to convert PNG to WebP references in database 2024-04-13 19:06:28 +05:30
Debanjum Singh Solanky
c6e8443631 Update clients to support rendering webp images inline 
This is for self-hosted scenarios where AWS S3 uploads is not enabled
 2024-04-13 13:11:18 +05:30
Debanjum Singh Solanky
d21f22ffa1 Store Khoj generated images as webp instead of png for faster loading 2024-04-13 13:03:32 +05:30
Debanjum Singh Solanky
b820daf38f Makes logs less noisy 
- Show telemetry enabled/disabled state on init, not every 2 minutes
- Convert no docs synced logs to debug level instead of warning
  Having synced docs isn't as important to use Khoj now, unlike before
 2024-04-13 11:22:58 +05:30
Debanjum Singh Solanky
b8bc6bee83 Always remove loading animation on Desktop app if can't login to server 2024-04-13 11:02:44 +05:30
Debanjum Singh Solanky
382507051f Fix get_user_photo to only return photo, not user name from DB 2024-04-13 11:02:30 +05:30
sabaimran
f06ec485cb Fix redirect url process for login flow, existing user 2024-04-12 17:10:05 +05:30
sabaimran
87b9a93fa1 Update assertion line to match new logic 2024-04-12 13:09:19 +05:30
sabaimran
b86e68a29d Make it easier to view agents in the admin page 2024-04-12 13:02:22 +05:30
sabaimran
e58bd0e485 Remove mbox file from list of files expected to be included 2024-04-12 12:55:22 +05:30
sabaimran
6634d603a8 Add links for contributors to use in the readme 2024-04-12 12:49:12 +05:30
sabaimran
1377a44a1a Suppress debug logs from uvicorn.error to avoid clutter from websockets 
- If application is not in DEBUG_MODE
 2024-04-12 12:12:16 +05:30
Debanjum Singh Solanky
89b8ec3546 Release Khoj version 1.10.2 2024-04-12 11:53:32 +05:30
Debanjum Singh Solanky
50b4788a91 Remove chat loading animation in login required state on Desktop app 2024-04-12 11:50:54 +05:30
Debanjum Singh Solanky
b3f4794d91 Remove the unnecessary async/await func chains on Desktop app 2024-04-12 11:49:25 +05:30
Debanjum Singh Solanky
1e30a072d4 Just use file ext to identify indexable files to fix Desktop app install 
- Magika on Desktop app was too bloated (100Mb to 250Mb) and broke
  install for some reason. Not sure why it was causing the app install
  to fail but do not have time to currently investigate

- Just use file extensions whitelist it's good enough for now. Let
  server handle the deeper identification of file type
 2024-04-12 11:16:07 +05:30
Debanjum Singh Solanky
5c7797dbca Only check content type if file extension cannot identify text file 2024-04-12 03:40:42 +05:30
Debanjum Singh Solanky
7d2ef728e6 Fix identifying pdf files on server 
Introduced bug in previous commit that would stop indexing PDF files
as trying to check content_group instead of mime_type is application/pdf
 2024-04-12 03:07:46 +05:30
Debanjum Singh Solanky
07f8fb5c5b Release Khoj version 1.10.1 2024-04-12 02:18:07 +05:30
Debanjum Singh Solanky
a7d9102c33 Make identifying text, code files with Magika more robust on server 
Use identified content group rather than mime_type to find text files.
 2024-04-12 02:12:26 +05:30
Debanjum Singh Solanky
60337086f9 Release Khoj version 1.10.0 2024-04-12 01:01:02 +05:30
Debanjum Singh Solanky
34c3f70203 Index only files with valid text extension in folders synced by Desktop app 
This maintains consistent set of indexable files from Desktop app,
whether indexing via file or folder filters
 2024-04-12 00:59:54 +05:30
Debanjum
9a48f72041 Index more text file types from Desktop, Github (#692) 
### Index more text file types 
- Index all text, code files in Github repos. Not just md, org files
- Send more text file types from Desktop app and improve indexing them
- Identify file type by content & allow server to index all text files

### Deprecate Github Indexing Features
- Stop indexing commits, issues and issue comments in a Github repo
- Skip indexing Github repo on hitting Github API rate limit

### Fixes and Improvements
- **Fix indexing files in sub-folders from Desktop app**
- Standardize structure of text to entries to match other entry processors
 2024-04-12 00:08:29 +05:30
Debanjum Singh Solanky
0819b83d0b Fix constructing status update strings for intermediate chat steps 2024-04-11 20:31:32 +05:30
Debanjum Singh Solanky
d15b9bc272 Tell doc search actor to not generate online queries for doc search 
This can pick up irrelevant details from notes
 2024-04-11 19:49:41 +05:30
Debanjum Singh Solanky
15a78b19ad Improve Inferred Document Search Query Extraction from GPT 
Using stop_words = "\n" was preventing JSON responses with newlines in
them
 2024-04-11 19:24:04 +05:30
Debanjum Singh Solanky
653681967e Show inferred document search queries in intermediate chat step on Web app 2024-04-11 19:24:04 +05:30
Debanjum Singh Solanky
997741119a Show better intermediate steps when responding to chat via web socket 
- Show internet search, webpage read, image query, image generation steps
- Standardize, improve rendering of the intermediate steps on the web app

Benefits:
1. Improved transparency, allow users to see what Khoj is doing behind
   the scenes and modify their query patterns to improve response quality
2. Reduced websocket connection keep alive timeouts for long running steps
 2024-04-11 18:04:40 +05:30
sabaimran
fae7900f19 Remove more 2024-04-11 00:27:44 +05:30
sabaimran
5d1dd3e2b7 If resend not enabled, don't send the welcome email 2024-04-10 23:52:42 +05:30
sabaimran
d2f9c43c8e Use datetime.timezone.utc instead of datetime.utc 2024-04-10 23:07:43 +05:30
Debanjum Singh Solanky
f2dc9709b7 Use Magika to more robustly identify text files to send for indexing 
- `file-type' doesn't handle mis-labelled files or files without
   extensions well

- Only show supported file types in file selector dialog on Desktop app
  Use Magika to get list of text file extensions. Combine with other
  supported extensions to get complete list of supported file extensions.
  Use it to limit selectable files in the File Open dialog.

  Note: Folder selector will index text files with no extensions as well
 2024-04-10 22:44:24 +05:30
sabaimran
3fe94a67b0 Send welcome emails when a new user signs up (#691) 
* Don't trigger any re-indexing on server initailization

* Integrate Resend to send welcome emails when a new user signs up

- Only send if this is the first time they've signed in
- Configure welcome email with basic styling, as more complex designs don't work and style tag did not work
 2024-04-10 19:57:33 +05:30
Debanjum
6d153022f6 Improve nav pane, chat session UI on Desktop, Web app (#693) 
### Enable copying chat messages. Improve copy button behavior and styling
  - Add button to copy chat messages on Desktop, Web apps
  - Improve copy button's icon, hover color & click animation in Desktop, Web apps

### Improve Navigation, Chat Session Panes on Desktop, Web apps
  - Dynamically generate navigation menu based on user info from server
  - Create API endpoint to get authenticated user information
  - Collapse navigation tabs into icons on mobile. Add spacing to them
  - Add Chat navigation tab back to top pane on Web app
  - Use proper icons for Search, Chat and Agents tab on navigation pane
  
### Miscellaneous Improvements
  - Make current chat expand to full width when session panel collapsed on Desktop App
  - Add chat session loading spinner to Desktop App (same as Web app)
   
### Fixes 
  - Show title bar in Khoj desktop app on Windows to simplify close, minimize etc.
  - Only render first run setup message once if error or server not running
  - Fix showing Search navigation tab from Agent pages on web client
 2024-04-10 19:54:12 +05:30
Debanjum Singh Solanky
48d249db9e Center the nav item text and user profile initial icons 2024-04-10 19:38:43 +05:30
Debanjum Singh Solanky
60f6a1c6f1 Use svg icons in nav pane to standardize styling on Web, Desktop apps 
Emojis varied based on device. svg icons standardize icon styles of
the web, desktop apps
 2024-04-10 19:38:43 +05:30
Debanjum Singh Solanky
cccea484e4 Pass username, location context in system prompt instead of chat message 
The username and location in system prompt should disambiguate user
context from user's actual message for the chat model.

It doesn't need to be told to not mention the context or acknowledge
the context instructions in it's response, as it understands that this
information is just context and not part of the user's actual message.
 2024-04-10 15:05:33 +05:30
Debanjum Singh Solanky
804c04f7b9 Do not render copy message button on every Khoj thinking step 
Only render copy chat message button once, after message text is rendered
 2024-04-10 14:48:36 +05:30
sabaimran
bb15c9605d Add a sitemap plugin 2024-04-10 14:35:04 +05:30
sabaimran
a4afada746 Remove client-side timeouts for the khoj socket 2024-04-10 13:35:25 +05:30
Debanjum Singh Solanky
cadeaac769 Align conversation sessions side panel on Desktop app with Web app 
- Move new conversation button to right of "Conversation" title
- Reduce size of chat message loading ellipsis animation
- Add loading animation for chat session
 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
1c3d129e08 Add button to copy chat messages on Desktop client 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
0a5a91619e Improve copy button's icon, hover color & click animation in Desktop UI 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
184873213c Add button to copy chat messages on Web client 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
f56522cb8e Improve copy button's icon, hover color & click animation in Web UI 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
8ff3890ba8 Dynamically generate navigation menu based on user info from server 2024-04-10 10:34:36 +05:30
Debanjum Singh Solanky
94c69eb8e3 Create API endpoint to get authenticated user information 
This help clients render UI with user information
 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
377e979800 Make current chat expand to full width when session panel collapsed 
This behavior also matches web client behavior on chat session panel
collapse
 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
913dcdfbcd Only render first run setup message once if error or server not running 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
3b630841bd s/aget_all_filenames_by_source/get_all_filenames_by_source as sync func 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
e45edbb992 Collapse navigation tabs into icons on mobile. Add spacing to them 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
93edd5427f Add Chat navigation tab back to top pane on web client 
Reduces user confusion on how to go to chat pane
Add emoji's for each tab to provide cleaner, iconified division between
the nav options
 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
8159d1ab25 Fix showing Search navigation tab from Agent pages on web client 
The `has_documents' flag wasn't being passed. So the search tab
always showing up as empty instead of being dynamically enabled if
documents had been indexed.
 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
76cb543347 Show title bar in Khoj desktop app on Windows 2024-04-09 21:04:44 +05:30
Debanjum Singh Solanky
f040418cf1 Fix indexing files in sub-folders on the Desktop app 
- `fs.readdir' func in node version 18.18.2 has buggy `recursive' option
  See nodejs/node#48640, effect-ts/effect#1801 for details

- We were recursing down a folder in two ways on the Desktop app.
  Remove `recursive: True' option to the `fs.readdirSync' method call
  to recurse down via app code only
 2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
a8dec1c9d5 Index all text, code files in Github repos. Not just md, org files 2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
8291b898ca Standardize structure of text to entries to match other entry processors 
Add process_single_plaintext_file func etc with similar signatures as
org_to_entries and markdown_to_entries processors

The standardization makes modifications, abstractions easier to create
 2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
079f409238 Skip indexing Github repo on hitting Github API rate limit 
Sleep until rate limit passed is too expensive, as it keeps a
app worker occupied.

Ideally we should schedule job to contine after rate limit wait time
has passed. But this can only be added once we support jobs scheduling.
 2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
d5c9b5cb32 Stop indexing commits, issues and issue comments in Github indexer 
Normal indexing quickly Github hits rate limits. Purpose of exposing
Github indexer is for indexing content like notes, code and other
knowledge base in a repo.

The current indexer doesn't scale to index metadata given Github's
rate limits, so remove it instead of giving a degraded experience of
partially indexed repos
 2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
7ff1bd9f8b Send more text file types from Desktop app and improve indexing them 
- Allow syncing more file types from desktop app to index on server
  - Use `file-type' package to identify valid text file types on Desktop app

- Split plaintext entries into smaller logical units than a whole file
  Since the text splitting upgrades in #645, compiled chunks have more
  logical splits like paragraph, sentence.
  Show those (potentially) smaller snippets to the user as references

- Tangential Fix:
  Initialize unbound currentTime variable for error log timestamp
 2024-04-09 20:19:40 +05:30
Debanjum Singh Solanky
89915dcb4c Identify file type by content & allow server to index all text files 
- Use Magika's AI for a tiny, portable and better file type
  identification system
- Existing file type identification tools like `file' and `magic'
  require system level packages, that may not be installed by default
  on all operating systems (e.g `file' command on Windows)
 2024-04-09 20:19:39 +05:30
sabaimran
312528d471 Fix typo in SECURE_PROXY_SSL_HEADER settings 2024-04-09 12:33:21 +05:30
sabaimran
e56c5e67dd Revert SSL Redirect setting as it prevents the admin page from loading 2024-04-09 12:24:48 +05:30
sabaimran
1770bb174b Add UUID to the KhojUser search fields and inc frequency of telemetry job to 2 mins 2024-04-09 11:51:51 +05:30
sabaimran
ab51ae9091 Use SECURE_SSL_REDIRECT to ensure requests are routed to https always 2024-04-09 10:18:12 +05:30
sabaimran
1c229dad91 Set daily limit for unsubsribed users to 5 in websocket API 2024-04-08 21:16:48 +05:30
sabaimran
27815d982c Redirect user to the login page when either of the csrf token inputs is missing 2024-04-08 20:22:17 +05:30
sabaimran
d257629f81 Handle case when properties field isn't present in the page 2024-04-08 16:15:47 +05:30
Debanjum
9b68062fa9 Add Sponsors Section to Readme 2024-04-08 03:09:24 -07:00
sabaimran
089e0d028b Add a more gracefull error message when the rate limit is exceeded 2024-04-08 15:20:54 +05:30
Debanjum
11ce3e2268 Update Text Chunking Strategy to Improve Search Context (#645) 
## Major
- Parse markdown, org parent entries as single entry if fit within max tokens
- Parse a file as single entry if it fits with max token limits
- Add parent heading ancestry to extracted markdown entries for context
- Chunk text in preference order of para, sentence, word, character

## Minor
- Create wrapper function to get entries from org, md, pdf & text files
- Remove unused Entry to Jsonl converter from text to entry class, tests
- Dedupe code by using single func to process an org file into entries

Resolves #620
 2024-04-08 13:56:38 +05:30
Debanjum Singh Solanky
9239c2c2ed Update drop large words test to ensure newlines considerd word boundary 
Prevent regression to #620
 2024-04-08 13:38:08 +05:30
Debanjum Singh Solanky
67b1178aec Remove debug logs generated while compiling org-mode entries 2024-04-08 13:01:24 +05:30
Debanjum
4eda79cc3a Support using Python 3.12 with Khoj (#690) 
### Why
- Python 3.12 is the default Python on Ubuntu 24.04 LTS, Windows and Mac via Homebrew
- Python 3.12 has a bunch of improvements that can be explored with Khoj (e.g per core GIL for performance)

## Changes
- The latest PyTorch now supports Python 3.12
- RapidOCR for indexing image PDFs doesn't currently support python 3.12.
  But it's an optional dependency, so only install it if python < 3.12

### Testing
- Verified Khoj installs fine on Windows and Mac with Python 3.12
- Verified Khoj chat works fine on Mac, Windows with Python 3.12

Resolves #522
 2024-04-08 11:43:34 +05:30
sabaimran
731ad03348 Skip indexing commits that are missing properties 2024-04-07 15:19:07 +05:30
sabaimran
376eaf64cd Check if results are present in the pages or db response in Notion 2024-04-07 15:19:07 +05:30
Debanjum Singh Solanky
8222615280 Do not add original user message to knowledge search queries for offline chat 
It's not required anymore. The extracted questions by the offline chat
model being used should be good enough.
 2024-04-07 11:29:35 +05:30
Debanjum Singh Solanky
e3deb29f8e Upgrade khoj.el workflow to use Python 3.11 2024-04-07 11:24:07 +05:30
Debanjum Singh Solanky
14fbf594b2 Support using Python 3.12 with Khoj 
- RapidOCR for indexing image PDFs doesn't currently support python 3.12.
  It's an optional dependency anyway, so only install it if python < 3.12
- Run unit tests with python version 3.12 as well

Resolves #522
 2024-04-07 11:23:44 +05:30
sabaimran
86c831f7e2 Add a link to the data sources portion in the clients documentation 2024-04-07 09:32:58 +05:30
sabaimran
351fb31a34 Add webpage search to socket codepath, add a feature page for online search 2024-04-07 09:23:29 +05:30
Debanjum Singh Solanky
4be4c53222 Release Khoj version 1.9.0 2024-04-05 17:13:58 +05:30
sabaimran
54db0152b9 Add link to the khoj cloud service for connection to Notion 2024-04-05 15:41:43 +05:30
sabaimran
81f1450c1c Update yarn.lock to sync with package.json for documentation 2024-04-05 15:36:23 +05:30
sabaimran
d22fd6dfe3 Get rid of unnecessary package-lock.json file 2024-04-05 15:34:02 +05:30
sabaimran
7d7ce92e46 Add updated information in docs about the Notion integration 2024-04-05 15:31:43 +05:30
sabaimran
2aedd3c819 Increase freq. of telemetry upload to every 5 minutes 2024-04-05 14:13:47 +05:30
sabaimran
3b1234d084 Await the calls to the db in the notion.py file 2024-04-05 13:58:14 +05:30
sabaimran
19c10b1418 Upgrade the package versions used in yarn.lock for the documentation project 2024-04-05 13:25:41 +05:30
sabaimran
00a67e9524 Add additional log lines when configuring the Notion settings for a user in the callback 2024-04-05 13:19:24 +05:30
sabaimran
d23f7da8e3 Handle the case where a previous serach model isn't set when updating the model 2024-04-05 13:18:51 +05:30
sabaimran
f57f9f672d Address Notion, Image tech debt in indexing code path (#687) 
* Add support for using OAuth2.0 in the Notion integration
* Add notion to the admin page
* Remove unnecessary content_index and image search/setup references
* Trigger background job to start indexing Notion after user configures it
* Add a log line when a new Notion integration is setup
* Fix references to the configure_content methods
 2024-04-05 12:10:03 +05:30
sabaimran
69dee75c34 Update the readme for accuracy, updated demos 2024-04-04 10:57:24 +05:30
sabaimran
a60321b68e Push khoj to include inline references when possible 2024-04-04 10:31:13 +05:30
sabaimran
5bdcb4e69c Wait for location data to be returned before setting up the socket connection 2024-04-04 10:31:13 +05:30
Debanjum Singh Solanky
00f599ea78 Fix passing flags to re.split to break org, md content by heading level 
`re.MULTILINE' should be passed to the `flags' argument, not the
`max_splits' argument of the `re.split' func

This was messing up the indexing by only allowing a maximum of
re.MULTILINE splits. Fixing this improves the search quality to
previous state
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
32ac0622ff Extract dates from compiled text entries 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
29c1c18042 Increase search distance to get relevant content for chat post indexer update 
More content indexed per entry would result in an overall scores
lowering effect. Increase default search distance threshold to counter that

- Details
  - Fix expected results post indexing updates
  - Fix search with max distance post indexing updates

- Minor
  - Remove openai chat actor test for after: operator as it's not expected anymore
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
ad4fa4b2f4 Fix adding file path instead of stem to markdown entries 2024-04-04 02:41:55 +05:30
sabaimran
720139c3c1 Fix all unit tests for test_text_search 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
44b3247869 Update logical splitting of org-mode text into entries 
- Major
  - Do not split org file, entry if it fits within the max token limits
    - Recurse down org file entries, one heading level at a time until
      reach leaf node or the current parent tree fits context window
    - Update `process_single_org_file' func logic to do this recursion

  - Convert extracted org nodes with children into entries
    - Previously org node to entry code just had to handle leaf entries
    - Now it recieve list of org node trees
    - Only add ancestor path to root org-node of each tree
    - Indent each entry trees headings by +1 level from base level (=2)

- Minor
  - Stop timing org-node parsing vs org-node to entry conversion
    Just time the wrapping function for org-mode entry extraction
    This standardizes what is being timed across at md, org etc.
  - Move try/catch to `extract_org_nodes' from `parse_single_org_file'
    func to standardize this also across md, org
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
eaa27ca841 Only add spaces after heading if any tags in orgnode raw entry repr 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
2ea8a832a0 Log error when fail to index md file. Fix, improve typing in md_to_entries 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
44eab74888 Dedupe code by using single func to process an org file into entries 
Add type hints to orgnode and org-to-entries packages
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
db2581459f Parse markdown parent entries as single entry if fit within max tokens 
These changes improve context available to the search model.
Specifically this should improve entry context from short knowledge trees,
that is knowledge bases with sparse, short heading/entry trees

Previously we'd always split markdown files by headings, even if a
parent entry was small enough to fit entirely within the max token
limits of the search model. This used to reduce the context available
to the search model to select appropriate entries for a query,
especially from short entry trees

Revert back to using regex to parse through markdown file instead of
using MarkdownHeaderTextSplitter. It was easier to implement the
logical split using regexes rather than bend MarkdowHeaderTextSplitter
to implement it.
- DFS traverse the markdown knowledge tree, prefix ancestry to each entry
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
982ac1859c Parse markdown file as single entry if it fits with max token limits 
These changes improve entry context available to the search model
Specifically this should improve entry context from short knowledge trees,
that is knowledge bases with small files

Previously we split all markdown files by their headings,
even if the file was small enough to fit entirely within the max token
limits of the search model. This used to reduce the context available
to select the appropriate entries for a given query for the search model,
especially from short knowledge trees
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
d8f01876e5 Add parent heading ancestory to extracted markdown entries for context 
Improve, update the markdown to entries extractor tests
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
86575b2946 Chunk text in preference order of para, sentence, word, character 
- Previous simplistic chunking strategy of splitting text by space
  didn't capture notes with newlines, no spaces. For e.g in #620

- New strategy will try chunk the text at more natural points like
  paragraph, sentence, word first. If none of those work it'll split
  at character to fit within max token limit

- Drop long words while preserving original delimiters

Resolves #620
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
a627f56a64 Remove unused Entry to Jsonl converter from text to entry class, tests 
This was earlier used when the index was plaintext jsonl file. Now
that documents are indexed in a DB this func is not required.

Simplify org,md,pdf,plaintext to entries tests by removing the entry
to jsonl conversion step
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
28105ee027 Create wrapper function to get entries from org, md, pdf & text files 
- Convert extract_org_entries function to actually extract org entries
  Previously it was extracting intermediary org-node objects instead
  Now it extracts the org-node objects from files and converts them
  into entries
- Create separate, new function to extract_org_nodes from files
- Similarly create wrapper funcs for md, pdf, plaintext to entries

- Update org, md, pdf, plaintext to entries tests to use the new
  simplified wrapper function to extract org entries
 2024-04-04 02:41:55 +05:30
Debanjum Singh Solanky
f01a12b1d2 Improve styling of chat sessions side panel 
- Move green server connected dot to the bottom. Show status when
  disconnected from server
- Move "New conversation" button to right of the "Conversation" title
- Center alignment of the new conversation and connection status buttons
 2024-04-04 01:43:26 +05:30
sabaimran
dd1e5e145a Use List[Any] for typing 2024-04-03 21:46:41 +05:30
sabaimran
b8087c4c8e Add typing to empty list variables in github_to_entries 2024-04-03 21:41:36 +05:30
sabaimran
d036fdfc26 If tree is not in the contents, then just return empty files list 2024-04-03 17:55:25 +05:30
Debanjum Singh Solanky
f915b2bd14 Fix passing model_name param to chatml formatter for online chat 2024-04-03 17:21:43 +05:30
sabaimran
6aa88761b8 Skip creating the default agent if there's no default conversation config 2024-04-03 17:21:01 +05:30
sabaimran
9c42c8be6b Merge pull request #679 from khoj-ai/features/chat-socket-streaming 
Add a websocket for streaming from the chat UI
 2024-04-03 04:43:31 -07:00
sabaimran
b4f71e06b3 Add timeout after 10 minutes of inactivity on socket 2024-04-02 22:12:27 +05:30
sabaimran
f48426623d resolve merge conflict in chat.html 2024-04-02 17:29:48 +05:30
sabaimran
bf1187f465 Use new online/websearch logic and add agent to chat_metadata 2024-04-02 17:20:38 +05:30
sabaimran
867e1007d1 Remove superfluous newline 2024-04-02 17:20:08 +05:30
sabaimran
228ad68042 Merge with origin/master 2024-04-02 17:02:21 +05:30
sabaimran
776550d5ce Add a migration for updating the default chat model, update for existing users 2024-04-02 17:01:31 +05:30
sabaimran
47fc7e1ce6 Rebase with matser 2024-04-02 16:16:06 +05:30
Debanjum
215ab6e66a Extract More Dates from entries to improve Date Filter (#683) 
- Overview
  - Extract more structured date variants (e.g with dot(.) & slash(/) separators, 2-digit year)
  - Extract some natural, partial dates as well from entries
- Capability
  Add ability to extract the following additional date forms:
  - Natural Dates: 21st April 2000, February 29 2024
  - Partial Natural Dates: March 24, Mar 2024
  - Structured Dates: 20/12/24, 20.12.2024, 2024/12/20
  Note: Previously only YYYY-MM-DD ISO-8601 structured date form was extracted for date filters
- Performance
  Using regexes is MUCH faster than using the `dateparser' python library
  It's a little crude but gives acceptable performance for large datasets
 2024-04-02 16:14:53 +05:30
Debanjum
3c3e48b18c Migrate to Llama.cpp for Offline Chat (#680) 
## Benefits
- Support all GGUF format chat models
- Support more GPUs like AMD, Nvidia, Mac, Vulcan (previously just Vulcan, Mac)
- Support more capabilities like larger context window, schema enforcement, speculative decoding etc.

## Changes
### Major
- Use llama.cpp for offline chat models
  - Support larger context window
  - Automatically apply appropriate chat template. So offline chat models not using llama2 format are now supported
  - Use better default offline chat model, NousResearch/Hermes-2-Pro-Mistral-7B
- Enable extract queries actor to improve notes search with offline chat
- Update documentation to use llama.cpp for offline chat in Khoj

### Minor
- Migrate to use NouseResearch's Hermes-2-Pro 7B as default offline chat model in khoj.yml
- Rename GPT4AllChatProcessor to OfflineChatProcessor Config, Model
- Only add location to image prompt generator when location known
 2024-04-02 15:49:42 +05:30
Debanjum Singh Solanky
7afee2d55c Let offline chat model set context window. Improve, fix prompts 2024-03-31 16:19:35 +05:30
Debanjum Singh Solanky
4228965c9b Handle msg truncation when question is larger than max prompt size 
Notice and truncate the question it self at this point
 2024-03-31 15:50:06 +05:30
Debanjum Singh Solanky
c6487f2e48 Fix docs showing how to setup llama-cpp with Khoj 2024-03-31 15:36:40 +05:30
Debanjum Singh Solanky
886d49e3a4 Merge branch 'master' into migrate-to-llama-cpp-for-offline-chat 2024-03-31 00:59:20 +05:30
Debanjum Singh Solanky
4f65dde201 Release Khoj version 1.8.0 2024-03-31 00:06:15 +05:30
sabaimran
c0e78fd56d Fix broken get-started documentation links 2024-03-30 15:05:12 +05:30
sabaimran
dd2a3f712b Add more demo videos, images, add feature sections 2024-03-30 14:48:46 +05:30
sabaimran
4cb91a042e Add an agents feature page, and clarification around custom domains 2024-03-30 14:20:46 +05:30
sabaimran
928f273bbe Configure production setup for moving to single worker model 2024-03-30 10:35:55 +05:30
Debanjum Singh Solanky
7923903d21 Improve date filter regexes to extract structured, natural, partial dates 
- Much faster than using dateparser
  - It took 2x-4x for improved regex to extracts 1-15% more dates
  - Whereas It took 33x to 100x for dateparser to extract 65% - 400% more dates
  - Improve date extractor tests to test deduping dates, natural,
    structured date extraction from content

- Extract some natural, partial dates and more structured dates
  Using regex is much faster than using dateparser. It's a little
  crude but should pay off in performance.

  Supports dates of form:
  - (Day-of-Month) Month|AbbreviatedMonth Year|2DigitYear
  - Month|AbbreviatedMonth (Day-of-Month) Year|2DigitYear
 2024-03-30 00:07:19 +05:30
Debanjum Singh Solanky
104eeea274 Extract natural language and locale specific dates in content 
Previously we just extracted dates in YYYY-MM-DD format from content
for date filterings during search.

Use dateparser to extract dates across locales and natural language

This should improve notes returned as context when chat searches
knowledge base with date filters

Fallback to regex for date parsing from content if dateparser fails

- Limit natural date extractor capabilities to improve performance
  - Assume language is english
    Language detection otherwise takes a REALLY long time
  - Do not extract unix timestamps, timezone
    - This isn't required, as just using date and approximating dates as UTC
 2024-03-30 00:06:56 +05:30
Debanjum Singh Solanky
90c5b3c410 Update stale Khoj pypi package metadata 
Use latest License, Intended Audience and Dev Status
 2024-03-29 00:06:55 +05:30
sabaimran
1195f843a3 Remove forward slash from the root agents endpoint 2024-03-28 23:06:55 +05:30
Debanjum Singh Solanky
a374288cea Use OIDC TrustedPublisher to publish khoj python package to PyPi 2024-03-28 22:58:36 +05:30
sabaimran
3417164ec2 Bump gunicorn workers up to 8 2024-03-28 22:34:13 +05:30
sabaimran
a1729b9b9e Add telemetry for agents used in conversation, increase image width in agents page 2024-03-28 22:18:11 +05:30
sabaimran
d503b3e867 Use Personality vernacular in agent page 
- When setting up the default agent, configure every conversation that doesn't have an agent to use the Khoj agent
- Fix reverse migration for the locale removal migration
 2024-03-28 15:07:02 +05:30
sabaimran
e59de8c9b1 Constrain width/size of agent image in agents view 2024-03-28 13:32:11 +05:30
sabaimran
6cb38d92c0 Specify version of pypi gh publish action 2024-03-28 12:47:31 +05:30
sabaimran
56da96b2e9 Increase minimum python required in the pyproject, use python 3.11 for building the wheel in the workflow 2024-03-28 12:19:07 +05:30
sabaimran
22014cfcbc Merge pull request #682 from khoj-ai/features/full-integration-agents 
Add support for custom agents configured by the server admin
 2024-03-27 23:27:15 -07:00
sabaimran
17776daed8 Merge from master 2024-03-28 11:38:29 +05:30
sabaimran
32a505d841 Revert to using the nvidia base image for the next release 2024-03-28 11:37:37 +05:30
sabaimran
51d0c9b8b0 Add telemetry to keep state of new agents being used 2024-03-28 11:37:24 +05:30
sabaimran
46ebc55e2b Add a top tab for agents 2024-03-28 11:37:01 +05:30
sabaimran
8397187231 Use default agent when creating a new conversation without agent specified 2024-03-28 11:36:27 +05:30
Debanjum Singh Solanky
8c4ef9270d Fix using format string for logger in chat API endpoint 2024-03-27 16:31:22 +05:30
Debanjum Singh Solanky
4912c0ee30 Use extract queries actor to improve notes search with offline chat 
Previously we were skipping the extract questions step for offline
chat as default offline chat model wasn't good enough to output proper
json given the time it took to extract questions.

The new default offline chat models gives json much more regularly and
with date filters, so the extract questions step becomes useful given
the impact on latency
 2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
1ebd5c3648 Rename GPT4AllChatProcessor* to OfflineChatProcessor Config, Model 2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
2a0b943bb4 Use Hermes-2-Pro as default offline chat model in khoj.yml 2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
dcdd1edde2 Update docs to show how to setup llama-cpp with Khoj 
- How to pip install khoj to run offline chat on GPU
  After migration to llama-cpp-python more GPU types are supported but
  require build step so mention how
- New default offline chat model
- Where to get supported chat models from on HuggingFace
 2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
8ca39a436c Use llama.cpp for offline chat models 
- Benefits of moving to llama-cpp-python from gpt4all:
  - Support for all GGUF format chat models
  - Support for AMD, Nvidia, Mac, Vulcan GPU machines (instead of just Vulcan, Mac)
  - Supports models with more capabilities like tools, schema
    enforcement, speculative ddecoding, image gen etc.
- Upgrade default chat model, prompt size, tokenizer for new supported
  chat models

- Load offline chat model when present on disk without requiring internet
  - Load model onto GPU if not disabled and device has GPU
  - Load model onto CPU if loading model onto GPU fails
  - Create helper function to check and load model from disk, when model
    glob is present on disk.

    `Llama.from_pretrained' needs internet to get repo info from
    HuggingFace. This isn't required, if the model is already downloaded

    Didn't find any existing HF or llama.cpp method that looked for model
    glob on disk without internet
 2024-03-26 22:33:01 +05:30
Debanjum Singh Solanky
0a7392f6ec Only add location to image prompt generator when location known 2024-03-26 22:33:01 +05:30
sabaimran
fdf78525b4 Part 2: Add web UI updates for basic agent interactions (#675) 
* Initial pass at backend changes to support agents
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications

* Customize default behaviors for conversations without agents or with default agents

* Add a new web client route for viewing all agents

* Use agent_id for getting correct agent

* Add web UI views for agents
- Add a page to view all agents
- Add slugs to manage agents
- Add a view to view single agent
- Display active agent when in chat window
- Fix post-login redirect issue

* Fix agent view

* Spruce up the 404 page and improve the overall layout for agents pages

* Create chat actor for directly reading webpages based on user message

- Add prompt for the read webpages chat actor to extract, infer
  webpage links
- Make chat actor infer or extract webpage to read directly from user
  message
- Rename previous read_webpage function to more narrow
  read_webpage_at_url function

* Rename agents_page -> agent_page

* Fix unit test for adding the filename to the compiled markdown entry

* Fix layout of agent, agents pages

* Merge migrations

* Let the name, slug of the default agent be Khoj, khoj

* Fix chat-related unit tests

* Add webpage chat command for read web pages requested by user

Update auto chat command inference prompt to show example of when to
use webpage chat command (i.e when url is directly provided in link)

* Support webpage command in chat API

- Fallback to use webpage when SERPER not setup and online command was
  attempted
- Do not stop responding if can't retrieve online results. Try to
  respond without the online context

* Test select webpage as data source and extract web urls chat actors

* Tweak prompts to extract information from webpages, online results

- Show more of the truncated messages for debugging context
- Update Khoj personality prompt to encourage it to remember it's capabilities

* Rename extract_content online results field to webpages

* Parallelize simple webpage read and extractor

Similar to what is being done with search_online with olostep

* Pass multiple webpages with their urls in online results context

Previously even if MAX_WEBPAGES_TO_READ was > 1, only 1 extracted
content would ever be passed.

URL of the extracted webpage content wasn't passed to clients in
online results context. This limited them from being rendered

* Render webpage read in chat response references on Web, Desktop apps

* Time chat actor responses & chat api request start for perf analysis

* Increase the keep alive timeout in the main application for testing

* Do not pipe access/error logs to separate files. Flow to stdout/stderr

* [Temp] Reduce to 1 gunicorn worker

* Change prod docker image to use jammy, rather than nvidia base image

* Use Khoj icon when Khoj web is installed on iOS as a PWA

* Make slug required for agents

* Simplify calling logic and prevent agent access for unauthenticated users

* Standardize to use personality over tuning in agent nomenclature

* Make filtering logic more stringent for accessible agents and remove unused method:

* Format chat message query

---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
 2024-03-26 18:13:24 +05:30
Debanjum Singh Solanky
15ed208996 Use Khoj icon when Khoj web is installed on iOS as a PWA 2024-03-26 00:13:12 +05:30
sabaimran
f8eaff574f Change prod docker image to use jammy, rather than nvidia base image 2024-03-25 23:09:58 +05:30
sabaimran
2b5341f53a [Temp] Reduce to 1 gunicorn worker 2024-03-25 16:13:04 +05:30
sabaimran
991f500775 Do not pipe access/error logs to separate files. Flow to stdout/stderr 2024-03-25 16:12:39 +05:30
Debanjum
586654e2af Allow directly reading web pages, even when SERP not enabled (#676) 
### Overview
Khoj can now read website directly without needing to go through the search step first

### Details
- Parallelize simple webpage read and extractor
- Rename extract_content online results field to web pages
- Tweak prompts to extract information from webpages, online results
- Test select webpage as data source and extract web urls chat actors

- Render webpage read in chat response references on Web, Desktop apps
- Pass multiple webpages with their urls in online results context

- Support webpage command in chat API
- Add webpage chat command for read web pages requested by user
- Create chat actor for directly reading webpages based on user message
 2024-03-24 16:25:25 +05:30
Debanjum Singh Solanky
9e52ae9e98 Time chat actor responses & chat api request start for perf analysis 2024-03-24 15:47:38 +05:30
Debanjum Singh Solanky
dabf71bc3c Render webpage read in chat response references on Web, Desktop apps 2024-03-24 15:47:38 +05:30
Debanjum Singh Solanky
a2e79c94be Pass multiple webpages with their urls in online results context 
Previously even if MAX_WEBPAGES_TO_READ was > 1, only 1 extracted
content would ever be passed.

URL of the extracted webpage content wasn't passed to clients in
online results context. This limited them from being rendered
 2024-03-24 15:47:38 +05:30
Debanjum Singh Solanky
71b6905008 Parallelize simple webpage read and extractor 
Similar to what is being done with search_online with olostep
 2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
1167f6ddf9 Rename extract_content online results field to webpages 2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
b22a7dae5d Tweak prompts to extract information from webpages, online results 
- Show more of the truncated messages for debugging context
- Update Khoj personality prompt to encourage it to remember it's capabilities
 2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
85c62efca1 Test select webpage as data source and extract web urls chat actors 2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
ad6f6bb0ed Support webpage command in chat API 
- Fallback to use webpage when SERPER not setup and online command was
  attempted
- Do not stop responding if can't retrieve online results. Try to
  respond without the online context
 2024-03-24 15:46:29 +05:30
Debanjum Singh Solanky
a6b7432837 Add webpage chat command for read web pages requested by user 
Update auto chat command inference prompt to show example of when to
use webpage chat command (i.e when url is directly provided in link)
 2024-03-24 15:46:29 +05:30
sabaimran
8abc8ded82 Part 1: Server-side changes to support agents integrated with Conversations (#671) 
* Initial pass at backend changes to support agents
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications

* Customize default behaviors for conversations without agents or with default agents

* Use agent_id for getting correct agent

* Merge migrations

* Simplify some variable definitions, add additional security checks for agents

* Rename agent.tuning -> agent.personality
 2024-03-23 22:09:38 +05:30
sabaimran
4deb849fb1 Merge branch 'features/add-agents-ui' of github.com:khoj-ai/khoj into features/chat-socket-streaming 2024-03-23 14:04:25 +05:30
sabaimran
8edbd7094f Let the name, slug of the default agent be Khoj, khoj 2024-03-23 14:03:58 +05:30
sabaimran
6b4c4f10b5 Merge branch 'features/add-agents-ui' of github.com:khoj-ai/khoj into features/chat-socket-streaming 2024-03-23 11:22:00 +05:30
sabaimran
20617614ae Merge branch 'features/customize-chat-with-agents' of github.com:khoj-ai/khoj into features/add-agents-ui 2024-03-23 11:20:57 +05:30
sabaimran
2399d91f61 Merge migrations 2024-03-22 10:05:33 +05:30
sabaimran
d38089ab57 Merge with origin 2024-03-22 09:55:33 +05:30
Debanjum Singh Solanky
7416ca9ae1 Lower the default gunicorn workers running on prod 2024-03-21 04:35:52 +05:30
Debanjum Singh Solanky
aed4313cfc Fix updating specific conversation by id from the chat API endpoint 
- Use the conversation id of the retrieved conversation rather than the
  potentially unset conversation id passed via API
- await creating new chat when no chat id provided and no existing
  conversations exist
 2024-03-21 02:46:52 +05:30
Debanjum Singh Solanky
ec6dc0daaf Bump up the default gunicorn workers running on prod 2024-03-20 22:56:09 +05:30
sabaimran
6ba0d8e379 Add a connected notification if the websocket is connected 2024-03-20 20:53:28 +05:30
sabaimran
255b69dc58 Add a comma delimeter between outputted search queries 2024-03-20 19:43:35 +05:30
sabaimran
d84188b221 Scroll down when a message is added in the chat interface's handle stream response method 2024-03-20 15:04:41 +05:30
sabaimran
70ad78990a Use a common method for sending a generic message to the client from the server in the ws connection 2024-03-20 15:04:14 +05:30
sabaimran
d4e83b060a Update the web UI for the chat interface to establish a connection via a socket to the server 
- Move some common methods into separate functions to make the UI components more efficient
- The normal HTTP-based chat connection will still work and serves as a fallback if the websocket is unavailable
 2024-03-20 14:34:47 +05:30
sabaimran
a346f79b39 Add support for chatting via the web socket connection 
- Convert to a model of calling the search API directly with a function call (rather than using the API method)
- Gracefully handle websocket connection disconnects
- Ensure that the rest of the response is still saved, as it is currently, if the user disconects from the client
- Setup unchangeable context at the beginning of the session when the connection is established (like location, username, etc)
 2024-03-20 14:33:33 +05:30
sabaimran
36af9776e6 Add the websockets dependency to pyproject.toml 2024-03-20 14:11:18 +05:30
Debanjum Singh Solanky
62a83dc9bb Fix online search actor to use natural dates not after: operator 
The recently added after: operator to online search actor was too
restrictive, gave worse results than when just use natural language
dates in search query
 2024-03-15 21:50:14 +05:30
Debanjum Singh Solanky
4a1e6a2275 Convert deleted old user requests log line to debug from info 2024-03-15 20:50:10 +05:30
Debanjum Singh Solanky
9a068dadbf Fix extract questions prompt to use YYYY-MM-DD date filter format 2024-03-15 18:43:18 +05:30
Debanjum
bb2693c792 Improve Chat Session UX, Fix Login, Chat Message Truncation (#677) 
### Improve
- Improve delete, rename chat session UX in Desktop, Web app
- Get conversation by title when requested via chat API

### Fix
- Allow unset locale for Google authenticating user
- Handle truncation when single long non-system chat message
- Fix setting chat session title from Desktop app
- Only create new chat on get if a specific chat id, slug isn't requested
 2024-03-15 18:19:36 +05:30
Debanjum Singh Solanky
ecddf98430 Handle truncation when single long non-system chat message 
Previously was assuming the system prompt is being always passed as
the first message. So expected there to be at least 2 messages in logs.

This broke chat actors querying with single long non system message.

A more robust way to extract system prompt is via the message role
instead
 2024-03-15 15:58:39 +05:30
Debanjum Singh Solanky
ec0c35b7ed Improve delete, rename chat session UX in Desktop, Web app 
- Ask for Confirmation before deleting chat session in Desktop, Web app
- Save chat session rename on hitting enter in title edit input box
- No need to flash previous conversation cleared status message
- Move chat session delete button after rename button in Desktop app
 2024-03-15 15:58:19 +05:30
Debanjum Singh Solanky
924b1215ce Allow unset locale for Google authenticated user 2024-03-15 15:35:20 +05:30
Debanjum Singh Solanky
c792fa819f Fix setting chat session title from Desktop app 
Pass auth headers to not have the chat session title update request fail
 2024-03-15 15:19:20 +05:30
Debanjum Singh Solanky
c9e05dc184 Get conversation by title when requested via chat API 2024-03-15 12:31:50 +05:30
sabaimran
724557fc7b Merge branch 'master' of github.com:khoj-ai/khoj into features/add-agents-ui 2024-03-15 12:14:34 +05:30
sabaimran
7fc484ba7a Merge branch 'master' of github.com:khoj-ai/khoj into features/customize-chat-with-agents 2024-03-15 12:13:28 +05:30
Debanjum Singh Solanky
cac26dafe3 Only create new chat on get if a specific chat id, slug isn't requested 2024-03-15 11:58:39 +05:30
sabaimran
416feb13ef Fix layout of agent, agents pages 2024-03-15 11:17:40 +05:30
sabaimran
1b3fc68a87 Fix unit test for adding the filename to the compiled markdown entry 2024-03-15 11:01:48 +05:30
sabaimran
d734be61cf Rename agents_page -> agent_page 2024-03-15 10:17:51 +05:30
Debanjum Singh Solanky
8cdfaf41ec Update project URLs to show on pypi project page 2024-03-15 04:03:39 +05:30
Debanjum Singh Solanky
08993ff109 Add new, remove old known chat models from model to prompt size map 2024-03-15 04:02:25 +05:30
Debanjum Singh Solanky
fba0338787 Release Khoj version 1.7.0 2024-03-15 00:08:32 +05:30
sabaimran
345afec47e Resolve merge conflicts/ use agent_slug instead of agent_id for lookup 2024-03-14 16:16:07 +05:30
Debanjum Singh Solanky
6118d1ff57 Create chat actor for directly reading webpages based on user message 
- Add prompt for the read webpages chat actor to extract, infer
  webpage links
- Make chat actor infer or extract webpage to read directly from user
  message
- Rename previous read_webpage function to more narrow
  read_webpage_at_url function
 2024-03-14 14:58:37 +05:30
Debanjum
e549824fe2 Improve OpenAI Chat Actors and their prompts (#673) 
### Major
- Enforce json mode response from OpenAI chat actors prev using string lists
- Use `gpt-4-turbo-preview' as default chat model, extract questions actor
- Make Khoj read khoj website to respond with accurate, up-to-date information about itself
- Dedupe query in notes prompt. Improve OAI chat actor, director tests

### Minor
- Test data source, output mode selector, web search query chat actors
- Improve notes search actor to always create a non-empty list of queries
- Construct available data sources, output modes as a bullet list in prompts
- Use consistent agent name across static and dynamic examples in prompts
- Add actor's name to extract questions prompt to improve context for guidance
 2024-03-14 12:44:40 +05:30
sabaimran
3caf0a79d8 Spruce up the 404 page and improve the overall layout for agents pages 2024-03-14 11:26:49 +05:30
sabaimran
c45030af44 Fix agent view 2024-03-14 11:13:19 +05:30
Debanjum Singh Solanky
a1ce12296f Fix rendering online with note references post streaming chat response 
Previously only the notes references would get rendered post response
streaming when when both online and notes references were used to
respond to the user's message
 2024-03-14 03:40:40 +05:30
Debanjum Singh Solanky
1aeea3d854 Fix opening external links from confirmation dialog box on desktop app 2024-03-14 02:29:22 +05:30
Debanjum Singh Solanky
2e5cc49cb3 Enforce json response from OpenAI chat actors prev using string lists 
- Allow passing response format type to OpenAI API via chat actors
- Convert in-context examples to use json objects instead of str lists
- Update actors outputting str list to request output to be json_object
  - OpenAI's json mode enforces the model to output valid json object
 2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
7211eb9cf5 Default to gpt-4-turbo-preview for chat model, extract questions actor 
GPT-4 is more expensive and generally less capable than gpt-4-turbo-preview
 2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
dd883dc53a Dedupe query in notes prompt. Improve OAI chat actor, director tests 
- Remove stale tests
- Improve tests to pass across gpt-3.5 and gpt-4-turbo
- The haiku creation director was failing because of duplicate query in
  instantiated prompt
 2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
70b04d16c0 Test data source, output mode selector, web search query chat actors 2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
14682d5354 Improve notes search actor to always create a non-empty list of queries 
- Remove the option for Notes search query generation actor to return
  no queries. Whether search should be performed is decided before,
  this step doesn't need to decide that
- But do not throw warning if the response is a list with no elements
 2024-03-14 01:22:33 +05:30
Debanjum Singh Solanky
f5734826cb Improve pick data source prompt to look online for info about Khoj 
- Add examples where user queries requesting information about Khoj
  results in the "online" data source being selected
- Add an example for "general" to select chat command prompt
 2024-03-14 01:21:13 +05:30
Debanjum Singh Solanky
9a516bed47 Construct available data sources, output modes as a bullet list in prompts 2024-03-14 00:34:57 +05:30
Debanjum Singh Solanky
f28fb89af8 Use consistent agent name across static and dynamic examples in prompts 
Previously the examples constructed from chat history used "Khoj" as
the agent's name but all 3 prompts using the func used static examples
with "AI:" as the pertinent agent's name
 2024-03-14 00:34:57 +05:30
Debanjum Singh Solanky
f5793149a9 Add actor's name to extract questions prompt to improve context for guidance 2024-03-14 00:34:57 +05:30
Debanjum Singh Solanky
73ad444086 Make online search Actor read khoj.dev for docs, info about Khoj 
- Add example to read khoj.dev website for up-to-date info to setup,
  use khoj, discover khoj features etc.
- Online search should use site: and after: google search operators
  - Show example of adding the after: date filter to google search
- Give local event lookup example using user's current location in
  query
- Remove unused select search content type prompt
 2024-03-14 00:34:57 +05:30
sabaimran
290712c3fe Add web UI views for agents 
- Add a page to view all agents
- Add slugs to manage agents
- Add a view to view single agent
- Display active agent when in chat window
- Fix post-login redirect issue
 2024-03-14 00:07:36 +05:30
Debanjum
3abe7ccb26 Improve Online Search Speed and Context (#670) 
### Major
- Read web pages in parallel to improve chat response time
- Read web pages directly when Olostep proxy not setup
- Include search results & web page content in online context for chat response

### Minor
- Simplify, modularize and add type hints to online search functions
 2024-03-11 22:16:30 +05:30
Debanjum Singh Solanky
dc86e44a07 Include search results & webpage content in online context for chat response 
Previously if a web page was read for a sub-query, only the extracted
web page content was provided as context for the given sub-query. But
the google results themselves have relevant snippets. So include them
 2024-03-11 18:41:02 +05:30
Debanjum Singh Solanky
d136a6be44 Simplify, modularize and add type hints to online search functions 
- Simplify content arg to `extract_relevant_info' function. Validate,
  clean the content arg inside the `extract_relevant_info' function

- Extract `search_with_google' function outside the parent function
- Call the parent function a more appropriate `search_online' instead
  of `search_with_google'
- Simplify the `search_with_google' function using list comprehension.
  Drop empty search result fields from chat model context for response
  to reduce cost and response latency

- No need to show stacktrace when unable to read webpage, basic error
  is enough
- Add type hints to online search functions to catch issues with mypy
 2024-03-11 18:41:02 +05:30
Debanjum Singh Solanky
88f096977b Read webpages directly when Olostep proxy not setup 
This is useful for self-hosted, individual user, low traffic setups
where a proxy service is not required
 2024-03-11 18:41:02 +05:30
Debanjum Singh Solanky
ca2f962e95 Read, extract information from web pages in parallel to lower response time 
- Time reading webpage, extract info from webpage steps for perf
  analysis
- Deduplicate webpages to read gathered across separate google
  searches
- Use aiohttp to make API requests non-blocking, pair with asyncio to
  parallelize all the online search webpage read and extract calls
 2024-03-11 18:41:02 +05:30
sabaimran
8e1445b15b Use agent_id for getting correct agent 2024-03-11 14:44:46 +05:30
sabaimran
6ab649312f Add a new web client route for viewing all agents 2024-03-11 14:40:40 +05:30
sabaimran
352168d6c2 Customize default behaviors for conversations without agents or with default agents 2024-03-11 14:20:28 +05:30
sabaimran
9b88976f36 Initial pass at backend changes to support agents 
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications
 2024-03-11 12:45:24 +05:30
sabaimran
1da453306e Add num online for Discord badge 2024-03-10 17:48:30 +05:30
Debanjum
18fa3e2384 Rerank Search Results by Default on GPU machines (#668) 
- Trigger
   SentenceTransformer Cross Encoder models now run fast on GPU enabled machines, including Mac ARM devices since UKPLab/sentence-transformers#2463

- Details
  - Use cross-encoder to rerank search results by default on GPU machines and when using an inference server
  - Only call search API when pause in typing search query on web, desktop apps
 2024-03-10 15:15:25 +05:30
Debanjum Singh Solanky
53d402480c Rerank search results with cross-encoder when using an inference server 
If an inference server is being used, we can expect the cross encoder
to be running fast enough to rerank search results by default
 2024-03-10 15:09:46 +05:30
Debanjum Singh Solanky
44c8d09342 Only call search API when pause in typing search query on web, desktop apps 
Wait for 300ms since stop typing before calling search API.

This smooths out UI jitter when rendering search results, especially
now that we're reranking for every search query on GPU enabled devices

Emacs already has 300ms debounce time. More convoluted to add
debounce time to Obsidian search modal, so not updating that yet
 2024-03-10 14:29:24 +05:30
Debanjum Singh Solanky
1105d8814f Use cross-encoder to rerank search results by default on GPU machines 
Latest sentence-transformer package uses GPU for cross-encoder. This
makes it fast enough to enable reranking on machines with GPU.

Enabling search reranking by default allows (at least) users with GPUs
to side-step learning the UI affordance to rerank results
(i.e hitting Cmd/Ctrl-Enter or ENTER).
 2024-03-10 14:29:21 +05:30
Debanjum
8eb3c441ec Do not create new chat session when an old chat session is deleted (#669) 
### Issue
Previously deleting a chat session from the side panel on desktop, web app would sometimes result in also creating a new chat session

### Fix
  `get_conversation_by_user' shouldn't return new conversation if
  conversation with requested id not found.

  It should only return new conversation if no specific conversation
  is requested and no conversations found for user at all

### Miscellaneous Improvements
  - Chat history load should be logged as call to that chat_history api,
    not the "chat" api
  - Show status updates of clearing conversation history in chat input
  - Simplify web, desktop client code by removing unnecessary new variables

### Repro
  - Delete a new chat, this calls loadChat via window.onload which
    calls server /chat/history API endpoint with conversationId set to
    that of just deleted conversation sporadically

    The call to GET chat/history API with conversationId set occurs
    when window.onload triggers before the conversationId is deleted
    by the delete button after the DELETE /chat/history API call (via race)

  - In such a scenario, get_conversation_by_user called by
    chat/history API with conversationId of deleted conversation
    returns a new conversation
 2024-03-10 14:14:43 +05:30
Debanjum Singh Solanky
fd81446ba3 Do not create new chat session when an old chat session is deleted 
- Fix
  `get_conversation_by_user' shouldn't return new conversation if
  conversation with requested id not found.

  It should only return new conversation if no specific conversation
  is requested and no conversations found for user at all

- Repro
  - Delete a new chat, this calls loadChat via window.onload which
    calls server /chat/history API endpoint with conversationId set to
    that of just deleted conversation sporadically

    The call to GET chat/history API with conversationId set occurs
    when window.onload triggers before the conversationId is deleted
    by the delete button after the DELETE /chat/history API call (via race)

  - In such a scenario, get_conversation_by_user called by
    chat/history API with conversationId of deleted conversation
    returns a new conversation

- Miscellaneous
  - Chat history load should be logged as call to that chat_history api,
    not the "chat" api
  - Show status updates of clearing conversation history in chat input
  - Simplify web, desktop client code by removing unnecessary new variables
 2024-03-10 02:17:23 +05:30
Debanjum Singh Solanky
b7fad04870 Use consistent field name for queries in chat history & better image prompt 2024-03-09 19:11:03 +05:30
sabaimran
086d5f8324 Add link to drag drop pdf demo video 2024-03-09 17:02:23 +05:30
sabaimran
6aae9864d3 Fix Notion indexing and add an admin view for Entry objects 2024-03-09 16:25:23 +05:30
sabaimran
b3b6278af2 Update documentation to show how you can upload files 2024-03-09 15:58:13 +05:30
sabaimran
12d6c4da7d Only include inferred queries in the conversation history for images, not links. Overflow the side panel when too long 2024-03-09 11:59:35 +05:30
Debanjum Singh Solanky
42d4bc6b14 Document installing Khoj on Phone as a Progressive Web App (PWA) 2024-03-08 21:18:06 +05:30
sabaimran
e5cd0237e3 Release Khoj version 1.6.2 2024-03-08 17:04:03 +05:30
Debanjum Singh Solanky
446ac7649d Remove unused js method in web chat client, add newline to web data in prompt 2024-03-08 16:40:39 +05:30
Debanjum Singh Solanky
12d32ac99c Increase user visibility into more errors during image generation 
Catch OpenAI connection error and errors during better image prompt
generation
 2024-03-08 16:40:39 +05:30
sabaimran
ff31759423 Fix target determination in the copy programmatic output button 2024-03-08 16:33:12 +05:30
sabaimran
9f934929c6 Infer mime type from file ending when not available in browser. Don't output image in conversation turns 2024-03-08 12:34:26 +05:30
sabaimran
81beb7940c Upload generated images to s3, if AWS credentials and bucket is available (#667) 
* Upload generated images to s3, if AWS credentials and bucket is available.
- In clients, render the images via the URL if it's returned with a text-to-image2 intent type
* Make the loading screen more intuitve, less jerky and update the programmatic copy button
* Update the loading icon when waiting for a chat response
 2024-03-08 10:54:13 +05:30
sabaimran
13894e1fd5 add instructions for drag/drop files in sys prompt 2024-03-07 17:57:42 +05:30
sabaimran
7357b6eff1 Revert white-space preline and add more detailed help text when selecting file 2024-03-06 16:47:27 +05:30
sabaimran
b615c0719e Support upload for files via drag/drop in the web UI (#666) 
* Add additional styling changes for showing UI changes when dragging file to the main screen

* Add a loading spinner when file upload is in progress, and don't index github/notion when indexing files

* Add an explicit icon for file uploading in the chat button menu

* Add appropriate dragover styling when picking a file from the file picker/browser

* Add a loading screen when retrieving chat history. Fix width of the chat window. Put attachment icon to the left of chat input
 2024-03-06 16:43:05 +05:30
sabaimran
e323a6d69b Include additional user context in the image generation flow (#660) 
* Make major improvements to the image generation flow

- Include user context from online references and personal notes for generating images
- Dynamically select the modality that the LLM should respond with
- Retun the inferred context in the query response for the dekstop, web chat views to read

* Add unit tests for retrieving response modes via LLM

* Move output mode unit tests to the actor suite, rather than director

* Only show the references button if there is at least one available

* Rename aget_relevant_modes to aget_relevant_output_modes

* Use a shared method for generating reference sections, simplify some of the prompting logic

* Make out of space errors in the desktop client more obvious
 2024-03-06 13:48:41 +05:30
sabaimran
3cbc5b0d52 Add links to blog in docs 2024-03-02 17:37:18 +05:30
sabaimran
880368635e Set default value of KHOJ_DEBUG to False in the docker-compose file 2024-03-01 21:51:13 +05:30
Debanjum Singh Solanky
2d61591c22 Improve user visibility into errors during image generation 2024-02-29 13:19:13 +05:30
547 changed files with 56578 additions and 47148 deletions
Expand all files Collapse all files

13
.dockerignore
View File

@@ -1,10 +1,11 @@
.git/
.pytest_cache/
.vscode/
.venv/
docs/
.*
**/__pycache__/
*.egg-info/
documentation/
tests/
build/
dist/
scripts/
*.egg-info/
src/interface/
src/telemetry/
!src/interface/web

4
.github/workflows/build_khoj_el.yml vendored
View File

@@ -21,9 +21,9 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Set up Python 3.9
- name: Set up Python 3.11
uses: actions/setup-python@v1
with: { python-version: 3.9 }
with: { python-version: 3.11 }
- name: ⏬️ Install Dependencies
run: |
python -m pip install --upgrade pip

8
.github/workflows/desktop.yml vendored
View File

@@ -42,10 +42,10 @@ jobs:
run: |
npx todesktop build
- name: 📦 Release Desktop App
if: startsWith(github.ref, 'refs/tags/')
run: |
npx todesktop release --latest --force
# - name: 📦 Release Desktop App
# if: startsWith(github.ref, 'refs/tags/')
# run: |
# npx todesktop release --latest --force
- name: ⤵️ Get Desktop Apps
if: startsWith(github.ref, 'refs/tags/')

75
.github/workflows/dockerize.yml vendored
View File

@@ -8,6 +8,7 @@ on:
- master
paths:
- src/khoj/**
- src/interface/web/**
- pyproject.toml
- Dockerfile
- prod.Dockerfile
@@ -30,19 +31,30 @@ on:
env:
# Tag Image with tag name on release
# else with user specified tag (default 'dev') if triggered via workflow
# else with run_id if triggered via a pull request
# else with 'pre' (if push to master)
DOCKER_IMAGE_TAG: ${{ github.ref_type == 'tag' && github.ref_name || github.event_name == 'workflow_dispatch' && github.event.inputs.tag || 'pre' }}
jobs:
build:
name: Publish Khoj Docker Images
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
image:
- 'local'
- 'cloud'
include:
- image: 'local'
platform: linux/amd64
runner: ubuntu-latest
- image: 'local'
platform: linux/arm64
runner: ubuntu-linux-arm64
- image: 'cloud'
platform: linux/amd64
runner: ubuntu-latest
- image: 'cloud'
platform: linux/arm64
runner: ubuntu-linux-arm64
runs-on: ${{ matrix.runner }}
steps:
- name: Checkout Code
uses: actions/checkout@v3
@@ -68,31 +80,70 @@ jobs:
run: rm -rf /opt/hostedtoolcache
- name: 📦 Build and Push Docker Image
uses: docker/build-push-action@v2
uses: docker/build-push-action@v4
if: (matrix.image == 'local' && github.event_name == 'workflow_dispatch') && github.event.inputs.khoj == 'true' || (matrix.image == 'local' && github.event_name == 'push')
with:
context: .
file: Dockerfile
platforms: linux/amd64, linux/arm64
push: true
tags: |
ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }}
${{ github.ref_type == 'tag' && format('ghcr.io/{0}:latest', github.repository) || '' }}
ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }}-${{ matrix.platform == 'linux/amd64' && 'amd64' || 'arm64' }}
build-args: |
VERSION=${{ steps.hatch.outputs.version }}
PORT=42110
cache-from: type=gha,scope=${{ matrix.image }}-${{ matrix.platform }}
cache-to: type=gha,mode=max,scope=${{ matrix.image }}-${{ matrix.platform}}
labels: |
org.opencontainers.image.description=Khoj AI - Your second brain powered by LLMs and Neural Search
org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
- name: 📦️⛅️ Build and Push Cloud Docker Image
uses: docker/build-push-action@v2
uses: docker/build-push-action@v4
if: (matrix.image == 'cloud' && github.event_name == 'workflow_dispatch') && github.event.inputs.khoj-cloud == 'true' || (matrix.image == 'cloud' && github.event_name == 'push')
with:
context: .
file: prod.Dockerfile
platforms: linux/amd64
push: true
tags: |
ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }}
${{ github.ref_type == 'tag' && format('ghcr.io/{0}-cloud:latest', github.repository) || '' }}
ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }}-${{ matrix.platform == 'linux/amd64' && 'amd64' || 'arm64' }}
build-args: |
VERSION=${{ steps.hatch.outputs.version }}
PORT=42110
cache-from: type=gha,scope=${{ matrix.image }}-${{ matrix.platform }}
cache-to: type=gha,mode=max,scope=${{ matrix.image }}-${{ matrix.platform}}
labels: |
org.opencontainers.image.description=Khoj AI Cloud - Your second brain powered by LLMs and Neural Search
org.opencontainers.image.source=${{ github.server_url }}/${{ github.repository }}
manifest:
needs: build
runs-on: ubuntu-latest
if: github.event_name != 'pull_request'
steps:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to GitHub Container Registry
uses: docker/login-action@v2
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
password: ${{ secrets.PAT }}
- name: Create and Push Local Manifest
if: github.event.inputs.khoj == 'true' || github.event_name == 'push'
run: |
docker buildx imagetools create \
-t ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }} \
-t ghcr.io/${{ github.repository }}:${{ github.ref_type == 'tag' && 'latest' || env.DOCKER_IMAGE_TAG }} \
ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }}-amd64 \
ghcr.io/${{ github.repository }}:${{ env.DOCKER_IMAGE_TAG }}-arm64
- name: Create and Push Cloud Manifest
if: github.event.inputs.khoj-cloud == 'true' || github.event_name == 'push'
run: |
docker buildx imagetools create \
-t ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }} \
-t ghcr.io/${{ github.repository }}-cloud:${{ github.ref_type == 'tag' && 'latest' || env.DOCKER_IMAGE_TAG }} \
ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }}-amd64 \
ghcr.io/${{ github.repository }}-cloud:${{ env.DOCKER_IMAGE_TAG }}-arm64

6
.github/workflows/pre-commit.yml vendored
View File

@@ -22,7 +22,7 @@ on:
jobs:
test:
name: Run Tests
name: Setup Application and Lint
runs-on: ubuntu-latest
strategy:
fail-fast: false
@@ -31,7 +31,7 @@ jobs:
with:
fetch-depth: 0
- name: Set up Python
- name: Set up Python 3.11
uses: actions/setup-python@v4
with:
python-version: 3.11
@@ -42,7 +42,7 @@ jobs:
python -m pip install --upgrade pip
- name: ⬇️ Install Application
run: pip install --upgrade .[dev]
run: pip install --no-cache-dir --upgrade .[dev]
- name: 🌡️ Validate Application
run: pre-commit run --hook-stage manual --all

39
.github/workflows/pypi.yml vendored
View File

@@ -8,6 +8,7 @@ on:
- 'master'
paths:
- src/khoj/**
- src/interface/web/**
- pyproject.toml
- .github/workflows/pypi.yml
pull_request:
@@ -15,26 +16,41 @@ on:
- 'master'
paths:
- src/khoj/**
- src/interface/web/**
- pyproject.toml
- .github/workflows/pypi.yml
workflow_dispatch:
jobs:
publish:
name: Publish Python Package to PyPI
runs-on: ubuntu-20.04
runs-on: ubuntu-latest
permissions:
id-token: write
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Set up Python 3.10
- name: Set up Python 3.11
uses: actions/setup-python@v4
with:
python-version: '3.10'
python-version: '3.11'
- name: ⬇️ Install Application
- name: ⬇️ Install Server
run: python -m pip install --upgrade pip && pip install --upgrade .
- name: ⬇️ Install Web Client
run: |
yarn install
yarn pypiciexport
working-directory: src/interface/web
- name: 📂 Copy Generated Files
run: |
mkdir -p src/khoj/interface/compiled
cp -r /opt/hostedtoolcache/Python/3.11.11/x64/lib/python3.11/site-packages/khoj/interface/compiled/* src/khoj/interface/compiled/
- name: ⚙️ Build Python Package
run: |
# Setup Environment for Reproducible Builds
@@ -42,7 +58,7 @@ jobs:
export SOURCE_DATE_EPOCH=$(git log -1 --pretty=%ct)
rm -rf dist
# Build PyPi Package
# Build PyPI Package
pipx run build
- name: 🌡️ Validate Python Package
@@ -52,13 +68,14 @@ jobs:
pipx run twine check dist/*
- name: ⏫ Upload Python Package Artifacts
uses: actions/upload-artifact@v3
uses: actions/upload-artifact@v4
with:
name: khoj-assistant
path: dist/*.whl
name: khoj
path: dist/khoj-*.whl
- name: 📦 Publish Python Package to PyPI
if: startsWith(github.ref, 'refs/tags') || github.ref == 'refs/heads/master'
uses: pypa/gh-action-pypi-publish@v1.6.4
uses: pypa/gh-action-pypi-publish@release/v1.12
with:
password: ${{ secrets.PYPI_API_KEY }}
skip-existing: true
print-hash: true

158
.github/workflows/run_evals.yml vendored Normal file
View File

@@ -0,0 +1,158 @@
name: eval
on:
# Run on every release
push:
tags:
- "*"
# Allow manual triggers from GitHub UI
workflow_dispatch:
inputs:
khoj_mode:
description: 'Khoj Mode (general/default/research)'
required: true
default: 'default'
type: choice
options:
- general
- default
- research
dataset:
description: 'Dataset to evaluate (frames/simpleqa)'
required: true
default: 'frames'
type: choice
options:
- frames
- simpleqa
- gpqa
- math500
sample_size:
description: 'Number of samples to evaluate'
required: false
default: 200
type: number
jobs:
eval:
runs-on: ubuntu-latest
strategy:
matrix:
# Use input from manual trigger if available, else run all combinations
khoj_mode: ${{ github.event_name == 'workflow_dispatch' && fromJSON(format('["{0}"]', inputs.khoj_mode)) || fromJSON('["general", "default", "research"]') }}
dataset: ${{ github.event_name == 'workflow_dispatch' && fromJSON(format('["{0}"]', inputs.dataset)) || fromJSON('["frames", "simpleqa"]') }}
services:
postgres:
image: ankane/pgvector
env:
POSTGRES_PASSWORD: postgres
POSTGRES_USER: postgres
POSTGRES_DB: postgres
ports:
- 5432:5432
options: >-
--health-cmd pg_isready
--health-interval 10s
--health-timeout 5s
--health-retries 5
steps:
- uses: actions/checkout@v3
with:
fetch-depth: 0
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.10'
- name: Get App Version
id: hatch
run: echo "version=$(pipx run hatch version)" >> $GITHUB_OUTPUT
- name: ⏬️ Install Dependencies
env:
DEBIAN_FRONTEND: noninteractive
run: |
# install postgres and other dependencies
sudo apt update && sudo apt install -y git python3-pip libegl1 sqlite3 libsqlite3-dev libsqlite3-0 ffmpeg libsm6 libxext6
sudo apt install -y postgresql postgresql-client && sudo apt install -y postgresql-server-dev-14
# upgrade pip
python -m ensurepip --upgrade && python -m pip install --upgrade pip
# install terrarium for code sandbox
git clone https://github.com/khoj-ai/terrarium.git && cd terrarium && npm install --legacy-peer-deps && mkdir pyodide_cache
- name: ⬇️ Install Application
run: |
sed -i 's/dynamic = \["version"\]/version = "${{ steps.hatch.outputs.version }}"/' pyproject.toml
pip install --upgrade .[dev]
- name: 📝 Run Eval
env:
KHOJ_MODE: ${{ matrix.khoj_mode }}
SAMPLE_SIZE: ${{ github.event_name == 'workflow_dispatch' && inputs.sample_size || 200 }}
BATCH_SIZE: "20"
RANDOMIZE: "True"
KHOJ_URL: "http://localhost:42110"
KHOJ_LLM_SEED: "42"
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
SERPER_DEV_API_KEY: ${{ matrix.dataset != 'math500' && secrets.SERPER_DEV_API_KEY }}
OLOSTEP_API_KEY: ${{ matrix.dataset != 'math500' && secrets.OLOSTEP_API_KEY }}
HF_TOKEN: ${{ secrets.HF_TOKEN }}
KHOJ_ADMIN_EMAIL: khoj
KHOJ_ADMIN_PASSWORD: khoj
POSTGRES_HOST: localhost
POSTGRES_PORT: 5432
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: postgres
KHOJ_TELEMETRY_DISABLE: "True" # To disable telemetry for tests
run: |
# Start Khoj server in background
khoj --anonymous-mode --non-interactive &
# Start code sandbox
npm install -g pm2
npm run ci --prefix terrarium
# Wait for server to be ready
timeout=120
while ! curl -s http://localhost:42110/api/health > /dev/null; do
if [ $timeout -le 0 ]; then
echo "Timed out waiting for Khoj server"
exit 1
fi
echo "Waiting for Khoj server..."
sleep 2
timeout=$((timeout-2))
done
# Run evals
python tests/evals/eval.py -d ${{ matrix.dataset }}
- name: Upload Results
if: always() # Upload results even if tests fail
uses: actions/upload-artifact@v3
with:
name: eval-results-${{ steps.hatch.outputs.version }}-${{ matrix.khoj_mode }}-${{ matrix.dataset }}
path: |
*_evaluation_results_*.csv
*_evaluation_summary_*.txt
- name: Display Results
if: always()
run: |
# Read and display summary
echo "## Evaluation Summary of Khoj on ${{ matrix.dataset }} in ${{ matrix.khoj_mode }} mode" >> $GITHUB_STEP_SUMMARY
echo "**$(head -n 1 *_evaluation_summary_*.txt)**" >> $GITHUB_STEP_SUMMARY
echo "- Khoj Version: ${{ steps.hatch.outputs.version }}" >> $GITHUB_STEP_SUMMARY
echo "- Chat Model: Gemini 1.5 Flash 002" >> $GITHUB_STEP_SUMMARY
echo "\`\`\`" >> $GITHUB_STEP_SUMMARY
tail -n +2 *_evaluation_summary_*.txt >> $GITHUB_STEP_SUMMARY
echo "" >> $GITHUB_STEP_SUMMARY
echo "\`\`\`" >> $GITHUB_STEP_SUMMARY
# Display in logs too
echo "===== EVALUATION RESULTS ====="
cat *_evaluation_summary_*.txt

15
.github/workflows/test.yml vendored
View File

@@ -5,6 +5,7 @@ on:
paths:
- src/khoj/**
- tests/**
- '!tests/evals/**'
- config/**
- pyproject.toml
- .pre-commit-config.yml
@@ -15,6 +16,7 @@ on:
paths:
- src/khoj/**
- tests/**
- '!tests/evals/**'
- config/**
- pyproject.toml
- .pre-commit-config.yml
@@ -29,9 +31,9 @@ jobs:
fail-fast: false
matrix:
python_version:
- '3.9'
- '3.10'
- '3.11'
- '3.12'
services:
postgres:
@@ -53,15 +55,13 @@ jobs:
with:
python-version: ${{ matrix.python_version }}
- name: Install Git
run: |
apt update && apt install -y git
- name: ⏬️ Install Dependencies
env:
DEBIAN_FRONTEND: noninteractive
run: |
apt update && apt install -y libegl1 sqlite3 libsqlite3-dev libsqlite3-0 ffmpeg libsm6 libxext6
apt update && apt install -y git libegl1 sqlite3 libsqlite3-dev libsqlite3-0 ffmpeg libsm6 libxext6
# required by llama-cpp-python prebuilt wheels
apt install -y musl-dev && ln -s /usr/lib/x86_64-linux-musl/libc.so /lib/libc.musl-x86_64.so.1
- name: ⬇️ Install Postgres
env:
@@ -76,6 +76,9 @@ jobs:
python -m pip install --upgrade pip
- name: ⬇️ Install Application
env:
PIP_EXTRA_INDEX_URL: "https://download.pytorch.org/whl/cpu https://abetlen.github.io/llama-cpp-python/whl/cpu"
CUDA_VISIBLE_DEVICES: ""
run: sed -i 's/dynamic = \["version"\]/version = "0.0.0"/' pyproject.toml && pip install --upgrade .[dev]
- name: 🧪 Test Application

16
.gitignore vendored
View File

@@ -16,13 +16,15 @@ todesktop.json
# Build artifacts
/src/khoj/interface/web/images
/src/khoj/interface/built/
/src/khoj/interface/compiled/404.html
/build/
/dist/
khoj_assistant.egg-info
/config/khoj*.yml
.pytest_cache
*.log
static
/src/khoj/static
# Obsidian plugin artifacts
# ---
@@ -35,6 +37,18 @@ src/interface/obsidian/main.js
# Exclude sourcemaps
*.map
# IntelliJ
.idea
# obsidian
data.json
# Android
src/interface/android/.gradle
src/interface/android/app/build
src/interface/android/build
src/interface/android/*.aab
src/interface/android/*.apk
src/interface/android/*.apk.idsig
src/interface/android/*.keystore
src/interface/android/local.properties

2
.pre-commit-config.yaml
View File

@@ -26,7 +26,7 @@ repos:
rev: v1.0.0
hooks:
- id: mypy
stages: [push, manual]
stages: [pre-push, manual]
pass_filenames: false
args:
- --config-file=pyproject.toml

55
Dockerfile
View File

@@ -1,28 +1,63 @@
# syntax=docker/dockerfile:1
FROM ubuntu:jammy
LABEL org.opencontainers.image.source https://github.com/khoj-ai/khoj
FROM ubuntu:jammy AS base
LABEL homepage="https://khoj.dev"
LABEL repository="https://github.com/khoj-ai/khoj"
LABEL org.opencontainers.image.source="https://github.com/khoj-ai/khoj"
LABEL org.opencontainers.image.description="Your second brain, containerized for personal, local deployment."
# Install System Dependencies
RUN apt update -y && apt -y install python3-pip swig
RUN apt update -y && apt -y install \
python3-pip \
swig \
curl \
# Required by RapidOCR
libgl1 \
libglx-mesa0 \
libglib2.0-0 \
# Required by llama-cpp-python pre-built wheels. See #1628
musl-dev && \
ln -s /usr/lib/x86_64-linux-musl/libc.so /lib/libc.musl-x86_64.so.1 && \
# Clean up
apt clean && rm -rf /var/lib/apt/lists/*
# Build Server
FROM base AS server-deps
WORKDIR /app
# Install Application
COPY pyproject.toml .
COPY README.md .
ARG VERSION=0.0.0
# use the pre-built llama-cpp-python, torch cpu wheel
ENV PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu https://abetlen.github.io/llama-cpp-python/whl/cpu"
# avoid downloading unused cuda specific python packages
ENV CUDA_VISIBLE_DEVICES=""
RUN sed -i "s/dynamic = \\[\"version\"\\]/version = \"$VERSION\"/" pyproject.toml && \
pip install --no-cache-dir .
# Copy Source Code
COPY . .
# Build Web App
FROM node:20-alpine AS web-app
# Set build optimization env vars
ENV NODE_ENV=production
ENV NEXT_TELEMETRY_DISABLED=1
WORKDIR /app/src/interface/web
# Install dependencies first (cache layer)
COPY src/interface/web/package.json src/interface/web/yarn.lock ./
RUN yarn install --frozen-lockfile
# Copy source and build
COPY src/interface/web/. ./
RUN yarn build
# Set the PYTHONPATH environment variable in order for it to find the Django app.
ENV PYTHONPATH=/app/src:$PYTHONPATH
# Merge the Server and Web App into a Single Image
FROM base
ENV PYTHONPATH=/app/src
WORKDIR /app
COPY --from=server-deps /usr/local/lib/python3.10/dist-packages /usr/local/lib/python3.10/dist-packages
COPY --from=web-app /app/src/interface/web/out ./src/khoj/interface/built
COPY . .
RUN cd src && python3 khoj/manage.py collectstatic --noinput
# Run the Application
# There are more arguments required for the application to run,
# but these should be passed in through the docker-compose.yml file.
# but those should be passed in through the docker-compose.yml file.
ARG PORT
EXPOSE ${PORT}
ENTRYPOINT ["python3", "src/khoj/main.py"]

64
README.md
View File

@@ -1,47 +1,71 @@
<p align="center"><img src="src/khoj/interface/web/assets/icons/khoj-logo-sideways-500.png" width="230" alt="Khoj Logo"></p>
<p align="center"><img src="https://assets.khoj.dev/khoj-logo-sideways-1200x540.png" width="230" alt="Khoj Logo"></p>
<div align="center">
[![test](https://github.com/khoj-ai/khoj/actions/workflows/test.yml/badge.svg)](https://github.com/khoj-ai/khoj/actions/workflows/test.yml)
[![dockerize](https://github.com/khoj-ai/khoj/actions/workflows/dockerize.yml/badge.svg)](https://github.com/khoj-ai/khoj/pkgs/container/khoj)
[![pypi](https://github.com/khoj-ai/khoj/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/khoj-assistant/)
[![docker](https://github.com/khoj-ai/khoj/actions/workflows/dockerize.yml/badge.svg)](https://github.com/khoj-ai/khoj/pkgs/container/khoj)
[![pypi](https://github.com/khoj-ai/khoj/actions/workflows/pypi.yml/badge.svg)](https://pypi.org/project/khoj/)
[![discord](https://img.shields.io/discord/1112065956647284756?style=plastic&label=discord)](https://discord.gg/BDgyabRM6e)
</div>
<div align="center">
<b>An AI personal assistant for your digital brain</b>
<b>Your AI second brain</b>
</div>
<br />
<div align="center">
[📜 Read Docs](https://docs.khoj.dev)
[📑 Docs](https://docs.khoj.dev)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[🌍 Try Khoj Cloud](https://khoj.dev)
[🌐 Web](https://khoj.dev)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[💬 Get Involved](https://discord.gg/BDgyabRM6e)
[🔥 App](https://app.khoj.dev)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[💬 Discord](https://discord.gg/BDgyabRM6e)
<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
[✍🏽 Blog](https://blog.khoj.dev)
</div>
<div align="center">
***
### 🎁 New
* Start any message with `/research` to try out the experimental research mode with Khoj.
* Anyone can now [create custom agents](https://blog.khoj.dev/posts/create-agents-on-khoj/) with tunable personality, tools and knowledge bases.
* [Read](https://blog.khoj.dev/posts/evaluate-khoj-quality/) about Khoj's excellent performance on modern retrieval and reasoning benchmarks.
***
Khoj is an AI application to search and chat with your notes and documents.<br />
It is open-source, self-hostable and accessible on Desktop, Emacs, Obsidian, Web and Whatsapp.<br />
It works with pdf, markdown, org-mode, notion files and github repositories.<br />
It can paint, search the internet and understand speech.<br />
## Overview
[Khoj](https://khoj.dev) is a personal AI app to extend your capabilities. It smoothly scales up from an on-device personal AI to a cloud-scale enterprise AI.
- Chat with any local or online LLM (e.g llama3, qwen, gemma, mistral, gpt, claude, gemini).
- Get answers from the internet and your docs (including image, pdf, markdown, org-mode, word, notion files).
- Access it from your Browser, Obsidian, Emacs, Desktop, Phone or Whatsapp.
- Create agents with custom knowledge, persona, chat model and tools to take on any role.
- Automate away repetitive research. Get personal newsletters and smart notifications delivered to your inbox.
- Find relevant docs quickly and easily using our advanced semantic search.
- Generate images, talk out loud, play your messages.
- Khoj is open-source, self-hostable. Always.
- Run it privately on [your computer](https://docs.khoj.dev/get-started/setup) or try it on our [cloud app](https://app.khoj.dev).
***
</div>
## See it in action
| 🔎 Search | 💬 Chat |
|:---------:|:-------:|
| Quickly retrieve relevant documents using natural language | Get answers and create content from your existing knowledge base |
| Does not need internet | Can be configured to work without internet |
| <img src="https://docs.khoj.dev/img/khoj_search_on_web.png" width="400px"> | <img src="https://docs.khoj.dev/img/khoj_chat_on_web.png" width="400px"> |
![demo_chat](https://github.com/khoj-ai/khoj/blob/master/documentation/assets/img/quadratic_equation_khoj_web.gif?raw=true)
Go to https://app.khoj.dev to see Khoj live.
## Full feature list
You can see the full feature list [here](https://docs.khoj.dev/category/features).
## Self-Host
To get started with self-hosting Khoj, [read the docs](https://docs.khoj.dev/get-started/setup).
## Contributors
Cheers to our awesome contributors! 🎉
@@ -51,3 +75,7 @@ Cheers to our awesome contributors! 🎉
</a>
Made with [contrib.rocks](https://contrib.rocks).
### Interested in Contributing?
We are always looking for contributors to help us build new features, improve the project documentation, or fix bugs. If you're interested, please see our [Contributing Guidelines](https://docs.khoj.dev/contributing/development) and check out our [Contributors Project Board](https://github.com/orgs/khoj-ai/projects/4).

62
docker-compose.yml
View File

@@ -1,4 +1,3 @@
version: "3.9"
services:
database:
image: ankane/pgvector
@@ -15,13 +14,25 @@ services:
interval: 30s
timeout: 10s
retries: 5
sandbox:
image: ghcr.io/khoj-ai/terrarium:latest
ports:
- "8080:8080"
search:
image: docker.io/searxng/searxng:latest
ports:
- "42113:8080"
volumes:
- khoj_search:/etc/searxng
environment:
- SEARXNG_BASE_URL=http://localhost:42113/
server:
depends_on:
database:
condition: service_healthy
# Use the following line to use the latest version of khoj. Otherwise, it will build from source.
# Use the following line to use the latest version of khoj. Otherwise, it will build from source. Set this to ghcr.io/khoj-ai/khoj-cloud:latest if you want to use the prod image.
image: ghcr.io/khoj-ai/khoj:latest
# Uncomment the following line to build from source. This will take a few minutes. Comment the next two lines out if you want to use the offiicial image.
# Uncomment the following line to build from source. This will take a few minutes. Comment the next two lines out if you want to use the official image.
# build:
# context: .
ports:
@@ -34,6 +45,7 @@ services:
volumes:
- khoj_config:/root/.khoj/
- khoj_models:/root/.cache/torch/sentence_transformers
- khoj_models:/root/.cache/huggingface
# Use 0.0.0.0 to explicitly set the host ip for the service on the container. https://pythonspeed.com/articles/docker-connection-refused/
environment:
- POSTGRES_DB=postgres
@@ -42,13 +54,53 @@ services:
- POSTGRES_HOST=database
- POSTGRES_PORT=5432
- KHOJ_DJANGO_SECRET_KEY=secret
- KHOJ_DEBUG=True
- KHOJ_DEBUG=False
- KHOJ_ADMIN_EMAIL=username@example.com
- KHOJ_ADMIN_PASSWORD=password
command: --host="0.0.0.0" --port=42110 -vv --anonymous-mode
# Default URL of Terrarium, the Python sandbox used by Khoj to run code. Its container is specified above
- KHOJ_TERRARIUM_URL=http://host.docker.internal:8080
# Default URL of SearxNG, the default web search engine used by Khoj. Its container is specified above
- KHOJ_SEARXNG_URL=http://host.docker.internal:42113
# Uncomment line below to use with Ollama running on your local machine at localhost:11434.
# Change URL to use with other OpenAI API compatible providers like VLLM, LMStudio etc.
# - OPENAI_API_BASE=http://host.docker.internal:11434/v1/
#
# Uncomment appropriate lines below to use chat models by OpenAI, Anthropic, Google.
# Ensure you set your provider specific API keys.
# ---
# - OPENAI_API_KEY=your_openai_api_key
# - GEMINI_API_KEY=your_gemini_api_key
# - ANTHROPIC_API_KEY=your_anthropic_api_key
#
# Uncomment appropriate lines below to enable web results with Khoj
# Ensure you set your provider specific API keys.
# ---
# Free, Slower API. Does both web search and webpage read. Get API key from https://jina.ai/
# - JINA_API_KEY=your_jina_api_key
# Paid, Fast API. Only does web search. Get API key from https://serper.dev/
# - SERPER_DEV_API_KEY=your_serper_dev_api_key
# Paid, Fast, Open API. Only does webpage read. Get API key from https://firecrawl.dev/
# - FIRECRAWL_API_KEY=your_firecrawl_api_key
# Paid, Fast, Higher Read Success API. Only does webpage read. Get API key from https://olostep.com/
# - OLOSTEP_API_KEY=your_olostep_api_key
#
# Uncomment the necessary lines below to make your instance publicly accessible.
# Replace the KHOJ_DOMAIN with either your domain or IP address (no http/https prefix).
# Proceed with caution, especially if you are using anonymous mode.
# ---
# - KHOJ_NO_HTTPS=True
# - KHOJ_DOMAIN=192.168.0.104
# - KHOJ_DOMAIN=khoj.example.com
# Uncomment the line below to disable telemetry.
# Telemetry helps us prioritize feature development and understand how people are using Khoj
# Read more at https://docs.khoj.dev/miscellaneous/telemetry
# - KHOJ_TELEMETRY_DISABLE=True
# Comment out this line when you're using the official ghcr.io/khoj-ai/khoj-cloud:latest prod image.
command: --host="0.0.0.0" --port=42110 -vv --anonymous-mode --non-interactive
volumes:
khoj_config:
khoj_db:
khoj_models:
khoj_search:

BIN
documentation/assets/img/admin_get_emali_login.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 89 KiB

BIN
documentation/assets/img/admin_successful_login_url.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 66 KiB

BIN
documentation/assets/img/agents_page_full.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 511 KiB

BIN
documentation/assets/img/chrome_pwa_alt.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 500 KiB

BIN
documentation/assets/img/dream_house.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 3.0 MiB

BIN
documentation/assets/img/example_chatmodel_option.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 34 KiB

BIN
documentation/assets/img/example_openai_processor_config.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 21 KiB

BIN
documentation/assets/img/example_search_model_admin_settings.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.2 MiB

BIN
documentation/assets/img/favicon-128x128.ico
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 200 KiB

After

Width:  |  Height:  |  Size: 170 KiB

BIN
documentation/assets/img/file_filters_conversation.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 18 KiB

BIN
documentation/assets/img/khoj_automation_email.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 232 KiB

BIN
documentation/assets/img/khoj_chat_on_desktop.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 298 KiB

BIN
documentation/assets/img/khoj_chat_on_web.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 358 KiB

After

Width:  |  Height:  |  Size: 187 KiB

BIN
documentation/assets/img/khoj_create_automation.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 102 KiB

BIN
documentation/assets/img/khoj_documentation.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 868 KiB

BIN
documentation/assets/img/khoj_search_on_desktop.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 333 KiB

BIN
documentation/assets/img/khoj_web_app_home.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 214 KiB

1
documentation/assets/img/logo.svg
View File

File diff suppressed because one or more lines are too long
Side by Side

Before

Width:  |  Height:  |  Size: 6.3 KiB

BIN
documentation/assets/img/magic_link.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 23 KiB

BIN
documentation/assets/img/plants_i_got.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 3.0 MiB

BIN
documentation/assets/img/pwa_install_1.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 103 KiB

BIN
documentation/assets/img/pwa_install_2.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 119 KiB

BIN
documentation/assets/img/pwa_install_3.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 265 KiB

BIN
documentation/assets/img/pwa_install_desktop.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 15 KiB

BIN
documentation/assets/img/quadratic_equation_khoj_web.gif Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 19 MiB

BIN
documentation/assets/img/search_agents_markdown.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 336 KiB

BIN
documentation/assets/img/select_file_filter.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 31 KiB

BIN
documentation/assets/img/speaker_icon.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 9.4 KiB

BIN
documentation/assets/img/summarize.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 94 KiB

BIN
documentation/assets/img/text_to_speech.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.9 KiB

BIN
documentation/assets/img/using_khoj_for_studying.gif Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 32 MiB

8
documentation/docs/advanced/_category_.json Normal file
View File

@@ -0,0 +1,8 @@
{
"label": "Advanced Self Hosting",
"position": 6,
"link": {
"type": "generated-index",
"description": "Advanced setup for Self Hosting Khoj server"
}
}

74
documentation/docs/advanced/admin.md Normal file
View File

@@ -0,0 +1,74 @@
# Admin Panel
> Describes the Khoj settings configurable via the admin panel
By default, you admin panel is available at `http://localhost:42110/server/admin/`. You can access the admin panel by logging in with your admin credentials (this would be your `KHOJ_ADMIN_EMAIL` and `KHOJ_ADMIN_PASSWORD`). The admin panel allows you to configure various settings for your Khoj server.
## App Settings
### Agents
Add all the agents you want to use for your different use-cases like Writer, Researcher, Therapist etc.
- `Personality`: This is a prompt to tell the chat model how to tune the personality of the agent.
- `Chat model`: The chat model to use for the agent.
- `Name`: The name of the agent. This field helps give the agent a unique identity across the app.
- `Avatar`: Url to the agents profile picture. It help give the agent a unique visual identity across the app.
- `Style color`, `Style icon`: These fields help give the agent a unique, visually identifiable identity across the app.
- `Slug`: This is the agent name to use in urls.
- `Public`: Check this if the agent is expected to be visible to all users on this Khoj server.
- `Managed by admin`: Check this if the agent is managed by admin, not by any user.
- `Creator`: The user who created the agent.
- `Tools`: The list of tools available to this agent. Tools include notes, image, online. This field is not currently configurable and only supports all tools (i.e `["*"]`)
### Chat Model Options
Add all the chat models you want to try, use and switch between for your different use-cases. For each chat model you add:
- `Chat model`: The name of an [OpenAI](https://platform.openai.com/docs/models), [Anthropic](https://docs.anthropic.com/en/docs/about-claude/models#model-names), [Gemini](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-models) or [Offline](https://huggingface.co/models?pipeline_tag=text-generation&library=gguf) chat model.
- `Model type`: The chat model provider like `OpenAI`, `Offline`.
- `Vision enabled`: Set to `true` if your model supports vision. This is currently only supported for vision capable OpenAI models like `gpt-4o`
- `Max prompt size`, `Subscribed max prompt size`: These are optional fields. They are used to truncate the context to the maximum context size that can be passed to the model. This can help with accuracy and cost-saving.<br />
- `Tokenizer`: This is an optional field. It is used to accurately count tokens and truncate context passed to the chat model to stay within the models max prompt size.
![example configuration for chat model options](/img/example_chatmodel_option.png)
### Server Chat Settings
The server chat settings are used as:
1. The default chat models for subscribed (`Advanced` field) and unsubscribed (`Default` field) users.
2. The chat model for all intermediate steps like intent detection, web search etc. during chat response generation.
If a server chat setting is not added the first ChatModelOption in your config is used as the default chat model.
To add a server chat setting:
- Set your preferred default chat models in the `Default` fields of your [ServerChatSettings](http://localhost:42110/server/admin/database/serverchatsettings/)
- The `Advanced` field doesn't need to be set when self-hosting. When unset, the `Default` chat model is used for all users and the intermediate steps.
### AI Model API
These settings configure APIs to interact with AI models.
For each AI Model API you [add](http://localhost:42110/server/admin/database/aimodelapi/add):
- `Api key`: Set to your [OpenAI](https://platform.openai.com/api-keys), [Anthropic](https://console.anthropic.com/account/keys) or [Gemini](https://aistudio.google.com/app/apikey) API keys.
- `Name`: Give the configuration any friendly name like `OpenAI`, `Gemini`, `Anthropic`.
- `Api base url`: Set the API base URL. This is only relevant to set if you're using another OpenAI-compatible proxy server like [Ollama](/advanced/ollama) or [LMStudio](/advanced/lmstudio).
![example configuration for ai model api](/img/example_openai_processor_config.png)
### Search Model Configs
Search models are used to generate vector embeddings of your documents for natural language search and chat. You can choose any [embeddings models on HuggingFace](https://huggingface.co/models?pipeline_tag=sentence-similarity) to try, use for your to create vector embeddings of your documents for natural language search and chat.
<img src="/img/example_search_model_admin_settings.png" alt="Example Search Model Settings" style={{width: 500}} />
### Text to Image Model Options
Add text to image generation models with these settings. Khoj currently supports text to image models available via OpenAI, Stability or Replicate API
- `api-key`: Set to your OpenAI, Stability or Replicate API key
- `model`: Set the model name available over the selected model provider
- `model-type`: Set to the appropiate model provider
- `openai-config`: For image generation models available via OpenAI (compatible) API you can set the appropriate OpenAI Processor Conversation Settings instead of specifying the `api-key` field above
### Speech to Text Model Options
Add speech to text models with these settings. Khoj currently only supports whisper speech to text model via OpenAI API or Offline
### Voice Model Options
Add text to speech models with these settings. Khoj currently supports models from [ElevenLabs](https://elevenlabs.io/).
## User Data
- Users, Entrys, Conversations, Subscriptions, Github configs, Notion configs, User search configs, User conversation configs, User voice configs
## Miscellaneous Data
- Process Locks: Persistent Locks for Automations
- Client Applications:
Client applications allow you to setup third party applications that can query your Khoj server using a client application ID + secret. The secret would go in a bearer token.

74
documentation/docs/advanced/authentication.mdx Normal file
View File

@@ -0,0 +1,74 @@
# Authenticate (Multi-User Setup)
```mdx-code-block
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
```
By default, most of the instructions for self-hosting Khoj assume a single user, and so the default configuration is to run in anonymous mode. However, if you want to enable authentication, you can do so either with with [Magic Links](#using-magic-links) or [Google OAuth](#using-google-oauth) as shown below. This can be helpful to make Khoj securely accessible to you and your team.
:::tip[Note]
Remove the `--anonymous-mode` flag from your khoj start up command or docker-compose file to enable authentication.
:::
## Using Magic Links
The most secure way to do this is to integrate with [Resend](https://resend.com).
1. Setup your account at https://resend.com
2. Set an environment variable for `RESEND_API_KEY`. You can get your API key [here](https://resend.com/api-keys).
3. Set an environment variable for `RESEND_EMAIL`. This is the email address that will show up in your `from` field when sending magic links.
This will allow you to automatically send sign-in links to users who want to log in.
It's still possible to use the magic links feature without Resend, but you'll need to manually send the magic links to users who want to log in.
## Manually sending magic links
1. The user will have to enter their email address in the login page at http://localhost:42110/login.
They'll click `Get Login Link`. Without the Resend API key, this will just create an unverified account for them in the backend
<img src="/img/magic_link.png" alt="Magic link login form" width="400"/>
2. You can get their magic link using the admin panel
Go to the [admin panel](http://localhost:42110/server/admin/database/khojuser/). You'll see a list of users. Search for the user you want to send a magic link to. Tick the checkbox next to their row, and use the action drop down at the top to 'Get email login URL'. This will generate a magic link that you can send to the user, which will appear at the top of the admin interface.
| Get email login URL | Retrieved login URL |
|---------------------|---------------------|
| <img src="/img/admin_get_emali_login.png" alt="Get user magic sign in link" width="400" />| <img src="/img/admin_successful_login_url.png" alt="Successfully retrieved a login URL" width="400" />|
3. Send the magic link to the user. They can click on it to log in.
Once they click on the link, they'll automatically be logged in. They'll have to repeat this process for every new device they want to log in from, but they shouldn't have to repeat it on the same device.
A given magic link can only be used once. If the user tries to use it again, they'll be redirected to the login page to get a new magic link.
## Using Google OAuth
For this method, you'll need to use the prod version of the Khoj package. You can install it as below:
<Tabs groupId="server" queryString>
<TabItem value="docker" label="Docker">
Update your `docker-compose.yml` to use the prod image
```bash
image: ghcr.io/khoj-ai/khoj-cloud:latest
```
</TabItem>
<TabItem value="pip" label="Pip">
```bash
pip install khoj[prod]
```
</TabItem>
</Tabs>
To set up your self-hosted Khoj with Google Auth, you need to create a project in the Google Cloud Console and enable the Google Auth API.
To implement this, you'll need to:
1. [Create authorization credentials](https://developers.google.com/identity/sign-in/web/sign-in) for your application.
2. Open your [Google cloud console](https://console.developers.google.com/apis/credentials) and create a configuration like below for the relevant `OAuth 2.0 Client IDs` project:
![Google auth login project settings](https://github.com/khoj-ai/khoj/assets/65192171/9bcbf6f4-197d-4d0c-973a-c10b1331c892)
3. Configure these environment variables: `GOOGLE_CLIENT_SECRET`, and `GOOGLE_CLIENT_ID`. You can find these values in the Google cloud console, in the same place where you configured the authorized origins and redirect URIs.
That's it! That should be all you have to do. Now, when you reload Khoj without `--anonymous-mode`, you should be able to use your Google account to sign in.

34
documentation/docs/advanced/litellm.md Normal file
View File

@@ -0,0 +1,34 @@
# LiteLLM
:::info
This is only helpful for self-hosted users. If you're using [Khoj Cloud](https://app.khoj.dev), you're limited to our first-party models.
:::
:::info
Khoj natively supports local LLMs [available on HuggingFace in GGUF format](https://huggingface.co/models?library=gguf). Using an OpenAI API proxy with Khoj maybe useful for ease of setup, trying new models or using commercial LLMs via API.
:::
[LiteLLM](https://docs.litellm.ai/docs/proxy/quick_start) exposes an OpenAI compatible API that proxies requests to other LLM API services. This provides a standardized API to interact with both open-source and commercial LLMs.
Using LiteLLM with Khoj makes it possible to turn any LLM behind an API into your personal AI agent.
## Setup
1. Install LiteLLM
```bash
pip install litellm[proxy]
```
2. Start LiteLLM and use Mistral tiny via Mistral API
```
export MISTRAL_API_KEY=<MISTRAL_API_KEY>
litellm --model mistral/mistral-tiny --drop_params
```
3. Create a new [API Model API](http://localhost:42110/server/admin/database/aimodelapi/add) on your Khoj admin panel
- Name: `proxy-name`
- Api Key: `any string`
- Api Base Url: **URL of your Openai Proxy API**
4. Create a new [Chat Model](http://localhost:42110/server/admin/database/chatmodel/add) on your Khoj admin panel.
- Name: `llama3.1` (replace with the name of your local model)
- Model Type: `Openai`
- Openai Config: `<the proxy config you created in step 3>`
- Max prompt size: `20000` (replace with the max prompt size of your model)
- Tokenizer: *Do not set for OpenAI, Mistral, Llama3 based models*
5. Go to [your config](http://localhost:42110/settings) and select the model you just created in the chat model dropdown.

27
documentation/docs/advanced/lmstudio.md Normal file
View File

@@ -0,0 +1,27 @@
# LM Studio
:::info
This is only helpful for self-hosted users. If you're using [Khoj Cloud](https://app.khoj.dev), you're limited to our first-party models.
:::
:::info
Khoj natively supports local LLMs [available on HuggingFace in GGUF format](https://huggingface.co/models?library=gguf). Using an OpenAI API proxy with Khoj maybe useful for ease of setup, trying new models or using commercial LLMs via API.
:::
[LM Studio](https://lmstudio.ai/) is a desktop app to chat with open-source LLMs on your local machine. LM Studio provides a neat interface for folks comfortable with a GUI.
LM Studio can expose an [OpenAI API compatible server](https://lmstudio.ai/docs/local-server). This makes it possible to turn chat models from LM Studio into your personal AI agents with Khoj.
## Setup
1. Install [LM Studio](https://lmstudio.ai/) and download your preferred Chat Model
2. Go to the Server Tab on LM Studio, Select your preferred Chat Model and Click the green Start Server button
3. Create a new [OpenAI Processor Conversation Config](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/add) on your Khoj admin panel
- Name: `proxy-name`
- Api Key: `any string`
- Api Base Url: `http://localhost:1234/v1/` (default for LMStudio)
4. Create a new [Chat Model](http://localhost:42110/server/admin/database/chatmodel/add) on your Khoj admin panel.
- Name: `llama3.1` (replace with the name of your local model)
- Model Type: `Openai`
- Openai Config: `<the proxy config you created in step 3>`
- Max prompt size: `20000` (replace with the max prompt size of your model)
- Tokenizer: *Do not set for OpenAI, mistral, llama3 based models*
5. Go to [your config](http://localhost:42110/settings) and select the model you just created in the chat model dropdown.

78
documentation/docs/advanced/ollama.mdx Normal file
View File

@@ -0,0 +1,78 @@
# Ollama
```mdx-code-block
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
```
:::info
This is only helpful for self-hosted users. If you're using [Khoj Cloud](https://app.khoj.dev), you can use our first-party supported models.
:::
:::info
Khoj can directly run local LLMs [available on HuggingFace in GGUF format](https://huggingface.co/models?library=gguf). The integration with Ollama is useful to run Khoj on Docker and have the chat models use your GPU or to try new models via CLI.
:::
Ollama allows you to run [many popular open-source LLMs](https://ollama.com/library) locally from your terminal.
For folks comfortable with the terminal, Ollama's terminal based flows can ease setup and management of chat models.
Ollama exposes a local [OpenAI API compatible server](https://github.com/ollama/ollama/blob/main/docs/openai.md#models). This makes it possible to use chat models from Ollama with Khoj.
## Setup
:::info
Restart your Khoj server after first run or update to the settings below to ensure all settings are applied correctly.
:::
<Tabs groupId="type" queryString>
<TabItem value="first-run" label="First Run">
<Tabs groupId="server" queryString>
<TabItem value="docker" label="Docker">
1. Setup Ollama: https://ollama.com/
2. Download your preferred chat model with Ollama. For example,
```bash
ollama pull llama3.1
```
3. Uncomment `OPENAI_API_BASE` environment variable in your downloaded Khoj [docker-compose.yml](https://github.com/khoj-ai/khoj/blob/master/docker-compose.yml#:~:text=OPENAI_API_BASE)
4. Start Khoj docker for the first time to automatically integrate and load models from the Ollama running on your host machine
```bash
# run below command in the directory where you downloaded the Khoj docker-compose.yml
docker-compose up
```
</TabItem>
<TabItem value="pip" label="Pip">
1. Setup Ollama: https://ollama.com/
2. Download your preferred chat model with Ollama. For example,
```bash
ollama pull llama3.1
```
3. Set `OPENAI_API_BASE` environment variable to `http://localhost:11434/v1/` in your shell before starting Khoj for the first time
```bash
export OPENAI_API_BASE="http://localhost:11434/v1/"
khoj --anonymous-mode
```
</TabItem>
</Tabs>
</TabItem>
<TabItem value="update" label="Update">
1. Setup Ollama: https://ollama.com/
2. Download your preferred chat model with Ollama. For example,
```bash
ollama pull llama3.1
```
3. Create a new [AI Model API](http://localhost:42110/server/admin/database/aimodelapi/add) on your Khoj admin panel
- Name: `ollama`
- Api Key: `any string`
- Api Base Url: `http://localhost:11434/v1/` (default for Ollama)
4. Create a new [Chat Model](http://localhost:42110/server/admin/database/chatmodel/add) on your Khoj admin panel.
- Name: `llama3.1` (replace with the name of your local model)
- Model Type: `Openai`
- Openai Config: `<the ollama config you created in step 3>`
- Max prompt size: `20000` (replace with the max prompt size of your model)
5. Go to [your config](http://localhost:42110/settings) and select the model you just created in the chat model dropdown.
If you want to add additional models running on Ollama, repeat step 4 for each model.
</TabItem>
</Tabs>
That's it! You should now be able to chat with your Ollama model from Khoj.

20
documentation/docs/advanced/remote.md Normal file
View File

@@ -0,0 +1,20 @@
# Remote Access
By default self-hosted Khoj is only accessible on the machine it is running. To securely access it from a remote machine:
- Set the `KHOJ_DOMAIN` environment variable to your remotely accessible ip or domain via shell or docker-compose.yml.
Examples: `KHOJ_DOMAIN=my.khoj-domain.com`, `KHOJ_DOMAIN=192.168.0.4`.
- Ensure the Khoj Admin password and `KHOJ_DJANGO_SECRET_KEY` environment variable are securely set.
- Setup [Authentication](/advanced/authentication).
- Open access to the Khoj port (default: 42110) from your OS and Network firewall.
:::warning[Use HTTPS certificate]
To expose Khoj on a custom domain over the public internet, use of an SSL certificate is strongly recommended. You can use [Let's Encrypt](https://letsencrypt.org/) to get a free SSL certificate for your domain.
To disable HTTPS, set the `KHOJ_NO_HTTPS` environment variable to `True`. This can be useful if Khoj is only accessible behind a secure, private network.
:::
:::info[Try Tailscale]
You can use [Tailscale](https://tailscale.com/) for easy, secure access to your self-hosted Khoj over the network.
1. Set `KHOJ_DOMAIN` to your machines [tailscale ip](https://tailscale.com/kb/1452/connect-to-devices#identify-your-devices) or [fqdn on tailnet](https://tailscale.com/kb/1081/magicdns#fully-qualified-domain-names-vs-machine-names). E.g `KHOJ_DOMAIN=100.4.2.0` or `KHOJ_DOMAIN=khoj.tailfe8c.ts.net`
2. Access Khoj by opening `http://tailscale-ip-of-server:42110` or `http://fqdn-of-server:42110` from any device on your tailscale network
:::

17
documentation/docs/advanced/support-multilingual-docs.md Normal file
View File

@@ -0,0 +1,17 @@
# Support Multilingual Docs
Khoj uses an embedding model to understand documents. Multilingual embedding models improve the search quality for documents not in English. This affects both search and chat with docs experiences across Khoj.
To improve search and chat quality for non-english documents you can use a [multilingual model](https://www.sbert.net/docs/pretrained_models.html#multi-lingual-models).<br />
For example, the [paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) supports [50+ languages](https://www.sbert.net/docs/pretrained_models.html#:~:text=we%20used%20the%20following%2050%2B%20languages), has decent search quality and speed for a consumer machine.
To use it:
1. Open [the search config](http://localhost:42110/server/admin/database/searchmodelconfig/) on your server's admin settings page. Either create a new search model, if none exists, or update the existing one. For example,
- Set the `bi_encoder` field to `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`
- Set the `cross_encoder` field to `mixedbread-ai/mxbai-rerank-xsmall-v1`
2. Regenerate your content index from all the relevant clients. This step is very important, as you'll need to re-encode all your content with the new model.
:::info[Note]
Modern search/embedding model like [mixedbread-ai/mxbai-embed-large-v1](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1) expect a prefix to the query (or docs) string to improve encoding. Update the `bi_encoder_query_encode_config` field of your [embedding model](http://localhost:42110/server/admin/database/searchmodelconfig/) with `{prompt: <prefix-prompt>}` to improve the search quality of these models.
E.g. `{prompt: "Represent this query for searching documents"}`. You can pass any valid JSON object that the SentenceTransformer `encode` function accepts
:::

39
documentation/docs/advanced/tailscale.md Normal file
View File

@@ -0,0 +1,39 @@
# Tailscale
:::info
This is only helpful for secure cross-device access to **self-hosted** Khoj. You **do not** need this if you're using [Khoj Cloud](https://app.khoj.dev).
:::
[Tailscale](https://tailscale.com) simplifies creating a private VPN using [Wireguard](https://www.wireguard.com/) and OAuth. So you can host and access services on your devices from anywhere.
The instructions below are one way to simply and securely access your self-hosted Khoj from your phone, laptop etc.
### Minimal Setup
1. Setup khoj on your preferred machine following the [standard steps](/get-started/setup)
2. Sign-up to [Tailscale](https://tailscale.com) and install the app on machines you want to access Khoj from. This usually includes your khoj server, your phone, laptop. Note the tailscale i.p of your khoj server.
3. Start khoj on your server by including the flag `--host <your_server_tailscale_ip>`
4. Open `http://<your_server_tailscale_ip>:42110` to access khoj from any device on your tailscale network!
### HTTPS Certificate
:::info
Tailscale uses Wireguard to encrypt and route traffic between your machines. So HTTPS isn't required with Tailscale for secure access. HTTPS with Tailscale is only useful for browsers to not complain about security and block certain features like clipboard access unless HTTPS is enabled.
:::
1. Enable [MagicDNS](https://tailscale.com/kb/1081/magicdns#enabling-magicdns) and [HTTPS](https://tailscale.com/kb/1153/enabling-https) toggle on your tailscale admin console [DNS](https://login.tailscale.com/admin/dns) page. Note your unique tailscale domain name (usually ends with .ts.net)
2. Create an https certificate for your Khoj server by running the following command:
```bash
# Assuming the server is named, `server` and your tailnet is `black-forest.ts.net`
# Note path of the .crt and .key files generated
tailscale cert server.black-forest.ts.net
```
3. Start khoj to be served via https on standard port
```bash
sudo KHOJ_DOMAIN=server.black-forest.ts.net \
khoj \
--sslcert /path/to/your/tailscale.crt \
--sslkey path/to/your/tailscale.key \
--host=server.black-forest.ts.net \
--port 443
```
4. You should now be able to access khoj on `https://server.black-forest.ts.net` from any device on your private tailscale network!

34
documentation/docs/advanced/use-openai-proxy.md Normal file
View File

@@ -0,0 +1,34 @@
---
sidebar_position: 1
---
# Use OpenAI Proxy
:::info
This is only helpful for self-hosted users. If you're using [Khoj Cloud](https://app.khoj.dev), you're limited to our first-party models.
:::
:::info
Khoj natively supports local LLMs [available on HuggingFace in GGUF format](https://huggingface.co/models?library=gguf). Using an OpenAI API proxy with Khoj maybe useful for ease of setup, trying new models or using commercial LLMs via API.
:::
Khoj can use any OpenAI API compatible server including local providers like [Ollama](/advanced/ollama), [LMStudio](/advanced/lmstudio) and [LiteLLM](/advanced/litellm) and commercial providers like [HuggingFace](https://huggingface.co/docs/api-inference/tasks/chat-completion#using-the-api), [OpenRouter](https://openrouter.ai/docs/quick-start) etc.
Configuring this allows you to use non-standard, open or commercial, local or hosted LLM models for Khoj
Combine them with Khoj can turn your favorite LLM into an AI agent. Allowing you to chat with your docs, find answers from the internet, build custom agents and run automations.
For specific integrations, see our [Ollama](/advanced/ollama), [LMStudio](/advanced/lmstudio) and [LiteLLM](/advanced/litellm) setup docs. For general instructions to setup Khoj with an OpenAI API proxy see below.
## General Setup
1. Start your preferred OpenAI API compatible app locally or get API keys from commercial AI model providers.
3. Create a new [API Model API](http://localhost:42110/server/admin/database/aimodelapi/add) on your Khoj admin panel
- Name: `any name`
- Api Key: `any string`
- Api Base Url: **URL of your Openai Proxy API**
3. Create a new [Chat Model](http://localhost:42110/server/admin/database/chatmodel/add) on your Khoj admin panel.
- Name: `llama3` (replace with the name of your local model)
- Model Type: `Openai`
- Openai Config: `<the proxy config you created in step 2>`
- Max prompt size: `2000` (replace with the max prompt size of your model)
- Tokenizer: *Do not set for OpenAI, mistral, llama3 based models*
4. Go to [your config](http://localhost:42110/settings) and select the model you just created in the chat model dropdown.

2
documentation/docs/clients/_category_.json
View File

@@ -3,6 +3,6 @@
"position": 4,
"link": {
"type": "generated-index",
"description": "Different ways for indexing data with the Khoj backend"
"description": "Different ways for indexing data with the Khoj backend. To see online data sources, go to https://docs.khoj.dev/category/data-sources"
}
}

48
documentation/docs/clients/desktop.md
View File

@@ -4,29 +4,41 @@ sidebar_position: 1
# Desktop
> Query your Second Brain from your machine
> Upload your knowledge base to Khoj and chat with your whole corpus
Use the Desktop app to chat and search with Khoj.
You can also sync any relevant files with Khoj using the app.
Khoj will use these files to provide contextual reponses when you search or chat.
## Companion App
## Features
- **Chat**
- **Faster answers**: Find answers quickly, from your private notes or the public internet
- **Assisted creativity**: Smoothly weave across retrieving answers and generating content
- **Iterative discovery**: Iteratively explore and re-discover your notes
- **Search**
- **Natural**: Advanced natural language understanding using Transformer based ML Models
- **Incremental**: Incremental search for a fast, search-as-you-type experience
Share your files, folders with Khoj using the app.
Khoj will keep these files in sync to provide contextual responses when you search or chat.
## Setup
:::info[Self Hosting]
If you are self-hosting the Khoj server, update the *Settings* page on the Khoj Desktop app to:
- Set the `Khoj URL` field to your Khoj server URL. By default, use `http://127.0.0.1:42110`.
- Do not set the `Khoj API Key` field if your Khoj server runs in anonymous mode. For example, `khoj --anonymous-mode`
:::
1. Install the [Khoj Desktop app](https://khoj.dev/downloads) for your OS
2. Generate an API key on the [Khoj Web App](https://app.khoj.dev/config#clients)
2. Generate an API key on the [Khoj Web App](https://app.khoj.dev/settings#clients)
3. Set your Khoj API Key on the *Settings* page of the Khoj Desktop app
4. [Optional] Add any files, folders you'd like Khoj to be aware of on the *Settings* page and Click *Save*
4. [Optional] Add any files, folders you'd like Khoj to be aware of on the *Settings* page and Click *Save*.
These files and folders will be automatically kept in sync for you
## Interface
| Chat | Search |
|:----:|:------:|
| ![](/img/khoj_chat_on_desktop.png) | ![](/img/khoj_search_on_desktop.png) |
# Main App
You can also install the Khoj application on your desktop as a progressive web app.
1. Open the [Khoj Web App](https://app.khoj.dev) in Chrome.
2. Click on the install button in the address bar to install the app. You must be logged into your Chrome browser for this to work.
![progressive web app install icon](/img/pwa_install_desktop.png)
Alternatively, you can also install using this route:
1. Open the three-dot menu in the top right corner of the browser.
2. Go to 'Cast, Save, and Share' option.
3. Click on the "Open in Khoj" option.
![progressive web app install route](/img/chrome_pwa_alt.png)

26
documentation/docs/clients/emacs.md
View File

@@ -30,7 +30,13 @@ sidebar_position: 2
| ![khoj search on emacs](/img/khoj_search_on_emacs.png) | ![khoj chat on emacs](/img/khoj_chat_on_emacs.png) |
## Setup
1. Generate an API key on the [Khoj Web App](https://app.khoj.dev/config#clients)
:::info[Self Hosting]
If you are self-hosting the Khoj server modify the install steps below:
- Set `khoj-server-url` to your Khoj server URL. By default, use `http://127.0.0.1:42110`.
- Do not set `khoj-api-key` if your Khoj server runs in anonymous mode. For example, `khoj --anonymous-mode`
:::
1. Generate an API key on the [Khoj Web App](https://app.khoj.dev/settings#clients)
2. Add below snippet to your Emacs config file, usually at `~/.emacs.d/init.el`
@@ -43,6 +49,7 @@ M-x package-install khoj
; Set your Khoj API key
(setq khoj-api-key "YOUR_KHOJ_CLOUD_API_KEY")
(setq khoj-server-url "https://app.khoj.dev")
```
#### **Minimal Install**
@@ -54,7 +61,8 @@ M-x package-install khoj
:ensure t
:pin melpa-stable
:bind ("C-c s" . 'khoj)
:config (setq khoj-api-key "YOUR_KHOJ_CLOUD_API_KEY"))
:config (setq khoj-api-key "YOUR_KHOJ_CLOUD_API_KEY"
khoj-server-url "https://app.khoj.dev"))
```
#### **Standard Install**
@@ -67,8 +75,9 @@ M-x package-install khoj
:pin melpa-stable
:bind ("C-c s" . 'khoj)
:config (setq khoj-api-key "YOUR_KHOJ_CLOUD_API_KEY"
khoj-org-directories '("~/docs/org-roam" "~/docs/notes")
khoj-org-files '("~/docs/todo.org" "~/docs/work.org")))
khoj-server-url "https://app.khoj.dev"
khoj-index-directories '("~/docs/org-roam" "~/docs/notes")
khoj-index-files '("~/docs/todo.org" "~/docs/work.org")))
```
#### **Straight.el**
@@ -81,6 +90,7 @@ M-x package-install khoj
:straight (khoj :type git :host github :repo "khoj-ai/khoj" :files (:defaults "src/interface/emacs/khoj.el"))
:bind ("C-c s" . 'khoj)
:config (setq khoj-api-key "YOUR_KHOJ_CLOUD_API_KEY"
khoj-server-url "https://app.khoj.dev"
khoj-org-directories '("~/docs/org-roam" "~/docs/notes")
khoj-org-files '("~/docs/todo.org" "~/docs/work.org")))
```
@@ -90,13 +100,13 @@ M-x package-install khoj
See [Khoj Search](/features/search) for details
1. Hit `C-c s s` (or `M-x khoj RET s`) to open khoj search
2. Enter your query in natural language<br/>
E.g *"What is the meaning of life?"*, *"My life goals for 2023"*
E.g. *"What is the meaning of life?"*, *"My life goals for 2023"*
### Chat
See [Khoj Chat](/features/chat) for details
1. Hit `C-c s c` (or `M-x khoj RET c`) to open khoj chat
2. Ask questions in a natural, conversational style<br/>
E.g *"When did I file my taxes last year?"*
E.g. *"When did I file my taxes last year?"*
### Find Similar Entries
This feature finds entries similar to the one you are currently on.
@@ -104,8 +114,8 @@ This feature finds entries similar to the one you are currently on.
2. Hit `C-c s f` (or `M-x khoj RET f`) to find similar entries
### Advanced Usage
- Add [query filters](https://github.com/khoj-ai/khoj/#query-filters) during search to narrow down results further
e.g `What is the meaning of life? -"god" +"none" dt>"last week"`
- Add [query filters](/miscellaneous/query-filters) during search to narrow down results further
e.g. `What is the meaning of life? -"god" +"none" dt>"last week"`
- Use `C-c C-o 2` to open the current result at cursor in its source org file
- This calls `M-x org-open-at-point` on the current entry and opens the second link in the entry.

30
documentation/docs/clients/obsidian.md
View File

@@ -6,6 +6,8 @@ sidebar_position: 3
> Query your Second Brain from Obsidian
![demo](https://assets.khoj.dev/obsidian_khoj_side_panel_pak_telemedicine.gif)
## Features
- **Chat**
- **Faster answers**: Find answers quickly, from your private notes or the public internet
@@ -14,27 +16,29 @@ sidebar_position: 3
- **Search**
- **Natural**: Advanced natural language understanding using Transformer based ML Models
- **Incremental**: Incremental search for a fast, search-as-you-type experience
## Interface
| Search | Chat |
|:------:|:----:|
| ![](/img/khoj_search_on_obsidian.png) | ![](/img/khoj_chat_on_obsidian.png) |
- **Similar**
- **Discover**: Find similar notes to the current one
## Setup
:::info[Self Hosting]
If you are self-hosting the Khoj server, update the Khoj Obsidian plugin settings step below:
- Set the `Khoj URL` field to your Khoj server URL. By default, use `http://127.0.0.1:42110`.
- Do not set the `Khoj API Key` field if your Khoj server runs in anonymous mode. For example, `khoj --anonymous-mode`
:::
1. Open [Khoj](https://obsidian.md/plugins?id=khoj) from the *Community plugins* tab in Obsidian settings panel
2. Click *Install*, then *Enable* on the Khoj plugin page in Obsidian
3. Generate an API key on the [Khoj Web App](https://app.khoj.dev/config#clients)
4. Set your Khoj API Key in the Khoj plugin settings in Obsidian
1. Open [Khoj](https://obsidian.md/plugins?id=khoj) from the *Community plugins* tab in Obsidian settings panel
2. Click *Install*, then *Enable* on the Khoj plugin page in Obsidian
3. Generate an API key on the [Khoj Web App](https://app.khoj.dev/settings#clients)
4. Set your Khoj API Key in the Khoj plugin settings on Obsidian
5. (Optional) Click `Force Sync` in the Khoj plugin settings on Obsidian to immediately sync your Obsidian vault.
<br />By default, your Obsidian vault is automatically synced periodically.
See the official [Obsidian Plugin Docs](https://help.obsidian.md/Extending+Obsidian/Community+plugins) for more details on installing Obsidian plugins.
## Use
### Chat
Click the *Khoj chat* icon 💬 on the [Ribbon](https://help.obsidian.md/User+interface/Workspace/Ribbon) or run *Khoj: Chat* from the [Command Palette](https://help.obsidian.md/Plugins/Command+palette) and ask questions in a natural, conversational style.<br />
E.g *"When did I file my taxes last year?"*
E.g. *"When did I file my taxes last year?"*
See [Khoj Chat](/features/chat) for more details
@@ -44,7 +48,7 @@ To see other notes similar to the current one, run *Khoj: Find Similar Notes* fr
### Search
Run *Khoj: Search* from the [Command Palette](https://help.obsidian.md/Plugins/Command+palette)
See [Khoj Search](/features/search) for more details. Use [query filters](/miscellaneous/advanced#query-filters) to limit entries to search
See [Khoj Search](/features/search) for more details. Use [query filters](/miscellaneous/query-filters) to limit entries to search
[search_demo](https://user-images.githubusercontent.com/6413477/218801155-cd67e8b4-a770-404a-8179-d6b61caa0f93.mp4 ':include :type=mp4')

26
documentation/docs/clients/web.md
View File

@@ -8,6 +8,10 @@ sidebar_position: 4
Without any desktop clients, you can start chatting with Khoj on the web. Bear in mind you do need one of the desktop clients in order to share and sync your data with Khoj.
Go see it here --> [Khoj Cloud](https://app.khoj.dev).
![](/img/khoj_web_app_home.png)
## Features
- **Chat**
- **Faster answers**: Find answers quickly, from your private notes or the public internet
@@ -18,10 +22,22 @@ Without any desktop clients, you can start chatting with Khoj on the web. Bear i
- **Incremental**: Incremental search for a fast, search-as-you-type experience
## Setup
No setup required. The Khoj web app is the default interface to Khoj. You can access it from any web browser. Try it on [Khoj Cloud](https://app.khoj.dev)
No setup required. The Khoj web app is the default Khoj client. You can access it from any web browser. Try it on [Khoj Cloud](https://app.khoj.dev)
## Interface
## Upload Documents
You can upload documents to Khoj from the web interface, one at a time. This is useful for uploading documents from your phone or tablet. To upload a document:
1. You can drag and drop the document into the chat window.
2. Or click the paperclip icon in the chat window and select the document from your file system.
| Search | Chat |
|:------:|:----:|
| ![](/img/khoj_search_on_web.png) | ![](/img/khoj_chat_on_web.png) |
![demo of dragging and dropping a file](https://assets.khoj.dev/home_page_data_upload.gif)
### Install on Phone
You can optionally install Khoj as a [Progressive Web App (PWA)](https://web.dev/learn/pwa/installation). This makes it quick and easy to access Khoj on your phone.
1. Login to [Khoj Cloud](https://app.khoj.dev) or your self-hosted Khoj server from the web browser (prefer Chrome/Edge) on your phone
2. Open the 3 dot menu on the browser and click the "Add to Home screen" option
3. Click "Install" on the next screen to add the Khoj icon to your phone Home screen
**Process via Screenshots**
| Step 1 | Step 2 | Step 3|
|:---:|:---:|:---:|
| ![](/img/pwa_install_1.png) | ![](/img/pwa_install_2.png) | ![](/img/pwa_install_3.png) |

10
documentation/docs/clients/whatsapp.md
View File

@@ -6,13 +6,15 @@ sidebar_position: 5
> Query your Second Brain from WhatsApp
Text [+1 (848) 800 4242](https://wa.me/18488004242) or scan [this QR code](https://khoj.dev/whatsapp) on your phone to chat with Khoj on WhatsApp.
Text [+1 (848) 800 4242](https://wa.me/18488004242) or scan the QQ code below on your phone to chat with Khoj on WhatsApp.
Without any desktop clients, you can start chatting with Khoj on WhatsApp. Bear in mind you do need one of the desktop clients in order to share and sync your data with Khoj. The WhatsApp AI bot will work right away for answering generic queries and using Khoj in default mode.
In order to use Khoj on WhatsApp with your own data, you need to setup a Khoj Cloud account and connect your WhatsApp account to it. This is a one time setup and you can do it from the [Khoj Cloud config page](https://app.khoj.dev/config).
In order to use Khoj on WhatsApp with your own data, you need to setup a Khoj Cloud account and connect your WhatsApp account to it. This is a one time setup and you can do it from the [Khoj Cloud config page](https://app.khoj.dev/settings).
If you hit usage limits for the WhatsApp bot, upgrade to [a paid plan](https://khoj.dev/pricing) on Khoj Cloud.
If you hit usage limits for the WhatsApp bot, upgrade to [a paid plan](https://khoj.dev/#pricing) on Khoj Cloud.
<img src="https://khoj-web-bucket.s3.amazonaws.com/khojwhatsapp.png" alt="WhatsApp QR Code" width="300" height="300" />
## Features
@@ -23,6 +25,6 @@ If you hit usage limits for the WhatsApp bot, upgrade to [a paid plan](https://k
We have more commands under development, including `/share` to uploading documents directly to your Khoj account from WhatsApp, and `/speak` in order to get a speech response from Khoj. Feel free to [raise an issue](https://github.com/khoj-ai/flint/issues) if you have any suggestions for new commands.
## Nerdy Details
## Source Code
You can find all of the code for the WhatsApp bot in the the [flint repository](https://github.com/khoj-ai/flint). As all of our code, it is open source and you can contribute to it.

105
documentation/docs/contributing/development.mdx
View File

@@ -14,14 +14,13 @@ If you're looking for a place to get started, check out the list of [Github Issu
## Local Server Installation
### Using Pip
#### 1. Install
#### 1. Khoj Installation
```mdx-code-block
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
```
```mdx-code-block
<Tabs>
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
```shell
# Get Khoj Code
@@ -34,7 +33,7 @@ python3 -m venv .venv && source .venv/bin/activate
pip install -e '.[dev]'
```
</TabItem>
<TabItem value="win" label="Windows">
<TabItem value="windows" label="Windows">
```shell
# Get Khoj Code
git clone https://github.com/khoj-ai/khoj && cd khoj
@@ -43,10 +42,10 @@ git clone https://github.com/khoj-ai/khoj && cd khoj
python3 -m venv .venv && .venv\Scripts\activate
# Install Khoj for Development
pip install -e .[dev]
pip install -e '.[dev]'
```
</TabItem>
<TabItem value="unix" label="Linux">
<TabItem value="linux" label="Linux">
```shell
# Get Khoj Code
git clone https://github.com/khoj-ai/khoj && cd khoj
@@ -55,14 +54,67 @@ git clone https://github.com/khoj-ai/khoj && cd khoj
python3 -m venv .venv && source .venv/bin/activate
# Install Khoj for Development
pip install -e .[dev]
pip install -e '.[dev]'
```
</TabItem>
</Tabs>
#### 2. Postgres Installation & Setup
Khoj uses the `pgvector` package to store embeddings of your index in a Postgres database. To use this, you need to have Postgres installed.
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
Install [Postgres.app](https://postgresapp.com/). This comes pre-installed with `pgvector` and relevant dependencies.
</TabItem>
<TabItem value="windows" label="Windows">
1. Use the [recommended installer](https://www.postgresql.org/download/windows/).
2. Follow instructions to [Install PgVector](https://github.com/pgvector/pgvector#windows) in case you need to manually install it. Windows support is experimental for pgvector currently, so we recommend using Docker. Refer to Windows Installation Notes below if there are errors.
</TabItem>
<TabItem value="linux" label="Linux">
From [official instructions](https://wiki.postgresql.org/wiki/Apt)
</TabItem>
<TabItem value="source" label="From Source">
1. Follow instructions to [Install Postgres](https://www.postgresql.org/download/)
2. Follow instructions to [Install PgVector](https://github.com/pgvector/pgvector#installation) in case you need to manually install it.
</TabItem>
</Tabs>
##### Create the Khoj database
Make sure to update your environment variables to match your Postgres configuration if you're using a different name. The default values should work for most people. When prompted for a password, you can use the default password `postgres`, or configure it to your preference. Make sure to set the environment variable `POSTGRES_PASSWORD` to the same value as the password you set here.
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
```shell
createdb khoj -U postgres --password
```
</TabItem>
<TabItem value="windows" label="Windows">
```shell
createdb -U postgres khoj --password
```
</TabItem>
<TabItem value="linux" label="Linux">
```shell
sudo -u postgres createdb khoj --password
```
</TabItem>
</Tabs>
#### 3. Build the front-end assets
```shell
cd src/interface/web/
yarn install
yarn export
```
You can optionally use `yarn dev` to start a development server for the front-end which will be available at http://localhost:3000. This is especially useful if you're making changes to the front-end code, but not necessary for running Khoj. Note that streaming does not work on the dev server due to how it is handled with SSR in Next.js.
#### 2. Run
Always run `yarn export` to test your front-end changes on http://localhost:42110 before creating a PR.
#### 4. Run
1. Start Khoj
```bash
khoj -vv
@@ -72,6 +124,37 @@ pip install -e .[dev]
Note: Wait after configuration for khoj to Load ML model, generate embeddings and expose API to query notes, images, documents etc specified in config YAML
#### Windows Installation Notes
1. Command `khoj` Not Recognized
- Try reactivating the virtual environment and rerunning the `khoj` command.
- If it still doesn't work repeat the installation process.
2. Python Package Missing
- Use `pip install xxx` and try running the `khoj` command.
3. Command `createdb` Not Recognized
- make sure path to postgres binaries is included in environment variables. It usually looks something like
```
C:\Program Files\PostgreSQL\16\bin
```
4. Connection Refused on port xxxx
- Locate the `pg_hba.conf` file in the location where postgres was installed.
- Edit the file to have **trust** as the method for user postgres, local, and host connections.
- Below is an example:
```
host all postgres 127.0.0.1/32 trust
# "local" is for Unix domain socket connections only
local all all trust
# IPv4 local connections:
host all all 127.0.0.1/32 trust
# IPv6 local connections:
host all all ::1/128 trust
```
4. Errors with installing pgvector
- Reinstall Visual Studio 2022 Build Tools with:
1. desktop development with c++ selected in workloads
2. MSVC (C++ Build Tools), Windows 10/11 SDK, and C++/CLI support for build tools selected in individual components.
- Open the x64 Native Tools Command Prompt as an Administrator
- Follow the pgvector windows installation [instructions](https://github.com/pgvector/pgvector?tab=readme-ov-file#windows) in this command prompt.
### Using Docker
Make sure you install the latest version of [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/).
@@ -110,7 +193,7 @@ In whichever clients you're using for testing, you'll need to update the server
### Before Making Changes
1. Install Git Hooks for Validation
```shell
pre-commit install -t pre-push -t pre-commit
./scripts/dev_setup.sh
```
- This ensures standard code formatting fixes and other checks run automatically on every commit and push
- Note 1: If [pre-commit](https://pre-commit.com/#intro) didn't already get installed, [install it](https://pre-commit.com/#install) via `pip install pre-commit`
@@ -153,7 +236,7 @@ The core code for the Obsidian plugin is under `src/interface/obsidian`. The fil
4. Open the `khoj` folder in the file explorer that opens. You'll see a file called `main.js` in this folder. To test your changes, replace this file with the `main.js` file that was generated by the development server in the previous section.
## Create Khoj Release (Only for Maintainers)
Follow the steps below to [release](https://github.com/debanjum/khoj/releases/) Khoj. This will create a stable release of Khoj on [Pypi](https://pypi.org/project/khoj-assistant/), [Melpa](https://stable.melpa.org/#%252Fkhoj) and [Obsidian](https://obsidian.md/plugins?id%253Dkhoj). It will also create desktop apps of Khoj and attach them to the latest release.
Follow the steps below to [release](https://github.com/khoj-ai/khoj/releases/) Khoj. This will create a stable release of Khoj on [Pypi](https://pypi.org/project/khoj/), [Melpa](https://stable.melpa.org/#%252Fkhoj) and [Obsidian](https://obsidian.md/plugins?id%253Dkhoj). It will also create desktop apps of Khoj and attach them to the latest release.
1. Create and tag release commit by running the bump_version script. The release commit sets version number in required metadata files.
```shell
@@ -172,7 +255,7 @@ Follow the steps below to [release](https://github.com/debanjum/khoj/releases/)
## Visualize Codebase
*[Interactive Visualization](https://mango-dune-07a8b7110.1.azurestaticapps.net/?repo=debanjum%2Fkhoj)*
*[Interactive Visualization](https://mango-dune-07a8b7110.1.azurestaticapps.net/?repo=khoj-ai%2Fkhoj)*
![](/img/khoj_codebase_visualization_0.2.1.png)

2
documentation/docs/online-data-sources/_category_.json → documentation/docs/data-sources/_category_.json
View File

@@ -1,5 +1,5 @@
{
"label": "Online Data Sources",
"label": "Data Sources",
"position": 5,
"link": {
"type": "generated-index",

6
documentation/docs/online-data-sources/github_integration.md → documentation/docs/data-sources/github_integration.md
View File

@@ -1,14 +1,14 @@
# Setup the Github integration
# Github integration
The Github integration allows you to index as many repositories as you want. It's currently default configured to index Issues, Commits, and all Markdown/Org files in each repository. For large repositories, this takes a fairly long time, but it works well for smaller projects.
# Configure your settings
1. Go to [https://app.khoj.dev/config](https://app.khoj.dev/config) and enter in settings for the data sources you want to index. You'll have to specify the file paths.
1. Go to [https://app.khoj.dev/settings](https://app.khoj.dev/settings) and enter in settings for the data sources you want to index. You'll have to specify the file paths.
## Use the Github plugin
1. Generate a [classic PAT (personal access token)](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens) from [Github](https://github.com/settings/tokens) with `repo` and `admin:org` scopes at least.
2. Navigate to [https://app.khoj.dev/config/content-source/github](https://app.khoj.dev/config/content-source/github) to configure your Github settings. Enter in your PAT, along with details for each repository you want to index.
2. Navigate to [https://app.khoj.dev/settings#github](https://app.khoj.dev/settings#github) to configure your Github settings. Enter in your PAT, along with details for each repository you want to index.
3. Click `Save`. Go back to the settings page and click `Configure`.
4. Go to [https://app.khoj.dev/](https://app.khoj.dev/) and start searching!

13
documentation/docs/online-data-sources/notion_integration.md → documentation/docs/data-sources/notion_integration.md
View File

@@ -2,13 +2,18 @@
The Notion integration allows you to search/chat with your Notion workspaces. [Notion](https://notion.so/) is a platform people use for taking notes, especially for collaboration.
We haven't setup a fancy integration with OAuth yet, so this integration still requires some effort on your end to generate an API key.
Go to https://app.khoj.dev/settings to connect your Notion workspace(s) to Khoj.
![notion_integration](https://assets.khoj.dev/notion_integration.gif)
## Self-Hosted Setup
1. Go to https://www.notion.so/my-integrations and create a new integration called Khoj to get an API key.
![setup_new_integration](https://github.com/khoj-ai/khoj/assets/65192171/b056e057-d4dc-47dc-aad3-57b59a22c68b)
3. Share all the workspaces that you want to integrate with the Khoj integration you just made in the previous step
![enable_workspace](https://github.com/khoj-ai/khoj/assets/65192171/98290303-b5b8-4cb0-b32c-f68c6923a3d0)
4. In the first step, you generated an API key. Use the newly generated API Key in your Khoj settings, by default at https://app.khoj.dev/config/content-source/notion. Click `Save`.
5. Click `Configure` in https://app.khoj.dev/config to index your Notion workspace(s).
4. In the first step, you generated an API key. Use the newly generated API Key in your Khoj settings, by default at [http://localhost:42110/settings#notion](http://localhost:42110/settings#notion). Click `Save`.
5. Click `Configure` in http://localhost:42110/settings to index your Notion workspace(s).
That's it! You should be ready to start searching and chatting. Make sure you've configured your OpenAI API Key for chat.
That's it! You should be ready to start searching and chatting. Make sure you've configured your [chat settings](/get-started/setup#use-khoj).

16
documentation/docs/data-sources/share_your_data.md Normal file
View File

@@ -0,0 +1,16 @@
---
sidebar_position: 0
keywords: ["upload data", "upload files", "share data", "share files", "pdf ai", "ai for pdf", "ai for documents", "ai for files", "local ai pdf", "local ai documents", "local ai files"]
---
# Upload your data
There are several ways you can get started with sharing your data with the Khoj AI.
- Drag and drop your documents via [the web UI](/clients/web/#upload-documents). This is best if you have a one-off document you need to interact with.
- Use the desktop app to [upload and sync your documents](/clients/desktop). This is best if you have a lot of documents on your computer or you need the docs to stay in sync.
- Setup the sync options for either [Obsidian](/clients/obsidian) or [Emacs](/clients/emacs) to automatically sync your documents with Khoj. This is best if you are already using these tools and want to leverage Khoj's AI capabilities.
- Configure your [Notion](/data-sources/notion_integration) or [Github](/data-sources/github_integration) to sync with Khoj. By providing your credentials, you can keep the data synced in the background.
![demo of dragging and dropping a file](https://assets.khoj.dev/upload_pdf_doc.gif)

15
documentation/docs/features/agents.md Normal file
View File

@@ -0,0 +1,15 @@
---
sidebar_position: 4
---
# Agents
You can use agents to setup custom system prompts with Khoj. The server host can setup their own agents, which are accessible to all users. You can see ours at https://app.khoj.dev/agents.
![Demo](/img/agents_page_full.png)
## Creating an Agent (Self-Hosted)
Go to `server/admin/database/agent` on your server and click `Add Agent` to create a new one. You have to set it to `public` in order for it to be accessible to all the users on your server. To limit access to a specific user, do not set the `public` flag and add the user in the `Creator` field.
Set your custom prompt in the `personality` field.

5
documentation/docs/features/all_features.md → documentation/docs/features/all-features.md
View File

@@ -2,7 +2,7 @@
sidebar_position: 1
---
# Features
# Overview
Khoj supports a variety of features, including search and chat with a wide range of data sources and interfaces.
@@ -29,6 +29,7 @@ Khoj is available as a [Desktop app](/clients/desktop), [Emacs package](/clients
![](/img/khoj_clients.svg ':size=400px')
### Supported Data Sources
Khoj can understand your org-mode, markdown, PDF, plaintext files, [Github projects](/online-data-sources/github_integration) and [Notion pages](/online-data-sources/notion_integration).
Khoj can understand your word, PDF, org-mode, markdown, plaintext files, [Github projects](/data-sources/github_integration) and [Notion pages](/data-sources/notion_integration).
![](/img/khoj_datasources.svg ':size=200px')

14
documentation/docs/features/automations.md Normal file
View File

@@ -0,0 +1,14 @@
# Automations
[Automations](https://app.khoj.dev/automations) are a powerful feature within Khoj to schedule repeated jobs for Khoj to do on your behalf. Automations allow you run your query automatically at a scheduled time and frequency. Khoj will send its research to you as an email.
You can ask Khoj to create custom newsletters, summarize news, notify you of world events etc.
Khoj uses your local time zone for scheduling. You can configure, share and delete your automations from the [automations page](https://app.khoj.dev/automations).
:::info[Self Hosting]
Self hosting users need to setup Resend and [Authentication](/advanced/authentication) setup to have Khoj send automation emails.
:::
| [Create Automation](https://app.khoj.dev/automations?subject=Weekly%20Newsletter&query=Compile%20a%20message%20including:%201.%20A%20recap%20of%20news%20from%20last%20week%202.%20An%20at-home%20workout%20I%20can%20do%20before%20work%203.%20A%20quote%20to%20inspire%20me%20for%20the%20week%20ahead&crontime=00%209%20*%20*%201) | Recieve Automation Email |
|--------|-------|
| <img src="/img/khoj_create_automation.png" alt="create automation" width="330" height="500" /> | <img src="/img/khoj_automation_email.png" alt="create automation" width="330" height="660" /> |

48
documentation/docs/features/chat.md
View File

@@ -4,56 +4,36 @@ sidebar_position: 2
# Chat
You can configure Khoj to chat with you about anything. When relevant, it'll use any notes or documents you shared with it to respond.
You can configure Khoj to chat with you about anything. When relevant, it'll use any notes or documents you shared with it to respond. It acts as an excellent research assistant, search engine, or personal tutor.
<img src="https://assets.khoj.dev/vision_chat_example.png" alt="Chat on Web" style={{width: '400px'}}/>
### Overview
- Creates a personal assistant for you to inquire and engage with your notes
- Creates a personal assistant for you to inquire and engage with your notes or online information as needed
- You can choose to use Online or Offline Chat depending on your requirements
- Supports multi-turn conversations with the relevant notes for context
- Shows reference notes used to generate a response
### Setup (Self-Hosting)
#### Offline Chat
Offline chat stays completely private and works without internet using open-source models.
> **System Requirements**:
> - Minimum 8 GB RAM. Recommend **16Gb VRAM**
> - Minimum **5 GB of Disk** available
> - A CPU supporting [AVX or AVX2 instructions](https://en.wikipedia.org/wiki/Advanced_Vector_Extensions) is required
> - A Mac M1+ or [Vulcan supported GPU](https://vulkan.gpuinfo.org/) should significantly speed up chat response times
1. Open your [Khoj offline settings](http://localhost:42110/server/admin/database/offlinechatprocessorconversationconfig/) and click *Enable* on the Offline Chat configuration.
2. Open your [Chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/) and add a new option for the offline chat model you want to use. Make sure to use `Offline` as its type. We currently only support offline models that use the [Llama chat prompt](https://replicate.com/blog/how-to-prompt-llama#wrap-user-input-with-inst-inst-tags) format. We recommend using `mistral-7b-instruct-v0.1.Q4_0.gguf`.
:::tip[Note]
Offline chat is not supported for a multi-user scenario. The host machine will encounter segmentation faults if multiple users try to use offline chat at the same time.
:::
#### Online Chat
Online chat requires internet to use ChatGPT but is faster, higher quality and less compute intensive.
:::danger[Warning]
This will enable Khoj to send your chat queries and query relevant notes to OpenAI for processing.
:::
1. Get your [OpenAI API Key](https://platform.openai.com/account/api-keys)
2. Open your [Khoj Online Chat settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/). Add a new setting with your OpenAI API key, and click *Save*. Only one configuration will be used, so make sure that's the only one you have.
3. Open your [Chat model options](http://localhost:42110/server/admin/database/chatmodeloptions/) and add a new option for the OpenAI chat model you want to use. Make sure to use `OpenAI` as its type.
See [the setup guide](/get-started/setup.mdx) to configure your chat models.
### Use
1. Open Khoj Chat
- **On Web**: Open [/chat](https://app.khoj.dev/chat) in your web browser
- **On Obsidian**: Search for *Khoj: Chat* in the [Command Palette](https://help.obsidian.md/Plugins/Command+palette)
- **On Emacs**: Run `M-x khoj <user-query>`
2. Enter your queries to chat with Khoj. Use [slash commands](#commands) and [query filters](/miscellaneous/advanced#query-filters) to change what Khoj uses to respond
2. Enter your queries to chat with Khoj. Use [slash commands](#commands) and [query filters](/miscellaneous/query-filters) to change what Khoj uses to respond
![](/img/khoj_chat_on_web.png ':size=400px')
#### Details
1. Your query is used to retrieve the most relevant notes, if any, using Khoj search
1. Your query is used to retrieve the most relevant notes, if any, using Khoj search using RAG.
2. These notes, the last few messages and associated metadata is passed to the enabled chat model along with your query to generate a response
#### Conversation File Filters
You can use conversation file filters to limit the notes used in the chat response. To do so, use the left panel in the web UI. Alternatively, you can also use [query filters](/miscellaneous/query-filters) to limit the notes used in the chat response.
<img src="/img/file_filters_conversation.png" alt="Conversation File Filter" style={{width: '400px'}}/>
#### Commands
Slash commands allows you to change what Khoj uses to respond to your query
- **/notes**: Limit chat to only respond using your notes, not just Khoj's general world knowledge as reference
@@ -62,3 +42,7 @@ Slash commands allows you to change what Khoj uses to respond to your query
- **/online**: Use online information and incorporate it in the prompt to the LLM to send you a response.
- **/image**: Generate an image in response to your query.
- **/help**: Use /help to get all available commands and general information about Khoj
- **/summarize**: Can be used to summarize 1 selected file filter for that conversation. Refer to [File Summarization](summarization) for details.
- **/diagram**: Generate a diagram in response to your query. This is built on [Excalidraw](https://excalidraw.com/).
- **/code**: Generate and run very simple Python code snippets. Refer to [Code Execution](code_execution) for details.
- **/research**: Go deeper in a topic for more accurate, in-depth responses.

30
documentation/docs/features/code_execution.md Normal file
View File

@@ -0,0 +1,30 @@
---
---
# Code Execution
Khoj can generate and run very simple Python code snippets as well. This is useful if you want to generate a plot, run a simple calculation, or do some basic data manipulation. LLMs by default aren't skilled at complex quantitative tasks. Code generation & execution can come in handy for such tasks.
Just use `/code` in your chat command.
### Setup (Self-Hosting)
Run [Cohere's Terrarium](https://github.com/cohere-ai/cohere-terrarium) on your machine to enable code generation and execution.
Check the [instructions](https://github.com/cohere-ai/cohere-terrarium?tab=readme-ov-file#development) for running from source.
For running with Docker, you can use our [docker-compose.yml](https://github.com/khoj-ai/khoj/blob/master/docker-compose.yml), or start it manually like this:
```bash
docker pull ghcr.io/khoj-ai/terrarium:latest
docker run -d -p 8080:8080 ghcr.io/khoj-ai/terrarium:latest
```
#### Verify
Verify that it's running, by evaluating a simple Python expression:
```bash
curl -X POST -H "Content-Type: application/json" \
--url http://localhost:8080 \
--data-raw '{"code": "1 + 1"}' \
--no-buffer
```

26
documentation/docs/features/image_generation.md Normal file
View File

@@ -0,0 +1,26 @@
# Image Generation
You can use Khoj to generate images from text prompts. You can get deeper into the details of our image generation flow in this blog post: https://blog.khoj.dev/posts/how-khoj-generates-images/.
To generate images, you just need to provide a prompt to Khoj in which the image generation is in the instructions. Khoj will automatically detect the image generation intent, augment your generation prompt, and then create the image. Here are some examples:
| Prompt | Image |
| --- | --- |
| Paint a picture of the plants I got last month, pixar-animation | ![plants](/img/plants_i_got.png) |
| Create a picture of my dream house, based on my interests | ![house](/img/dream_house.png) |
## Setup (Self-Hosting)
You have a couple of image generation options.
### Image Generation Models
We support most state of the art image generation models, including Ideogram, Flux, and Stable Diffusion. These will run using [Replicate](https://replicate.com). Here's how to set them up:
1. Get a Replicate API key [here](https://replicate.com/account/api-tokens).
2. Create a new [Text to Image Model](http://localhost:42110/server/admin/database/texttoimagemodelconfig/). Set the `type` to `Replicate`. Use any of the model names you see [on this list](https://replicate.com/pricing#image-models). We recommend the `model name` `black-forest-labs/flux-1.1-pro` from [Replicate](https://replicate.com/black-forest-labs/flux-1.1-pro).
### OpenAI
1. Get [an OpenAI API key](https://platform.openai.com/settings/organization/api-keys).
2. Setup your OpenAI API key, if you haven't already. See instructions [here](/get-started/setup#add-chat-models)
3. Create a text to image config at http://localhost:42110/server/admin/database/texttoimagemodelconfig/. Use `model name` `dall-e-3` to use openai for image generation. Make sure to set the `Ai model api` field to the the OpenAI AI model api you setup in step 2.

18
documentation/docs/features/keyboard_shortcuts.md Normal file
View File

@@ -0,0 +1,18 @@
# Keyboard Shortcuts
Oftentimes, having to leave your keyboard to move the mouse can break your flow. We want to make it as easy as possible for AI to flow with you as you are, so we've added some keyboard shortcuts to facilitate that.
## Obsidian
### Up/Down Arrow Keys (Chat Input)
- **Up Arrow Key**: Move up in the list of most recent messages in your chat window.
- **Down Arrow Key**: Move down in the list of most recent messages in your chat window.
You can watch the demo to see how it works on [this sample conversation](http://app.khoj.dev/share/chat/in-particular-assess-the-prospect-for-brazil-/).
<img src="https://assets.khoj.dev/up_down_shortcuts.gif" height="300" alt="Up/Down Arrow Keys"></img>
### Enter (Chat Input)
Press 'Enter' to send the message you've typed in the chat window.

9
documentation/docs/features/khoj_mini.md Normal file
View File

@@ -0,0 +1,9 @@
# Desktop Quick Chat (Khoj Mini)
Once you have the Khoj [desktop application](https://khoj.dev/downloads) installed, you can use the desktop shortcut to quickly pull up a mini chat module for quicker answers. See the desktop setup instructions [in the docs](/clients/desktop.md) for more information.
To use it, you just have to copy the text you want to inject into your query, and then run `Ctrl + Shift + K` (or `Cmd + Shift + K` on Mac) to open the mini chat module. The text you copied will be automatically pasted into the chat module, and you can then hit enter to get the answer. You can edit the text before hitting enter if you want to refine your query.
The desktop shortcut is a great way to quickly get answers to your questions without having to switch between windows or tabs. It's especially useful when you're working on a project and need to quickly look up something without losing your focus.
![Desktop Shortcut](https://assets.khoj.dev/courseload_decision_dekstop.gif)

31
documentation/docs/features/online_search.md Normal file
View File

@@ -0,0 +1,31 @@
# Online Search
Khoj will research on the internet to ground its responses, when it determines that it would need fresh information outside its existing knowledge to answer the query. It will always show any online references it used to respond to your requests.
By default, Khoj will try to infer which information sources, it needs to read to answer your question. This can include reading your documents or researching information online. You can also explicitly trigger an online search by adding the `/online` prefix to your chat query.
Example queries that should trigger an online search:
- What's the latest news about the Israel-Palestine war?
- Where can I find the best pizza in New York City?
- /online Deadline for filing taxes 2024.
- Give me a summary of this article: https://en.wikipedia.org/wiki/Haitian_Revolution
Try it out yourself! https://app.khoj.dev
## Self-Hosting
### Search
Online search can work even with self-hosting! You have a few options:
- If you're using Docker, online search should work out of the box with [searxng](https://github.com/searxng/searxng) using our standard `docker-compose.yml`.
- For a non-local, free solution, you can use [JinaAI's reader API](https://jina.ai/reader/) to search online and read webpages. You can get a free API key via https://jina.ai/reader. Set the `JINA_API_KEY` environment variable to your Jina AI reader API key to enable online search.
- To get production-grade, fast online search, set the `SERPER_DEV_API_KEY` environment variable to your [Serper.dev](https://serper.dev/) API key. These search results include additional context like answer box, knowledge graph etc.
### Webpage Reading
Out of the box, you **don't have to do anything to enable webpage reading**. Khoj will automatically read webpages by using the `requests` library. To get more distributed and scalable webpage reading, you can use the following options:
- If you're using Jina AI's reader API for search, it should work automatically for webpage reading as well.
- For scalable webpage scraping, you can use [Firecrawl](https://www.firecrawl.dev/). Create a new [Webscraper](http://localhost:42110/server/admin/database/webscraper/add/). Set your Firecrawl API key to the Api Key field, and set the type to Firecrawl.
- For advanced webpage reading, you can use [Olostep](https://www.olostep.com/). This has a higher success rate at reading webpages than the default webpage readers. Create a new [Webscraper](http://localhost:42110/server/admin/database/webscraper/add/). Set your Olostep API key to the Api Key field, and set the type to Olostep.

4
documentation/docs/features/search.md
View File

@@ -11,7 +11,7 @@ Take advantage of super fast search to find relevant notes and documents from yo
- **On Web**: Open https://app.khoj.dev/ in your web browser
- **On Obsidian**: Click the *Khoj search* icon 🔎 on the [Ribbon](https://help.obsidian.md/User+interface/Workspace/Ribbon) or Search for *Khoj: Search* in the [Command Palette](https://help.obsidian.md/Plugins/Command+palette)
- **On Emacs**: Run `M-x khoj <user-query>`
2. Query using natural language to find relevant entries from your knowledge base. Use [query filters](/miscellaneous/advanced#query-filters) to limit entries to search
2. Query using natural language to find relevant entries from your knowledge base. Use [query filters](/miscellaneous/query-filters) to limit entries to search
### Demo
![](/img/khoj_search_on_web.png ':size=400px')
![](/img/search_agents_markdown.png ':size=400px')

7
documentation/docs/features/share.md Normal file
View File

@@ -0,0 +1,7 @@
# Shareable Chat
You can share any of your conversations by going to the three dot menu on the conversation and selecting 'Share'. This will create a **public** link that you can share with anyone. The link will open the conversation in the same state it was when you shared it, so your future messages will not be visible to the person you shared it with.
This means you can easily share a conversation with someone to show them how you solved a problem, or to get help with something you're working on.
![demo of sharing a conversation](https://assets.khoj.dev/share_side_panel_conversation.gif)

26
documentation/docs/features/summarization.md Normal file
View File

@@ -0,0 +1,26 @@
---
sidebar_position: 5
---
# File Summarization
You can use the `/summarize` command to get Khoj to generate context driven summaries of your documents.
Simply select a single file filter on the left panel menu and then use `/summarize [any context]` and Khoj
will produce a tailored summary of the text.
You can also try a natural language query which include the intent for summary without explicitly using the `/summarize` command.
## Design Diagram
<img src="/img/summarize.jpg" alt="Chat on Web" style={{width: '800px'}}/>
## Example Usage
* `/summarize in a way that can be used as practice questions for a test`
* `/summarize in a way a toddler can understand`
* `/summarize in one paragraph`
Without using the `/summarize` command:
* `create a summary of the document in a way that can be used as practice questions for a test`
* `summarize the document in a way a toddler can understand`
* `generate a one paragraph summary of the document`

27
documentation/docs/features/voice-chat.md Normal file
View File

@@ -0,0 +1,27 @@
# Voice
You can talk to Khoj using your voice. Khoj will respond to your queries using the same models as the chat feature. You can use voice chat on the web, Desktop, and Obsidian apps.
![Voice Chat](https://assets.khoj.dev/speech_to_text_demo.gif)
Click on the little mic icon to send your voice message to Khoj. It will send back what it heard via text. You can edit the message before sending it, if required. Try it at https://app.khoj.dev/.
## Voice Response
If you send a voice message, Khoj will automatically respond back with a voice message.
You can also click on the speaker icon next to any message to hear it out loud. The voice response feature is available only on the web view right now.
![Speaker Icon](/img/text_to_speech.png)
## Setup (Self-Hosting)
Voice chat will automatically be configured when you initialize the application. The default configuration will run locally. If you want to use the OpenAI whisper API for voice chat, you can set it up by following these steps:
1. Setup your OpenAI API key. See instructions [here](/get-started/setup#add-chat-models).
2. Create a new configuration at http://localhost:42110/server/admin/database/speechtotextmodeloptions/. We recommend the value `whisper-1` and model type `Openai`.
If you want to use the Text to Speech feature, you can set it up by following these steps:
1. Setup your account on [ElevenLabs.io](https://elevenlabs.io/).
2. Configure your API key in your environment variables with the key `ELEVEN_LABS_API_KEY`.
3. (Optional) Create a new [Voice model option](http://localhost:42110/server/admin/database/voicemodeloption/) with a specific voice ID from whichever voice you want to use. You can explore the options [here](https://elevenlabs.io/app/voice-library).

51
documentation/docs/get-started/demos.md
View File

@@ -1,51 +0,0 @@
---
sidebar_position: 2
---
# Demos
Check out a couple of demos and screenshots of Khoj in action.
### Screenshots
| Web | Obsidian | Emacs |
|:---:|:--------:|:-----:|
| ![](/img/khoj_search_on_web.png ':size=300px') | ![](/img/khoj_search_on_obsidian.png ':size=300px') | ![](/img/khoj_search_on_emacs.png ':size=300px') |
| ![](/img/khoj_chat_on_web.png ':size=300px') | ![](/img/khoj_chat_on_obsidian.png ':size=300px') | ![](/img/khoj_chat_on_emacs.png ':size=400px') |
### Videos
#### Khoj in Obsidian
[Link to Video](https://github-production-user-asset-6210df.s3.amazonaws.com/6413477/240061700-3e33d8ea-25bb-46c8-a3bf-c92f78d0f56b.mp4)
##### Installation
1. Install Khoj via `pip` and start Khoj backend in a terminal (Run `khoj`)
```bash
python -m pip install khoj-assistant
khoj
```
2. Install Khoj plugin via Community Plugins settings pane on Obsidian app
- Check the new Khoj plugin settings
- Let Khoj backend index the markdown, pdf, Github markdown files in the current Vault
- Open Khoj plugin on Obsidian via Search button on Left Pane
- Search \"*Announce plugin to folks*\" in the [Obsidian Plugin docs](https://marcus.se.net/obsidian-plugin-docs/)
- Jump to the [search result](https://marcus.se.net/obsidian-plugin-docs/publishing/submit-your-plugin)
#### Khoj in Emacs, Browser
[Link to Video](https://user-images.githubusercontent.com/6413477/184735169-92c78bf1-d827-4663-9087-a1ea194b8f4b.mp4)
##### Installation
- Install Khoj via pip
- Start Khoj app
- Add this readme and [khoj.el readme](https://github.com/khoj-ai/khoj/tree/master/src/interface/emacs) as org-mode for Khoj to index
- Search \"*Setup editor*\" on the Web and Emacs. Re-rank the results for better accuracy
- Top result is what we are looking for, the [section to Install Khoj.el on Emacs](https://github.com/khoj-ai/khoj/tree/master/src/interface/emacs#2-Install-Khojel)
##### Analysis
- The results do not have any words used in the query
- *Based on the top result it seems the re-ranking model understands that Emacs is an editor?*
- The results incrementally update as the query is entered
- The results are re-ranked, for better accuracy, once user hits enter

31
documentation/docs/get-started/overview.md
View File

@@ -1,14 +1,12 @@
---
sidebar_position: 0
slug: /
keywords: ["khoj", "khoj ai", "khoj docs", "khoj documentation", "khoj features", "khoj overview", "khoj quickstart", "khoj chat", "khoj search", "khoj cloud", "khoj self-host", "khoj setup", "open source ai", "local llm", "ai copilot", "second brain", "personal ai", "ai search engine", "research assistant", "open source llm", "self-host llm", "self-host chatgpt", "ai chatbot", "ai assistant", "ai research assistant", "ai search engine", "ai knowledge base", "ai knowledge graph", "ai personal assistant", "ai second brain", "open source ai assistant"]
---
# Overview
<p align="center"><img src="/img/khoj-logo-sideways-500.png" width="200" alt="Khoj Logo"></img></p>
<div align="center">
<b>An AI copilot for your Second Brain</b>
<b>Your Second Brain</b>
</div>
<br />
@@ -26,27 +24,14 @@ slug: /
Welcome to the Khoj Docs! This is the best place to get setup and explore Khoj's features.
- Khoj is an open source, personal AI
- You can [chat](/features/chat) with it about anything. It'll use files you shared with it to respond, when relevant
- You can [chat](/features/chat) with it about anything. It'll use files you shared with it to respond, when relevant. It can also access information from the public internet.
- Quickly [find](/features/search) relevant notes and documents using natural language
- It understands pdf, plaintext, markdown, org-mode files, [notion pages](/online-data-sources/notion_integration) and [github repositories](/online-data-sources/github_integration)
- Access it from your [Emacs](/clients/emacs), [Obsidian](/clients/obsidian), [Web browser](/clients/web) or the [Khoj Desktop app](/clients/desktop)
- Use [cloud](https://app.khoj.dev/login) to access your Khoj anytime from anywhere, [self-host](/get-started/setup) on consumer hardware for privacy
- It understands pdf, plaintext, markdown, org-mode files, [notion pages](/data-sources/notion_integration) and [github repositories](/data-sources/github_integration)
- Access it from your [Emacs](/clients/emacs), [Obsidian](/clients/obsidian), the [Khoj desktop app](/clients/desktop), or [any web browser](/clients/web)
- Use our [cloud](https://app.khoj.dev/login) instance to access your Khoj anytime from anywhere, [self-host](/get-started/setup) on consumer hardware for privacy
![demo_chat](https://assets.khoj.dev/quadratic_equation_khoj_web.gif)
## Quickstart
- [Try Khoj Cloud](https://app.khoj.dev) to get started quickly
- [Read these instructions](/get-started/setup) to self-host a private instance of Khoj
## At a Glance
<img src="https://docs.khoj.dev/img/khoj_search_on_web.png" width="400px" />
<span>&nbsp;&nbsp;</span>
<img src="https://docs.khoj.dev/img/khoj_chat_on_web.png" width="400px" />
#### [Search](/features/search)
- **Natural**: Use natural language queries to quickly find relevant notes and documents.
- **Incremental**: Incremental search for a fast, search-as-you-type experience
#### [Chat](/features/chat)
- **Faster answers**: Find answers faster, smoother than search. No need to manually scan through your notes to find answers.
- **Iterative discovery**: Iteratively explore and (re-)discover your notes
- **Assisted creativity**: Smoothly weave across answers retrieval and content generation
- **Online or Offline**: Choose online or offline chat depending on your requirements

4
documentation/docs/get-started/privacy_security.md → documentation/docs/get-started/privacy-security.md
View File

@@ -14,7 +14,7 @@ Here's what to consider if you're using Khoj, whether self-hosted or on our clou
1. We collect completely anonymized usage telemetry and send it to [PostHog](https://posthog.com/). This includes data like unique chat requests, unique search requests, unique requests to index data. Usage data is collected to help us understand how people are using Khoj, and to help us prioritize features.
- We do not log your IP address, nor upload any of your personal data to PostHog.
- You can see our telemetry aggregation code [here](https://github.com/khoj-ai/khoj/blob/master/src/khoj/routers/helpers.py#L71) and see our telemetry server [here](https://github.com/khoj-ai/khoj/blob/master/src/telemetry/telemetry.py).
- If you're self-hosting, you can opt out of telemetry by following [these instructions](./miscellaneous/telemetry).
- If you're self-hosting, you can opt out of telemetry by following [these instructions](/miscellaneous/telemetry).
Self-hosting isn't for everyone, so we've still taken steps to make Khoj privacy-friendly, even if you choose to use our [cloud offering](https://app.khoj.dev/login). Here's what to consider when using Khoj Cloud:
@@ -22,6 +22,8 @@ Self-hosting isn't for everyone, so we've still taken steps to make Khoj privacy
1. Your embeddings and the associated raw text are stored in a secure Postgres DB in our private AWS cloud. Your data is sharded on a unique user ID. We store the raw text in your files to improve file syncing and provide context when you chat with Khoj.
1. When you use the single-sign-on option with Google, we only receive your name, a link to your profile photo, and your email address.
You can see our full privacy policy [here](https://khoj.dev/privacy-policy).
:::tip[Info]
Your data is yours. We do not sell your data or use it for training models. Khoj is a sustainable, open-source alternative to closed-source, commercial personal AI. We have no interest in selling your data to make a quick buck.

488
documentation/docs/get-started/setup.mdx
View File

@@ -14,51 +14,121 @@ import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
```
## Setup
## Setup Khoj
These are the general setup instructions for self-hosted Khoj.
You can install the Khoj server using either [Docker](?server=docker) or [Pip](?server=pip).
- Make sure [python](https://realpython.com/installing-python/) and [pip](https://pip.pypa.io/en/stable/installation/) are installed on your machine
- Check the [Khoj Emacs docs](/clients/emacs#setup) to setup Khoj with Emacs<br />
It's simpler as it can skip the server *install*, *run* and *configure* step below.
- Check the [Khoj Obsidian docs](/clients/obsidian#setup) to setup Khoj with Obsidian<br />
Its simpler as it can skip the *configure* step below.
:::info[Offline Model + GPU]
To use the offline chat model with your GPU, we recommend using the Docker setup with Ollama . You can also use the local Khoj setup via the Python package directly.
:::
For Installation, you can either use Docker or install the Khoj server locally.
:::info[First Run]
Restart your Khoj server after the first run to ensure all settings are applied correctly.
:::
### Installation Option 1 (Docker)
<Tabs groupId="server" queryString>
<TabItem value="docker" label="Docker">
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
<h3>Prerequisites</h3>
<h4>Docker</h4>
- *Option 1*: Click here to install [Docker Desktop](https://docs.docker.com/desktop/install/mac-install/). Make sure you also install the [Docker Compose](https://docs.docker.com/desktop/install/mac-install/) tool.
#### Prerequisites
1. Install Docker Engine. See [official instructions](https://docs.docker.com/engine/install/).
2. Ensure you have Docker Compose. See [official instructions](https://docs.docker.com/compose/install/).
- *Option 2*: Use [Homebrew](https://brew.sh/) to install Docker and Docker Compose.
```shell
brew install --cask docker
brew install docker-compose
```
<h3>Setup</h3>
1. Download the Khoj docker-compose.yml file [from Github](https://github.com/khoj-ai/khoj/blob/master/docker-compose.yml)
```shell
mkdir ~/.khoj && cd ~/.khoj
wget https://raw.githubusercontent.com/khoj-ai/khoj/master/docker-compose.yml
```
2. Configure the environment variables in the `docker-compose.yml`
- Set `KHOJ_ADMIN_PASSWORD`, `KHOJ_DJANGO_SECRET_KEY` (and optionally the `KHOJ_ADMIN_EMAIL`) to something secure. This allows you to customize Khoj later via the admin panel.
- Set `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `GEMINI_API_KEY` to your API key if you want to use OpenAI, Anthropic or Gemini commercial chat models respectively.
- Uncomment `OPENAI_API_BASE` to use [Ollama](/advanced/ollama?type=first-run&server=docker#setup) running on your host machine. Or set it to the URL of your OpenAI compatible API like vLLM or [LMStudio](/advanced/lmstudio).
3. Start Khoj by running the following command in the same directory as your docker-compose.yml file.
```shell
cd ~/.khoj
docker-compose up
```
</TabItem>
<TabItem value="windows" label="Windows">
<h3>Prerequisites</h3>
1. Install [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) and restart your machine
```shell
# Run in PowerShell
wsl --install
```
2. Install [Docker Desktop](https://docs.docker.com/desktop/install/windows-install/) with **[WSL2 backend](https://docs.docker.com/desktop/wsl/#turn-on-docker-desktop-wsl-2)** (default)
#### Setup
<h3>Setup</h3>
1. Download the Khoj docker-compose.yml file [from Github](https://github.com/khoj-ai/khoj/blob/master/docker-compose.yml)
```shell
# Windows users should use their WSL2 terminal to run these commands
mkdir ~/.khoj && cd ~/.khoj
wget https://raw.githubusercontent.com/khoj-ai/khoj/master/docker-compose.yml
```
2. Configure the environment variables in the `docker-compose.yml`
- Set `KHOJ_ADMIN_PASSWORD`, `KHOJ_DJANGO_SECRET_KEY` (and optionally the `KHOJ_ADMIN_EMAIL`) to something secure. This allows you to customize Khoj later via the admin panel.
- Set `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `GEMINI_API_KEY` to your API key if you want to use OpenAI, Anthropic or Gemini commercial chat models respectively.
- Uncomment `OPENAI_API_BASE` to use [Ollama](/advanced/ollama) running on your host machine. Or set it to the URL of your OpenAI compatible API like vLLM or [LMStudio](/advanced/lmstudio).
3. Start Khoj by running the following command in the same directory as your docker-compose.yml file.
```shell
# Windows users should use their WSL2 terminal to run these commands
cd ~/.khoj
docker-compose up
```
</TabItem>
<TabItem value="linux" label="Linux">
<h3>Prerequisites</h3>
Install [Docker Desktop](https://docs.docker.com/desktop/install/linux/).
You can also use your package manager to install Docker Engine & Docker Compose.
Use the sample docker-compose [in Github](https://github.com/khoj-ai/khoj/blob/master/docker-compose.yml) to run Khoj in Docker. Start by configuring all the environment variables to your choosing. Your admin account will automatically be created based on the admin credentials in that file, so pay attention to those. To start the container, run the following command in the same directory as the docker-compose.yml file. This will automatically setup the database and run the Khoj server.
<h3>Setup</h3>
1. Download the Khoj docker-compose.yml file [from Github](https://github.com/khoj-ai/khoj/blob/master/docker-compose.yml)
```shell
mkdir ~/.khoj && cd ~/.khoj
wget https://raw.githubusercontent.com/khoj-ai/khoj/master/docker-compose.yml
```
2. Configure the environment variables in the `docker-compose.yml`
- Set `KHOJ_ADMIN_PASSWORD`, `KHOJ_DJANGO_SECRET_KEY` (and optionally the `KHOJ_ADMIN_EMAIL`) to something secure. This allows you to customize Khoj later via the admin panel.
- Set `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `GEMINI_API_KEY` to your API key if you want to use OpenAI, Anthropic or Gemini commercial chat models respectively.
- Uncomment `OPENAI_API_BASE` to use [Ollama](/advanced/ollama) running on your host machine. Or set it to the URL of your OpenAI compatible API like vLLM or [LMStudio](/advanced/lmstudio).
3. Start Khoj by running the following command in the same directory as your docker-compose.yml file.
```shell
cd ~/.khoj
docker-compose up
```
</TabItem>
</Tabs>
```shell
docker-compose up
```
Khoj should now be running at http://localhost:42110. You can see the web UI in your browser.
### Installation Option 2 (Local)
:::info[Remote Access]
By default Khoj is only accessible on the machine it is running. To access Khoj from a remote machine see [Remote Access Docs](/advanced/remote).
:::
#### Prerequisites
Your setup is complete once you see `🌖 Khoj is ready to use` in the server logs on your terminal.
</TabItem>
<TabItem value="pip" label="Pip">
##### Install Postgres (with PgVector)
<h3>1. Install Postgres (with PgVector)</h3>
Khoj uses the `pgvector` package to store embeddings of your index in a Postgres database. In order to use this, you need to have Postgres installed.
Khoj uses Postgres DB for all server configuration and to scale to multi-user setups. It uses the pgvector package in Postgres to manage your document embeddings. Both Postgres and pgvector need to be installed for Khoj to work.
```mdx-code-block
<Tabs groupId="operating-systems">
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
Install [Postgres.app](https://postgresapp.com/). This comes pre-installed with `pgvector` and relevant dependencies.
</TabItem>
<TabItem value="win" label="Windows">
<TabItem value="windows" label="Windows">
For detailed instructions and troubleshooting, see [this section](/contributing/development#2-postgres-installation--setup).
1. Use the [recommended installer](https://www.postgresql.org/download/windows/).
2. Follow instructions to [Install PgVector](https://github.com/pgvector/pgvector#windows) in case you need to manually install it. Windows support is experimental for pgvector currently, so we recommend using Docker.
</TabItem>
<TabItem value="unix" label="Linux">
<TabItem value="linux" label="Linux">
From [official instructions](https://wiki.postgresql.org/wiki/Apt)
</TabItem>
<TabItem value="source" label="From Source">
@@ -66,162 +136,288 @@ Install [Postgres.app](https://postgresapp.com/). This comes pre-installed with
2. Follow instructions to [Install PgVector](https://github.com/pgvector/pgvector#installation) in case you need to manually install it.
</TabItem>
</Tabs>
```
##### Create the Khoj database
<h3>2. Create the Khoj database</h3>
Make sure to update your environment variables to match your Postgres configuration if you're using a different name. The default values should work for most people. When prompted for a password, you can use the default password `postgres`, or configure it to your preference. Make sure to set the environment variable `POSTGRES_PASSWORD` to the same value as the password you set here.
```mdx-code-block
<Tabs groupId="operating-systems">
<TabItem value="macos" label="MacOS">
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
```shell
createdb khoj -U postgres --password
createdb khoj -U postgres --password
```
</TabItem>
<TabItem value="win" label="Windows">
</TabItem>
<TabItem value="windows" label="Windows">
```shell
createdb -U postgres khoj --password
```
</TabItem>
<TabItem value="unix" label="Linux">
```shell
sudo -u postgres createdb khoj --password
```
</TabItem>
</Tabs>
```
#### Install package
##### Local Server Setup
- *Make sure [python](https://realpython.com/installing-python/) and [pip](https://pip.pypa.io/en/stable/installation/) are installed on your machine*
Run the following command in your terminal to install the Khoj backend.
```mdx-code-block
<Tabs groupId="operating-systems">
<TabItem value="macos" label="MacOS">
```shell
python -m pip install khoj-assistant
createdb -U postgres khoj --password
```
</TabItem>
<TabItem value="win" label="Windows">
```shell
py -m pip install khoj-assistant
```
</TabItem>
<TabItem value="unix" label="Linux">
```shell
python -m pip install khoj-assistant
```
</TabItem>
</Tabs>
```
</TabItem>
<TabItem value="linux" label="Linux">
```shell
sudo -u postgres createdb khoj --password
```
</TabItem>
</Tabs>
##### Local Server Start
:::info[Postgres Env Config]
Make sure to update the `POSTGRES_HOST`, `POSTGRES_PORT`, `POSTGRES_USER`, `POSTGRES_DB` or `POSTGRES_PASSWORD` environment variables to match any customizations in your Postgres configuration.
:::
Before getting started, configure the following environment variables in your terminal for the first run
<h3>3. Install Khoj Server</h3>
- Make sure [python](https://realpython.com/installing-python/) and [pip](https://pip.pypa.io/en/stable/installation/) are installed on your machine
- Check [llama-cpp-python setup](https://github.com/abetlen/llama-cpp-python?tab=readme-ov-file#supported-backends) if you hit any llama-cpp issues with the installation
```mdx-code-block
<Tabs groupId="operating-systems">
Run the following command in your terminal to install the Khoj server.
<Tabs groupId="operating-systems" queryString="os">
<TabItem value="macos" label="MacOS">
```shell
export KHOJ_ADMIN_EMAIL=<your-email>
export KHOJ_ADMIN_PASSWORD=<your-password>
```
<Tabs groupId="gpu" queryString="gpu">
<TabItem value="arm" label="ARM/M1+">
```shell
CMAKE_ARGS="-DGGML_METAL=on" python -m pip install khoj
```
</TabItem>
<TabItem value="intel" label="Intel">
```shell
python -m pip install khoj
```
</TabItem>
</Tabs>
</TabItem>
<TabItem value="win" label="Windows">
If you're using PowerShell:
```shell
$env:KHOJ_ADMIN_EMAIL="<your-email>"
$env:KHOJ_ADMIN_PASSWORD="<your-password>"
<TabItem value="windows" label="Windows">
Run the following command in PowerShell on Windows
<Tabs groupId="gpu" queryString="gpu">
<TabItem value="cpu" label="CPU">
```shell
# Install Khoj
py -m pip install khoj
```
</TabItem>
<TabItem value="nvidia" label="NVIDIA (CUDA) GPU">
```shell
# 1. To use NVIDIA (CUDA) GPU
$env:CMAKE_ARGS = "-DGGML_CUDA=on"
# 2. Install Khoj
py -m pip install khoj
```
</TabItem>
<TabItem value="amd" label="AMD (ROCm) GPU">
```shell
# 1. To use AMD (ROCm) GPU
$env:CMAKE_ARGS = "-DGGML_HIPBLAS=on"
# 2. Install Khoj
py -m pip install khoj
```
</TabItem>
<TabItem value="vulkan" label="VULKAN GPU">
```shell
# 1. To use VULCAN GPU
$env:CMAKE_ARGS = "-DGGML_VULKAN=on"
# 2. Install Khoj
py -m pip install khoj
```
</TabItem>
</Tabs>
</TabItem>
<TabItem value="unix" label="Linux">
```shell
export KHOJ_ADMIN_EMAIL=<your-email>
export KHOJ_ADMIN_PASSWORD=<your-password>
```
<TabItem value="linux" label="Linux">
<Tabs groupId="gpu" queryString="gpu">
<TabItem value="cpu" label="CPU">
```shell
python -m pip install khoj
```
</TabItem>
<TabItem value="nvidia" label="NVIDIA (CUDA) GPU">
```shell
CMAKE_ARGS="-DGGML_CUDA=on" FORCE_CMAKE=1 python -m pip install khoj
```
</TabItem>
<TabItem value="amd" label="AMD (ROCm) GPU">
```shell
CMAKE_ARGS="-DGGML_HIPBLAS=on" FORCE_CMAKE=1 python -m pip install khoj
```
</TabItem>
<TabItem value="vulkan" label="VULKAN GPU">
```shell
CMAKE_ARGS="-DGGML_VULKAN=on" FORCE_CMAKE=1 python -m pip install khoj
```
</TabItem>
</Tabs>
</TabItem>
</Tabs>
```
<h3>4. Start Khoj Server</h3>
Run the following command from your terminal to start the Khoj backend and open Khoj in your browser.
Run the following command from your terminal to start the Khoj service.
```shell
khoj --anonymous-mode
```
`--anonymous-mode` allows you to run the server without setting up Google credentials for login. This allows you to use any of the clients without a login wall. If you want to use Google login, you can skip this flag, but you will have to add your Google developer credentials.
`--anonymous-mode` allows access to Khoj without requiring login. This is usually fine for local only, single user setups. If you need authentication follow the [authentication setup docs](/advanced/authentication).
On the first run, you will be prompted to input credentials for your admin account and do some basic configuration for your chat model settings. Once created, you can go to http://localhost:42110/server/admin and login with the credentials you just created.
Khoj should now be running at http://localhost:42110. You can see the web UI in your browser.
Note: To start Khoj automatically in the background use [Task scheduler](https://www.windowscentral.com/how-create-automated-task-using-task-scheduler-windows-10) on Windows or [Cron](https://en.wikipedia.org/wiki/Cron) on Mac, Linux (e.g with `@reboot khoj`)
<h4>First Run</h4>
On the first run of the above command, you will be prompted to:
1. Create an admin account with a email and secure password
2. Customize the chat models to enable
- Keep your [OpenAI](https://platform.openai.com/api-keys), [Anthropic](https://console.anthropic.com/account/keys), [Gemini](https://aistudio.google.com/app/apikey) API keys and [OpenAI](https://platform.openai.com/docs/models), [Anthropic](https://docs.anthropic.com/en/docs/about-claude/models#model-names), [Gemini](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-models), [Offline](https://huggingface.co/models?pipeline_tag=text-generation&library=gguf) chat model names handy to set any of them up during first run.
3. Your setup is complete once you see `🌖 Khoj is ready to use` in the server logs on your terminal!
### 2. Download the desktop client
:::tip[Auto Start]
To start Khoj automatically in the background use [Task scheduler](https://www.windowscentral.com/how-create-automated-task-using-task-scheduler-windows-10) on Windows or [Cron](https://en.wikipedia.org/wiki/Cron) on Mac, Linux (e.g. with `@reboot khoj`)
:::
</TabItem>
</Tabs>
You can use our desktop executables to select file paths and folders to index. You can simply select the folders or files, and they'll be automatically uploaded to the server. Once you specify a file or file path, you don't need to update the configuration again; it will grab any data diffs dynamically over time.
## Use Khoj
**To download the latest desktop client, go to https://download.khoj.dev** and the correct executable for your OS will automatically start downloading. You can also go to https://khoj.dev/downloads to explicitly download your image of choice. Once downloaded, you can configure your folders for indexing using the settings tab. To set your chat configuration, you'll have to use the web interface for the Khoj server you setup in the previous step.
You can now open the web app at http://localhost:42110 and start interacting!<br />
Nothing else is necessary, but you can customize your setup further by following the steps below.
To use the desktop client, you need to go to your Khoj server's settings page (http://localhost:42110/config) and copy the API key. Then, paste it into the desktop client's settings page. Once you've done that, you can select files and folders to index. Set the desktop client settings to use `http://127.0.0.1:42110` as the host URL.
:::info[First Message to Offline Chat Model]
The offline chat model gets downloaded when you first send a message to it. The download can take a few minutes! Subsequent messages should be faster.
:::
### 3. Configure
1. Go to http://localhost:42110/server/admin and login with your admin credentials.
1. Go to [OpenAI settings](http://localhost:42110/server/admin/database/openaiprocessorconversationconfig/) in the server admin settings to add an OpenAI processor conversation config. This is where you set your API key. Alternatively, you can go to the [offline chat settings](http://localhost:42110/server/admin/database/offlinechatprocessorconversationconfig/) and simply create a new setting with `Enabled` set to `True`.
2. Go to the ChatModelOptions if you want to add additional models for chat.
- Set the `chat-model` field to a supported chat model[^1] of your choice. For example, you can specify `gpt-4` if you're using OpenAI or `mistral-7b-instruct-v0.1.Q4_0.gguf` if you're using offline chat.
- Make sure to set the `model-type` field to `OpenAI` or `Offline` respectively.
- The `tokenizer` and `max-prompt-size` fields are optional. Set them only when using a non-standard model (i.e not mistral, gpt or llama2 model).
1. Select files and folders to index [using the desktop client](/get-started/setup#2-download-the-desktop-client). When you click 'Save', the files will be sent to your server for indexing.
- Select Notion workspaces and Github repositories to index using the web interface.
### Add Chat Models
<h4>Login to the Khoj Admin Panel</h4>
Go to http://localhost:42110/server/admin and login with the admin credentials you setup during installation.
[^1]: Khoj, by default, can use [OpenAI GPT3.5+ chat models](https://platform.openai.com/docs/models/overview) or [GPT4All chat models that follow Llama2 Prompt Template](https://github.com/nomic-ai/gpt4all/blob/main/gpt4all-chat/metadata/models2.json). See [this section](/miscellaneous/advanced#use-openai-compatible-llm-api-server-self-hosting) to use non-standard chat models
:::info[CSRF Error]
Ensure you are using **localhost, not 127.0.0.1**, to access the admin panel to avoid the CSRF error.
:::
:::info[DISALLOWED HOST or Bad Request (400) Error]
You may hit this if you try access Khoj exposed on a custom domain (e.g. 192.168.12.3 or example.com) or over HTTP.
Set the environment variables KHOJ_DOMAIN=your-domain and KHOJ_NO_HTTPS=True if required to avoid this error.
:::
:::tip[Note]
Using Safari on Mac? You might not be able to login to the admin panel. Try using Chrome or Firefox instead.
:::
<h4>Configure Chat Model</h4>
Setup which chat model you'd want to use. Khoj supports local and online chat models.
### 4. Install Client Plugins (Optional)
Khoj exposes a web interface to search, chat and configure by default.<br />
The optional steps below allow using Khoj from within an existing application like Obsidian or Emacs.
<Tabs groupId="chatmodel" queryString>
<TabItem value="openai" label="OpenAI">
- **Khoj Obsidian**:<br />
[Install](/clients/obsidian#setup) the Khoj Obsidian plugin
:::info[Ollama Integration]
Using Ollama? See the [Ollama Integration](/advanced/ollama) section for more custom setup instructions.
:::
- **Khoj Emacs**:<br />
[Install](/clients/emacs#setup) khoj.el
1. Create a new [AI Model Api](http://localhost:42110/server/admin/database/aimodelapi/add) in the server admin settings.
- Add your [OpenAI API key](https://platform.openai.com/api-keys)
- Give the configuration a friendly name like `OpenAI`
- (Optional) Set the API base URL. It is only relevant if you're using another OpenAI-compatible proxy server like [Ollama](/advanced/ollama) or [LMStudio](/advanced/lmstudio).<br />
![example configuration for ai model api](/img/example_openai_processor_config.png)
2. Create a new [chat model](http://localhost:42110/server/admin/database/chatmodel/add)
- Set the `chat-model` field to an [OpenAI chat model](https://platform.openai.com/docs/models). Example: `gpt-4o`.
- Make sure to set the `model-type` field to `OpenAI`.
- If your model supports vision, set the `vision enabled` field to `true`. This is currently only supported for OpenAI models with vision capabilities.
- The `tokenizer` and `max-prompt-size` fields are optional. Set them only if you're sure of the tokenizer or token limit for the model you're using. Contact us if you're unsure what to do here.<br />
![example configuration for chat model options](/img/example_chatmodel_option.png)
</TabItem>
<TabItem value="anthropic" label="Anthropic">
1. Create a new [AI Model API](http://localhost:42110/server/admin/database/aimodelapi/add) in the server admin settings.
- Add your [Anthropic API key](https://console.anthropic.com/account/keys)
- Give the configuration a friendly name like `Anthropic`. Do not configure the API base url.
2. Create a new [chat model](http://localhost:42110/server/admin/database/chatmodel/add)
- Set the `chat-model` field to an [Anthropic chat model](https://docs.anthropic.com/en/docs/about-claude/models#model-names). Example: `claude-3-5-sonnet-20240620`.
- Set the `model-type` field to `Anthropic`.
- Set the `ai model api` field to the Anthropic AI Model API you created in step 1.
</TabItem>
<TabItem value="gemini" label="Gemini">
1. Create a new [AI Model API](http://localhost:42110/server/admin/database/aimodelapi/add) in the server admin settings.
- Add your [Gemini API key](https://aistudio.google.com/app/apikey)
- Give the configuration a friendly name like `Gemini`. Do not configure the API base url.
2. Create a new [chat model](http://localhost:42110/server/admin/database/chatmodel/add)
- Set the `chat-model` field to a [Google Gemini chat model](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-models). Example: `gemini-1.5-flash`.
- Set the `model-type` field to `Gemini`.
- Set the `ai model api` field to the Gemini AI Model API you created in step 1.
#### Setup host URL
To configure your host URL on your clients when self-hosting, use `http://127.0.0.1:42110`. This is the default port for the Khoj server. Note that `localhost` will not work.
</TabItem>
<TabItem value="offline" label="Offline">
Offline chat stays completely private and can work without internet using any open-weights model.
### 5. Use Khoj 🚀
:::tip[System Requirements]
- Minimum 8 GB RAM. Recommend **16Gb VRAM**
- Minimum **5 GB of Disk** available
- A Nvidia, AMD GPU or a Mac M1+ machine would significantly speed up chat responses
:::
You can head to http://localhost:42110 to use the web interface. You can also use the desktop client to search and chat.
1. Get the name of your preferred chat model from [HuggingFace](https://huggingface.co/models?pipeline_tag=text-generation&library=gguf). *Most GGUF format chat models are supported*.
2. Open the [create chat model page](http://localhost:42110/server/admin/database/chatmodel/add/) on the admin panel
3. Set the `chat-model` field to the name of your preferred chat model
- Make sure the `model-type` is set to `Offline`
4. Set the newly added chat model as your preferred model in your [User chat settings](http://localhost:42110/settings) and [Server chat settings](http://localhost:42110/server/admin/database/serverchatsettings/).
5. Restart the Khoj server and [start chatting](http://localhost:42110) with your new offline model!
</TabItem>
</Tabs>
:::tip[Multiple Chat Models]
Set your preferred default chat model in the `Default`, `Advanced` fields of your [ServerChatSettings](http://localhost:42110/server/admin/database/serverchatsettings/).
Khoj uses these chat model for all intermediate steps like intent detection, web search etc.
:::
:::info[Chat Model Fields]
- The `tokenizer` and `max-prompt-size` fields are optional. Set them only if you're sure of the tokenizer or token limit for the model you're using. This improves context stuffing. Contact us if you're unsure what to do here.
- Only tick the `vision enabled` field for OpenAI models with vision capabilities like gpt-4o. Vision capabilities in other chat models is not currently utilized.
:::
### Sync your Knowledge
- You can chat with your notes and documents using Khoj.
- Khoj can keep your files and folders synced using the Khoj [Desktop](/clients/desktop#setup), [Obsidian](/clients/obsidian#setup) or [Emacs](/clients/emacs#setup) clients.
- Your [Notion workspace](/data-sources/notion_integration) can be directly synced from the web app.
- You can also just drag and drop specific files you want to chat with on the [Web app](/clients/web#upload-documents).
### Setup Khoj Clients
The Khoj web app is available by default to chat, search and configure Khoj.<br />
You can also install a Khoj client to easily access it from Obsidian, Emacs, Whatsapp or your OS and keep your documents synced with Khoj.
:::info[Note]
Set the host URL on your clients settings page to your Khoj server URL. By default, use `http://127.0.0.1:42110` or `http://localhost:42110`. Note that `localhost` may not work in all cases.
:::
<Tabs groupId="client" queryString>
<TabItem value="desktop" label="Desktop">
- Read the Khoj Desktop app [setup docs](/clients/desktop#setup).
</TabItem>
<TabItem value="emacs" label="Emacs">
- Read the Khoj Emacs package [setup docs](/clients/emacs#setup).
</TabItem>
<TabItem value="obsidian" label="Obsidian">
- Read the Khoj Obsidian plugin [setup docs](/clients/obsidian#setup).
</TabItem>
<TabItem value="whatsapp" label="Whatsapp">
- Read the Khoj Whatsapp app [setup docs](/clients/whatsapp).
</TabItem>
</Tabs>
## Upgrade
### Upgrade Khoj Server
```mdx-code-block
<Tabs groupId="environment">
<TabItem value="localsetup" label="Local Setup">
### Upgrade Server
<Tabs groupId="server" queryString>
<TabItem value="pip" label="Pip">
```shell
pip install --upgrade khoj-assistant
pip install --upgrade khoj
```
*Note: To upgrade to the latest pre-release version of the khoj server run below command*
</TabItem>
<TabItem value="docker" label="Docker">
From the same directory where you have your `docker-compose` file, this will fetch the latest build and upgrade your server.
Run the commands below from the same directory where you have your `docker-compose.yml` file.
This will fetch the latest build and upgrade your server.
```shell
# Windows users should use their WSL2 terminal to run these commands
cd ~/.khoj # assuming your khoj docker-compose.yml file is here
docker-compose up --build
```
</TabItem>
</Tabs>
### Upgrade Clients
<Tabs groupId="client" queryString>
<TabItem value="desktop" label="Desktop">
- The Desktop app automatically updates to the latest released version on restart.
- You can manually download the latest version from the [Khoj Website](https://khoj.dev/downloads).
</TabItem>
<TabItem value="emacs" label="Emacs">
- Use your Emacs Package Manager to Upgrade
- See [khoj.el package setup](/clients/emacs#setup) for details
@@ -231,39 +427,41 @@ You can head to http://localhost:42110 to use the web interface. You can also us
- See the [khoj plugin setup](/clients/obsidian#setup) for details
</TabItem>
</Tabs>
```
## Uninstall
### Uninstall Khoj Server
```mdx-code-block
<Tabs groupId="environment">
<TabItem value="localsetup" label="Local Setup">
### Uninstall Server
<Tabs groupId="server" queryString>
<TabItem value="pip" label="Pip">
```shell
# uninstall khoj server
pip uninstall khoj-assistant
pip uninstall khoj
# delete khoj postgres db
dropdb khoj -U postgres
```
</TabItem>
<TabItem value="docker" label="Docker">
From the same directory where you have your `docker-compose` file, run the command below to remove the server to delete its containers, networks, images and volumes.
Run the command below from the same directory where you have your `docker-compose` file.
This will remove the server containers, networks, images and volumes.
```shell
docker-compose down --volumes
```
</TabItem>
</Tabs>
### Uninstall Clients
<Tabs groupId="client" queryString>
<TabItem value="desktop" label="Desktop">
Uninstall the Khoj Desktop client in the standard way from your OS.
</TabItem>
<TabItem value="emacs" label="Emacs">
Uninstall the khoj Emacs, or desktop client in the standard way from Emacs or your OS respectively
You can also `rm -rf ~/.khoj` to remove the Khoj data directory if did a local install.
Uninstall the Khoj Emacs package in the standard way from Emacs.
</TabItem>
<TabItem value="obsidian" label="Obsidian">
Uninstall the khoj Obisidan, or desktop client in the standard way from Obsidian or your OS respectively
You can also `rm -rf ~/.khoj` to remove the Khoj data directory if did a local install.
Uninstall via the Community plugins tab on the settings pane in the Obsidian app
</TabItem>
</Tabs>
```
## Troubleshoot
@@ -274,13 +472,12 @@ You can head to http://localhost:42110 to use the web interface. You can also us
1. Install [pipx](https://pypa.github.io/pipx/#install-pipx)
2. Use `pipx` to install Khoj to avoid dependency conflicts with other python packages.
```shell
pipx install khoj-assistant
pipx install khoj
```
3. Now start `khoj` using the standard steps described earlier
#### Install fails while building Tokenizer dependency
- **Details**: `pip install khoj-assistant` fails while building the `tokenizers` dependency. Complains about Rust.
- **Details**: `pip install khoj` fails while building the `tokenizers` dependency. Complains about Rust.
- **Fix**: Install Rust to build the tokenizers package. For example on Mac run:
```shell
brew install rustup
@@ -289,7 +486,6 @@ You can head to http://localhost:42110 to use the web interface. You can also us
```
- **Refer**: [Issue with Fix](https://github.com/khoj-ai/khoj/issues/82#issuecomment-1241890946) for more details
#### Khoj in Docker errors out with \"Killed\" in error message
- **Fix**: Increase RAM available to Docker Containers in Docker Settings
- **Refer**: [StackOverflow Solution](https://stackoverflow.com/a/50770267), [Configure Resources on Docker for Mac](https://docs.docker.com/desktop/mac/#resources)

2
documentation/docs/miscellaneous/_category_.json
View File

@@ -1,6 +1,6 @@
{
"label": "Miscellaneous",
"position": 6,
"position": 7,
"link": {
"type": "generated-index",
"description": "Additional resources for learning about Khoj"

54
documentation/docs/miscellaneous/advanced.md
View File

@@ -1,54 +0,0 @@
---
sidebar_position: 3
---
# Advanced Usage
## Search across Different Languages (Self-Hosting)
To search for notes in multiple, different languages, you can use a [multi-lingual model](https://www.sbert.net/docs/pretrained_models.html#multi-lingual-models).<br />
For example, the [paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) supports [50+ languages](https://www.sbert.net/docs/pretrained_models.html#:~:text=we%20used%20the%20following%2050%2B%20languages), has good search quality and speed. To use it:
1. Manually update the search config in server's admin settings page. Go to [the search config](http://localhost:42110/server/admin/database/searchmodelconfig/). Either create a new one, if none exists, or update the existing one. Set the bi_encoder to `sentence-transformers/multi-qa-MiniLM-L6-cos-v1` and the cross_encoder to `cross-encoder/ms-marco-MiniLM-L-6-v2`.
2. Regenerate your content index from all the relevant clients. This step is very important, as you'll need to re-encode all your content with the new model.
## Query Filters
Use structured query syntax to filter entries from your knowledge based used by search results or chat responses.
- **Word Filter**: Get entries that include/exclude a specified term
- Entries that contain term_to_include: `+"term_to_include"`
- Entries that contain term_to_exclude: `-"term_to_exclude"`
- **Date Filter**: Get entries containing dates in YYYY-MM-DD format from specified date (range)
- Entries from April 1st 1984: `dt:"1984-04-01"`
- Entries after March 31st 1984: `dt>="1984-04-01"`
- Entries before April 2nd 1984 : `dt<="1984-04-01"`
- **File Filter**: Get entries from a specified file
- Entries from incoming.org file: `file:"incoming.org"`
- Combined Example
- `what is the meaning of life? file:"1984.org" dt>="1984-01-01" dt<="1985-01-01" -"big" -"brother"`
- Adds all filters to the natural language query. It should return entries
- from the file *1984.org*
- containing dates from the year *1984*
- excluding words *"big"* and *"brother"*
- that best match the natural language query *"what is the meaning of life?"*
## Use OpenAI compatible LLM API Server (Self Hosting)
Use this if you want to use non-standard, open or commercial, local or hosted LLM models for Khoj chat
1. Setup your desired chat LLM by installing an OpenAI compatible LLM API Server like [LiteLLM](https://docs.litellm.ai/docs/proxy/quick_start), [llama-cpp-python](https://github.com/abetlen/llama-cpp-python?tab=readme-ov-file#openai-compatible-web-server)
2. Set environment variable `OPENAI_API_BASE="<url-of-your-llm-server>"` before starting Khoj
3. Add ChatModelOptions with `model-type` `OpenAI`, and `chat-model` to anything (e.g `gpt-4`) during [Config](/get-started/setup#3-configure)
- *(Optional)* Set the `tokenizer` and `max-prompt-size` relevant to the actual chat model you're using
#### Sample Setup using LiteLLM and Mistral API
```shell
# Install LiteLLM
pip install litellm[proxy]
# Start LiteLLM and use Mistral tiny via Mistral API
export MISTRAL_API_KEY=<MISTRAL_API_KEY>
litellm --model mistral/mistral-tiny --drop_params
# Set OpenAI API Base to LiteLLM server URL and start Khoj
export OPENAI_API_BASE='http://localhost:8000'
khoj --anonymous-mode
```

7
documentation/docs/miscellaneous/credits.md
View File

@@ -5,9 +5,10 @@ sidebar_position: 4
# Credits
Many Open Source projects are used to power Khoj. Here's a few of them:
- [Multi-QA MiniLM Model](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1), [All MiniLM Model](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) for Text Search. See [SBert Documentation](https://www.sbert.net/examples/applications/retrieve_rerank/README.html)
- [OpenAI CLIP Model](https://github.com/openai/CLIP) for Image Search. See [SBert Documentation](https://www.sbert.net/examples/applications/image-search/README.html)
- [Llama.cpp](https://github.com/ggerganov/llama.cpp) to chat with local LLM
- [SentenceTransformer](https://www.sbert.net/examples/applications/retrieve_rerank/README.html) for Text Search
- [HuggingFace](https://huggingface.co/) for hosting open-source chat and search models
- Charles Cave for [OrgNode Parser](http://members.optusnet.com.au/~charles57/GTD/orgnode.html)
- [Org.js](https://mooz.github.io/org-js/) to render Org-mode results on the Web interface
- [Markdown-it](https://github.com/markdown-it/markdown-it) to render Markdown results on the Web interface
- [GPT4All](https://github.com/nomic-ai/gpt4all) to chat with local LLM
- [Katex](https://katex.org/) to render math

12
documentation/docs/miscellaneous/performance.md
View File

@@ -6,20 +6,22 @@ sidebar_position: 2
Here are some top-level performance metrics for Khoj. These are rough estimates and will vary based on your hardware and data.
:::info
These performance metrics were last evaluated in 2022.
:::
### Search performance
- Semantic search using the bi-encoder is fairly fast at \<100 ms across all content types
- Reranking using the cross-encoder is slower at \<2s on 15 results. Tweak `top_k` to tradeoff speed for accuracy of results
- Filters in query (e.g by file, word or date) usually add \<20ms to query latency
- Semantic search using the default embeddings model is fairly fast at \<100 ms across all content types
- Reranking using the cross-encoder model is slower at \<2s on 15 results. Tweak `top_k` to tradeoff speed for accuracy of results
- Filters in query (e.g. by file, word or date) usually add \<20ms to query latency
### Indexing performance
- Indexing is more strongly impacted by the size of the source data
- Indexing 100K+ line corpus of notes takes about 10 minutes
- Indexing 4000+ images takes about 15 minutes and more than 8Gb of RAM
- Note: *It should only take this long on the first run* as the index is incrementally updated
### Miscellaneous
- Testing done on a Mac M1 and a \>100K line corpus of notes
- Search, indexing on a GPU has not been tested yet

24
documentation/docs/miscellaneous/query-filters.md Normal file
View File

@@ -0,0 +1,24 @@
---
sidebar_position: 3
---
# Query Filters
Use structured query syntax to filter entries from your knowledge based used by search results or chat responses.
- **Word Filter**: Get entries that include/exclude a specified term
- Entries that contain term_to_include: `+"term_to_include"`
- Entries that contain term_to_exclude: `-"term_to_exclude"`
- **Date Filter**: Get entries containing dates in YYYY-MM-DD format from specified date (range)
- Entries from April 1st 1984: `dt:"1984-04-01"`
- Entries after March 31st 1984: `dt>="1984-04-01"`
- Entries before April 2nd 1984 : `dt<="1984-04-01"`
- **File Filter**: Get entries from a specified file
- Entries from incoming.org file: `file:"incoming.org"`
- Combined Example
- `what is the meaning of life? file:"1984.org" dt>="1984-01-01" dt<="1985-01-01" -"big" -"brother"`
- Adds all filters to the natural language query. It should return entries
- from the file *1984.org*
- containing dates from the year *1984*
- excluding words *"big"* and *"brother"*
- that best match the natural language query *"what is the meaning of life?"*

7
documentation/docs/miscellaneous/telemetry.md
View File

@@ -4,7 +4,7 @@ sidebar_position: 1
# Telemetry
We collect some high level, anonymized metadata about usage of Khoj. This includes:
We collect some high level, anonymized metadata about usage of self-hosted Khoj. This includes:
- Client (Web, Emacs, Obsidian)
- API usage (Search, Chat)
- Configured content types (Github, Org, etc)
@@ -14,9 +14,6 @@ We don't send any personal information or any information from/about your conten
## Disable Telemetry
If you're self-hosting Khoj, you can opt out of telemetry at any time. To do so,
1. Open `~/.khoj/khoj.yml`
2. Set `should-log-telemetry` to `false`
3. Save the file and restart Khoj
If you're self-hosting Khoj, you can opt out of telemetry at any time by setting the `KHOJ_TELEMETRY_DISABLE` environment variable to `True` via shell or `docker-compose.yml`
If you have any questions or concerns, please reach out to us on [Discord](https://discord.gg/BDgyabRM6e).

55
documentation/docusaurus.config.js
View File

@@ -9,7 +9,7 @@ import {themes as prismThemes} from 'prism-react-renderer';
/** @type {import('@docusaurus/types').Config} */
const config = {
title: 'Khoj AI',
tagline: 'An AI copilot for your Second Brain',
tagline: 'Your Second Brain',
staticDirectories: ['assets'],
@@ -37,6 +37,9 @@ const config = {
locales: ['en'],
},
// Add a widget for Chatwoot for live chat if users need help
clientModules: [require.resolve('./src/components/ChatwootWidget.js')],
presets: [
[
'classic',
@@ -60,23 +63,26 @@ const config = {
theme: {
customCss: './src/css/custom.css',
},
sitemap: {
lastmod: 'date',
changefreq: 'weekly',
priority: 0.5,
filename: 'sitemap.xml',
},
}),
],
],
themeConfig:
/** @type {import('@docusaurus/preset-classic').ThemeConfig} */
({
image: 'img/khoj-logo-sideways-500.png',
image: 'img/khoj_documentation.png',
metadata: [
{name: 'keywords', content: 'khoj, khoj ai, chatgpt, open ai, open source, productivity'},
{name: 'og:title', content: 'Khoj Documentation'},
{name: 'og:title', content: 'Docs'},
{name: 'og:type', content: 'website'},
{name: 'og:site_name', content: 'Khoj Documentation'},
{name: 'og:description', content: 'Quickly get started with using or self-hosting Khoj'},
{name: 'og:image', content: 'https://khoj-web-bucket.s3.amazonaws.com/link_preview_docs.png'},
{name: 'og:url', content: 'https://docs.khoj.dev'},
{name: 'keywords', content: 'khoj, khoj ai, chatgpt, open ai, open source, productivity'}
{name: 'keywords', content: 'khoj, khoj ai, chatgpt, open source ai, open source, transparent, accessible, trustworthy, hackable, index notes, rag, productivity'}
],
navbar: {
title: 'Khoj',
@@ -87,18 +93,31 @@ const config = {
items: [
{
href: 'https://github.com/khoj-ai/khoj',
label: '📖 GitHub',
position: 'right',
className: 'header-github-link',
title: 'Codebase',
'aria-label': 'GitHub repository',
},
{
href: 'https://app.khoj.dev/login',
label: '🌍 Cloud',
position: 'right',
className: 'header-cloud-link',
title: 'Khoj Cloud',
'aria-label': 'Khoj Cloud',
},
{
href: 'https://discord.gg/BDgyabRM6e',
label: '💬 Discord',
position: 'right',
className: 'header-discord-link',
title: 'Community',
'aria-label': 'Discord community',
},
{
href: 'https://blog.khoj.dev',
position: 'right',
className: 'header-blog-link',
title: 'Blog',
'aria-label': 'Khoj Blog',
},
],
},
@@ -118,18 +137,18 @@ const config = {
},
{
label: 'Features',
to: '/features/all_features',
to: '/features/all-features',
},
{
label: 'Client Apps',
to: '/category/clients',
},
{
label: 'Self-Hosting',
label: 'Self-Host',
to: '/get-started/setup',
},
{
label: 'Contributing',
label: 'Contribute',
to: '/contributing/development',
},
],
@@ -162,16 +181,16 @@ const config = {
{
title: 'More',
items: [
// {
// label: 'Blog',
// to: '/blog',
// },
{
href: 'https://blog.khoj.dev',
label: 'Blog',
},
{
label: 'Khoj Cloud',
href: 'https://app.khoj.dev/login',
},
{
label: 'Open Source',
label: 'GitHub',
href: 'https://github.com/khoj-ai/khoj',
},
{

14629
documentation/package-lock.json generated
View File

File diff suppressed because it is too large Load Diff

9
documentation/package.json
View File

@@ -14,8 +14,9 @@
"write-heading-ids": "docusaurus write-heading-ids"
},
"dependencies": {
"@docusaurus/core": "3.1.0",
"@docusaurus/preset-classic": "3.1.0",
"@docusaurus/core": "^3.2.1",
"@docusaurus/plugin-sitemap": "^3.2.1",
"@docusaurus/preset-classic": "^3.2.1",
"@mdx-js/react": "^3.0.0",
"clsx": "^2.0.0",
"prism-react-renderer": "^2.3.0",
@@ -23,8 +24,8 @@
"react-dom": "^18.0.0"
},
"devDependencies": {
"@docusaurus/module-type-aliases": "3.1.0",
"@docusaurus/types": "3.1.0"
"@docusaurus/module-type-aliases": "^3.2.1",
"@docusaurus/types": "^3.2.1"
},
"browserslist": {
"production": [

19
documentation/src/components/ChatwootWidget.js Normal file
View File

@@ -0,0 +1,19 @@
import ExecutionEnvironment from '@docusaurus/ExecutionEnvironment';
// Only execute on client-side
if (ExecutionEnvironment.canUseDOM) {
(function (d, t) {
var BASE_URL = "https://app.chatwoot.com";
var g = d.createElement(t), s = d.getElementsByTagName(t)[0];
g.src = BASE_URL + "/packs/js/sdk.js";
g.defer = true;
g.async = true;
s.parentNode.insertBefore(g, s);
g.onload = function () {
window.chatwootSDK.run({
websiteToken: 'cFxvnLSjfE2UF4UUiPCA5NsF',
baseUrl: BASE_URL
})
}
})(document, 'script');
}

76
documentation/src/css/custom.css
View File

@@ -8,13 +8,13 @@
/* You can override the default Infima variables here. */
:root {
--ifm-color-primary: #fcc50b;
--ifm-color-primary-dark: #fcc50b;
--ifm-color-primary-darker: #fcc50b;
--ifm-color-primary-darkest: #fcc50b;
--ifm-color-primary-light: #fcc50b;
--ifm-color-primary-lighter: #fcc50b;
--ifm-color-primary-lightest: #fcc50b;
--ifm-color-primary: #FFA07A;
--ifm-color-primary-dark: #FFA07A;
--ifm-color-primary-darker: #FFA07A;
--ifm-color-primary-darkest: #FFA07A;
--ifm-color-primary-light: #FFA07A;
--ifm-color-primary-lighter: #FFA07A;
--ifm-color-primary-lightest: #FFA07A;
--ifm-code-font-size: 95%;
--ifm-heading-font-family: 'Source Sans 3', sans-serif;
--docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.1);
@@ -22,16 +22,64 @@
/* For readability concerns, you should choose a lighter palette in dark mode. */
[data-theme='dark'] {
--ifm-color-primary: #fcc50b;
--ifm-color-primary-dark: #fcc50b;
--ifm-color-primary-darker: #fcc50b;
--ifm-color-primary-darkest: #fcc50b;
--ifm-color-primary-light: #fcc50b;
--ifm-color-primary-lighter: #fcc50b;
--ifm-color-primary-lightest: #fcc50b;
--ifm-color-primary: #FFA07A;
--ifm-color-primary-dark: #FFA07A;
--ifm-color-primary-darker: #FFA07A;
--ifm-color-primary-darkest: #FFA07A;
--ifm-color-primary-light: #FFA07A;
--ifm-color-primary-lighter: #FFA07A;
--ifm-color-primary-lightest: #FFA07A;
--docusaurus-highlighted-code-line-bg: rgba(0, 0, 0, 0.3);
}
body {
font-family: 'Source Sans 3', sans-serif;
}
.header-github-link::before {
content: '';
width: 24px;
height: 24px;
display: flex;
background-color: var(--ifm-navbar-link-color);
mask-image: url("data:image/svg+xml,%3Csvg viewBox='0 0 24 24' xmlns='http://www.w3.org/2000/svg'%3E%3Cpath d='M12 .297c-6.63 0-12 5.373-12 12 0 5.303 3.438 9.8 8.205 11.385.6.113.82-.258.82-.577 0-.285-.01-1.04-.015-2.04-3.338.724-4.042-1.61-4.042-1.61C4.422 18.07 3.633 17.7 3.633 17.7c-1.087-.744.084-.729.084-.729 1.205.084 1.838 1.236 1.838 1.236 1.07 1.835 2.809 1.305 3.495.998.108-.776.417-1.305.76-1.605-2.665-.3-5.466-1.332-5.466-5.93 0-1.31.465-2.38 1.235-3.22-.135-.303-.54-1.523.105-3.176 0 0 1.005-.322 3.3 1.23.96-.267 1.98-.399 3-.405 1.02.006 2.04.138 3 .405 2.28-1.552 3.285-1.23 3.285-1.23.645 1.653.24 2.873.12 3.176.765.84 1.23 1.91 1.23 3.22 0 4.61-2.805 5.625-5.475 5.92.42.36.81 1.096.81 2.22 0 1.606-.015 2.896-.015 3.286 0 .315.21.69.825.57C20.565 22.092 24 17.592 24 12.297c0-6.627-5.373-12-12-12'/%3E%3C/svg%3E");
transition: background-color var(--ifm-transition-fast) var(--ifm-transition-timing-default);
}
.header-blog-link::before {
content: '';
width: 24px;
height: 24px;
display: flex;
background-color: var(--ifm-navbar-link-color);
mask-image: url("data:image/svg+xml,%3Csvg viewBox='0 0 512 512' xmlns='http://www.w3.org/2000/svg'%3E%3C!--!Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free Copyright 2024 Fonticons, Inc.--%3E%3Cpath d='M278.5 215.6L23 471c-9.4 9.4-9.4 24.6 0 33.9s24.6 9.4 33.9 0l57-57 68 0c49.7 0 97.9-14.4 139-41c11.1-7.2 5.5-23-7.8-23c-5.1 0-9.2-4.1-9.2-9.2c0-4.1 2.7-7.6 6.5-8.8l81-24.3c2.5-.8 4.8-2.1 6.7-4l22.4-22.4c10.1-10.1 2.9-27.3-11.3-27.3l-32.2 0c-5.1 0-9.2-4.1-9.2-9.2c0-4.1 2.7-7.6 6.5-8.8l112-33.6c4-1.2 7.4-3.9 9.3-7.7C506.4 207.6 512 184.1 512 160c0-41-16.3-80.3-45.3-109.3l-5.5-5.5C432.3 16.3 393 0 352 0s-80.3 16.3-109.3 45.3L139 149C91 197 64 262.1 64 330l0 55.3L253.6 195.8c6.2-6.2 16.4-6.2 22.6 0c5.4 5.4 6.1 13.6 2.2 19.8z'/%3E%3C/svg%3E");
transition: background-color var(--ifm-transition-fast) var(--ifm-transition-timing-default);
}
.header-cloud-link::before {
content: '';
width: 24px;
height: 24px;
display: flex;
background-color: var(--ifm-navbar-link-color);
mask-image: url("data:image/svg+xml,%3Csvg viewBox='0 0 512 512' xmlns='http://www.w3.org/2000/svg'%3E%3C!--!Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free Copyright 2024 Fonticons, Inc.--%3E%3Cpath d='M0 224c0 53 43 96 96 96l47.2 0L290 202.5c17.6-14.1 42.6-14 60.2 .2s22.8 38.6 12.8 58.8L333.7 320l18.3 0 64 0c53 0 96-43 96-96s-43-96-96-96c-.5 0-1.1 0-1.6 0c1.1-5.2 1.6-10.5 1.6-16c0-44.2-35.8-80-80-80c-24.3 0-46.1 10.9-60.8 28C256.5 24.3 219.1 0 176 0C114.1 0 64 50.1 64 112c0 7.1 .7 14.1 1.9 20.8C27.6 145.4 0 181.5 0 224zm330.1 3.6c-5.8-4.7-14.2-4.7-20.1-.1l-160 128c-5.3 4.2-7.4 11.4-5.1 17.8s8.3 10.7 15.1 10.7l70.1 0L177.7 488.8c-3.4 6.7-1.6 14.9 4.3 19.6s14.2 4.7 20.1 .1l160-128c5.3-4.2 7.4-11.4 5.1-17.8s-8.3-10.7-15.1-10.7l-70.1 0 52.4-104.8c3.4-6.7 1.6-14.9-4.2-19.6z'/%3E%3C/svg%3E");
transition: background-color var(--ifm-transition-fast) var(--ifm-transition-timing-default);
}
.header-discord-link::before {
content: '';
width: 30px;
height: 24px;
display: flex;
background-color: var(--ifm-navbar-link-color);
mask-image: url("data:image/svg+xml,%3Csvg viewBox='0 0 640 512' xmlns='http://www.w3.org/2000/svg'%3E%3C!--!Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free Copyright 2024 Fonticons, Inc.--%3E%3Cpath d='M524.5 69.8a1.5 1.5 0 0 0 -.8-.7A485.1 485.1 0 0 0 404.1 32a1.8 1.8 0 0 0 -1.9 .9 337.5 337.5 0 0 0 -14.9 30.6 447.8 447.8 0 0 0 -134.4 0 309.5 309.5 0 0 0 -15.1-30.6 1.9 1.9 0 0 0 -1.9-.9A483.7 483.7 0 0 0 116.1 69.1a1.7 1.7 0 0 0 -.8 .7C39.1 183.7 18.2 294.7 28.4 404.4a2 2 0 0 0 .8 1.4A487.7 487.7 0 0 0 176 479.9a1.9 1.9 0 0 0 2.1-.7A348.2 348.2 0 0 0 208.1 430.4a1.9 1.9 0 0 0 -1-2.6 321.2 321.2 0 0 1 -45.9-21.9 1.9 1.9 0 0 1 -.2-3.1c3.1-2.3 6.2-4.7 9.1-7.1a1.8 1.8 0 0 1 1.9-.3c96.2 43.9 200.4 43.9 295.5 0a1.8 1.8 0 0 1 1.9 .2c2.9 2.4 6 4.9 9.1 7.2a1.9 1.9 0 0 1 -.2 3.1 301.4 301.4 0 0 1 -45.9 21.8 1.9 1.9 0 0 0 -1 2.6 391.1 391.1 0 0 0 30 48.8 1.9 1.9 0 0 0 2.1 .7A486 486 0 0 0 610.7 405.7a1.9 1.9 0 0 0 .8-1.4C623.7 277.6 590.9 167.5 524.5 69.8zM222.5 337.6c-29 0-52.8-26.6-52.8-59.2S193.1 219.1 222.5 219.1c29.7 0 53.3 26.8 52.8 59.2C275.3 311 251.9 337.6 222.5 337.6zm195.4 0c-29 0-52.8-26.6-52.8-59.2S388.4 219.1 417.9 219.1c29.7 0 53.3 26.8 52.8 59.2C470.7 311 447.5 337.6 417.9 337.6z'/%3E%3C/svg%3E");
transition: background-color var(--ifm-transition-fast) var(--ifm-transition-timing-default);
}
.header-github-link:hover::before,
.header-cloud-link:hover::before,
.header-discord-link:hover::before,
.header-blog-link:hover::before {
background-color: var(--ifm-navbar-link-hover-color);
transform: scale(1.1);
}

5911
documentation/yarn.lock
View File

File diff suppressed because it is too large Load Diff

6
gunicorn-config.py
View File

@@ -1,10 +1,10 @@
import multiprocessing
bind = "0.0.0.0:42110"
workers = 4
workers = 2
worker_class = "uvicorn.workers.UvicornWorker"
timeout = 120
keep_alive = 60
accesslog = "access.log"
errorlog = "error.log"
accesslog = "-"
errorlog = "-"
loglevel = "debug"

4
manifest.json
View File

@@ -1,9 +1,9 @@
{
"id": "khoj",
"name": "Khoj",
"version": "1.6.1",
"version": "1.33.1",
"minAppVersion": "0.15.0",
"description": "An AI copilot for your Second Brain",
"description": "Your Second Brain",
"author": "Khoj Inc.",
"authorUrl": "https://github.com/khoj-ai",
"isDesktopOnly": false

63
prod.Dockerfile
View File

@@ -1,31 +1,64 @@
# Use Nvidia's latest Ubuntu 22.04 image as the base image
FROM nvidia/cuda:12.2.0-devel-ubuntu22.04
LABEL org.opencontainers.image.source https://github.com/khoj-ai/khoj
# syntax=docker/dockerfile:1
FROM ubuntu:jammy AS base
LABEL homepage="https://khoj.dev"
LABEL repository="https://github.com/khoj-ai/khoj"
LABEL org.opencontainers.image.source="https://github.com/khoj-ai/khoj"
LABEL org.opencontainers.image.description="Your second brain, containerized for multi-user, cloud deployment"
# Install System Dependencies
RUN apt update -y && apt -y install python3-pip libsqlite3-0 ffmpeg libsm6 libxext6
# Install Optional Dependencies
RUN apt install vim -y
RUN apt update -y && apt -y install \
python3-pip \
libsqlite3-0 \
ffmpeg \
libsm6 \
libxext6 \
swig \
curl \
# Required by llama-cpp-python pre-built wheels. See #1628
musl-dev && \
ln -s /usr/lib/x86_64-linux-musl/libc.so /lib/libc.musl-x86_64.so.1 && \
# Clean up
apt clean && rm -rf /var/lib/apt/lists/*
# Build Server
FROM base AS server-deps
WORKDIR /app
# Install Application
COPY pyproject.toml .
COPY README.md .
ARG VERSION=0.0.0
# use the pre-built llama-cpp-python, torch cpu wheel
ENV PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu https://abetlen.github.io/llama-cpp-python/whl/cpu"
# avoid downloading unused cuda specific python packages
ENV CUDA_VISIBLE_DEVICES=""
RUN sed -i "s/dynamic = \\[\"version\"\\]/version = \"$VERSION\"/" pyproject.toml && \
TMPDIR=/home/cache/ pip install --cache-dir=/home/cache/ -e .[prod]
pip install --no-cache-dir -e .[prod]
# Copy Source Code
COPY . .
# Build Web App
FROM node:20-alpine AS web-app
# Set build optimization env vars
ENV NODE_ENV=production
ENV NEXT_TELEMETRY_DISABLED=1
WORKDIR /app/src/interface/web
# Install dependencies first (cache layer)
COPY src/interface/web/package.json src/interface/web/yarn.lock ./
RUN yarn install --frozen-lockfile
# Copy source and build
COPY src/interface/web/. ./
RUN yarn build
# Set the PYTHONPATH environment variable in order for it to find the Django app.
# Merge the Server and Web App into a Single Image
FROM base
ENV PYTHONPATH=/app/src:$PYTHONPATH
WORKDIR /app
COPY --from=server-deps /usr/local/lib/python3.10/dist-packages /usr/local/lib/python3.10/dist-packages
COPY --from=server-deps /usr/local/bin /usr/local/bin
COPY --from=web-app /app/src/interface/web/out ./src/khoj/interface/built
COPY . .
RUN cd src && python3 khoj/manage.py collectstatic --noinput
# Run the Application
# There are more arguments required for the application to run,
# but these should be passed in through the docker-compose.yml file.
# but those should be passed in through the docker-compose.yml file.
ARG PORT
EXPOSE ${PORT}
ENTRYPOINT [ "gunicorn", "-c", "gunicorn-config.py", "src.khoj.main:app" ]
ENTRYPOINT ["gunicorn", "-c", "gunicorn-config.py", "src.khoj.main:app"]

80
pyproject.toml
View File

@@ -3,11 +3,11 @@ requires = ["hatchling", "hatch-vcs"]
build-backend = "hatchling.build"
[project]
name = "khoj-assistant"
description = "An AI copilot for your Second Brain"
name = "khoj"
description = "Your Second Brain"
readme = "README.md"
license = "AGPL-3.0-or-later"
requires-python = ">=3.8"
requires-python = ">=3.10"
authors = [
{ name = "Debanjum Singh Solanky, Saba Imran" },
]
@@ -23,89 +23,107 @@ keywords = [
"pdf",
]
classifiers = [
"Development Status :: 4 - Beta",
"License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
"Development Status :: 5 - Production/Stable",
"License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.9",
"Programming Language :: Python :: 3.10",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Topic :: Internet :: WWW/HTTP :: Indexing/Search",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
"Topic :: Scientific/Engineering :: Human Machine Interfaces",
"Topic :: Text Processing :: Linguistic",
"Intended Audience :: Information Technology",
]
dependencies = [
"bs4 >= 0.0.1",
"beautifulsoup4 ~= 4.12.3",
"dateparser >= 1.1.1",
"defusedxml == 0.7.1",
"fastapi >= 0.104.1",
"fastapi >= 0.110.0",
"python-multipart >= 0.0.7",
"jinja2 == 3.1.3",
"jinja2 == 3.1.5",
"openai >= 1.0.0",
"tiktoken >= 0.3.2",
"tenacity >= 8.2.2",
"pillow ~= 9.5.0",
"pydantic >= 2.0.0",
"pyyaml == 6.0",
"magika ~= 0.5.1",
"pillow ~= 10.0.0",
"pydantic[email] >= 2.0.0",
"pyyaml ~= 6.0",
"rich >= 13.3.1",
"schedule == 1.1.0",
"sentence-transformers == 2.3.1",
"sentence-transformers == 3.0.1",
"einops == 0.8.0",
"transformers >= 4.28.0",
"torch == 2.0.1",
"uvicorn == 0.17.6",
"torch == 2.2.2",
"uvicorn == 0.30.6",
"aiohttp ~= 3.9.0",
"langchain <= 0.2.0",
"langchain-openai >= 0.0.5",
"langchain == 0.2.5",
"langchain-community == 0.2.5",
"requests >= 2.26.0",
"bs4 >= 0.0.1",
"tenacity == 8.3.0",
"anyio == 3.7.1",
"pymupdf >= 1.23.5",
"django == 4.2.10",
"pymupdf == 1.24.11",
"django == 5.0.10",
"django-unfold == 0.42.0",
"authlib == 1.2.1",
"gpt4all == 2.1.0; platform_system == 'Linux' and platform_machine == 'x86_64'",
"gpt4all == 2.1.0; platform_system == 'Windows' or platform_system == 'Darwin'",
"llama-cpp-python == 0.2.88",
"itsdangerous == 2.1.2",
"httpx == 0.25.0",
"pgvector == 0.2.4",
"psycopg2-binary == 2.9.9",
"gunicorn == 21.2.0",
"lxml == 4.9.3",
"tzdata == 2023.3",
"rapidocr-onnxruntime == 1.3.11",
"rapidocr-onnxruntime == 1.3.24",
"openai-whisper >= 20231117",
"django-phonenumber-field == 7.3.0",
"phonenumbers == 8.13.27",
"markdownify ~= 0.11.6",
"markdown-it-py ~= 3.0.0",
"websockets == 12.0",
"psutil >= 5.8.0",
"huggingface-hub >= 0.22.2",
"apscheduler ~= 3.10.0",
"pytz ~= 2024.1",
"cron-descriptor == 1.4.3",
"django_apscheduler == 0.6.2",
"anthropic == 0.26.1",
"docx2txt == 0.8",
"google-generativeai == 0.8.3",
"pyjson5 == 1.6.7",
"resend == 1.0.1",
]
dynamic = ["version"]
[project.urls]
Homepage = "https://github.com/khoj-ai/khoj#readme"
Issues = "https://github.com/khoj-ai/khoj/issues"
Discussions = "https://github.com/khoj-ai/khoj/discussions"
Releases = "https://github.com/khoj-ai/khoj/releases"
Homepage = "https://khoj.dev"
Documentation = "https://docs.khoj.dev"
Code = "https://github.com/khoj-ai/khoj"
[project.scripts]
khoj = "khoj.main:run"
[project.optional-dependencies]
prod = [
"gunicorn == 22.0.0",
"google-auth == 2.23.3",
"stripe == 7.3.0",
"twilio == 8.11",
"boto3 >= 1.34.57",
]
dev = [
"khoj-assistant[prod]",
"khoj[prod]",
"pytest >= 7.1.2",
"pytest-xdist[psutil]",
"pytest-django == 4.5.2",
"pytest-asyncio == 0.21.1",
"freezegun >= 1.2.0",
"factory-boy >= 3.2.1",
"psutil >= 5.8.0",
"mypy >= 1.0.1",
"black >= 23.1.0",
"pre-commit >= 3.0.4",
"gitpython ~= 3.1.43",
"datasets",
"pandas",
]
[tool.hatch.version]

94
scripts/bump_version.sh
View File

@@ -2,25 +2,31 @@
project_root=$PWD
while getopts 'nc:' opt;
while getopts 'nc:t:' opt;
do
case "${opt}" in
c)
# Get current project version
current_version=$OPTARG
t)
# Get version type to bump. Options: major, minor, patch
version_type=$OPTARG
# Bump Web app to current version
cd $project_root/src/interface/web
yarn version --$version_type --no-git-tag-version
# Bump Desktop app to current version
cd $project_root/src/interface/desktop
sed -E -i.bak "s/version\": \"(.*)\",/version\": \"$current_version\",/" package.json
rm *.bak
yarn version --$version_type --no-git-tag-version
# Get bumped project version
current_version=$(grep '"version":' package.json | awk -F '"' '{print $4}')
# Bump Obsidian plugin to current version
cd $project_root/src/interface/obsidian
sed -E -i.bak "s/version\": \"(.*)\",/version\": \"$current_version\",/" package.json
sed -E -i.bak "s/version\": \"(.*)\"/version\": \"$current_version\"/" manifest.json
yarn build # verify build before bumping version
yarn version --$version_type --no-git-tag-version
# append current version, min Obsidian app version from manifest to versions json
cp $project_root/versions.json .
npm run version # append current version
rm *.bak
yarn run version # run Obsidian version script
# Bump Emacs package to current version
cd ../emacs
@@ -38,8 +44,57 @@ do
# Commit changes and tag commit for release
git add \
$project_root/src/interface/web/package.json \
$project_root/src/interface/desktop/package.json \
$project_root/src/interface/obsidian/package.json \
$project_root/src/interface/obsidian/yarn.lock \
$project_root/src/interface/obsidian/manifest.json \
$project_root/src/interface/obsidian/versions.json \
$project_root/src/interface/emacs/khoj.el \
$project_root/manifest.json \
$project_root/versions.json
git commit -m "Release Khoj version $current_version"
git tag $current_version master
;;
c)
# Get current project version
current_version=$OPTARG
# Bump Web app to current version
cd $project_root/src/interface/web
yarn version --new-version $current_version --no-git-tag-version
# Bump Desktop app to current version
cd $project_root/src/interface/desktop
yarn version --new-version $current_version --no-git-tag-version
# Bump Obsidian plugin to current version
cd $project_root/src/interface/obsidian
yarn version --new-version $current_version --no-git-tag-version
# append current version, min Obsidian app version from manifest.json to versions.json
cp $project_root/versions.json .
yarn run version # run Obsidian version script
# Bump Emacs package to current version
cd ../emacs
sed -E -i.bak "s/^;; Version: (.*)/;; Version: $current_version/" khoj.el
git add khoj.el
rm *.bak
# Copy current obsidian versioned files to project root
cd $project_root
cp src/interface/obsidian/versions.json .
cp src/interface/obsidian/manifest.json .
# Run pre-commit validation to fix jsons
pre-commit run --hook-stage manual --all
# Commit changes and tag commit for release
git add \
$project_root/src/interface/web/package.json \
$project_root/src/interface/desktop/package.json \
$project_root/src/interface/obsidian/package.json \
$project_root/src/interface/obsidian/yarn.lock \
$project_root/src/interface/obsidian/manifest.json \
$project_root/src/interface/obsidian/versions.json \
$project_root/src/interface/emacs/khoj.el \
@@ -54,17 +109,20 @@ do
next_version=$(touch bump.txt && git add bump.txt && hatch version | sed 's/\.dev.*//g')
git rm --cached -- bump.txt && rm bump.txt
# Bump Web app to next version
cd $project_root/src/interface/web
yarn version --new-version $next_version --no-git-tag-version
# Bump Desktop app to next version
cd $project_root/src/interface/desktop
sed -E -i.bak "s/version\": \"(.*)\",/version\": \"$current_version\",/" package.json
rm *.bak
yarn version --new-version $next_version --no-git-tag-version
# Bump Obsidian plugins to next version
cd $project_root/src/interface/obsidian
sed -E -i.bak "s/version\": \"(.*)\",/version\": \"$next_version\",/" package.json
sed -E -i.bak "s/version\": \"(.*)\"/version\": \"$next_version\"/" manifest.json
npm run version # updates versions.json
rm *.bak
yarn version --new-version $next_version --no-git-tag-version
# append next version, min Obsidian app version from manifest to versions json
git rm --cached -- versions.json
yarn run version # run Obsidian version script
# Bump Emacs package to next version
cd $project_root/src/interface/emacs
@@ -76,15 +134,17 @@ do
# Commit changes
git add \
$project_root/src/interface/web/package.json \
$project_root/src/interface/desktop/package.json \
$project_root/src/interface/obsidian/package.json \
$project_root/src/interface/obsidian/yarn.lock \
$project_root/src/interface/obsidian/manifest.json \
$project_root/src/interface/obsidian/versions.json \
$project_root/src/interface/emacs/khoj.el
git commit -m "Bump Khoj to pre-release version $next_version"
;;
?)
echo -e "Invalid command option.\nUsage: $(basename $0) [-c] [-n]"
echo -e "Invalid command option.\nUsage: $(basename $0) [-t] [-c] [-n]"
exit 1
;;
esac

119
scripts/dev_setup.sh Executable file
View File

@@ -0,0 +1,119 @@
# Initialize the development environment for the project
# ---
PROJECT_ROOT=$(git rev-parse --show-toplevel)
# Install Web App
# ---
echo "Installing Web App..."
cd $PROJECT_ROOT/src/interface/web
yarn install
# Install Obsidian App
# ---
echo "Installing Obsidian App..."
cd $PROJECT_ROOT/src/interface/obsidian
yarn install
# Install Desktop App
# ---
echo "Installing Desktop App..."
cd $PROJECT_ROOT/src/interface/desktop
yarn install
# Install Server App
# ---
echo "Installing Server App..."
cd $PROJECT_ROOT
# pip install --user pipenv && pipenv install -e '.[dev]' --skip-lock && pipenv shell
python3 -m venv .venv && pip install -e '.[dev]' && . .venv/bin/activate
# Install pre-commit hooks
# ----
echo "Installing pre-commit hooks..."
# Setup pre-commit hooks using the pre-commit package
pre-commit install -t pre-push -t pre-commit
# Run Prettier on web app
cat << 'EOF' > temp_pre_commit
# Run Prettier for Web App
# -------------------------
# Function to check if color output is possible
can_use_color() {
if [ -t 1 ] && command -v tput >/dev/null 2>&1 && tput colors >/dev/null 2>&1; then
return 0
else
return 1
fi
}
# Function to print colored text if possible
print_color() {
if can_use_color; then
tput setab "$1"
printf "%s" "$2"
tput sgr0
else
printf "%s" "$2"
fi
}
print_status() {
local status="$1"
local color="$2"
printf "prettier%-64s" "..."
print_color "$color" "$status"
printf "\n"
}
PROJECT_ROOT=$(git rev-parse --show-toplevel)
# Get the list of staged files
FILES=$(git diff --cached --name-only --diff-filter=ACMR | grep '^src/interface/web/' | sed 's| |\\ |g')
if [ -z "$FILES" ]; then
if [ -t 1 ]; then
print_status "Skipped" 6
else
echo "prettier.....................................................Skipped"
fi
else
# Run prettier on staged files
echo "$FILES" | xargs $PROJECT_ROOT/src/interface/web/node_modules/.bin/prettier --ignore-unknown --write
# Check if any files were modified by prettier
MODIFIED=$(git diff --name-only -- $FILES)
if [ -n "$MODIFIED" ]; then
if [ -t 1 ]; then
print_status "Modified" 1
else
echo "prettier.....................................................Modified"
fi
exit 1
fi
# Add back the modified/prettified files to staging
# echo "$FILES" | xargs git add
# Show the user if changes were made
if [ -t 1 ]; then
print_status "Passed" 2
else
echo "prettier.....................................................Passed"
fi
fi
EOF
# Prepend the new content to the existing pre-commit file
cat temp_pre_commit "$(git rev-parse --git-dir)/hooks/pre-commit" > temp_combined_pre_commit
# Replace the old pre-commit file with the new combined one
mv temp_combined_pre_commit "$(git rev-parse --git-dir)/hooks/pre-commit"
# Clean up
# ---
# Remove the temporary pre-commit file
rm temp_pre_commit
# Make sure the pre-commit hook is executable
chmod +x "$(git rev-parse --git-dir)/hooks/pre-commit"

Some files were not shown because too many files have changed in this diff Show More