mirror of
https://github.com/browseros-ai/BrowserOS.git
synced 2026-05-21 12:55:09 +00:00
1abbee638a
* implement validator eval * implement online eval foundation * further implementing online evals * enhance evaluation data logging * implement LLM scoring, remove redundant EventEnricher * cleanup * fix build errs from merging, extend LLM scorer context * settled evaluation framework * update evals documentation * fix evals screenshots * fix typos * Evals config moved to env variables and tested * test * Update manifest to 49.1 * Removed duplciate + button * Just use previous way of registering tools as that is not required for evals * Add claude commands for research, plan and implement * evals2 research and plan implementation plan new implementation plan * Evals2 implementation test test * Removed old eval hooks Remove old evals hooks * evals 2 added to env * Eval2 enhancement plan backup * Make Braintrust project configurable Make Braintrust project configurable * Enhanced scorer -- using Gemini 2.5 pro for evaluation backup v0.1 enhancement v0.2 v0.2 backup v0.3 backup v0.4 * Deleted old evals directory * Clean up old evals code * Bunch of fixes and improvements backup fixes 0.1 more fixes fixes more elaborate prompts braintrust logger fix * Renamed files backup
20 lines
442 B
Plaintext
20 lines
442 B
Plaintext
LITELLM_API_KEY=""
|
|
POSTHOG_API_KEY=""
|
|
KLAVIS_API_KEY=""
|
|
|
|
# Braintrust Telemetry Configuration
|
|
ENABLE_TELEMETRY=false
|
|
BRAINTRUST_API_KEY=""
|
|
BRAINTRUST_PROJECT_UUID=""
|
|
BRAINTRUST_PROJECT_NAME="browseros-agent-online"
|
|
|
|
# OpenAI Configuration for Scoring
|
|
OPENAI_API_KEY_FOR_SCORING=""
|
|
OPENAI_MODEL_FOR_SCORING="gpt-4o"
|
|
|
|
# Simplified Evals2 System
|
|
ENABLE_EVALS2=false
|
|
|
|
# Gemini API keys for evals2 scoring
|
|
GOOGLE_GENAI_API_KEY=""
|
|
GEMINI_API_KEY="" |