LLM/manbot
1
0
Fork 0
mirror of https://github.com/larchanka/manbot.git synced 2026-05-13 21:42:08 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
ae92de7bc80eeed7221228c2ddac58f04001bf20
manbot/_docs/TECH.md
larchanka ae92de7bc8 FP-14: Update documentation for file processing pipeline 
- COMPONENTS.md: add File Processor service description,
  add File Upload integration flow (steps 1-9)
- TECH.md: add File Processing section (nodejs-whisper, ffmpeg-static, vision)
- MESSAGE PROTOCOL SPEC.md: already updated in FP-03 commit
- README.md:
  - Add 'File Processing' to Features list
  - Add whisper.* and fileProcessor.* config keys
  - Add WHISPER_* and FILE_PROCESSOR_* env vars
  - Add 'File Processing' full section with supported types table,
    how it works, first-use notes, model pull command
  - Update Project layout with new files and services
- _board/_BOARD.md: FP-07 through FP-14 done, FP-15 remaining
- Build clean, all 156 tests pass
2026-02-21 23:59:46 +01:00

1.5 KiB
Raw Blame History

Technology Stack and Dependencies

Core Runtime

  • Node.js (>= 20)
  • TypeScript

Process Management

  • child_process (native)
  • optionally: execa

Communication

  • JSON-RPC style internal protocol
  • zod (schema validation)

LLM

  • Ollama
  • Models:
    • Small: llama3:8b
    • Medium: mistral
    • Large: deepseek-coder / mixtral

Embeddings

  • Ollama embedding models
  • RAG: SQLite-backed document store; sqlite-vss for scalable KNN vector search when available (macOS x64/arm64, Linux x64); fallback to in-DB dot-product on other platforms. Configurable rag.embeddingDimensions (default 768).

Databases

  • SQLite (better-sqlite3)
    • Task memory (with conversation_id for session grouping)
    • RAG documents (rag.dbPath)
    • Structured memory (cron, etc.)

Telegram

  • node-telegram-bot-api

Cron

  • node-cron

Logging

  • pino (structured logs)
  • file-based storage

Validation

  • zod

File Processing

  • nodejs-whisper (^0.2.9) — local Whisper speech-to-text inference; model auto-downloaded on first use
  • ffmpeg-static (^5.3.0) — bundled ffmpeg binary for audio format conversion (any → 16 kHz mono WAV)
  • OllamaAdapter.chatWithImage() — multimodal image OCR/description via configured vision model

Dev Tools

  • tsup or esbuild
  • eslint
  • prettier
  • vitest

Optional Future

  • Web dashboard (React + WebSocket)
  • Redis (distributed bus)
  • NATS
  • Docker Compose