transcription/.env.example
keboss-m eee8f4c8a4 Replace LightRAG with native Python RAG engine + add deploy tooling
- New: src/rag/engine/ — in-process hybrid search (FTS5 BM25 + sqlite-vec + LLM rerank)
- New: src/rag/qmd/ — compatibility layer (qmd_query, qmd_chat, qmd_chat_stream, qmd_index_*)
- New: src/ingest/stub_writer.py — .md stubs for binary files (videos, archives)
- New: scripts/deploy.sh + scripts/pull_models.sh + Makefile + .env.example
- Removed: LightRAG, sentence-transformers embedding via separate package, rag_standalone/
- Removed: @nousresearch/qmd npm dep (package not published); Node.js from Dockerfile
- Updated: tests/ (46 passed), docker-compose, .dockerignore, config.yaml, README

Engine: in-process Python (no daemon, no npm), sentence-transformers 384-dim,
RRF fusion (k=60), BM25 + vector with numpy fallback. WebSocket API unchanged.

Deploy: 'git clone' + 'make init' + 'make pull-models MODELS_SOURCE=...' + 'make up'.
Models (5.83 GB) live outside git; pulled via rsync from dev host.
2026-06-10 14:24:01 +03:00

19 lines
823 B
Plaintext

# WhisperX + Native Python RAG transcription service
# Скопируйте в .env: `cp .env.example .env` (или `make init`)
# HuggingFace (для pyannote-диаризации)
# Регистрация: https://huggingface.co/settings/tokens
HF_TOKEN=hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
# OpenCode / DeepSeek API (LLM для классификации и чат-ответов)
OPENCODE_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxx
OPENCODE_URL=https://opencode.ai/zen/v1
# JWT-секрет для аутентификации
# Сгенерируйте: openssl rand -hex 32
JWT_SECRET=change-me-in-production-32-bytes-random-hex
# Пароль админа по умолчанию (при первом бутстрапе)
# Смените сразу после первого входа!
AUTH_ADMIN_PASSWORD=admin123