- 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.
17 lines
602 B
YAML
17 lines
602 B
YAML
# Production overrides for Linux server deployment (bind-mount data dirs)
|
|
services:
|
|
transcription:
|
|
volumes:
|
|
- ./uploads:/app/uploads
|
|
- ./processed:/app/processed
|
|
- ./tmp:/app/tmp
|
|
- ./config.yaml:/app/config.yaml:ro
|
|
- ./backend:/app/backend:ro
|
|
- ./src:/app/src:ro
|
|
- ./scripts:/app/scripts:ro
|
|
- ./models/huggingface:/root/.cache/huggingface
|
|
- ./models/nltk_data:/root/nltk_data:ro
|
|
- ./data:/app/data
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/api/health')"]
|