Consolidate onto PostgreSQL by using pgvector instead of a separate
ChromaDB instance. This removes a Docker volume, a large dependency,
and simplifies the stack without meaningful performance impact at
our document scale.
- Swap langchain-chroma for langchain-postgres (PGVector)
- Use pgvector/pgvector:pg16 Docker image with init script
- Lazy-initialize vector store to avoid eager DB connections
- Add SQL helpers for stats/delete/list (replacing _collection access)
- Remove legacy main.py, chunker, petmd scraper, and /api/query endpoint
Re-index required after deploy (POST /api/rag/index + /index-obsidian).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Switch to host network mode for direct access to Ollama on host
- Update OLLAMA_URL to use localhost:11434
- Add startup.sh script to trigger reindex before app starts
- Update Dockerfile to execute startup script
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Move Python application code copy before frontend build step to improve
Dockerfile organization and ensure all app code is available earlier.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Install uv via official installer script
- Replace pip with uv pip install --system
- Add uv to PATH for container usage
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Ryan Chen