Replace ChromaDB with pgvector for vector storage

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>

Dockerfile

@@ -37,15 +37,14 @@ WORKDIR /app/raggr-frontend
 RUN yarn install && yarn build
 WORKDIR /app
 
-# Create ChromaDB and database directories
-RUN mkdir -p /app/chromadb /app/database
+# Create database directory
+RUN mkdir -p /app/database
 
 # Expose port
 EXPOSE 8080
 
 # Set environment variables
 ENV PYTHONPATH=/app
-ENV CHROMADB_PATH=/app/chromadb
 
 # Run the startup script
 CMD ["./startup.sh"]