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>

.env.example

@@ -19,11 +19,6 @@ BASE_URL=192.168.1.5:8000
 LLAMA_SERVER_URL=http://192.168.1.213:8080/v1
 LLAMA_MODEL_NAME=llama-3.1-8b-instruct
 
-# ChromaDB Configuration
-# For Docker: This is automatically set to /app/data/chromadb
-# For local development: Set to a local directory path
-CHROMADB_PATH=./data/chromadb
-
 # OpenAI Configuration
 OPENAI_API_KEY=your-openai-api-key