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>

This commit is contained in:

Ryan Chen

2026-04-24 08:43:52 -04:00

parent 9ed4ca126a

commit 438399646f

19 changed files with 241 additions and 1690 deletions

									
										startup-dev.sh
									
		-3
	
												View File
												
				@@ -1,9 +1,6 @@

				#!/bin/bash

				set -e

				echo "Initializing directories..."

				mkdir -p /app/data/chromadb

				echo "Rebuilding frontend..."

				cd /app/raggr-frontend

				yarn build