Your RAG app forgets small customers: I measured filtered pgvector search in 12 framework stores
Most multi-tenant RAG apps I see store every customer's chunks in one table with one HNSW index, and search like this: SELECT * FROM documents WHERE metadata ->> 'user_id' = $1 ORDER BY embedding $2 LIMIT 10 ; It looks correct, and for your biggest customer it mostly is. For a customer who uploaded…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-17 10:16 · DEV Community — AI
Your RAG app forgets small customers: I measured filtered pgvector search in 12 framework stores