pgvector
PostgreSQL extension for storing embeddings and running vector similarity search — the vector store behind RAG on Postgres and Supabase.
pgvector is an open-source PostgreSQL extension that adds a vector column type and nearest-neighbour search (exact and approximate indexes). It lets a team keep embeddings next to relational data instead of running a separate vector database — and it is available out of the box on Supabase.
How I use it
pgvector is part of my RAG (Retrieval-Augmented Generation) toolkit and of the stack in my current role at Somnio Software, alongside Python, TypeScript and Supabase. My public RAG work uses other stores — Chroma in local-rag-chatbot and an in-memory store in Akashi.