ModelRefs / pgvector — AI Glossary
pgvector — AI Glossary
A PostgreSQL extension adding vector similarity search, enabling RAG applications without a separate vector database.
Overview
pgvector (open source, 2021) adds a vector column type and IVFFlat/HNSW indexes to PostgreSQL. Supports exact and approximate nearest-neighbor search using L2, inner product, and cosine distances. Ideal for teams already on Postgres seeking minimal infrastructure overhead. Used by Supabase, Neon, and AWS RDS for vector workloads.
Reference details
| Topic | rag |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to pgvector — AI Glossary.
Frequently asked questions
What is pgvector?
A PostgreSQL extension adding vector similarity search, enabling RAG applications without a separate vector database.
What concepts are related to pgvector?
Closely related concepts include faiss, ann, dense retrieval.