pgvector

 pgvector is an open-source extension that adds vector storage and similarity search to PostgreSQL, created by Andrew Kane. It introduces a vector column type with distance operators, so embeddings live in the same database as relational data and join directly to it in plain SQL. Teams that already run Postgres adopt it to add semantic search without standing up separate vector infrastructure, and most managed Postgres providers support it. Keeping vectors beside relational data simplifies architecture, which has made the extension a popular first step into semantic search. Because it ships with most managed Postgres services, teams add it without changing databases.

Key Capabilities:

• Vector column type with L2, inner product, and cosine distance

• HNSW and IVFFlat indexes for approximate nearest-neighbor search

• Exact nearest-neighbor search for smaller datasets

• SQL joins between embeddings and relational data

• Half-precision and binary vectors for storage efficiency

• PostgreSQL license with broad managed-provider support