pgvector
Vector similarity search inside PostgreSQL
- Open source
- Vector Databases
What it is
pgvector is a PostgreSQL extension adding vector column types and distance operators, with HNSW and IVFFlat index types for approximate nearest-neighbour search. Because vectors live in ordinary tables, similarity conditions compose with joins, transactions, row-level security and your existing backup story. An existing Postgres instance becomes a usable vector store without new infrastructure.
Best for
Applications already on PostgreSQL that want retrieval without adding another datastore to operate and keep in sync.
Where it falls short
Large indexes compete with your transactional workload for memory and CPU, which is the point at which a dedicated vector service starts to pay off.
Characteristics
- postgresql
- extension
- hnsw
- sql-joins
This page carries no score, star rating or review count, and nothing about its placement in the directory was paid for. The outbound links above go to the product’s own domain with no referral parameters. Read the directory methodology for what that means in practice.
More in Vector Databases
Other tools solving the same problem, so you can see what pgvector is actually competing with.
Pinecone
FreemiumManaged vector database
Qdrant
Open sourceVector search engine with first-class filtering
Weaviate
Open sourceOpen-source vector database with hybrid search