pgvector
Open-source PostgreSQL extension for vector similarity search alongside relational data
pgvector is a PostgreSQL extension that adds vector similarity search directly within Postgres. Store, index, and query high-dimensional embeddings alongside your relational data with full ACID compliance. Supports L2, cosine, inner product, L1, Hamming, and Jaccard distances with IVFFlat and HNSW indexing. Handles single-precision, half-precision, binary, and sparse vectors. Works with standard Postgres features like JOINs. Available via Docker, Homebrew, PGXN, and preinstalled on Supabase, Neon, and other hosted providers.
Pricing: Free
Choosing a vector database right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing a vector database right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
pgvector Alternatives
Explore 26 products in the Vector databases category. View all pgvector alternatives.
FAISS
Meta's open-source library for efficient similarity search and dense vector clustering
Supabase Vector
Open-source Postgres vector database and AI toolkit built on pgvector
Turbopuffer
Serverless vector and full-text search engine built on object storage for cost-efficient scale
Elasticsearch
Distributed full-text search and analytics engine with built-in vector and hybrid search
Redis
In-memory vector database for low-latency similarity search across AI applications
TopK
AI-native search engine combining vector, keyword, and faceted search
Work on pgvector? Feature it at the top of Vector databases.
Is your product missing?