pgvector ☆
« Back to VersTracker
Description:
Open-source vector similarity search for Postgres
Type: Formula  |  Tracked Since: Dec 28, 2025
Links: Homepage  |  formulae.brew.sh
Category: Databases
Tags: vector postgresql ai similarity-search database
Install: brew install pgvector
About:
Pgvector is an open-source extension for PostgreSQL that enables efficient storage and querying of vector embeddings for similarity search. It supports exact and approximate nearest neighbor search, allowing developers to build AI applications with vector data directly in their database. This integration simplifies architectures by eliminating the need for separate vector databases.
Key Features:
  • Support for exact and approximate nearest neighbor search (HNSW, IVFFlat)
  • Seamless integration with PostgreSQL and its ecosystem
  • ACID compliance and point-in-time recovery support
  • Language-agnostic support via standard SQL interface
Use Cases:
  • Building retrieval-augmented generation (RAG) applications
  • Implementing semantic search for documents and text
  • Creating recommendation systems for products or content
  • Image similarity search using vector embeddings
Alternatives:
  • Chroma – Standalone vector database; requires separate infrastructure vs. pgvector's direct Postgres integration
  • Weaviate – Feature-rich vector database with GraphQL API vs. pgvector's SQL-based approach
Version History
Detected Version Rev Change Commit
Sep 16, 2025 1:14pm 0 VERSION_BUMP 21c7834c
Oct 30, 2024 8:53pm 0 VERSION_BUMP e2031d36
Oct 30, 2024 1:23pm 0 VERSION_BUMP cb0ed3c0
Sep 27, 2024 8:03pm 0 VERSION_BUMP 5812265c
« Back to VersTracker  |  Browse Packages  |  About