pgvector
FreeOpen-source vector extension for PostgreSQL — the default choice for SQL + embeddings.
Tool Info
Categories
Vector DBs
Developer
pgvector
License
Open Source
Official Website
Repository
Overview
pgvector adds vector similarity search to PostgreSQL.
It is the most common choice when teams want SQL, joins, and embeddings in one database.
Supported by Supabase, Neon, RDS, and most Postgres hosts.
Features
- HNSW and IVFFlat indexes
- SQL joins with vectors
- Supabase and Neon support
- ACID transactions
Pricing
Free tier available
Free (open source)
Pros
- No new database
- Transactional consistency
- Massive hosting support
Best For
RAG with relational dataSmall-to-medium vector workloadsSupabase and RDS deployments
When NOT to Use
- Performance limits at very large scale
- Tuning required for millions of vectors
Typical Users
Backend engineersStartupsTeams with existing Postgres
Related Tools
Alternatives
Related Architecture Guides
Tags
#vector-db#postgres#open-source
Related Guides
- Vector Databases
Purpose-built databases for storing, indexing, and querying embedding vectors at scale.
- RAG
A comprehensive guide to RAG - the dominant pattern for building AI applications that answer questions using your own data.
- Embeddings
Discover how AI converts text, images, and data into numerical vectors that capture meaning.
Stay Updated
Get the latest AI news, tools, and engineering guides delivered to your inbox.
Subscribe to Newsletter