From $16 per monthAvailable internationally
Serverless search engine on object storage for vector, full-text and hybrid search, with regions in North America, Europe and Asia Pacific.
pgvector overview and key facts (October 2026)
Open-source PostgreSQL extension that stores vectors next to your other data and searches them by similarity.
Free
What is pgvector?
pgvector adds vector similarity search to PostgreSQL. Teams that already run Postgres can store embeddings in the same tables as their business data and query them with SQL, without adding a separate vector database.
The extension supports Postgres 13 and newer, exact and approximate search with HNSW and IVFFlat indexes, several vector types and distance functions, and quantization for large datasets. Because data stays in Postgres, it keeps ACID transactions, point-in-time recovery and joins. The repository has more than 23,000 GitHub stars and was updated on September 28, 2026. It comes preinstalled with many hosted Postgres providers.
pgvector AI features and use cases
- Adds semantic search to existing appsEmbeddings live in a vector column next to product, ticket or document records. Developers add meaning-based search with an ORDER BY on distance instead of syncing data to another system.
- Stores context for RAG in PostgresA RAG pipeline retrieves the closest passages with SQL and can join them with permissions or metadata. Access rules already defined in the database apply to AI retrieval.
- Scales with quantizationHalf-precision and binary vectors reduce storage for large collections. Teams keep costs in check while staying on one database.
What sets pgvector apart
- Runs inside PostgreSQL, so transactions, backups and joins work as usual.
- HNSW and IVFFlat indexes for approximate search.
- Preinstalled with many hosted Postgres services.
Where pgvector is strongest
Available internationally
pgvector is an internationally used PostgreSQL extension without a stated country focus.
Questions to ask before you buy pgvector
Check that your Postgres version and hosting provider support the pgvector release you need. Very large vector collections can need index tuning and memory planning that a dedicated vector database handles differently. pgvector is published under the permissive PostgreSQL License; plan who maintains the extension in self-managed databases.
pgvector reviews
No reviews yet. Be the first to share how your team uses it.
Every review shows its verification level. We read each one before it goes live. How we check reviews
Questions about pgvector
Which PostgreSQL versions are supported?
The installation guide covers Postgres 13 and newer on Linux, Mac and Windows.
Do I need a separate vector database?
Not necessarily. pgvector stores and searches vectors inside Postgres, next to the rest of your data. Very large or specialized workloads may still justify a dedicated system.
Is pgvector available on hosted Postgres?
Yes. The project states that it comes preinstalled with many hosted Postgres providers and with Postgres.app.
pgvector update historyno updates yet
No changes recorded for pgvector yet.
Changes the vendor made and confirmed user reports, each checked against the vendor's own pages. We review every tool monthly.
Alternatives to pgvector
Tools in the same category (Embedding stores) with the most overlapping markets.
From $45 per month · Free plan🇳🇱
Open-source vector database from Amsterdam with hosted embedding models and a Query Agent for natural-language queries.
From $197 per month · Free plan🇺🇸
Managed vector database built on Milvus with hybrid search, a free tier, AWS, Google Cloud and Azure, plus bring-your-own-cloud.
Free🇺🇸
Open-source embedding database with a four-function API, usable locally or as managed Chroma Cloud.