pgvector
PostgreSQL users can add vector similarity search with pgvector, an open-source extension.
About pgvector
pgvector is an open-source extension for PostgreSQL that adds vector similarity search. It stores vectors in ordinary Postgres tables next to other data and finds nearest neighbors using several distance measures. By default it runs exact nearest neighbor search. Approximate search is available through an index, which trades some recall for speed. The extension supports Postgres 13 and later. It is installed by compiling it from source on Linux, Mac, or Windows, or through packages or images such as Docker, Homebrew, APT, or conda-forge. The source does not state pricing.
Key features
- Exact and approximate nearest neighbor search
- Single-precision, half-precision, binary, and sparse vector types
- Distance functions: L2, inner product, cosine, L1, Hamming, and Jaccard
- Vectors stored in regular Postgres tables and queried with JOINs
- Quantization for scaling to large numbers of vectors
- Bulk loading with COPY, plus upsert, update, and delete statements
Best for: Developers and teams that already run PostgreSQL and want to add vector similarity search to their existing data.
Good for
- Vectors are stored with the rest of the database data in Postgres.
- Inherits Postgres features such as ACID compliance and point-in-time recovery, as the source states.
- Works from any language that has a Postgres client.
Watch out for
- Requires Postgres 13 or later.
- Approximate nearest neighbor indexes trade some recall for speed.
- On Windows, the build requires Visual Studio C++ support and an administrator command prompt.
pgvector at a glance
- Website
- github.com/pgvector/pgvector
- Category
- Development › APIs & Databases
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Guides for APIs & Databases
pgvector alternatives
Tools and sites you could use instead, ranked by how closely they match.
PostgreSQL vector search can use pgvecto.rs, an extension described as scalable and low latency.
Open source
24 alternatives
ParadeDB adds full text search, vector retrieval, and aggregations to PostgreSQL.
Open source
24 alternatives
Vector similarity search is provided by Qdrant, an open-source search engine written in Rust.
Popular in APIs & Databases
Well-known listings from the same topic.
API3api3.orgTwiliotwilio.comDB Browsersqlitebrowser.orgPocketBasepocketbase.ioBrunousebruno.comMeilisearchmeilisearch.com
pgvector FAQ
Which Postgres versions are supported?
The installation instructions state that the extension supports Postgres 13 and later.
Does pgvector use exact or approximate search by default?
By default it performs exact nearest neighbor search, which provides perfect recall. An index can be added to use approximate nearest neighbor search instead.
How is the extension enabled?
Run CREATE EXTENSION vector once in each database where it will be used.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.