pgvector logo

pgvector

pgvector/pgvector

Open-source vector similarity search for Postgres

GraphCanon updated 3w · GitHub synced 3w · 35 views this month

22k stars1.3k forksLast push 3w C Other

Decision brief

pgvector extends PostgreSQL with efficient vector similarity searches.

Good fit when

  • When you need to perform approximate nearest neighbor or exact nearest neighbor searches on your vectors and prefer to keep the data within a PostgreSQL database.
  • For projects requiring customization or integration with Postgres-specific features such as stored procedures, triggers, and complex SQL queries.

Avoid when

  • When the requirement is to have a standalone in-memory or distributed vector database system as pgvector remains strictly integrated with PostgreSQL.
  • For scenarios where high availability and clustering capabilities without manual intervention (beyond what standard PostgreSQL offers) are necessary.

Observed Jul 11, 2026 · Source: enrich:decision_facts

Verify the decision

Adoption

Package downloads where a registry match exists. GitHub stars (22,375) are secondary evidence.

Docker Hub pulls (30d)
130,121,796·Docker Hub API·3w

Maintenance and security

Full trust report
Maintenance
Very active (0d since push)
As of 3w
Provenance
Not a fork · Organization account
As of 3w
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/pgvector/pgvector

How it fits your stack(27)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Alternative

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

pgvector extends PostgreSQL to enable efficient vector similarity searches.

Capability facts

Deploy
Self-host

Source: dockerfile:Dockerfile · Jul 28, 2026

Docker
Dockerfile present

Source: dockerfile:Dockerfile · Jul 28, 2026

Languages
c

Source: github.language · Jul 28, 2026

Categories

Graph entities

Tags

README

Getting Started

Enable the extension (do this once in each database where you want to use it)

CREATE EXTENSION vector;

Create a vector column with 3 dimensions

CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3));

Insert vectors

INSERT INTO items (embedding) VALUES ('[1,2,3]'), ('[4,5,6]');

Get the nearest neighbors by L2 distance

SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5;

Also supports inner product (<#>), cosine distance (<=>), and L1 distance (<+>)

Note: <#> returns the negative inner product since Postgres only supports ASC order index scans on operators


Docker

Get the Docker image with:

docker pull pgvector/pgvector:pg18-trixie

This adds pgvector to the Postgres image (replace 18 with your Postgres server version, and run it the same way).

Supported tags are:

  • pg18-trixie, 0.8.5-pg18-trixie
  • pg18-bookworm, 0.8.5-pg18-bookworm, pg18, 0.8.5-pg18
  • pg17-trixie, 0.8.5-pg17-trixie
  • pg17-bookworm, 0.8.5-pg17-bookworm, pg17, 0.8.5-pg17
  • pg16-trixie, 0.8.5-pg16-trixie
  • pg16-bookworm, 0.8.5-pg16-bookworm, pg16, 0.8.5-pg16
  • pg15-trixie, 0.8.5-pg15-trixie
  • pg15-bookworm, 0.8.5-pg15-bookworm, pg15, 0.8.5-pg15
  • pg14-trixie, 0.8.5-pg14-trixie
  • pg14-bookworm, 0.8.5-pg14-bookworm, pg14, 0.8.5-pg14
  • pg13-trixie, 0.8.5-pg13-trixie
  • pg13-bookworm, 0.8.5-pg13-bookworm, pg13, 0.8.5-pg13

You can also build the image manually:

git clone --branch v0.8.5 https://github.com/pgvector/pgvector.git
cd pgvector
docker build --pull --build-arg PG_MAJOR=18 -t myuser/pgvector .

If you increase maintenance_work_mem, make sure --shm-size is at least that size to avoid an error with parallel HNSW index builds.

docker run --shm-size=1g ...

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.