Run This Ai
EN DE

pgvector

Open-source vector similarity search for PostgreSQL

★ 21,963 GitHub PostgreSQL vector-databasepostgresqlpgvectorembeddingssimilarity-searchrag RAG & Knowledge

Overview

pgvector is an open-source vector similarity search extension for PostgreSQL. It enables you to store and query high-dimensional vectors alongside your relational data, supporting exact and approximate nearest neighbor search (ANN) with IVFFlat and HNSW indexes. Features include distance functions (L2, cosine, inner product, Hamming, Jaccard) plus halfvec, bit, and sparsevec types. With over 22,000 GitHub stars, it is the most popular PostgreSQL vector extension — a drop-in addition to any Postgres database.

Requirements

Min vCPU
1
Min RAM
256 MB
Min Disk
10 GB
Rec vCPU
2
Rec RAM
1024 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 2

2 vCPU · 8192 MB · 100 GB

$6.99
View plan

Hostinger · KVM 2

2 vCPU · 8192 MB · 100 GB

$6.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  pgvector:
    image: pgvector/pgvector:pg16
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/pgvector:/data

Best VPS for pgvector →

Related tools

Guides & articles