• Home
  • Categories
  • Tags
  • Pricing
  • Submit
  1. Home
  2. Sdks & Libraries
  3. PGVector

PGVector

PostgreSQL supports vector indexing and similarity search via the PGVector extension, allowing relational databases to manage and retrieve vector embeddings efficiently.

🌐Visit Website

About this tool

PGVector

PGVector is an open-source PostgreSQL extension that enables efficient storage, indexing, and similarity search for vector embeddings directly within a Postgres database. It supports both exact and approximate nearest neighbor search, and a variety of vector types and distance metrics.

Features

  • Vector Storage: Store vectors alongside other data in Postgres tables.
    • Supports single-precision, half-precision (halfvec), binary (bit), and sparse (sparsevec) vectors.
    • Can store vectors with up to 16,000 dimensions (vector), 4,000 (halfvec), 64,000 (bit), or 1,000 non-zero elements (sparsevec).
  • Similarity Search:
    • Exact and approximate nearest neighbor search.
    • Multiple distance metrics: L2 (Euclidean), inner product, cosine, L1 (taxicab), Hamming (for binary), and Jaccard (for binary).
  • Indexing:
    • Exact search by default.
    • Approximate search via HNSW and IVFFlat indexes for faster queries at the cost of some recall.
    • Index tuning options for memory, parallelism, and recall/speed tradeoffs.
    • Support for filtering and iterative index scans to improve recall when filtering.
  • Querying:
    • Retrieve nearest neighbors to a vector or another row.
    • Query by distance threshold.
    • Aggregate functions: average, sum of vectors.
    • Subvector indexing and querying.
  • Hybrid Search:
    • Combine with Postgres full-text search for hybrid queries.
  • Language Support:
    • Usable from any language with a Postgres client.
    • Libraries/examples available for C, C++, C#, Go, Java, JavaScript/TypeScript, Python, Ruby, Rust, and more.
  • Postgres Integration:
    • ACID compliance, point-in-time recovery, JOINs, and all standard Postgres features.
    • Supports replication through WAL.
    • Scalable with standard Postgres scaling techniques (vertical and horizontal).
  • Performance and Tuning:
    • Bulk loading with COPY.
    • Index build and query performance tuning.
    • Monitoring with pg_stat_statements.
    • Options for concurrent index creation, parallelism, and memory usage.
  • Installation:
    • Available via compiling from source, Docker, Homebrew, PGXN, APT, Yum, pkg, conda-forge, and preinstalled on some hosted Postgres providers.
    • Works on Linux, macOS, and Windows.
  • Data Flexibility:
    • Store vectors with different dimensions using untyped columns (with some limitations on indexing).
    • Support for higher-precision vectors using Postgres array types.
  • Functions and Operators:
    • Rich set of operators for vector arithmetic and similarity.
    • Functions for distance calculation, normalization, quantization, and more.
  • Open Source:
    • Licensed under an open-source license, available for community contributions.

Pricing

PGVector is open-source and free to use.

Links

  • Source code and documentation
Surveys

Loading more......

Information

Websitegithub.com
PublishedMay 13, 2025

Categories

1 Item
Sdks & Libraries

Tags

4 Items
#open-source
#vector search
#PostgreSQL
#similarity search

Similar Products

6 result(s)
RediSearch

RediSearch is a Redis module that provides high-performance vector search and similarity search capabilities on top of Redis, enabling advanced search and retrieval features for AI and data applications.

arroy

Arroy is an open-source library for efficient similarity search and management of vector embeddings, useful in vector database systems.

KGraph

KGraph is an open-source library for fast approximate nearest neighbor search in high-dimensional vector spaces, applicable to vector database solutions.

puck

Puck is an open-source vector search engine designed for fast similarity search and retrieval of embedding vectors.

Qdrant

Qdrant is a dedicated vector database and similarity search engine supporting advanced filtering and efficient retrieval, suitable for faceted search and retrieval-augmented generation. It offers self-hosted and cloud deployment options, making it highly relevant for vector search applications.

Supabase Vector

Supabase Vector extends the Supabase platform by providing vector database functionalities, making it easy to add vector search capabilities to applications with PostgreSQL backend.

Built with
Ever Works
Ever Works

Connect with us

Stay Updated

Get the latest updates and exclusive content delivered to your inbox.

Product

  • Categories
  • Tags
  • Pricing
  • Help

Clients

  • Sign In
  • Register
  • Forgot password?

Company

  • About Us
  • Admin
  • Sitemap

Resources

  • Blog
  • Submit
  • API Documentation
All product names, logos, and brands are the property of their respective owners. All company, product, and service names used in this repository, related repositories, and associated websites are for identification purposes only. The use of these names, logos, and brands does not imply endorsement, affiliation, or sponsorship. This directory may include content generated by artificial intelligence.
Copyright © 2025 Acme. All rights reserved.·Terms of Service·Privacy Policy·Cookies