Approximate Nearest Neighbor Search Python Packages

lancedb

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

pynndescent

A Python nearest neighbor descent for approximate nearest neighbors

annoy

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

usearch

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

usearch-iscc

Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

tiledb-vector-search

Cloud-native vector similarity search and storage with efficient, serverless scale-out

libpecos

PECOS - Prediction for Enormous and Correlated Spaces

annoy-mm

Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

pgml

Postgres with GPUs for ML/AI apps.

annlite

⚡ A fast embedded library for approximate nearest neighbor search

pymuvera

Python library for MUVERA multi-vector retrieval via Fixed Dimensional Encodings. ColBERT / ColQwen2 / ColQwen3.5 compatible.

ngt

Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

lotf

[CVPR25] LotusFilter: Fast Diverse Nearest Neighbor Search

nanopq

Pure python implementation of product quantization for nearest neighbor search

nilvec

A lightweight library for nearest neighbor search in Rust.

lynsedb

A pure Python-implemented, lightweight, server-optional, multi-end compatible, vector database deployable locally or remotely.

citrusdb

open-source vector database. store and retrieve embeddings for your next ai project!

hannoy

Production-ready KV-backed HNSW implementation in Rust using LMDB

instant-distance

Fast approximate nearest neighbor searching in Rust, based on HNSW index

superkmeans

⚡ Super fast clustering for high-dimensional vectors on CPUs (x86, ARM) and GPUs — for Python and C++. 100x faster clustering of vector embeddings than FAISS

mlots

mlots is python package that provides Machine Learning tools for Time-Series Classification.

sklearn-ann

Integration with (approximate) nearest neighbors libraries for scikit-learn + clustering based on with kNN-graphs.

semantic-ai

Sematic AI RAG System

zeusdb

High-performance database management system