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

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text

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

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

Fast and lightweight header-only C++ library (with Python bindings) for approximate nearest neighbor search

Fast and memory-efficient ANN with a subset-search functionality

Node.js bindings for faiss

hnswlib-node provides Node.js bindings for Hnswlib

SONG: Approximate Nearest Neighbor Search on GPU. SONG is a graph-based approximate nearest neighbor search toolbox.

Approximate Nearest Neighbor search using reduced-rank regression, with extremely fast queries, tiny memory usage, and rapid indexing on modern vector embeddings.

Rcpp bindings for the approximate nearest neighbors library hnswlib

annoy-rb provides Ruby bindings for the Annoy (Approximate Nearest Neighbors Oh Yeah).

Performance comparison of the MRPT algorithm to other approximate nearest neighbor search libraries

C++/Python implementation of Nearest Neighbor Descent for efficient approximate nearest neighbor search

An Effective and Scalable Framework for Multimodal Search of Target Modality

hnswlib.rb provides Ruby bindings for Hnswlib

🏆 The winner code for ACM SIGMOD 2023 Programming Contest, can build highly accurate KNN graphs efficiently

R package implementing the Nearest Neighbor Descent method for approximate nearest neighbors

Two-stage routing with Optimized Guided search and Greedy algorithm