
Starred repositories
Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.
Up to 200x Faster Dot Products & Similarity Metrics — for Python, Rust, C, JS, and Swift, supporting f64, f32, f16 real & complex, i8, and bit vectors using SIMD for both AVX2, AVX-512, NEON, SVE, …
DuckDB is an analytical in-process SQL database management system
A vector search SQLite extension that runs anywhere!
A complement to pgvector for high performance, cost efficient vector search on large workloads.
Simple vector quantization utilities and functions.
🧰 The Rust SQL Toolkit. An async, pure Rust SQL crate featuring compile-time checked queries without a DSL. Supports PostgreSQL, MySQL, and SQLite.
DocumentDB is the open-source engine powering vCore-based Azure Cosmos DB for MongoDB. It offers a native implementation of document-oriented NoSQL database, enabling seamless CRUD operations on BS…
Implementation of the paper "Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search" by Severo et al.
gpu powered brute force knn ground truth dataset generator
Efficient Retrieval Augmentation and Generation Framework
Vector Search Scenarios with CosmosDB.
Garnet is a remote cache-store from Microsoft Research that offers strong performance (throughput and latency), scalability, storage, recovery, cluster sharding, key migration, and replication feat…
This repository is for the active development of the Azure SDK for Rust. For consumers of the SDK we recommend visiting Docs.rs and looking up the docs for any of libraries in the SDK.
An open-source C++ library developed and used at Facebook.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.
Pipeline for ingesting documents (like pdfs and docx) into a searchable Azure Cosmos DB container for vector and hybrid searching.
A Rust library to help interacting with cache directories and CACHEDIR.TAG files as defined in Cache Directory Tagging Specification (https://bford.info/cachedir/).
.NET SDK for Azure Cosmos DB for the core SQL API
This repository is for active development of the Azure SDK for .NET. For consumers of the SDK we recommend visiting our public developer docs at https://learn.microsoft.com/dotnet/azure/ or our ver…
cuVS - a library for vector search and clustering on the GPU
mimalloc is a compact general purpose allocator with excellent performance.