{"repo":"AlayaDB-AI/AlayaLite","free":true,"listed":false,"github":"https://github.com/AlayaDB-AI/AlayaLite","clone":"git clone https://github.com/AlayaDB-AI/AlayaLite.git","description":"AlayaLite – A Fast, Flexible Vector Database for Everyone.","language":"C++","stars":207,"topics":["alaya","ann","hnsw","lightweight","python","python-sdk","user-friendly","vector-database","alaya-lite","alaya-sdk"],"license":"AGPL-3.0","category":"databases-storage","readme_excerpt":"AlayaLite – A Fast, Flexible Vector Database for Everyone . Seamless Knowledge, Smarter Outcomes. Features - High Performance : Modern vector techniques integrated into a well-designed architecture. - Elastic Scalability : Seamlessly scale across multiple threads, which is optimized by C++20 coroutines. - Adaptive Flexibility : Easy customization for quantization methods, metrics, and data types. - Two index paths in one package : an in-memory graph + RaBitQ path for low-latency retrieval, and the LASER on-disk Quantized Graph index for billion-scale workloads that do not fit in RAM. - Ease of Use : Intuitive APIs in Python. Documentation - Client User Guide - LASER Guide Quick Start Get started with just one command! In-memory index: quick start Hybrid search in Collection: quick start Use Collection when you want ANN results together with document IDs, documents, and metadata filters. LASER on-disk index: quick start For datasets that exceed RAM, the LASER on-disk Quantized Graph index keeps hot data on SSD and only the search-time working set in memory. Vectors must be float32 with raw dim = 128 ; L2 is the only supported metric in v1. LASER is available on Linux x86 64 (libaio backend, default), macOS (thread-pool backend), and Windows x64 (IOCP backend). Platform notes: - Linux x86 64 builds need libaio headers, for example sudo apt-get install libaio-dev on Debian/Ubuntu. - macOS builds need OpenMP from Homebrew: brew install libomp . - Windows x64 builds should run fro","default_branch":null,"files":null,"tree":[],"storefront":"/r/AlayaDB-AI","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/AlayaDB-AI/AlayaLite/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}