{"repo":"1yefuwang1/vectorlite","free":true,"listed":false,"github":"https://github.com/1yefuwang1/vectorlite","clone":"git clone https://github.com/1yefuwang1/vectorlite.git","description":"Fast, SQL powered, in-process vector search for any language with an SQLite driver","language":"C++","stars":362,"topics":["hnsw","sqlite3","vector-database","cpp17","python3"],"license":"Apache-2.0","category":"databases-storage","readme_excerpt":"Overview Vectorlite is a Runtime-loadable extension for SQLite that enables fast vector search based on hnswlib and works on Windows, MacOS and Linux. It provides fast vector search capabilities with a SQL interface and runs on every language with a SQLite driver. For motivation and background of this project, please check here. Below is an example of using it in sqlite CLI shell: Currently, vectorlite is pre-compiled for Windows-x64, Linux-x64, MacOS-x64, MacOS-arm64 and distributed as python wheels and npm packages. It can be installed simply by: For other languages, vectorlite.[so dll dylib] can be extracted from the wheel for your platform, given that a .whl file is actually a zip archive. Vectorlite is currently in beta. There could be breaking changes. Highlights 1. Fast ANN(approximate nearest neighbors) search backed by hnswlib. Vector query is significantly faster than similar projects like sqlite-vec and sqlite-vss. Please see benchmark below. 2. Works on Windows, Linux and MacOS(x64 and ARM). 3. A fast and portable SIMD accelerated vector distance implementation using Google's highway library. On my PC(i5-12600KF with AVX2 support), vectorlite's implementation is 1.5x-3x faster than hnswlib's when dealing vectors with dimension = 256. 4. Supports all vector distance types provided by hnswlib: l2(squared l2), cosine, ip(inner product. I do not recomend you to use it though). For more info please check hnswlib's doc. 3. Full control over HNSW parameters for performan","default_branch":null,"files":null,"tree":[],"storefront":"/r/1yefuwang1","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/1yefuwang1/vectorlite/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."}