{"repo":"NGT-labs/NGT","free":true,"listed":false,"github":"https://github.com/NGT-labs/NGT","clone":"git clone https://github.com/NGT-labs/NGT.git","description":"Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data","language":"C++","stars":1370,"topics":["approximate-nearest-neighbor-search","k-nearest-neighbors","knn-search","nearest-neighbors","nearest-neighbor-search","vector-database","vector-search"],"license":"Apache-2.0","category":"databases-storage","readme_excerpt":"Neighborhood Graph and Tree for Indexing High-dimensional Data Home / Installation / Command / License / Publications / About Us / 日本語 NGT provides commands and a library for performing high-speed approximate nearest neighbor searches against a large volume of data in high dimensional vector data space (several ten to several thousand dimensions). News ---- - 05/26/2025 Product quantization is now available as a data type for graph indices. (v2.4.0) - 10/29/2024 Scalar quantization is now available as a data type for graph indices and QBG. (v2.3.0) - 04/10/2024 Inner product (or dot product) is now available. (v2.1.0) - 08/10/2022 QBG (Quantized Blob Graph) and QG (renewed NGTQG) are now available. The command-line interface ngtq and ngtqg are now obsolete by replacing qbg. (v2.0.0) - 02/04/2022 FP16 (half-precision floating point) is now available. (v1.14.0) - 03/12/2021 The results for the quantized graph are added to this README. - 01/15/2021 NGT v1.13.0 to provide the quantized graph (NGTQG) is released. - 11/04/2019 NGT tutorial has been released. - 06/26/2019 Jaccard distance is available. (v1.7.6) - 06/10/2019 PyPI NGT package v1.7.5 is now available. - 01/17/2019 Python NGT can be installed via pip from PyPI. (v1.5.1) - 12/14/2018 NGTQ (NGT with Quantization) is now available. (v1.5.0) - 08/08/2018 ONNG is now available. (v1.4.0) Methods ------- This repository provides the following methods. - NGT: Graph and tree-based method - QG: Quantized graph-based method - QBG:","default_branch":null,"files":null,"tree":[],"storefront":"/r/NGT-labs","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/NGT-labs/NGT/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."}