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.
Перейти к файлу
MaggieQi 5bd0182dd4 Update issue templates 2018-11-08 19:58:46 +08:00
.github/ISSUE_TEMPLATE Update issue templates 2018-11-08 19:58:46 +08:00
AnnService remove Common.cpp 2018-11-08 19:25:38 +08:00
PythonWrapper track the newest update 2018-11-05 15:39:43 +08:00
Test track the newest update 2018-11-05 15:39:43 +08:00
docs/img update img 2018-10-31 15:51:36 +08:00
.gitignore track the newest update 2018-11-05 15:39:43 +08:00
AnnService.users.props track the newest update 2018-11-05 15:39:43 +08:00
CMakeLists.txt fix linux build test bug 2018-10-31 14:46:03 +08:00
README.md add azure pipeline build status 2018-11-08 19:56:23 +08:00
SPTAG.sdf add unit test 2018-10-18 20:21:57 +08:00
SPTAG.sln add unit test 2018-10-18 20:21:57 +08:00
azure-pipelines.yml remove Common.cpp 2018-11-08 19:25:38 +08:00

README.md

Space Partition Tree And Graph for Vector Search

MIT licensed Build status

SPTAG (Space Partition Tree And Graph) is a toolkit which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

architecture

Why to consider using SPTAG

  • Performance
  • New features
  1. ..
  2. ..

Install

requirements

  • swig >= 3.0
  • cmake >= 3.12.0
  • boost >= 1.67.0

compile && install

For Linux:

mkdir build
cd build && cmake .. && make

It will generate a Release folder in the code directory which contains all the build targets.

For Windows:

mkdir build
cd build && cmake -A x64 ..

It will generate a SPTAGLib.sln in the build directory, open the solution in the Visual Studio (at least 2015) and compile the ALL_BUILD project, it will generate a Release directory which contains all the build targets.

test

Run the test (or Test.exe) in the Release folder to verify all the tests have passed.

Documentation

  • Overview
  • Get started

Contribute

This project welcomes contributions and suggestions from all the users.

We use GitHub issues for tracking suggestions and bugs.

License

The entire codebase is under MIT license