Skip to content

Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.

License

Notifications You must be signed in to change notification settings

weiliu1031/knowhere

This branch is 293 commits behind zilliztech/knowhere:main.

Folders and files

NameName
Last commit message
Last commit date
Apr 10, 2024
Apr 19, 2024
May 21, 2024
May 15, 2024
May 10, 2024
May 8, 2024
Mar 5, 2024
May 15, 2024
Jan 18, 2023
May 10, 2024
May 21, 2024
Jan 6, 2022
Jan 18, 2023
Mar 15, 2024
Dec 8, 2023
Mar 24, 2023
Apr 28, 2024
Dec 28, 2021
Oct 17, 2023
Feb 29, 2024
May 23, 2023
Apr 7, 2024

Repository files navigation

Knowhere Logo

This document will help you to build the Knowhere repository from source code and to run unit tests. Please file an issue if there's a problem.

Introduction

Knowhere is written in C++. It is an independent project that act as Milvus's internal core.

Building Knowhere Within Milvus

If you wish to only use Knowhere within Milvus without changing any of the Knowhere source code, we suggest that you move to the Milvus main project and build Milvus directly, where Knowhere is then built implicitly during Milvus build.

System Requirements

All Linux distributions are available for Knowhere development. However, a majority of our contributor worked with Ubuntu or CentOS systems, with a small portion of Mac (both x86_64 and Apple Silicon) contributors. If you would like Knowhere to build and run on other distributions, you are more than welcome to file an issue and contribute!

Here's a list of verified OS types where Knowhere can successfully build and run:

  • Ubuntu 20.04 x86_64
  • Ubuntu 20.04 Aarch64
  • MacOS (x86_64)
  • MacOS (Apple Silicon)

Building Knowhere From Source Code

Install Dependencies

$ sudo apt install build-essential libopenblas-dev libaio-dev python3-dev python3-pip
$ pip3 install conan==1.61.0 --user
$ export PATH=$PATH:$HOME/.local/bin

Build From Source Code

  • Ubuntu 20.04
$ mkdir build && cd build
#add conan remote
$ conan remote add default-conan-local https://milvus01.jfrog.io/artifactory/api/conan/default-conan-local
#DEBUG CPU
$ conan install .. --build=missing -o with_ut=True -s compiler.libcxx=libstdc++11 -s build_type=Debug
#RELEASE CPU
$ conan install .. --build=missing -o with_ut=True -s compiler.libcxx=libstdc++11 -s build_type=Release
#DEBUG GPU
$ conan install .. --build=missing -o with_ut=True -o with_raft=True -s compiler.libcxx=libstdc++11 -s build_type=Debug
#RELEASE GPU
$ conan install .. --build=missing -o with_ut=True -o with_raft=True -s compiler.libcxx=libstdc++11 -s build_type=Release
#DISKANN SUPPORT
$ conan install .. --build=missing -o with_ut=True -o with_diskann=True -s compiler.libcxx=libstdc++11 -s build_type=Debug/Release
#build with conan
$ conan build ..
#verbose
export VERBOSE=1
  • MacOS
#RELEASE CPU
conan install .. --build=missing -o with_ut=True -s compiler.libcxx=libc++ -s build_type=Release
#DEBUG CPU
conan install .. --build=missing -o with_ut=True -s compiler.libcxx=libc++ -s build_type=Debug

Running Unit Tests

# in build directories
#Debug
$ ./Debug/tests/ut/knowhere_tests
#Release
$ ./Release/tests/ut/knowhere_tests

Clean up

$ git clean -fxd

GEN PYTHON WHEEL(NEED REALSE BUILD)

install dependency:

sudo apt install swig python3-dev
pip3 install bfloat16

after build knowhere:

cd python
python3 setup.py bdist_wheel

install knowhere wheel:

pip3 install dist/pyknowhere-0.0.0-cp38-cp38-linux_x86_64.whl

clean

cd python
rm -rf build
rm -rf dist
rm -rf knowhere.egg-info
rm knowhere/knowhere_wrap.cpp
rm knowhere/swigknowhere.py

Contributing

Pre-Commit

Before submitting a pull request, please make sure running pre-commit checks locally to ensure the code is ready for review. Use the following command to install pre-commit checks:

pip3 install pre-commit
pre-commit install --hook-type pre-commit --hook-type pre-push

# If clang-format and clang-tidy not already installed:
# linux
apt install clang-format clang-tidy
# mac
brew install llvm
ln -s "$(brew --prefix llvm)/bin/clang-format" "/usr/local/bin/clang-format"
ln -s "$(brew --prefix llvm)/bin/clang-tidy" "/usr/local/bin/clang-tidy"

About

Knowhere is an open-source vector search engine, integrating FAISS, HNSW, etc.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 74.9%
  • C 8.2%
  • Cuda 5.4%
  • Python 3.0%
  • CMake 2.9%
  • SWIG 1.5%
  • Other 4.1%