VSAG is a vector indexing library used for similarity search. The indexing algorithm allows users to search through various sizes of vector sets, especially those that cannot fit in memory. The library also provides methods for generating parameters based on vector dimensions and data scale, allowing developers to use it without understanding the algorithm’s principles. VSAG is written in C++ and provides a Python wrapper package called pyvsag.

The VSAG algorithm achieves a significant boost of efficiency and outperforms the previous state-of-the-art (SOTA) by a clear margin. Specifically, VSAG's QPS exceeds that of the previous SOTA algorithm, Glass, by over 100%, and the baseline algorithm, HNSWLIB, by over 300% according to the ann-benchmark result on the GIST dataset at 90% recall. The test in ann-benchmarks is running on an r6i.16xlarge machine on AWS with --parallelism 31, single-CPU, and hyperthreading disabled. The result is as follows:

# CMakeLists.txt
cmake_minimum_required(VERSION 3.11)

project (myproject)

set (CMAKE_CXX_STANDARD 11)

# download and compile vsag
include (FetchContent)
FetchContent_Declare (
  vsag
  GIT_REPOSITORY https://github.com/antgroup/vsag
  GIT_TAG main
)
FetchContent_MakeAvailable (vsag)
include_directories (vsag-cmake-example PRIVATE ${vsag_SOURCE_DIR}/include)

# compile executable and link to vsag
add_executable (vsag-cmake-example src/main.cpp)
target_link_libraries (vsag-cmake-example PRIVATE vsag)

# add dependency
add_dependencies (vsag-cmake-example vsag)

Currently Python and C++ examples are provided, please explore examples directory for details.

We suggest you start with 101_index_hnsw.cpp and example_hnsw.py.

Please read the DEVELOPMENT guide for instructions on how to build.

• OceanBase
• TuGraph
• GreptimeDB

If your system uses VSAG, then feel free to make a pull request to add it to the list.

Although VSAG is initially developed by the Vector Database Team at Ant Group, it's the work of the community, and contributions are always welcome! See CONTRIBUTING for ways to get started.

Thrive together in VSAG community with users and developers from all around the world.

• Discuss at discord.
• Follow us on Weixin Official Accounts（微信公众平台）to get the latest news.

• v0.15 (ETA: Apr. 2025)
  • support sparse vector searching
  • introduce pluggable product quantization(known as PQ) in datacell
• v0.16 (ETA: May 2025)
  • support neon instruction acceleration on ARM platform
  • support using GPU to accelerate index building
  • provide an optimizer that supports optimizing search parameters by recall or latency
• v0.17 (ETA: Jun. 2025)
  • support amx instruction acceleration on Intel CPU
  • support attributes stored in vector index
  • support graph structure compression

1. VSAG: An Optimized Search Framework for Graph-based Approximate Nearest Neighbor Search [VLDB (industry), 2025]
   Xiaoyao Zhong, Haotian Li, Jiabao Jin, Mingyu Yang, Deming Chu, Xiangyu Wang, Zhitao Shen, Wei Jia, George Gu, Yi Xie, Xuemin Lin, Heng Tao Shen, Jingkuan Song, Peng Cheng
   PDF | DOI

2. Effective and General Distance Computation for Approximate Nearest Neighbor Search [ICDE, 2025]
   Mingyu Yang, Wentao Li, Jiabao Jin, Xiaoyao Zhong, Xiangyu Wang, Zhitao Shen, Wei Jia, Wei Wang
   PDF | DOI

3. SINDI: an Efficient Index for Approximate Maximum Inner Product Search on Sparse Vectors [arxiv, 2025]
   Ruoxuan Li, Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Wangze Ni, Lei Chen, Zhitao Shen, Wei Jia, Xiangyu Wang, Xuemin Lin, Heng Tao Shen, Jingkuan Song
   PDF

4. EnhanceGraph: A Continuously Enhanced Graph-based Index for High-dimensional Approximate Nearest Neighbor Search [arxiv, 2025]
   Xiaoyao Zhong, Jiabao Jin, Peng Cheng, Mingyu Yang, Lei Chen, Haoyang Li, Zhitao Shen, Xuemin Lin, Heng Tao Shen, Jingkuan Song
   PDF

5. Fast High-dimensional Approximate Nearest Neighbor Search with Efficient Index Time and Space [arxiv, 2025]
   Mingyu Yang, Wentao Li, Wei Wang
   PDF

VSAG referenced the following works during its implementation:

1. RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search [SIGMOD, 2024]
   Jianyang Gao, Cheng Long
   PDF | DOI | CODE

2. Quasi-succinct Indices [WSDM, 2013]
   Sebastiano Vigna
   PDF | DOI

Apache License 2.0