SPTAG
SPTAG is a distributed approximate nearest neighbor (ANN) library for building and searching large-scale vector indexes, supporting efficient and scalable vector search scenarios.
About this tool
SPTAG
Description
SPTAG (Space Partition Tree And Graph) is an open-source, distributed library for approximate nearest neighbor (ANN) search, designed for building and searching large-scale vector indexes efficiently and scalably.
Features
- Approximate Nearest Neighbor Search: Efficiently finds vectors in large datasets that are nearest to a query vector, using L2 or cosine distance metrics.
- Large-Scale Vector Indexing: Designed to handle billions of vectors, suitable for big data scenarios.
- Multiple Indexing Methods:
- SPTAG-KDT: Uses kd-tree and relative neighborhood graph; advantageous for faster index building.
- SPTAG-BKT: Uses balanced k-means tree and relative neighborhood graph; advantageous for higher search accuracy in high-dimensional data.
- Distributed Online Serving: Supports searching across multiple machines for scalability.
- Online Vector Updates: Fresh update support allows for online vector insertion and deletion.
- Index Builder and Searcher Modules: Modular architecture for index construction and search.
- Docker Support: Can be built and run in Docker containers for easy deployment.
- Language Support: Core in C++ with Python wrappers available.
- Open Source and Extensible: Released under the MIT license, welcoming community contributions.
- Research-Backed: Features and algorithms are based on recent research, including support for relaxed monotonicity and incremental in-place updates.
Requirements
- swig >= 4.0.2
- cmake >= 3.12.0
- boost >= 1.67.0
Installation
- Supports installation on Linux and Windows, with instructions for both.
- Dockerfile provided for containerized builds.
Tags
open-source, ann, distributed, scalable
License
MIT License
Pricing
SPTAG is open-source and free to use under the MIT license.
Loading more......
Information
Categories
Tags
Similar Products
6 result(s)FAISS (Facebook AI Similarity Search) is a popular open-source library for efficient similarity search and clustering of dense vectors. Developed by Facebook/Meta, it supports billions of vectors and is widely used to power vector search engines and databases, especially where raw speed and scalability are needed.
NGT (Neighborhood Graph and Tree) is an open-source vector search engine designed for fast and scalable approximate nearest neighbor search.
A distributed vector database designed for scalable and efficient vector similarity search. It is purpose-built for handling large-scale vector data and search workloads.
Vald is an open-source, highly scalable distributed vector search engine known for its asynchronous auto-indexing and ability to efficiently handle large-scale vector data in real time, making it suitable for demanding vector search applications.
ParlayANN is a scalable and deterministic parallel graph-based approximate nearest neighbor (ANN) search library. It provides parallel algorithms and implementations for high-dimensional vector similarity search, suitable as a core search component in large-scale vector database and retrieval systems.
Voyager is a Spotify open-source vector search library and service for efficient nearest neighbor search on large-scale vector datasets.