/vearch

A distributed system for embedding-based retrieval

Primary LanguageGoOtherNOASSERTION

Build Status     Gitter

Overview

Vearch is a scalable distributed system for efficient similarity search of deep learning vectors.

Architecture

arc

  • Data Model

    space, documents, vectors, scalars

  • Components

    Master, Router and PartitionServer

  • Master

    Responsible for schema mananagement, cluster-level metadata, and resource coordination.

  • Router

    Provides RESTful API: create , delete search and update ; request routing, and result merging.

  • PartitionServer (PS)

    Hosts document partitions with raft-based replication.

    Gamma is the core vector search engine implemented based on faiss. It provides the ability of storing, indexing and retrieving the vectors and scalars.

Quick start

docs/img/plugin/main_process.gif

  • One-click binary installation, please see docs/BinaryInstallation.md(中文版).

  • Quickly compile the source codes to build a distributed vector search system with RESTful API, please see docs/SourceCompileDeployment.md.

  • Vearch can be leveraged to build a complete visual search system to index billions of images. The image retrieval plugin for object detection and feature extraction is also required. For more information, please refer to docs/Quickstart.md.

  • Vearch Python SDK enables vearch to use locally. Vearch python sdk can be installed easily by pip install vearch. For more information, please refer to docs/APIPythonSDK.md.

APIs and Use Cases

LowLevelAPI

VisualSearchAPI

PythonSDKAPI

Document

Benchmarks

Publication

Jie Li, Haifeng Liu, Chuanghua Gui, Jianyu chen, Zhenyun Ni, Ning Wang, Yuan Chen, Qiang Liu. The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform. In the 19th International ACM Middleware Conference, December 10–14, 2018, Rennes, France. https://arxiv.org/abs/1908.07389

Community

You can report bugs or ask questions in the issues page of the repository.

For public discussion of Vearch or for questions, you can also send email to vearch-maintainers@groups.io.

Our slack : https://vearchwrokspace.slack.com

Known Users

Welcome to register the company name in this issue: vearch#230 (in order of registration)

欢迎在此 issue vearch#230 中登记公司名称

科大讯飞 飞搜科技 君库科技 爱奇艺 人民科技 趣头条 网易严选 咸唐科技 华为技术 OPPO 汽车之家 芯翌智能 图灵机器人

License

Licensed under the Apache License, Version 2.0. For detail see LICENSE and NOTICE.