https://github.com/vearch/vearch

Distributed vector search for AI-native applications
https://github.com/vearch/vearch

ai-native ai-native-database cloud-native document-retrieval embeddings hybrid-search rag retrieval-augmented-generation vector-database vector-search vectors

Last synced: 4 days ago
JSON representation

Distributed vector search for AI-native applications

• Host: GitHub
• URL: https://github.com/vearch/vearch
• Owner: vearch
• License: apache-2.0
• Created: 2019-05-13T02:37:31.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2024-12-06T08:34:05.000Z (15 days ago)
• Last Synced: 2024-12-10T07:28:33.349Z (11 days ago)
• Topics: ai-native, ai-native-database, cloud-native, document-retrieval, embeddings, hybrid-search, rag, retrieval-augmented-generation, vector-database, vector-search, vectors
• Language: Go
• Homepage: https://vearch.github.io
• Size: 34.3 MB
• Stars: 2,083
• Watchers: 77
• Forks: 332
• Open Issues: 159
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md
  • Governance: GOVERNANCE.md
  • Roadmap: ROADMAP.md

Awesome Lists containing this project

• awesome-vector-search - Vearch - A scalable distributed system for efficient similarity search of deep learning vectors
• awesome-llmops - Vearch - based vector retrieval |  | (Search / Vector search)
• StarryDivineSky - vearch/vearch

README

        


  

  


    简体中文 | English

  



[![License: Apache-2.0](https://img.shields.io/badge/License-Apache--2.0-blue.svg)](./LICENSE)

[![Build Status](https://github.com/vearch/vearch/actions/workflows/CI.yml/badge.svg)](https://github.com/vearch/vearch/actions/workflows/CI.yml)

[![Go Report Card](https://goreportcard.com/badge/github.com/vearch/vearch/v3)](https://goreportcard.com/report/github.com/vearch/vearch/v3)

[![Gitter](https://badges.gitter.im/vector_search/community.svg)](https://gitter.im/vector_search/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge)

## Overview

Vearch is a cloud-native distributed vector database for efficient similarity search of embedding vectors in your AI applications.

## Key features

- **Hybrid search**: Both vector search and scalar filtering.

- **Performance**: Fast vector retrieval - search from millions of objects in milliseconds.

- **Scalability & Reliability**: Replication and elastic scaling out.

## Document

### Restful APIs

- [Tutorial](https://vearch.readthedocs.io/en/latest) | [参考文档](https://vearch.readthedocs.io/zh_CN/latest)

### OpenAPIs

- [Tutorial](https://vearch.github.io/tools#/)

### SDK

- **[Python SDK](sdk/python/README.md)**

- **[Go SDK](sdk/go/README.md)**

- **[Java SDK(under development)](sdk/java/README.md)**

## Usage cases

### Use Vearch as a memory backend

- **[Langchain](sdk/integrations/langchain/README.md)**

- **[LlamaIndex](sdk/integrations/llama-index/README.md)**

- **[Langchaingo](sdk/integrations/langchaingo/vearch/README.md)**

- **[LangChain4j](sdk/integrations/langchain4j/README.md)**

### Real world Demos

- **[VisualSearch](docs/Quickstart.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.

## Quick start

**[Deploy vearch cluster on k8s](https://vearch.github.io/vearch-helm/)**

**Add charts through the repo**

```

$ helm repo add vearch https://vearch.github.io/vearch-helm

$ helm repo update && helm install my-release vearch/vearch

```

**Add charts from local**

```

$ git clone https://github.com/vearch/vearch-helm.git && cd vearch-helm

$ helm install my-release ./charts -f ./charts/values.yaml

```

**Start by docker-compose**

standalone mode

```

$ cd cloud

$ cp ../config/config.toml .

$ docker-compose --profile standalone up -d

```

cluster mode

```

$ cd cloud

$ cp ../config/config_cluster.toml .

$ docker-compose --profile cluster up -d

```

**Deploy by docker**: Quickly start with vearch docker image, please see [DeployByDocker](docs/DeployByDocker.md)

**Compile by source code**: Quickly compile the source codes, please see [SourceCompileDeployment](docs/SourceCompileDeployment.md)

## Components

**Vearch Architecture**

![arc](assets/architecture.excalidraw.png)

**Master**: Responsible for schema management, cluster-level metadata, and resource coordination.

**Router**: Provides RESTful API: `upsert`, `delete`, `search` and `query`; 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](https://github.com/facebookresearch/faiss). It provides the ability of storing, indexing and retrieving the vectors and scalars.

## Reference

Reference to cite when you use Vearch in a research paper:

```

@misc{li2019design,

      title={The Design and Implementation of a Real Time Visual Search System on JD E-commerce Platform},

      author={Jie Li and Haifeng Liu and Chuanghua Gui and Jianyu Chen and Zhenyun Ni and Ning Wang},

      year={2019},

      eprint={1908.07389},

      archivePrefix={arXiv},

      primaryClass={cs.IR}

}

```

## Community

You can report bugs or ask questions in the [issues page](https://github.com/vearch/vearch/issues) of the repository.

For public discussion of Vearch or for questions, you can also send email to [email protected].

Our slack : https://vearchworkspace.slack.com

## Known Users

Welcome to register the company name in this issue: https://github.com/vearch/vearch/issues/230 (in order of registration)

![Users](assets/company_logos/all.jpg)

## License

Licensed under the Apache License, Version 2.0. For detail see [LICENSE and NOTICE](https://github.com/vearch/vearch/blob/master/LICENSE).