ai-agent

vearch: Fast Vector Search

Name: vearch: Fast Vector Search
Author: vearch

Get fast and scalable vector search for AI-native apps with vearch, used by developers with 2.3k+ GitHub stars.

2,318 stars362 forksGoQuality 8/10Updated 7/21/2026100% free · open source

What it does

Vearch provides fast and scalable vector search capabilities for AI-native applications, allowing developers to efficiently search and retrieve similar vectors in large datasets.

Install / run

go get github.com/vearch/vearch/cmd/vearch

When to use it

•Building recommendation systems that require fast and accurate similarity searches
•Developing AI-powered chatbots that need to retrieve relevant information from large knowledge bases
•Creating image or video search applications that rely on vector embeddings for similarity matching

Quick start

1Run 'vearch server' to start the vearch server
2Configure the server by editing the 'config.yaml' file, specifying parameters such as 'port', 'dimension', and 'index_type'
3Use the vearch client to index vectors by sending a 'POST' request to 'http://localhost:16666/index' with a JSON payload containing the vector data
4Search for similar vectors by sending a 'POST' request to 'http://localhost:16666/search' with a JSON payload containing the query vector
5Monitor the server's performance and adjust configuration as needed using the vearch dashboard

Ready-to-paste prompt

curl -X POST 'http://localhost:16666/index' -H 'Content-Type: application/json' -d '[{"id":"vec1","vector":[1.0, 2.0, 3.0]}]'}'

Heads up: Vearch requires a compatible version of Go (at least 1.17) to be installed on the system, and the 'vearch server' command must be run with appropriate permissions to bind to the specified port

Saves to your device