OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Vearch

Vearch is an open-source, cloud-native distributed vector database and search infrastructure project. It stores, indexes and retrieves embedding vectors and scalars for similarity search, document retrieval, hybrid search and RAG-oriented applications.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vearch — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Vearch when an application needs distributed, self-managed infrastructure for storing and querying embeddings, including hybrid retrieval or framework-based RAG integrations.

Who it is for

  • Developers building AI-native applications
  • Teams implementing semantic document retrieval or RAG knowledge bases
  • Engineers needing hybrid vector search with scalar filtering
  • Developers integrating vector storage with supported AI frameworks

Documented uses

  • Store and query embedding vectors
  • Retrieve documents by semantic similarity
  • Combine vector search with scalar filtering
  • Provide a vector-store or memory backend for supported frameworks
  • Deploy a distributed search service for AI or visual-search applications
Before you choose

Requirements & limits

The repository is publicly accessible and licensed under Apache-2.0. Documented deployment options include Kubernetes with Helm, Docker Compose, Docker and source compilation.

  • Choose between Kubernetes, Docker Compose, Docker or source compilation based on the deployment path documented by the project.
  • Use its scalar-filtering capability when retrieval needs both semantic similarity and structured conditions.
  • Consider the available Python, Go, Java and Rust SDKs when selecting an integration language.
  • Check the framework integrations if using LangChain, LlamaIndex, Langchaingo or LangChain4j.
  • Visual-search deployments may require additional object-detection and feature-extraction tooling.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Deploy Vearch with Docker Compose

Set up Vearch in standalone or cluster mode using the repository’s documented Docker Compose configuration.

Before you start

  • A checkout of the Vearch repository
  • Docker Compose
  • The repository configuration files

Steps

  1. Change to the cloud directory.

  2. For standalone mode, copy config/config.toml into the cloud directory; for cluster mode, copy config/config_cluster.toml instead.

  3. Start Docker Compose with the corresponding standalone or cluster profile in detached mode.

Expected outcome

A Docker Compose deployment is started in the selected standalone or cluster mode.

Guide limitations

  • This recipe documents deployment steps only; it does not verify application queries or data ingestion.
  • The source does not specify hardware, operating-system or Docker Compose version requirements.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
VearchStore and query embedding vectorsCloud, Self-hosted, ServerThe repository is publicly accessible and licensed under Apache-2.0. Documented deployment options include Kubernetes with Helm, Docker Compose, Docker and source compilation.
MettisIndex text documents through an HTTP endpoint.Linux, Self-hosted, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
1 October 2026
Original website title
vearch/vearch · Official homepage title · retained in its source language
How we review sourcesSuggest a correction