Skip to content
SPECIFICTION
Get listed

Vearch

vearch.github.io

Free plan macOSLinuxAPISelf-hosted
Visit vearch.github.io
Spec score 7.8 #16 of 27 in Vector Databases

What it is

Vearch is a free, open-source, cloud-native distributed vector database for similarity search in AI applications. It searches embedding vectors and can combine vector queries with scalar filtering for metadata conditions. The project describes replication and elastic scale-out and says it can retrieve vectors among millions of objects in milliseconds. Its Router exposes REST operations for upserting, deleting, searching, and querying data. Client SDKs are listed for Python, Go, Java, and Rust, with integrations for LangChain, LlamaIndex, LangChainGo, and LangChain4j. Deployment options include Kubernetes through Helm, Docker Compose in standalone or cluster mode, Docker, and compilation from source. PartitionServer uses Raft-based replication for document partitions, while Gamma is a Faiss-based vector search engine. Vearch is licensed under Apache License 2.0 and supports Linux and macOS self-hosted deployments. Community support is available through GitHub Issues, an email discussion group, and Slack. The VisualSearch demo requires an image retrieval plugin for object detection and feature extraction.

Spec sheet

Product
Vearch is a cloud-native distributed vector database for similarity search of embedding vectors in AI applications.Read 10 Oct 2026 · github.com
Deployment
Documented deployment options include Kubernetes with Helm, Docker Compose, Docker, and source compilation.Read 10 Oct 2026 · github.com
API
The Router exposes REST endpoints for upsert, delete, search, and query operations.Read 10 Oct 2026 · github.com
Integrations
The project lists integrations with LangChain, LlamaIndex, LangChainGo, and LangChain4j.Read 4 Oct 2026 · github.com
Support
The project directs users to GitHub Issues, a public email discussion list, and Slack for community support.Read 10 Oct 2026 · github.com
License
Vearch is licensed under Apache License, Version 2.0.Read 10 Oct 2026 · github.com
Community support
The project points users to GitHub Issues, an email discussion group, and a Slack channel for questions and support.Read 4 Oct 2026 · github.com
Framework integrations
The README lists LangChain, LlamaIndex, Langchaingo, and LangChain4j integrations.Read 10 Oct 2026 · github.com
Hybrid search
It supports vector search together with scalar filtering.Read 10 Oct 2026 · github.com
Notable limit
The Vearch 3.5 database guide says a database cannot be deleted while it contains a space.Read 10 Oct 2026 · vearch.readthedocs.io
Scale and reliability
The project describes replication and elastic scale-out as features.Read 10 Oct 2026 · github.com
SDKs
The README lists Python, Go, Java, and Rust SDKs.Read 10 Oct 2026 · github.com
Search performance
The project says it can retrieve vectors among millions of objects in milliseconds.Read 10 Oct 2026 · github.com
Security policy
GitHub's security page says the repository has no SECURITY.md policy and no published security advisories.Read 10 Oct 2026 · github.com
Storage engine
PartitionServer hosts document partitions with Raft-based replication, and Gamma is the core vector search engine based on Faiss.Read 10 Oct 2026 · github.com
Supported build environments
Vearch's installation guide says CentOS, Ubuntu, and Mac OS are supported for compiling the software.Read 10 Oct 2026 · vearch.readthedocs.io
Visual search requirement
The VisualSearch demo requires an image retrieval plugin for object detection and feature extraction.Read 4 Oct 2026 · github.com

Plans and prices

Vearch Free Apache License, Version 2.0 · self-hosted deployment Read 10 Oct 2026 · github.com

Every Vearch plan and price →

Strong points and limits

Strong points

  • Vector search supports scalar metadata filtering
  • REST API covers core data operations
  • SDKs available for four languages
  • Replication and elastic scale-out are described
  • Apache License 2.0 open-source distribution

Limits

  • VisualSearch needs an additional image retrieval plugin
  • Database cannot be deleted while containing a space
  • Repository has no SECURITY.md or published advisories

Who it suits

It suits AI teams building self-hosted similarity-search systems that need APIs, SDKs, metadata filtering, and deployment choice. It is also relevant to users working with Kubernetes, Docker, or source builds.

Verdict

Vearch provides a self-hosted vector database with distributed storage, filtering, APIs, and several deployment paths. Users should note the VisualSearch dependency and the documented database-deletion restriction.

Where Specifiction places it

Alternatives to VearchAll alternatives →