Weaviate

Open source

A cloud-native vector database that stores objects and embeddings and combines semantic search with keyword filtering, RAG and reranking in one query interface.

weaviate.io
Weaviate homepage screenshot
GitHub stars
17k
Last 30 days
+68(+0%)
Last commit
yesterday
Repository age
10 years
Version
v1.40.5
Licence
Custom
Self-hosted
Yes

About Weaviate

Weaviate is a vector database that stores both data objects and their vector embeddings, enabling semantic search at scale. One query interface can blend vector similarity search, keyword filtering, retrieval-augmented generation and reranking, and it is written in Go as a cloud-native system.

Common applications are RAG pipelines, semantic and image search, recommenders, chatbots and content classification. Vectors can be created automatically on import by integrated models from providers such as OpenAI, Cohere and Hugging Face, or you can import pre-computed embeddings. For production, it offers built-in multi-tenancy, replication and role-based access control. Topics reference approximate nearest neighbor search and HNSW indexing.

Weaviate can be deployed with Docker, on Kubernetes, or through the managed Weaviate Cloud, with guides for AWS and GCP, and the documentation includes quickstarts for both cloud and a local Docker instance. Its license is listed as 'Other' on GitHub, so check the repository terms. It suits teams building AI applications that need a scalable store for embeddings alongside structured filters.

Key features

  • Stores objects and vectors together
  • Hybrid vector and keyword search
  • Integrated vectorizer models or bring your own
  • Multi-tenancy and replication
  • Role-based access control
  • Docker, Kubernetes and Weaviate Cloud options

Good fit for

  • RAG pipelines for chatbots
  • Semantic and image search
  • Recommendation systems
Built with
Go tools
Tags
vector-database
semantic-search
rag
embeddings
golang
hnsw
ai
search-engine
self-hosted

Weaviate: questions and answers

What is Weaviate used for?
Weaviate is a cloud-native vector database that stores objects and embeddings and combines semantic search with keyword filtering, RAG and reranking in one query interface. It is a good fit for RAG pipelines for chatbots, semantic and image search, and recommendation systems.
Is Weaviate open source?
Yes. Weaviate is open source under a custom licence. Its source code is on GitHub at weaviate/weaviate and is written mainly in Go.
Is Weaviate free?
Yes. Weaviate is open source, so the software itself is free to use under the terms of its own licence. A managed cloud version is also available.
Can I self-host Weaviate?
Yes. Weaviate can be self-hosted on your own server or infrastructure.
What is Weaviate an alternative to?
Weaviate is an open-source alternative to Pinecone, Glean, Upstash and Azure AI Search. Other open-source alternatives to Pinecone include Qdrant and Milvus.
Is Weaviate actively maintained?
Yes. The most recent commit to Weaviate was on 12 November 2026, and the latest release is v1.40.5, published on 10 November 2026. The project has 17k stars on GitHub, with 68 added in the last 30 days.

Open-source alternatives to Weaviate

See all

SaaS alternatives to Weaviate

See all