What is Weaviate?
Weaviate is a cloud-native vector database that stores both objects and vectors, which enables semantic search at scale. Its README says it combines vector similarity search with keyword filtering, retrieval-augmented generation (RAG) and reranking in a single query interface. Common use cases include RAG systems, semantic and image search, recommendation engines, chatbots and content classification. The company behind it was founded in 2019 and is headquartered in Amsterdam, Netherlands.
Vectors can be created in two ways: automatic vectorization at import through integrated model providers such as OpenAI, Cohere and HuggingFace, or direct import of pre-computed embeddings. Production deployments get built-in multi-tenancy, replication and RBAC authorization. The database is built in Go.
Weaviate can be installed with Docker or Kubernetes, or used through Weaviate Cloud, with more options on AWS and GCP marketplaces. Client libraries exist for Python, JavaScript and TypeScript, Java, Go and C#/.NET, and the server exposes REST, gRPC and GraphQL APIs.
Key capabilities
- Storage of objects and vectors with semantic search at scale.
- Vector search combined with keyword filtering and reranking.
- Automatic vectorization at import or direct import of pre-computed embeddings.
- Multi-tenancy, replication and RBAC authorization.
- Client libraries for Python, JavaScript and TypeScript, Java, Go and C#/.NET.
- REST, gRPC and GraphQL APIs.
Where Weaviate fits
- Vector search Stores objects and vectors and enables semantic search at scale, including hybrid queries that combine vector similarity with keyword filtering.
- Retrieval-augmented generation Combines vector search, RAG and reranking in a single query interface.
- Query Agent Translates natural-language questions into optimized database queries automatically.
- Embeddings Generates vectors from text, images and more, or accepts pre-computed vector embeddings.
- Application use cases Common uses are semantic and image search, recommendation engines, chatbots and content classification.
- Multi-tenancy and access control Production deployments use built-in multi-tenancy, replication and RBAC authorization.
- Deployment Run it in Docker, on Kubernetes or in Weaviate Cloud, with client libraries for several programming languages.
Reviews of Weaviate
Be the first to share your experience with Weaviate.
Write a review
Loading review form…
