weaviate
View on GitHubWeaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
Weaviate is a Go-based, cloud-native vector database storing objects and vectors together, so you can combine vector similarity search with structured filtering, hybrid BM25 search, integrated vectorization, RAG, and reranking in one API.
Use Cases
Retrieval-augmented generation (RAG) pipelinesSemantic search over documentsHybrid keyword + vector searchImage similarity searchRecommendation enginesChatbots and Q&A systemsContent classificationMulti-tenant search infrastructureReranking retrieved resultsBring-your-own-embedding vector storage
Built With
- Language
- Go
- Frameworks
- Go · gRPC · GraphQL · REST · Docker · Kubernetes · Raft · HNSW
Tags
vector-database · semantic-search · hybrid-search · vector-search · hnsw · embeddings · rag · bm25 · image-search · reranking · multi-tenancy · similarity-search · neural-search · recommender-system · grpc · scalable