Weaviate

Weaviate is an open-source, cloud-native vector database that stores objects and vectors in one system. It is built for semantic search at scale and combines vector similarity search with keyword filtering, retrieval-augmented generation, and reranking through a single query interface.

It supports automatic vectorization at import time with integrated models or direct import of pre-computed embeddings. Query access is available through REST, gRPC, and GraphQL APIs, and production features include built-in multi-tenancy, replication, RBAC authorization, horizontal scaling, object TTL, and vector compression.

Weaviate is written in Go and ships with client libraries for Python, JavaScript/TypeScript, Java, Go, and C#/.NET. It can run with Docker, Kubernetes, or Weaviate Cloud, and the codebase is open source under the BSD 3-Clause license.