Weaviate
An open-source, cloud-native vector database that stores objects together with their vectors, combining vector similarity search with keyword filtering, retrieval-augmented generation and reranking in one query interface.
Weaviate is an open-source, cloud-native vector database that stores both objects and vectors, enabling semantic search at scale. It combines vector similarity search with keyword filtering, retrieval-augmented generation and reranking in a single query interface, for use cases such as RAG systems, semantic and image search, recommendation engines, chatbots and content classification.
Vectors can be created automatically at import time using integrated models from providers such as OpenAI, Cohere and Hugging Face, or imported directly as precomputed embeddings. Production deployments get built-in multi-tenancy, replication and role-based access control.
It deploys through Docker, Kubernetes or a managed Weaviate Cloud service, exposes REST, gRPC and GraphQL APIs, and provides client libraries for Python, JavaScript and TypeScript, Java, Go, and C#/.NET. It is written in Go.