Weaviate is a cloud-native vector database that stores both objects and vectors, enabling the combination of vector search with structured filtering. Unlike simpler vector stores, Weaviate includes built-in vectorization modules that can automatically generate embeddings from text, images, and other data types using models from OpenAI, Cohere, Hugging Face, and others.
The database supports multiple search types — pure vector (semantic), keyword (BM25), and hybrid search that combines both approaches. Its GraphQL-based API and REST endpoints make integration straightforward. Weaviate also supports generative search (RAG) natively, combining retrieval with LLM-based answer generation.
Weaviate is open source under the BSD 3-Clause license. Self-hosted deployment is free. Weaviate Cloud offers a managed service with a free sandbox tier and production pricing based on storage and compute.