What is Weaviate?

Weaviate is an open-source, Go-built vector database that stores both data objects and their vector embeddings together, letting an application combine semantic vector search with structured filtering, keyword search, and even graph-like relationships in a single system. Its core engine is Apache 2.0 licensed.

It was created by Bob van Luijt and Etienne Dilocker, who began the open-source project in 2016 and incorporated Weaviate B.V. in Amsterdam in 2019. Weaviate distinguishes itself with a modular vectorizer system: rather than requiring an application to generate embeddings externally before inserting data, Weaviate can connect to embedding providers (OpenAI, Cohere, Google, HuggingFace, and others) and generate vectors automatically at ingestion and query time.

Beyond core vector storage and search, Weaviate ships built-in support for retrieval-augmented generation (RAG) through generative modules, native hybrid search combining keyword and vector signals, and, more recently, an agentic layer (the Query Agent) for natural-language querying across collections.