Glossary · Generative AI and LLMs
What is Weaviate? Definition and meaning
A vector database that stores objects with embeddings and supports hybrid and filtered search.
Definition
Weaviate: A vector database that stores objects with embeddings and supports hybrid and filtered search.
In short: Open-source vector database with hybrid search.
When it is used
Semantic and hybrid search with rich metadata.
Where it fits
Weaviate belongs to Vector databases in the Generative AI and LLMs topic. These are the other terms in the same group:
- ChromaDB: A simple embedding store that is easy to embed in an application.
- Milvus: A distributed vector database built for billion-scale similarity search.
- Qdrant: A vector database with strong filtering, payloads and efficient indexing.
- Vespa: An engine that combines text, vector and structured search with on-node ranking.
- FAISS: Meta's library for nearest-neighbour search and clustering of dense vectors, with CPU and GPU indexes.
- pgvector: A PostgreSQL extension that stores embeddings and supports exact and approximate nearest-neighbour search.
Learn more
The full guide to Weaviate explains how it works, when to use it and how it compares with the alternatives, with examples. The glossary lists every term on the site from A to Z.
Previous term: VQ-VAE · Next term: Weight initialization