Chroma

Chroma is open-source search infrastructure for AI that stores, indexes, and searches document collections by similarity. It is aimed at applications that need to add and query embeddings without wiring up separate tokenization and indexing components, making it a common building block for retrieval-augmented generation.

Collections support add, update, delete, get, and query operations. You can filter on metadata, search by document text, and ask for the most similar results. Chroma handles tokenization, embedding, and indexing automatically, or you can supply your own embeddings. It runs in memory for quick prototyping, and persistence can be added when needed.

Chroma offers Python and JavaScript clients and is licensed under Apache 2.0. A hosted service, Chroma Cloud, provides serverless vector, hybrid, and full-text search for teams that prefer a managed option.