Memory & evals · Project

Chroma

Chroma stores embeddings, documents and metadata for retrieval.

+ Follow

Builder facts

  • Client modes. Python supports in-memory and on-disk persistent clients. Chroma Cloud takes an API key, and key-only database discovery requires a key scoped to a single database. Source ↗
  • Collection queries. Query embeds text with the collection’s configured embedding function or takes vectors with the collection’s dimension. Get retrieves records without similarity ranking. Source ↗
  • Cloud search. The Cloud Search API combines metadata filters, vector scoring and reciprocal rank fusion, with explicit selection of returned fields. Source ↗
  • Hosted billing. Chroma Cloud meters compute, storage and search. Starter includes credits and usage limits for the managed service. Source ↗

Sources checked

Publisher update ·

Chroma 1.5.9 ↗

Search grouping now merges groups across shards and applies the per-group result limit across the collection.

Change timeline

0 stories

No verified releases in this timeline yet.