Chroma

Chroma

0 bookmarks
Visit

Summary

The embedding database that starts as a Python import and grows into a distributed cloud service.

Description

Chroma is the vector store people reach for first, because getting started is genuinely two lines: pip install chromadb, then create a collection. It runs in-process with no server, which makes it ideal for prototypes, notebooks, and tests.

What it does

  • In-memory or persistent local storage, so a prototype needs no infrastructure at all
  • Automatic embedding using a default model or any provider you configure, so you can pass raw text rather than vectors
  • Metadata filtering and full-text search alongside vector similarity
  • Multimodal collections for images as well as text
  • A client/server mode for when several processes need the same store, and a managed cloud for production scale

Why it matters

Chroma optimised for the first five minutes, and that turned out to be the right call — it is the default in an enormous number of tutorials, courses, and agent frameworks. Crucially, the API is the same locally and in the cloud, so moving from prototype to production is a connection change rather than a rewrite.

Open source under Apache 2.0 and free to self-host; Chroma Cloud is usage-based with a free tier.

Reviews

Similar App Suggestions