Source: Chroma documentation introduction

Chroma's overview: an Apache-2.0 retrieval database for AI apps with dense, sparse and hybrid search, metadata filtering, local and cloud deployment.

Contents

Summary

Chroma positions itself as open-source data infrastructure for AI. It stores embeddings with metadata and can run locally, self-hosted or as the managed serverless Chroma Cloud. Its scope has grown from a prototyping vector store to dense, sparse and hybrid retrieval with keyword and regex search.

Key claims

  • Open source under Apache 2.0.
  • Supports dense, sparse and hybrid vector search, keyword and regex search, and metadata filtering at query time.
  • Integrates embedding functions for OpenAI, Cohere, Hugging Face and sentence-transformers.
  • Deploys locally, self-hosted, or on Chroma Cloud (managed, serverless).

Feeds

Vector databases

Suggest changes →