Chroma
An open-source embedding database for AI applications, which stores documents, vectors and metadata in collections searched with HNSW.
In more detail
Each collection fixes its distance space, l2 by default or cosine or inner product, when it is created. Chroma also publishes research such as its 2025 context rot study.
Related terms
- vector database — A database or extension that stores embedding vectors with their metadata and answers nearest-neighbour queries.
- HNSW — An approximate vector index built as a layered graph of links between nearby vectors, searched by walking from a coarse top layer down to a dense bottom one.
Taught in
- When Context Fails — AI Engineering: LLM Apps, RAG & Agents
- What An Embedding Is — AI Engineering: LLM Apps, RAG & Agents
- Vector Indexes And Databases — AI Engineering: LLM Apps, RAG & Agents
References
- Chroma: Configure collections (HNSW space defaults)
- Chroma: Context Rot: How Increasing Input Tokens Impacts LLM Performance (2025-07-14)