Chroma

← All terms · Hosting, infrastructure, databases

Also called ChromaDB

An open-source, embedding database optimized specifically for developer experience and rapid integration into local AI applications.

What it is

Chroma is designed to be the default vector database for developers building AI apps. It runs easily locally via a Python or JavaScript package, seamlessly integrates with frameworks like LangChain, and provides a highly intuitive API for storing embeddings, documents, and metadata, making prototyping RAG applications frictionless.

When you would use it

You use Chroma when you are prototyping an AI application locally or building agentic workflows and need an embedding database that is effortless to install and query.

Common operations

• Prototyping a local document-chat AI application.
• Managing memory and context retrieval for autonomous AI agents locally.

Related terms

• Pinecone
• Weaviate
• Embedding

Where this is taught

• Retrieval memory for long-context work