Back to Skills

chroma

Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.

3,579stars289forksUpdated 2/18/2026

Security Assessment

Low Risk(70/100)

Detected risks:

Secret Exposure([SKILL.md] api_key=)
Security Score70/100

About chroma

Chroma is an open-source embedding database designed for AI applications, particularly useful in semantic search, retrieval-augmented generation (RAG), and document retrieval. It allows users to store and search through embeddings and their associated metadata, making it an ideal solution for handling vector-based data. Chroma can scale from simple prototyping in notebooks to full-scale production environments, allowing both local and self-hosted deployments. This solution supports seamless integration with machine learning and natural language processing applications, making it a robust choice for AI-driven search tasks and data retrieval.

FAQ

How do I install Chroma?

You can install Chroma via Python using 'pip install chromadb', or for JavaScript/TypeScript, use 'npm install chromadb @chroma-core/default-embed'.

What are the main features of Chroma?

Chroma offers key features including vector search, full-text search, filtering by metadata, and the ability to scale from local notebooks to production clusters. It supports a simple 4-function API for managing collections, adding documents, querying, and retrieving data.

Which programming languages are supported?

Chroma supports both Python and JavaScript/TypeScript. Python users can use the 'chromadb' library, while JavaScript/TypeScript users can install 'chromadb' and '@chroma-core/default-embed'.

What are the common use cases for Chroma?

Chroma is ideal for use cases such as semantic search, document retrieval, and building RAG applications. It is particularly suited for local or self-hosted vector databases and is best for open-source projects and prototyping in notebooks.

What dependencies does Chroma require?

Chroma requires the 'chromadb' library and 'sentence-transformers' for embedding generation.

Install chroma

Download and extract the skill files to your .claude/skills/ directory.

Quick Setup:

  1. Copy the skill folder to .claude/skills/
  2. Claude will automatically detect and use the skill