chroma

WHAT IT CONNECTS

What chroma gives an AI Agent

• **Semantic Search**: Find documents based on meaning using Chroma's embeddings
• **Metadata Filtering**: Filter search results by metadata fields
• **Content Filtering**: Additional filtering based on document content
• **Persistent Storage**: Data persists in local directory between server restarts
• **Error Handling**: Comprehensive error handling with clear messages
• **Retry Logic**: Automatic retries for transient failures
• Install dependencies:
• Windows: `src/chroma/data`
• MacOS/Linux: `src/chroma/data`
• Start the server:
• Use MCP tools to interact with the server:
• `Document already exists [id=X]`
• `Document not found [id=X]`
• `Invalid input: Missing document_id or content`
• `Invalid filter`
• `Operation failed: [details]`
• Run the MCP Inspector for interactive testing:
• Use the inspector's web interface to:
• Test CRUD operations
• Verify search functionality
• Check error handling
• Monitor server logs
• Update dependencies:
• Build package:
• Code style
• Testing requirements
• Pull request process