haiku.rag
pipStandardhaiku.rag provides agentic RAG functionality using LanceDB for vector storage, Pydantic AI for schema validation, and Docling for document processing. It exposes document ingestion, retrieval, and conversational interfaces. Connects to LanceDB and integrates with Pydantic AI and Docling. Useful for developers building AI applications requiring document management and conversational AI capabilities.
482270Updated 2 weeks ago
Overview
haiku.rag provides agentic RAG functionality using LanceDB for vector storage, Pydantic AI for schema validation, and Docling for document processing. It exposes document ingestion, retrieval, and conversational interfaces. Connects to LanceDB and integrates with Pydantic AI and Docling. Useful for developers building AI applications requiring document management and conversational AI capabilities.
Installation
1Install the package
pip
pip install haiku.rag2Add to Claude
Add this configuration to your claude_desktop_config.json:
claude_desktop_config.json
{
"mcpServers": {
"ggozad-haikurag-github": {
"command": "uvx",
"args": [
"pip install haiku.rag"
]
}
}
}3Verify installation
Restart Claude Desktop, then ask:
"What tools do you have available from haiku.rag?"
Prerequisites
- Python 3.10 or higher
- pip or uv package manager
- Claude Desktop or Claude API access
Configuration
No configuration required. This server works out of the box.
Usage Examples
List Resources
"What resources are available in haiku.rag?"
Claude will query available resources and return a list of what you can access.
Get Details
"Show me details about [specific item] in haiku.rag"
Claude will fetch and display detailed information about the requested item.
Create New
"Create a new [item] in haiku.rag with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
Works with haiku.rag
Related skills
Browse all skillsNeed help with MCP integration?
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.