haiku.rag/docs/index.md

haiku.rag

haiku.rag is an opinionated agentic RAG system that uses LanceDB for vector storage, Pydantic AI for multi-agent workflows, and Docling for document processing. It supports hybrid search (vector + full-text) with Reciprocal Rank Fusion, multiple embedding providers (Ollama, LM Studio, vLLM, OpenAI, VoyageAI), and includes research agents that plan, search, evaluate, and synthesize answers.

Features

• Local LanceDB: No external servers required, supports also LanceDB cloud storage, S3, Google Cloud & Azure
• Multiple embedding providers: Ollama, LM Studio, VoyageAI, OpenAI, vLLM
• Multiple QA providers: Any provider/model supported by Pydantic AI (Ollama, LM Studio, OpenAI, Anthropic, etc.)
• Native hybrid search: Vector + full-text search with native LanceDB RRF reranking
• Reranking: Optional result reranking with MixedBread AI, Cohere, Zero Entropy, or vLLM
• Question answering: Built-in QA agents on your documents
• Research graph (multi‑agent): Plan → Search → Evaluate → Synthesize with agentic AI
• File monitoring: Auto-index files when run as server
• Extended file format support: Parse PDF, DOCX, HTML, Markdown, images, code files and more
• Flexible document processing: Local processing with docling or remote with docling-serve
• MCP server: Expose as tools for AI assistants
• CLI & Python API: Use from command line or Python

Quick Start

Install haiku.rag:

uv pip install haiku.rag

Use from Python:

from haiku.rag.client import HaikuRAG

async with HaikuRAG("database.lancedb") as client:
    # Add a document
    doc = await client.create_document("Your content here")

    # Search documents
    results = await client.search("query")

    # Ask questions
    answer = await client.ask("Who is the author of haiku.rag?")

Or use the CLI:

haiku-rag add "Your document content"
haiku-rag add "Your document content" --meta author=alice
haiku-rag add-src /path/to/document.pdf --title "Q3 Financial Report" --meta source=manual
haiku-rag search "query"
haiku-rag ask "Who is the author of haiku.rag?"

Documentation

• Getting started - Tutorial
• Installation - Install haiku.rag with different providers
• Configuration - Environment variables and settings
• CLI - Command line interface usage
• Server - File monitoring and server mode
• MCP - Model Context Protocol integration
• Python - Python API reference
• Agents - QA agent and multi-agent research
• Remote processing - Remote document processing with docling-serve

License

This project is licensed under the MIT License.