Haiku RAG

Agentic RAG built on LanceDB, Pydantic AI, and Docling.

Features

• Hybrid search — Vector + full-text with Reciprocal Rank Fusion
• Reranking — MxBAI, Cohere, Zero Entropy, or vLLM
• Question answering — QA agents with citations (page numbers, section headings)
• Research agents — Multi-agent workflows via pydantic-graph: plan, search, evaluate, synthesize
• Document structure — Stores full DoclingDocument, enabling structure-aware context expansion and visual grounding
• Multiple providers — Embeddings: Ollama, OpenAI, VoyageAI, LM Studio, vLLM. QA/Research: any model supported by Pydantic AI
• Local-first — Embedded LanceDB, no servers required. Also supports S3, GCS, Azure, and LanceDB Cloud
• MCP server — Expose as tools for AI assistants (Claude Desktop, etc.)
• File monitoring — Watch directories and auto-index on changes
• Inspector — TUI for browsing documents, chunks, and search results
• CLI & Python API — Full functionality from command line or code

Installation

Python 3.12 or newer required

Full Package (Recommended)

uv pip install haiku.rag

Includes all features: document processing, all embedding providers, and rerankers.

Slim Package (Minimal Dependencies)

uv pip install haiku.rag-slim

Install only the extras you need. See the Installation documentation for available options

Quick Start

# Index a PDF
haiku-rag add-src paper.pdf

# Search
haiku-rag search "attention mechanism"

# Ask questions with citations
haiku-rag ask "What datasets were used for evaluation?" --cite

# Deep QA — decomposes complex questions into sub-queries
haiku-rag ask "How does the proposed method compare to the baseline on MMLU?" --deep

# Research mode — iterative planning and search
haiku-rag research "What are the limitations of the approach?" --verbose

# Watch a directory for changes
haiku-rag serve --monitor

See Configuration for customization options.

Python API

from haiku.rag.client import HaikuRAG

async with HaikuRAG("research.lancedb", create=True) as rag:
    # Index documents
    await rag.create_document_from_source("paper.pdf")
    await rag.create_document_from_source("https://arxiv.org/pdf/1706.03762")

    # Search — returns chunks with provenance
    results = await rag.search("self-attention")
    for result in results:
        print(f"{result.score:.2f} | p.{result.page_numbers} | {result.content[:100]}")

    # QA with citations
    answer, citations = await rag.ask("What is the complexity of self-attention?")
    print(answer)
    for cite in citations:
        print(f"  [{cite.chunk_id}] p.{cite.page_numbers}: {cite.content[:80]}")

For research agents and streaming with AG-UI, see the Agents docs.

MCP Server

Use with AI assistants like Claude Desktop:

haiku-rag serve --mcp --stdio

Add to your Claude Desktop configuration:

{
  "mcpServers": {
    "haiku-rag": {
      "command": "haiku-rag",
      "args": ["serve", "--mcp", "--stdio"]
    }
  }
}

Provides tools for document management, search, QA, and research directly in your AI assistant.

Examples

See the examples directory for working examples:

• Interactive Research Assistant - Full-stack research assistant with Pydantic AI and AG-UI featuring human-in-the-loop approval and real-time state synchronization
• Docker Setup - Complete Docker deployment with file monitoring and MCP server
• A2A Server - Self-contained A2A protocol server package with conversational agent interface

Documentation

Full documentation at: https://ggozad.github.io/haiku.rag/

• Installation - Provider setup
• Configuration - YAML configuration
• CLI - Command reference
• Python API - Complete API docs
• Agents - QA agent and multi-agent research
• Server - File monitoring, MCP, and AG-UI
• MCP - Model Context Protocol integration
• Inspector - Database browser TUI
• Benchmarks - Performance benchmarks
• Changelog - Version history

mcp-name: io.github.ggozad/haiku-rag