haiku.rag 0.13.1

Agentic Retrieval Augmented Generation (RAG) with LanceDB

Haiku RAG

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

Retrieval-Augmented Generation (RAG) library built on LanceDB.

haiku.rag is a Retrieval-Augmented Generation (RAG) library built to work with LanceDB as a local vector database. It uses LanceDB for storing embeddings and performs semantic (vector) search as well as full-text search combined through native hybrid search with Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.

Note: Configuration now uses YAML files instead of environment variables. If you're upgrading from an older version, run haiku-rag init-config --from-env to migrate your .env file to haiku.rag.yaml. See Configuration for details.

Features

• Local LanceDB: No external servers required, supports also LanceDB cloud storage, S3, Google Cloud & Azure
• Multiple embedding providers: Ollama, VoyageAI, OpenAI, vLLM
• Multiple QA providers: Any provider/model supported by Pydantic AI
• Research graph (multi‑agent): Plan → Search → Evaluate → Synthesize with agentic AI
• Native hybrid search: Vector + full-text search with native LanceDB RRF reranking
• Reranking: Default search result reranking with MixedBread AI, Cohere, or vLLM
• Question answering: Built-in QA agents on your documents
• File monitoring: Auto-index files when run as server
• 40+ file formats: PDF, DOCX, HTML, Markdown, code files, URLs
• MCP server: Expose as tools for AI assistants
• A2A agent: Conversational agent with context and multi-turn dialogue
• CLI & Python API: Use from command line or Python

Quick Start

# Install
# Python 3.12 or newer required
uv pip install haiku.rag

# Add documents
haiku-rag add "Your content here"
haiku-rag add "Your content here" --meta author=alice --meta topic=notes
haiku-rag add-src document.pdf --meta source=manual

# Search
haiku-rag search "query"

# Ask questions
haiku-rag ask "Who is the author of haiku.rag?"

# Ask questions with citations
haiku-rag ask "Who is the author of haiku.rag?" --cite

# Deep QA (multi-agent question decomposition)
haiku-rag ask "Who is the author of haiku.rag?" --deep --cite

# Deep QA with verbose output
haiku-rag ask "Who is the author of haiku.rag?" --deep --verbose

# Multi‑agent research (iterative plan/search/evaluate)
haiku-rag research \
  "What are the main drivers and trends of global temperature anomalies since 1990?" \
  --max-iterations 2 \
  --confidence-threshold 0.8 \
  --max-concurrency 3 \
  --verbose

# Rebuild database (re-chunk and re-embed all documents)
haiku-rag rebuild

# Start server with file monitoring
haiku-rag serve --monitor

To customize settings, create a haiku.rag.yaml config file (see Configuration).

Python Usage

from haiku.rag.client import HaikuRAG
from haiku.rag.research import (
    PlanNode,
    ResearchContext,
    ResearchDeps,
    ResearchState,
    build_research_graph,
    stream_research_graph,
)

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

    # Search (reranking enabled by default)
    results = await client.search("query")
    for chunk, score in results:
        print(f"{score:.3f}: {chunk.content}")

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

    # Ask questions with citations
    answer = await client.ask("Who is the author of haiku.rag?", cite=True)
    print(answer)

    # Multi‑agent research pipeline (Plan → Search → Evaluate → Synthesize)
    graph = build_research_graph()
    question = (
        "What are the main drivers and trends of global temperature "
        "anomalies since 1990?"
    )
    state = ResearchState(
        context=ResearchContext(original_question=question),
        max_iterations=2,
        confidence_threshold=0.8,
        max_concurrency=2,
    )
    deps = ResearchDeps(client=client)

    # Blocking run (final result only)
    result = await graph.run(
        PlanNode(provider="openai", model="gpt-4o-mini"),
        state=state,
        deps=deps,
    )
    print(result.output.title)

    # Streaming progress (log/report/error events)
    async for event in stream_research_graph(
        graph,
        PlanNode(provider="openai", model="gpt-4o-mini"),
        state,
        deps,
    ):
        if event.type == "log":
            iteration = event.state.iterations if event.state else state.iterations
            print(f"[{iteration}] {event.message}")
        elif event.type == "report":
            print("\nResearch complete!\n")
            print(event.report.title)
            print(event.report.executive_summary)

MCP Server

Use with AI assistants like Claude Desktop:

haiku-rag serve --stdio

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

A2A Agent

Run as a conversational agent with the Agent-to-Agent protocol:

# Start the A2A server
haiku-rag serve --a2a

# Connect with the interactive client (in another terminal)
haiku-rag a2aclient

The A2A agent provides:

• Multi-turn dialogue with context
• Intelligent multi-search for complex questions
• Source citations with titles and URIs
• Full document retrieval on request

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, MCP server, and A2A agent
• A2A Security - Authentication examples (API key, OAuth2, GitHub)

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
• MCP Server - Model Context Protocol integration
• A2A Agent - Agent-to-Agent protocol support
• Benchmarks - Performance Benchmarks