GraphRAG SDK

​

Key Highlights

• #1 on GraphRAG-Bench — 66.09 ACC on Novel and 76.87 on Medical (benchmark)
• Simple API — ingest() + completion() with sensible defaults
• 100+ LLM providers via LiteLLM (OpenAI, Azure, Anthropic, Cohere, Ollama, and more)
• Fully modular — swap chunking, extraction, resolution, retrieval, and reranking strategies
• Production-ready — async-first, connection pooling, circuit breaker, batched writes
• Full provenance — every answer traces back to its source document and chunk

​

Quick Start

pip install graphrag-sdk[litellm]
docker run -p 6379:6379 falkordb/falkordb

import asyncio
from graphrag_sdk import GraphRAG, ConnectionConfig, LiteLLM, LiteLLMEmbedder

async def main():
    async with GraphRAG(
        connection=ConnectionConfig(host="localhost", graph_name="my_graph"),
        llm=LiteLLM(model="openai/gpt-4o"),
        embedder=LiteLLMEmbedder(model="openai/text-embedding-3-small"),
    ) as rag:
        await rag.ingest("my_document.pdf")
        await rag.finalize()
        answer = await rag.completion("What is the main topic?")
        print(answer.answer)

asyncio.run(main())

​

Next Steps

• Getting Started — Full tutorial from install to first query
• Architecture — How the 9-step pipeline works
• Reducing LLM Hallucinations — Grounded retrieval, provenance, and abstention
• Strategies — All swappable strategy ABCs and built-in options
• Ontology Discovery — Auto-draft a schema from a corpus (method="llm" or method="grounded" with DBpediaCatalog)
• Ontology Evolution — Safely change schema on a populated graph
• Incremental Updates — update(), delete_document(), apply_changes(), finalize()
• Benchmark — Methodology and reproduction instructions
• API Reference — Full API documentation