[Paper]

• Usage
• Citation
• Frequently Asked Questions (FQA)

SubgraphRAG is a retrieval-and-reasoning pipeline for knowledge-graph-based retrieval-augmented generation.

1. For the retrieval stage, see the retrieve folder.
2. For the reasoning stage, see the reason folder.

We welcome your feedback and sincerely appreciate your time! If you encounter bugs or have feature requests, you may open an issue or email us at {mufei.li, siqi.miao}@gatech.edu. Your input helps us improve and better serve the community!

@inproceedings{li2024subgraphrag,
    title={Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation},
    author={Li, Mufei and Miao, Siqi and Li, Pan},
    booktitle={International Conference on Learning Representations},
    year={2025}
}