hhy-huang/HiRAG

[EMNLP'25 findings] This is the official repo for the paper, HiRAG: Retrieval-Augmented Generation with Hierarchical Knowledge.

53
/ 100
Established

This project helps you get more accurate and comprehensive answers from large language models (LLMs) when querying your specific documents or knowledge base. You provide your textual content, and it processes it to enable a system that understands the hierarchical relationships within your information. The result is a more insightful and detailed response to your questions. This is for data scientists, researchers, or anyone building advanced question-answering systems over their proprietary data.

522 stars.

Use this if you need to build a question-answering system over your domain-specific text data where the relationships and hierarchy of information are important for generating high-quality, detailed responses.

Not ideal if you are looking for a simple keyword search tool or if your data does not have inherent hierarchical structures that would benefit a more complex retrieval method.

knowledge-management domain-specific-search intelligent-assistants information-retrieval enterprise-search
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

522

Forks

83

Language

Python

License

MIT

Last pushed

Nov 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/hhy-huang/HiRAG"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.