chensyCN/LogicRAG

Source code of LogicRAG at AAAI'26.

43
/ 100
Emerging

This project helps AI developers enhance their Retrieval Augmented Generation (RAG) systems by allowing them to handle complex, multi-step queries without needing to pre-build knowledge graphs. It takes a complex question and a corpus of documents as input, then outputs a more accurate answer with an interpretable reasoning path. Developers building advanced RAG applications for question-answering, data analysis, or content generation would use this.

180 stars.

Use this if you are a developer building RAG systems and need to process complex questions requiring multi-step reasoning from large or frequently updated knowledge bases without the overhead of maintaining pre-built knowledge graphs.

Not ideal if you are looking for a plug-and-play solution for simple factual retrieval or if you do not have the technical expertise to integrate a Python library into an existing RAG pipeline.

AI-development question-answering-systems natural-language-processing information-retrieval LLM-applications
No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

180

Forks

31

Language

Python

License

Last pushed

Dec 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/chensyCN/LogicRAG"

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