chensyCN/LogicRAG

Source code of LogicRAG at AAAI'26.

42
/ 100
Emerging

Constructs query logic dependency graphs at test time to guide multi-step retrieval without requiring pre-built knowledge graphs, enabling efficient structured RAG on large or dynamic corpora. The system linearizes complex graph reasoning into sequential subproblems while maintaining logical coherence, with optimization via graph pruning and rolling memory. Integrates with OpenAI's API and supports flexible evaluation on custom datasets and corpora through configurable retrieval rounds and context windows.

180 stars.

No License No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 7 / 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.