chensyCN / LogicRAG
Source code of LogicRAG at AAAI'26.
Why this job: topics: rag, graphrag
What it does
- ❶ Logic Dependency Analysis. Convert complex questions into logical dependency graphs for planning multi-step retrieval.
- ❷ Graph Reasoning Linearization. Linearize complex graph reasoning into sequential subproblem solution while maintaining logic-coherence.
- ❸ Efficiency. Efficient scheduling via graph pruning, and context-length optimization via rolling memory.
- ❹ Interpretable Results. Provides clear reasoning paths and dependency analysis for better explainability.
Get started
pip install -r requirements.txt- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 241
- On GitHub
- Licence
- GPL-3.0
- Share-alike terms
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 0 merged
- 1 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| microsoft / graphrag | 36,613 | 8 days ago | MIT | No downloads |
| nageoffer / ragent | 4,449 | 2 days ago | Apache-2.0 | No downloads |
| DEEP-PolyU / LinearRAG | 568 | 4 months ago | GPL-3.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- agentic-rag
- graphrag
- llms
- rag
Project record
- JobRAG and search
- StatusListed
- Commits43
- Forks37
- Watching8
- Stars in 28 days+3
- CreatedApr 7, 2025
- First seen by usNov 7, 2026
- CheckedNov 7, 2026