tpoisonooo/ROGRAG
[ACL2025 demo track] ROGRAG: A Robustly Optimized GraphRAG Framework
Implements a two-stage retrieval pipeline combining dense entity/relationship matching with structured logic reasoning to ground LLM responses in domain knowledge graphs, achieving 15% accuracy gains on specialized QA benchmarks. Features incremental graph construction, fuzzy entity matching, and incremental database support for multi-domain scenarios. Offers Docker deployment with Gradio UI and REST API compatibility, integrating with LLM providers like SiliconCloud while maintaining backward compatibility with existing chat platforms.
196 stars.
Stars
196
Forks
19
Language
Python
License
BSD-3-Clause
Category
Last pushed
Dec 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/tpoisonooo/ROGRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation
getzep/graphiti
Build Real-Time Knowledge Graphs for AI Agents