RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
RAGU is an open-source modular GraphRAG system that separates entity extraction from consolidation via two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. Its accompanying 7B model, Meno-Lite-0.1, outperforms Qwen2.5-32B on knowledge-graph construction (+12.5% relative harmonic mean) despite being far smaller, and the system achieves higher evidence recall (up to 0.84 vs. <=0.76) than competitors on medical-domain benchmarks; it runs on a single GPU and is MIT-licensed with public code and weights.
Why it matters
This paper has 130 upvotes on HuggingFace Daily Papers, and demonstrates that a much smaller domain-adapted model can beat a 32B general model on knowledge-graph construction, relevant to cost-efficient RAG deployment.
Importance: 3/5
HF Daily Papers top-voted (130 upvotes, >=100 threshold) -> +1 bump from base 2.