MrRezaeiUofT/AMG-RAG
AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating of Medical Knowledge Graphs (MKGs), integrates reasoning, and retrieves current external evidence for medical Question Answering (QA).
Employs a six-stage agentic pipeline combining LLM-based entity extraction with confidence scoring (1-10 scale), bidirectional relationship analysis, multi-source evidence retrieval (PubMed API, Wikipedia, vector databases), and chain-of-thought reasoning for medical QA. Supports both OpenAI and local Ollama inference, with real-time graph updates incorporating latest medical literature. Evaluated on MEDQA (74.1% F1) and MedMCQA (66.34% accuracy) benchmarks, demonstrating performance comparable to much larger models while maintaining interpretability.
Stars
21
Forks
4
Language
Python
License
—
Category
Last pushed
Feb 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/MrRezaeiUofT/AMG-RAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
NVIDIA/context-aware-rag
Context-Aware RAG library for Knowledge Graph ingestion and retrieval functions.