Lin-A1/MediGraphRAG
构建一个医疗知识图谱并基于此实现 RAG，并以此实现医学试题的生成
Implements a three-stage knowledge graph construction pipeline (entity extraction, relation extraction, and fusion via Qwen2.5) stored in Neo4j, then performs RAG retrieval using FAISS indexing with BGE embeddings and reranking to generate medical exam questions. Integrates MetaGPT for multi-agent orchestration (decomposing question generation and validation across DeepSeek-r1 and Qwen models) with FastAPI endpoints and a web frontend for interactive access.
No commits in the last 6 months.
Stars
59
Forks
5
Language
Jupyter Notebook
License
—
Category
Last pushed
May 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Lin-A1/MediGraphRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ImprintLab/Medical-Graph-RAG
A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]
Warma10032/cyber-doctor
赛博医生项目——”赛博华佗“，基于多模态大模型的多功能智能体，一键搭建本地多模态大模型。接入医疗健康相关的知识图谱和知识库后可以进行疾病初诊，病历分析，专业知识问答等功能，成为你的私人医生。赛博...
koishi510/MomShell
Your Family Translator — An AI-powered wellness platform combining emotional companionship,...
avnlp/biothink
Self-Reflective Question Answering for Biomedical Reasoning
Tyler-KD/multi-model-AI-assistant-medical-bot
RAG-enabled multi-agentic system for medical diagnosis and assistance