ImprintLab/Medical-Graph-RAG
A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]
Constructs hierarchical medical knowledge graphs across three data levels (clinical records, biomedical literature, medical ontologies like UMLS) with Neo4j backend, enabling grounded retrieval over private clinical data. Uses LLM-based graph construction with optional fine-grained chunking and graph merging to connect entities across hierarchy levels. Integrates with OpenAI APIs and CAMEL framework for multi-agent orchestration, with Docker deployment supporting live PubMed search integration.
742 stars.
Stars
742
Forks
127
Language
Python
License
MIT
Category
Last pushed
Oct 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ImprintLab/Medical-Graph-RAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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
NJUxlj/Chinese-MedQA-Qwen2
基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了自定义的 SFTTrainer/DPOTrainer/TRPOTrainer用于训练，其次，项目还调用各种知识库工具（neo4j,...