README.md

metadata

title: MedeX - Medical AI System
emoji: 🏥
colorFrom: green
colorTo: blue
sdk: docker
app_port: 7860
pinned: true
license: mit
short_description: AI medical assistant for professionals and students!

🏥 MedeX - Advanced Medical AI Intelligence System

Professional Medical AI Assistant with Intelligent User Detection

🚀 Try Demo | 📖 Documentation | 🤝 Contribute

🎯 Overview

MedeX represents a sophisticated evolution in medical AI technology, powered by Kimi K2-0711-Preview with RAG (Retrieval-Augmented Generation) capabilities. The system automatically adapts responses for healthcare professionals and patients, providing accurate medical information with built-in safety protocols.

✨ Key Features

🧠 Intelligent Detection

• Automatic User Classification: Distinguishes between healthcare professionals and patients
• Context-Aware Responses: Adapts language and technical detail accordingly
• Emergency Recognition: Instantly identifies medical emergencies with appropriate protocols

📚 Comprehensive Knowledge Base

• ICD-10 Coded Conditions: Complete medical conditions database
• Pharmaceutical Information: Drug interactions, dosages, and contraindications
• Clinical Protocols: Evidence-based treatment guidelines
• RAG-Enhanced Search: Semantic search through medical literature
• Laboratory Values: Normal ranges and interpretation guidelines

🔬 Advanced Capabilities

• Real-Time Streaming: Progressive response generation for better UX
• Multi-modal Processing: Text consultations with image analysis capability
• Web Search Integration: Real-time medical information retrieval
• Structured Responses: Professional medical documentation format
• Session Management: Intelligent conversation history and statistics

🛡️ Medical Safety

• Built-in Disclaimers: Professional medical disclaimers on all responses
• Emergency Protocols: Automatic activation for critical conditions
• Professional Referral: Appropriate guidance for medical consultation
• Quality Standards: Adherence to medical information standards

🚀 Quick Start

Try on Hugging Face Spaces

Simply click the app link at the top of this page to start using MedeX immediately!

Local Installation

# Clone the repository
git clone <repository-url>
cd MedeX-main

# Install dependencies
pip install -r requirements.txt

# Run Streamlit app
streamlit run streamlit_app.py

Docker Deployment

# Build Docker image
docker build -t medex-app .

# Run container
docker run -p 7860:7860 medex-app

💡 Usage Examples

For Healthcare Professionals

"Paciente 65 años, diabético, dolor precordial de 2 horas de evolución"

MedeX will provide:

• Detailed clinical analysis
• Differential diagnoses with probabilities
• Management protocols with specific dosages
• Evidence-based guidelines references

For Patients

"Me duele el pecho y estoy preocupado"

MedeX will provide:

• Clear, understandable explanation
• Possible causes in simple terms
• When to seek medical attention
• Self-care recommendations

Emergency Queries

"Dolor torácico intenso, no puedo respirar"

MedeX will:

• 🚨 Activate emergency protocol
• Provide immediate action steps
• Emphasize calling 911
• Guide until professional help arrives

🏗️ System Architecture

MedeX Ultimate RAG System
├── Kimi K2-0711-Preview (LLM)
├── RAG System (Semantic Search)
│   ├── Medical Knowledge Base
│   ├── Pharmaceutical Database
│   └── Clinical Protocols
├── User Detection Engine
├── Emergency Protocol System
└── Streamlit Interface

🔧 Configuration

Environment Variables

For Hugging Face Spaces, configure these in your Space settings:

• KIMI_API_KEY: Your Moonshot AI API key (required)
• STREAMLIT_SERVER_PORT: Port for Streamlit (default: 7860)

API Key Setup

The system uses Moonshot AI's Kimi API. Configure your API key:

1. Get your API key from Moonshot AI Platform
2. Add it to your Space secrets as KIMI_API_KEY
3. Or use the default key in the code (for testing only)

📊 Technical Stack

• LLM: Kimi K2-0711-Preview (Moonshot AI)
• Framework: Streamlit 1.28+
• RAG: Sentence Transformers + Scikit-learn
• Container: Docker with Python 3.10
• Deployment: Hugging Face Spaces

⚠️ Important Disclaimers

MEDICAL DISCLAIMER:

• This system is for educational and informational purposes only
• It does NOT provide medical advice, diagnosis, or treatment
• It should NOT replace professional medical consultation
• In case of medical emergency, call 911 immediately
• Always consult qualified healthcare professionals for medical decisions

LIABILITY:

• The developers and contributors are not liable for any medical decisions made based on information from this system
• Users assume all responsibility for how they use this information
• This is an AI system and may contain errors or inaccuracies

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

👥 Authors

• Medical AI Systems Team
• Powered by Moonshot AI (Kimi K2)

🙏 Acknowledgments

• Moonshot AI for Kimi K2-0711-Preview
• Hugging Face for Spaces infrastructure
• Medical community for knowledge validation
• Open-source contributors

📧 Contact

For questions, issues, or suggestions:

• Open an issue on GitHub
• Contact through Hugging Face Spaces discussion

---

MedeX v25.83 Ultimate RAG

Advancing Medical AI for Better Healthcare