🏥 Good Health AI Assistant – Smart Medical Chatbot with LangGraph & GPT

An intelligent, memory-aware conversational assistant for Good Health Clinic, built with LangGraph, LangChain, and OpenAI GPT. This system routes patient queries, detects emergencies, manages appointments, and updates medical records — all through natural multi-turn conversations.

---

✨ Key Features

• 🤖 AI-Powered Appointment Scheduling
• 👤 Patient Profile Management (history, allergies, treatments)
• 🚨 Emergency Detection & Alert System
• 💬 Multi-turn Memory Conversations
• 🧠 LangGraph-Based Decision Routing

---

🧩 How It Works

🔹 check_condition()

Determines the route of conversation:

• Routes to handle_emergency() if message contains "emergency"
• Otherwise, calls call_model() for regular processing

🔹 call_model()

• Retrieves patient data
• Generates GPT-based responses contextualized with history

🔹 handle_emergency()

• Delivers urgent care instructions instantly

🔹 write_memory()

• Updates and persists medical records securely

---

⚙️ Setup & Installation

1️⃣ Clone the Repo

git clone https://github.com/co-dev0909/medical-ai-assistant
cd medical-ai-assistant

2️⃣ Install Dependencies

Make sure you're using Python 3.8+

pip install -r requirements.txt

3️⃣ Configure Environment Variables

Create a .env file:

OPENAI_API_KEY=your-api-key-here

---

🚀 Running the Assistant

To launch the chatbot:

python main.py

💡 Example Interaction

Routine Check-up:

User: I need to book a follow-up appointment.
Assistant: Hello Taher! I can help you schedule a check-up. When are you available?

Emergency:

User: This is an emergency! I’m having severe chest pain.
Assistant: We've detected an emergency. Please call emergency services or our 24/7 urgent line: +43 00 00 00.

---

🧠 Tech Stack

Tool	Purpose
LangGraph	Graph-based conversational routing
LangChain	LLM + Memory integration
OpenAI GPT	Natural language response generation
Python	Backend implementation
InMemoryStore	Persistent session-based memory

---

👨‍💻 Maintainer

Ying Zhou 📧 zying1309@gmail.com

Contributions welcome! Fork the repo and submit a pull request 🚀

---

📝 License

This project is licensed under the MIT License.