AI-powered health assistant for elderly users with appointment booking, health monitoring, and emergency response capabilities.
elderly-agent/
├── backend/ # Flask API server
└── frontend/ # React web application
-
Navigate to backend directory:
cd backend -
Install Python dependencies:
pip install -r requirements.txt
-
Configure environment variables: Create a
.envfile in thebackend/directory with:OPENAI_API_KEY=your_openai_api_key_here PINECONE_API_KEY=your_pinecone_api_key_here PINECONE_ENVIRONMENT=your_pinecone_environment_here GOOGLE_APPLICATION_CREDENTIALS=path_to_your_service_account_key.json -
Run the Flask server:
python app.py
The backend will start on
http://localhost:5050
-
Navigate to frontend directory:
cd frontend -
Install dependencies (if not already installed):
npm install
-
Start the development server:
npm start
The frontend will start on
http://localhost:3000
-
Terminal 1 - Start Backend:
cd backend python app.py -
Terminal 2 - Start Frontend:
cd frontend npm start -
Open your browser: Navigate to
http://localhost:3000
- Health Monitoring: Track vitals, food intake, and medical records via RAG
- Appointment Booking: Book doctor appointments with calendar integration
- Voice Input: Record and transcribe voice messages using Whisper API
- Emergency Response: Automated 911 calling and emergency contact notification
- Follow-up Reminders: Automated check-ins after health concerns
POST /chat- Send chat messages to the AI agentPOST /check-followups- Check for pending follow-up messagesPOST /transcribe- Transcribe audio files to text
Backend:
- Flask (Python web framework)
- LangChain (AI agent framework)
- OpenAI GPT-4 (LLM)
- Pinecone (Vector database)
- Google Calendar API (Appointment scheduling)
Frontend:
- React 18
- Modern CSS with dark theme
- MediaRecorder API (Voice recording)
- Fetch API (HTTP requests)