Azure OpenAI Function App

A serverless Azure Functions application built with TypeScript that provides a chat interface powered by Azure OpenAI and RAG (Retrieval-Augmented Generation) capabilities.

🚀 Features

• Serverless Architecture: Built on Azure Functions for scalable, cost-effective deployment
• RAG Integration: Connects to Azure RAG endpoint for enhanced AI responses
• TypeScript: Fully typed for better development experience and code reliability
• HTTP Triggered: RESTful API endpoint for chat interactions
• Error Handling: Comprehensive error handling and logging

📋 Prerequisites

• Node.js (v18 or later)
• Azure Functions Core Tools
• Azure CLI (for deployment)
• Azure subscription with access to:
  • Azure Functions
  • Azure OpenAI Service
  • Azure RAG endpoint

🛠️ Installation

1. Clone the repository

   git clone <repository-url>
   cd azure-openai-fn

2. Install dependencies

   npm install

3. Configure environment variables

   Create a .env file in the root directory:

   AZURE_RAG_ENDPOINT=<your-rag-endpoint-url>
   AZURE_RAG_API_KEY=<your-rag-api-key>

🏃‍♂️ Local Development

1. Build the project

   npm run build

2. Start the function app locally

   npm start

3. Test the endpoint

   The chat handler will be available at:

   POST http://localhost:7071/api/chatHandler
   

   Example request:

   {
     "message": "Hello, how can you help me?"
   }

   Example response:

   {
     "answer": "I'm an AI assistant powered by Azure OpenAI..."
   }

📁 Project Structure

azure-openai-fn/
├── src/
│   └── functions/
│       └── chatHandler.ts      # Main chat function handler
├── host.json                   # Azure Functions host configuration
├── package.json               # Dependencies and scripts
├── tsconfig.json              # TypeScript configuration
└── README.md                  # This file

🔧 Available Scripts

• npm run build - Compile TypeScript to JavaScript
• npm run watch - Watch for changes and recompile
• npm run clean - Remove compiled output
• npm start - Build and start the function locally
• npm test - Run tests (placeholder)

🌐 API Reference

POST /api/chatHandler

Chat with the AI assistant using RAG-enhanced responses.

Request Body:

{
  "message": "Your question or message here"
}

Response:

{
  "answer": "AI-generated response"
}

Error Responses:

• 400 Bad Request - Invalid JSON or missing message
• 500 Internal Server Error - RAG endpoint error or server issue

🚀 Deployment

Deploy to Azure

1. Login to Azure

   az login

2. Create a Function App

   az functionapp create \
     --resource-group <resource-group-name> \
     --consumption-plan-location <location> \
     --runtime node \
     --runtime-version 18 \
     --functions-version 4 \
     --name <function-app-name> \
     --storage-account <storage-account-name>

3. Configure application settings

   az functionapp config appsettings set \
     --name <function-app-name> \
     --resource-group <resource-group-name> \
     --settings \
     AZURE_RAG_ENDPOINT=<your-rag-endpoint> \
     AZURE_RAG_API_KEY=<your-rag-api-key>

4. Deploy the function

   func azure functionapp publish <function-app-name>

🔐 Security Considerations

• API Keys: Store sensitive information like API keys in Azure Key Vault or Function App settings
• Authentication: Consider implementing authentication for production use
• CORS: Configure CORS settings if accessed from web applications
• Rate Limiting: Implement rate limiting to prevent abuse

🔍 Monitoring and Logging

The function app includes:

• Application Insights integration for monitoring
• Structured logging for debugging
• Error tracking and performance metrics

Monitor your function in the Azure portal under:

• Function App → Monitor
• Application Insights → Logs

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

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

🆘 Troubleshooting

Common Issues

1. Build Errors

   • Ensure TypeScript is installed: npm install -g typescript
   • Check Node.js version compatibility

2. Function Not Starting

   • Verify Azure Functions Core Tools installation
   • Check host.json configuration

3. RAG Endpoint Errors

   • Verify endpoint URL and API key
   • Check network connectivity
   • Review Azure OpenAI service status

4. Environment Variables

   • Ensure .env file is in the root directory
   • Check variable names match exactly

Getting Help

• Check the Azure Functions documentation
• Review Azure OpenAI documentation
• Open an issue in this repository

---

Built with ❤️ using Azure Functions and TypeScript