API LangGraph - React Code Generation API

This project provides an API service that generates React TypeScript code based on natural language descriptions. It uses LangGraph for workflow management and GPT-4o for code generation.

Features

• Generate complete React TypeScript applications from text descriptions
• Automatic styling with Tailwind CSS
• Streaming API responses
• Modern code generation with best practices
• Type-safe code generation
• Responsive design patterns

Getting Started

Prerequisites

• Python 3.8 or higher
• Node.js 16 or higher
• OpenAI API key

Installation

1. Clone the repository:

git clone https://github.com/yourusername/api-langraph.git
cd api-langraph

2. Install Python dependencies:

pip install -r requirements.txt

3. Set up environment variables:

cp .env.example .env
# Edit .env and add your OpenAI API key

Running the API

1. Start the FastAPI server:

uvicorn main:app --reload

2. The API will be available at http://localhost:8000

API Endpoints

POST /generate-code

Generates React TypeScript code based on a description.

Request Body:

{
  "description": "string"
}

Response: Server-sent events stream with the following format:

{
  "description": "string",
  "code": "string (JSON with file contents)",
  "status": "string",
  "review_feedback": "string"
}

GET /health

Health check endpoint.

Response:

{
  "status": "healthy"
}

Testing

Run the test script to verify the API functionality:

python test_api.py

Project Structure

• main.py - FastAPI application and API endpoints
• workflow.py - LangGraph workflow definition and code generation logic
• test_api.py - API testing script
• requirements.txt - Python dependencies

Generated Code Structure

The API generates a complete React TypeScript project with the following structure:

src/
  ├── App.tsx
  ├── index.tsx
  ├── App.css
  ├── index.css
  └── react-app-env.d.ts
public/
  └── index.html
package.json
tsconfig.json
tailwind.config.js
postcss.config.js
.gitignore

Error Handling

The API includes comprehensive error handling:

• Invalid JSON format detection
• Missing required files validation
• Code generation error handling
• API request/response validation

Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some 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.

Acknowledgments

• OpenAI for GPT-4o
• LangGraph for workflow management
• FastAPI for the web framework
• React and TypeScript communities