setup.py

import os
import pandas as pd

def setup_project():
    """Setup the Cold Email Generator project structure"""
    
    # Create necessary directories
    directories = ["resources", "chroma_db", "templates", "static"]
    for directory in directories:
        os.makedirs(directory, exist_ok=True)
        print(f"Created directory: {directory}")
    
    # Create default portfolio CSV
    portfolio_data = {
        'Techstack': [
            'React, Node.js, MongoDB',
            'Python, FastAPI, PostgreSQL', 
            'AWS, Docker, Kubernetes',
            'Machine Learning, TensorFlow, PyTorch',
            'JavaScript, HTML5, CSS3, Bootstrap',
            'Java, Spring Boot, MySQL',
            'Python, Django, Redis, Celery',
            'Vue.js, Express.js, SQLite',
            'Flutter, Dart, Firebase',
            'Angular, TypeScript, GraphQL',
            'PHP, Laravel, Apache',
            'Ruby on Rails, PostgreSQL',
            'Go, Gin, Docker',
            'C#, .NET Core, SQL Server',
            'Scala, Akka, Cassandra'
        ],
        'Links': [
            'https://github.com/example/ecommerce-platform',
            'https://github.com/example/api-gateway-microservices',
            'https://github.com/example/cloud-infrastructure-automation',
            'https://github.com/example/ml-recommendation-system',
            'https://github.com/example/responsive-web-dashboard',
            'https://github.com/example/enterprise-inventory-system',
            'https://github.com/example/real-time-chat-application',
            'https://github.com/example/task-management-suite',
            'https://github.com/example/mobile-banking-app',
            'https://github.com/example/analytics-dashboard',
            'https://github.com/example/cms-blog-platform',
            'https://github.com/example/social-media-platform',
            'https://github.com/example/payment-processing-api',
            'https://github.com/example/healthcare-management-system',
            'https://github.com/example/data-pipeline-framework'
        ]
    }
    
    df = pd.DataFrame(portfolio_data)
    df.to_csv('resources/my_portfolio.csv', index=False)
    print("Created default portfolio CSV")
    
    # Create .env template
    env_template = """# Groq API Configuration
GROQ_API_KEY=your_groq_api_key_here

# Optional: Other configurations
DEBUG=True
LOG_LEVEL=INFO
"""
    
    with open('.env.template', 'w') as f:
        f.write(env_template)
    print("Created .env template")
    
    # Create README
    readme_content = """# Cold Email Generator

A powerful tool for service companies to streamline business outreach by generating personalized cold emails based on job listings.

## Features

- **Web Scraping**: Extract job listings from company career pages
- **AI-Powered**: Uses Llama 3.1 LLM via Groq for intelligent email generation
- **Portfolio Integration**: ChromaDB-powered portfolio matching
- **User-Friendly**: Streamlit web interface
- **Customizable**: Upload your own portfolio and templates

## Setup

1. Install dependencies:
   ```bash
   pip install -r requirements.txt
   ```

2. Set up the project:
   ```bash
   python setup.py
   ```

3. Get your Groq API key from https://console.groq.com/

4. Run the application:
   ```bash
   streamlit run app.py
   ```

## Usage

1. Enter your Groq API key in the sidebar
2. Input a company's career page URL
3. Extract job listings automatically
4. Generate personalized cold emails for each position
5. Download and use the generated emails

## Project Structure

```
cold-email-generator/
├── app.py                 # Main Streamlit application
├── requirements.txt       # Python dependencies
├── setup.py              # Project setup script
├── resources/            # Portfolio and templates
│   └── my_portfolio.csv  # Your portfolio data
├── chroma_db/           # ChromaDB vector database
└── demo.html           # Demo HTML file
```

## Technologies Used

- **Llama 3.1 LLM**: Advanced language model for email generation
- **Groq**: High-performance inference platform
- **LangChain**: Framework for LLM applications
- **Streamlit**: Web application framework
- **ChromaDB**: Vector database for portfolio matching
- **BeautifulSoup**: Web scraping capabilities

## License

MIT License
"""
    
    with open('README.md', 'w') as f:
        f.write(readme_content)
    print("Created README.md")
    
    print("\n✅ Project setup complete!")
    print("\nNext steps:")
    print("1. Install dependencies: pip install -r requirements.txt")
    print("2. Get your Groq API key from https://console.groq.com/")
    print("3. Run the app: streamlit run app.py")

if __name__ == "__main__":
    setup_project()