PyZerox Demo

A demonstration project showcasing the usage of PyZerox library for processing PDF documents using GPT-4 models.

🚀 Features

• PDF document processing
• Integration with GPT-4 models
• Asynchronous operation
• Configurable page selection
• Custom system prompts support

📋 Prerequisites

• Python 3.7+
• OpenAI API key
• Internet connection for accessing remote PDF files

🔧 Installation

1. Clone the repository:

git clone https://github.com/felipefontoura/pyzerox-demo.git
cd pyzerox-demo

2. Install dependencies:

pip install -r requirements.txt

3. Set up your OpenAI API key on .env file.

🎯 Usage

The main script demonstrates how to process a PDF file using PyZerox:

import asyncio
from pyzerox import zerox

async def main():
    result = await zerox(
        file_path="your_pdf_url",
        model="gpt-4o-mini",
        output_dir="./tmp"
    )
    return result

result = asyncio.run(main())

⚙️ Configuration

The following parameters can be configured:

• file_path: URL or local path to the PDF file
• model: The GPT model to use (default: "gpt-4o-mini")
• output_dir: Directory for output files
• custom_system_prompt: Optional custom system prompt
• select_pages: Optional page selection (None for all pages)

📦 Dependencies

• py-zerox==0.0.7

🤝 Contributing

Contributions, issues, and feature requests are welcome! Feel free to check issues page.

📝 License

This project is licensed under the MIT License.