pdfgenius 0.1.0

No project description provided

PDF GENIUS

PDF GENUIS is a powerful Python package that converts PDF documents into text using AI-powered optical character recognition (OCR). It currently supports both Google's Gemini and OpenAI's GPT-4 Vision models for text extraction, with an extensible architecture that makes it easy to add support for additional AI models.

Features

• Extract text from PDF documents using state-of-the-art AI models
• Support for multiple AI providers (Gemini and OpenAI)
• Secure local storage of API keys
• Command-line interface (CLI) for easy use
• Extensible architecture for adding new AI models
• Automatic handling of multi-page PDFs
• Clean temporary file management

Installation

You can install the package using pip:

pip install pdfgenius

The package requires Python 3.7 or later.

System Dependencies

This package requires Poppler for PDF processing. Install it based on your operating system:

• Linux (Ubuntu/Debian):

  sudo apt-get install poppler-utils
  

• macOS:

  brew install poppler
  

• Windows: Download and install poppler from poppler releases, then add the bin directory to your system PATH.

Quick Start

Extract text from a PDF using the default Gemini model:

# Store your API key (one-time setup)
extract-pdf keys add gemini "your-gemini-api-key"

# Extract text from PDF
extract-pdf extract document.pdf

API Key Management

The package provides secure local storage for your API keys. You can manage them using these commands:

# Add an API key
extract-pdf keys add gemini "your-gemini-api-key"
extract-pdf keys add openai "your-openai-api-key"

# List stored keys (shows partial keys for security)
extract-pdf keys list

# Delete a stored key
extract-pdf keys delete gemini

Command Line Usage

Basic Usage

# Extract using default settings (Gemini model)
extract-pdf extract document.pdf

# Specify output file
extract-pdf extract document.pdf -o output.txt

# Use OpenAI model
extract-pdf extract document.pdf -m openai

# Provide API key directly (without storing)
extract-pdf extract document.pdf -m openai --api-key "your-api-key"

Full Command Reference

# Show help
extract-pdf --help

# Show help for extract command
extract-pdf extract --help

# Show help for key management
extract-pdf keys --help

Python API

You can also use the package programmatically in your Python code:

from pdf_extractor import GeminiExtractor, OpenAIExtractor
from pdf_extractor.utils import process_pdf

# Using Gemini
extractor = GeminiExtractor(api_key="your-api-key")
extractor.initialize_client()
text = process_pdf("document.pdf", extractor)

# Using OpenAI
extractor = OpenAIExtractor(api_key="your-api-key")
extractor.initialize_client()
text = process_pdf("document.pdf", extractor)

Adding Support for New AI Models

The package is designed to be easily extensible. To add support for a new AI model:

1. Create a new extractor class that inherits from BaseExtractor
2. Implement the required methods
3. Register the new extractor in the CLI

Example:

from pdf_extractor.extractors.base import BaseExtractor

class NewModelExtractor(BaseExtractor):
    def initialize_client(self):
        # Initialize your AI client
        pass

    def extract_text_from_image(self, image_path: Path) -> str:
        # Implement text extraction logic
        pass

Security

• API keys are stored encrypted in the user's home directory
• The encryption key is stored separately
• Only partial keys are displayed when listing stored keys
• Keys can be easily deleted when no longer needed

Environment Variables

The package also supports providing API keys through environment variables:

export GEMINI_API_KEY="your-gemini-api-key"
export OPENAI_API_KEY="your-openai-api-key"

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

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

Acknowledgments

This package uses several open-source libraries:

• pdf2image for PDF processing
• google-generativeai for Gemini API
• openai for OpenAI API
• click for CLI interface
• cryptography for secure key storage

Support

If you encounter any issues or have questions, please file an issue on the GitHub repository.