PDF to Jupyter Notebook Converter

A powerful Python tool that converts instructional PDF documents into executable Jupyter notebooks, using Groq's LLM API to intelligently detect and separate code blocks from explanatory text.

Features

• PDF Text Extraction: Extract text content from PDF documents
• AI-powered Content Processing: Uses Groq's LLM (llama3-70b-8192) to intelligently parse content
• Smart Code Detection: Advanced algorithm to identify Python code blocks even when not explicitly marked
• Post-processing Pipeline: Robust processing to ensure code blocks remain complete and logically grouped
• Clean Output: Well-formatted Jupyter notebook with alternating markdown and code cells

Installation

Prerequisites

• Python 3.7+
• Groq API key (sign up here)

Setup

1. Clone the repository:

   git clone https://github.com/yourusername/pdf-to-notebook.git
   cd pdf-to-notebook
   

2. Install the required dependencies:

   pip install -r requirements.txt
   

3. Set your Groq API key:

   # Option 1: Set as environment variable
   export GROQ_API_KEY="your-groq-api-key-here"
   
   # Option 2: Create a .env file (requires python-dotenv)
   echo "GROQ_API_KEY=your-groq-api-key-here" > .env
   

Usage

Basic Usage

Convert a PDF file to a Jupyter notebook:

python pdf_to_notebook.py path/to/your/document.pdf

This will create a new notebook file with the same name as your PDF in the current directory.

Advanced Options

python pdf_to_notebook.py path/to/your/document.pdf --output output/notebook.ipynb --model llama3-70b-8192

Command Line Arguments

• pdf_path: Path to the PDF file (required)
• --output, -o: Output path for the notebook (optional, defaults to the PDF name with .ipynb extension)
• --api-key: Groq API key (optional if set as environment variable)
• --model: Groq model to use (optional, defaults to "llama3-70b-8192")

How It Works

1. PDF Extraction: The tool extracts raw text from the PDF document
2. Text Processing: The content is segmented into manageable chunks
3. AI Analysis: Each chunk is sent to Groq's API with a specialized prompt for code/text separation
4. Post-Processing: The responses are processed to ensure code blocks remain complete
5. Notebook Creation: A properly formatted Jupyter notebook is generated

Example

Converting a Python tutorial PDF:

python pdf_to_notebook.py python_basics.pdf

Output:

Extracting text from PDF...
Processing content with Groq...
Processing chunks with Groq: 100%|██████████| 3/3 [00:12<00:00, 4.12s/chunk]
Creating Jupyter notebook...
Notebook created successfully: python_basics.ipynb
Total cells created: 28 (12 code, 16 markdown)

Limitations

• PDF formatting can affect extraction quality (especially for complex layouts)
• Some code blocks with unusual formatting might not be perfectly detected
• Very large PDFs may require significant processing time
• The quality of the output depends partly on the clarity of the input PDF

Contributing

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

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

• PyPDF2 for PDF parsing
• Groq for their fast and powerful LLM API
• nbformat for Jupyter notebook creation