PDFProc is a seamless way to extract, transform, and reassemble (ETR) data stored in PDF documents. For now, PDFProc uses OpenAI's ChatGPT 3.5-turbo LLM via Q&A + Lang Chain to return data based on the relationship with identified tags.
- Ensure requirements are installed (virtual environment recommended).
- Run
python main.pyin your terminal. - Coming soon
