PDF Chatter

Unknown

This is a pretty quick CLI program I threw together leveraging LLMs to perform Q&A over extracted PDF text. It uses Nougat-OCR to extract the text from the PDF, and then uses GPT-4 to answer questions about the text. The entire interface is run via a simple REPL in the terminal.

Example

PDF Chatter Demo

Getting Started

To get started, you can install the package from PyPI:

pip install pdf-chatter

Then you can run the program with the following command:

pdf-chatter path/to/pdf

Which will drop you into a REPL where you can ask questions about your PDF.

Links