gptscript-ai/pdf-tool

GPTScript tool to parse PDFs with Cloud OCR offerings.

PDF Tools

Overview

This repository contains a collection of lower level tools to work with PDF files using major cloud provider OCR tools. Each of the tools will extract one page at a time from the PDF file and send it to the OCR service. The extracted text will be consumed by the LLM.

Tools

• Azure - Uses Computer Vision
• Google - Uses Vision API
• AWS - Uses Textract
• OpenAI GPT-4o