https://github.com/ynstf/automated-document-analysis-and-question-generation

Explore automated document processing with OCR techniques and utilize GPT-3.5-turbo for generating insightful questions and answers. Enhance your document analysis workflow with this versatile Python project.
https://github.com/ynstf/automated-document-analysis-and-question-generation

Last synced: about 2 months ago
JSON representation

Explore automated document processing with OCR techniques and utilize GPT-3.5-turbo for generating insightful questions and answers. Enhance your document analysis workflow with this versatile Python project.

• Host: GitHub
• URL: https://github.com/ynstf/automated-document-analysis-and-question-generation
• Owner: ynstf
• Created: 2024-01-18T14:45:59.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-01-18T15:00:51.000Z (over 2 years ago)
• Last Synced: 2025-02-28T10:38:06.079Z (over 1 year ago)
• Language: Python
• Size: 2.76 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# OCR-QA Project

Automate document analysis and question generation using Optical Character Recognition (OCR) techniques and OpenAI's GPT-3.5-turbo model.

input:

![pdf](https://github.com/ynstf/Automated-Document-Analysis-and-Question-Generation/assets/107154559/64ac355c-c6ab-408d-8f23-1f34e57c1543)

output:

![Capture](https://github.com/ynstf/Automated-Document-Analysis-and-Question-Generation/assets/107154559/07e84483-c586-4a87-b146-14b9b6951284)

## Overview

This project utilizes PyPDFium, EasyOCR, Tesseract, and OpenAI's GPT-3.5-turbo to extract text from images and generate insightful questions and answers based on the content. Enhance your document analysis workflow with this versatile Python project.

## Features

- **OCR Techniques:** Utilize PyPDFium, EasyOCR, and Tesseract for efficient text extraction from images.

- **Question Generation:** Leverage GPT-3.5-turbo to automatically generate questions based on extracted text.

- **Versatile Usage:** Easily adapt the project for various document types and languages.

## Getting Started

1. Clone the repository:

    ```bash

    git clone https://github.com/ynstf/Automated-Document-Analysis-and-Question-Generation.git

    cd OCR-QA-Project

    ```

2. Install dependencies:

    ```bash

    pip install -r requirements.txt

    ```

3. Set up your environment variables:

    ```bash

    # Add your OpenAI GPT-3.5-turbo API key to the .env file

    echo "chatgpt_token=your-api-key" > .env

    ```

4. Run the script:

   **This module is much faster with a GPU.**

    ```bash

    python main.py

    ```