Textify

Overview

Welcome to Textify! Textify extracts text from images and compiles them into searchable PDFs, facilitating efficient Document Management and accessibility in applications requiring Image Text Extraction. Whether you are a developer or contributor, this README.md will guide you through the essentials of the project.

Table of Content

1. Introduction
2. Getting Started
3. Installation
4. Contribution

Introduction

Textify leverages EasyOCR for Image Text Extraction, integrates OpenAI's language model for text formatting, and converts the extracted text into PDFs. It offers a seamless solution for converting images to formatted PDF Documents with enhanced accuracy and efficiency.

Getting Started

Before diving into the project, ensure you have the following prerequisites:

• Programming Language: Python 3.X
• Package Manager: pip
• Version Control: Git
• Integrated Development Environment: Visual Studio Code, PyCharm

Installation

1. Clone Repository

   https://github.com/Arko-Sengupta/Textify.git

2. Navigate to the Project Directory

   cd/<Project-Directory>

3. Create .env.local inside <Project-Directory>.

4. Add below to .env.local file

   API_KEY=<Your-OpenAI-API-Key>

5. Install Dependencies

   pip install -r requirements.txt

6. Start Backend Server

   python ImageToFormat_API.py

7. Confirm Server Start: Open the below URL at Browser: http://localhost:5000/

8. Start the Application

   streamlit run App.py

Contribution

If you'd like to contribute, follow the guidelines

• Create a branch using the format Textify_<YourUsername> when contributing to the project.
• Add the label Contributor to your contributions to distinguish them within the project.