BrevityAI

AI-powered Document Summarization

View Demo · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Keywords
   • Installation
3. Usage
4. Contributing

About The Project

BrevityAI is an AI-powered document summarization tool that helps you quickly understand and summarize long documents. With the integration of the T5 model and a user-friendly interface, it generates concise, accurate, and context-aware summaries in multiple languages.

Key Features:

• Multilingual Summarization: Automatically generates summaries in multiple languages.
• Document Upload & Management: Securely upload and manage documents for summarization.
• Detailed Summaries: View and download summaries in a clean and readable format.
• Export Results: Export your document summaries and logs as PDFs for easy sharing.

(back to top)

Built With

• 
• 
• 
• 
• 
• 

(back to top)

Getting Started

This section explains how to set up the project locally.

Keywords

• Maximum Summary Length: Sets the maximum word count for the summary (Range: 50–500).
• Minimum Summary Length: Sets the minimum word count (Range: 10–100).
• Length Penalty: Adjusts brevity vs. coverage:
  • < 1.5: Produces concise summaries.
  • > 1.5: Generates longer summaries.
  • 1.5: Neutral balance.

Installation

1. Clone the repository:

   git clone https://github.com/mansi104-ai/BrevityAI.git
   
   cd BrevityAI

2. Setup the environment:

   python -m venv env
   
   source env/bin/activate  ( For Linux/MacOS )
   
   env\Scripts\activate     ( For Windows )
   

3. Install the dependencies :

 pip install -r requirements.txt

4. Run the application :

streamlit run main.py

5. Access the App: Open your browser and navigate to http://localhost:8501.

Usage

Follow these steps to use the Text Summarization App:

1. Launch the App:

   • Start the app by running the following command:

     streamlit run app.py

   • Open your browser and navigate to http://localhost:8501.

2. Choose Input Method:

   • File Upload:
     • Click on "Upload a file" to upload a PDF or JSON file.
     • The app extracts text from the uploaded file.
   • Manual Input:
     • Enter or paste text directly into the provided text area.

3. Customize Summary Settings:

   • Use the sliders to adjust:
     • Maximum summary length.
     • Minimum summary length.
     • Length penalty (controls brevity).
   • Default values are set for quick summarization.

4. Generate Summary:

   • Click the "Generate Summary" button.
   • Wait for the app to process and display the summary.

5. Download Summary:

   • After the summary is generated, click on the "Download Summary as PDF" button to save the summary locally.

---

Contributing

We welcome contributions to enhance the Text Summarization App! Here's how you can contribute:

Steps to Contribute

1. Fork the Repository:

   • Navigate to the GitHub repository and click Fork.

2. Clone the Forked Repository:

   • Clone the repository to your local system:

     git clone https://github.com/mansi104-ai/BrevityAI
     

3. Create a Branch:

   • Create a new branch for your feature or bug fix:

     git checkout -b feature-or-bugfix-name

4. Make Your Changes:

   • Modify the code or documentation as needed.

5. Test Your Changes:

   • Run the app locally and ensure all changes work as expected.

6. Commit and Push:

   • Commit your changes with a descriptive message:

     git add .
     git commit -m "Description of changes"

   • Push the changes to your forked repository:

     git push origin feature-or-bugfix-name

7. Create a Pull Request:

   • Open a pull request from your forked repository to the original repository.
   • Provide a clear description of your changes and the problem they solve.

---

Contribution Guidelines

• Adhere to the existing code style and conventions.
• Ensure that all dependencies are up to date.
• Document your changes clearly in the README file if applicable.
• Test your changes thoroughly before submitting a pull request.

---

We appreciate your contributions and look forward to building this app together!