text-summarizer

Overview

The Text Summarizer project is a Django-based web application that leverages AI to generate concise summaries of long texts. It uses the Facebook BART model for high-quality text summarization, ensuring that key information is preserved while reducing the overall length of the input text.

Features

• Web Interface: A user-friendly interface to input text and view summaries.
• AI-Powered Summarization: Utilizes the transformers library and the BART model for accurate and efficient text summarization.
• API Support: Provides an API endpoint for programmatic access to the summarization functionality.
• Customizable Model: Includes a pre-trained model that can be fine-tuned or replaced with other summarization models.

Installation

1. Clone the repository:

   git clone <repository-url>
   cd text-summarizer

2. Set up a virtual environment:

   python3 -m venv venv
   source venv/bin/activate

3. Install dependencies:

   pip install -r requirements.txt

4. Apply migrations:

   python manage.py migrate

5. Start the development server:

   python manage.py runserver

6. Access the application at http://127.0.0.1:8000/.

Usage

Web Interface

1. Navigate to the home page.
2. Paste your text into the input box.
3. Click "Generate Summary" to view the summarized text.

API

• Endpoint: /api/summarize/
• Method: POST
• Payload: { "text": "Your text here" }
• Response: { "summary": "Summarized text" }

Example usage

• Using Curl

curl -X POST "http://localhost:8000/api/v1/summarize/" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Your long text here...",
    "max_length": 150,
    "min_length": 40
  }'

• Using javascript(fetch Api)

const summarizeText = async (text) => {
  const response = await fetch('/api/v1/summarize/', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      text: text,
      max_length: 150,
      min_length: 40
    })
  });
  
  return await response.json();
};

// Usage
summarizeText("Your long article text...")
  .then(data => console.log(data))
  .catch(error => console.error('Error:', error));

• Using Python requests library

import requests

api_url = "http://localhost:8000/api/v1/summarize/"
data = {
    "text": "Your long text here...",
    "max_length": 150,
    "min_length": 40
}

response = requests.post(api_url, json=data)
print(response.json())

• Check Api status

curl http://localhost:8000/api/v1/status/

Project Structure

• summarizer/: Contains Django project settings and configurations.
• text/: Main app for text summarization, including views, templates, and services.
• my_summarizer_model/: Directory for the pre-trained summarization model.
• templates/: HTML templates for the web interface.

Model Details

The project uses the facebook/bart-large-cnn model from Hugging Face's Transformers library. The model is downloaded and saved locally for efficient reuse.

License

This project is licensed under the MIT License.