app.py

import os
from flask import Flask, request, render_template, jsonify
import pdfplumber
from transformers import pipeline
import torch

app = Flask(__name__)
app.config['UPLOAD_FOLDER'] = 'uploads'
app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16MB max file size

# Ensure upload directory exists
os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)

# Initialize the summarization pipeline
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")

def extract_text_from_pdf(pdf_path):
    text = ""
    with pdfplumber.open(pdf_path) as pdf:
        for page in pdf.pages:
            text += page.extract_text() or ""
    return text

def generate_review(text):
    # Split text into chunks that fit within model's max token limit
    max_chunk_length = 1024
    chunks = [text[i:i + max_chunk_length] for i in range(0, len(text), max_chunk_length)]
    
    summaries = []
    for chunk in chunks:
        if len(chunk.strip()) > 100:  # Only process chunks with substantial content
            summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
            summaries.append(summary[0]['summary_text'])
    
    return " ".join(summaries)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/upload', methods=['POST'])
def upload_file():
    if 'file' not in request.files:
        return jsonify({'error': 'No file part'}), 400
    
    file = request.files['file']
    if file.filename == '':
        return jsonify({'error': 'No selected file'}), 400
    
    if file and file.filename.lower().endswith('.pdf'):
        filepath = os.path.join(app.config['UPLOAD_FOLDER'], file.filename)
        file.save(filepath)
        
        try:
            # Extract text from PDF
            text = extract_text_from_pdf(filepath)
            
            # Generate review
            review = generate_review(text)
            
            # Clean up
            os.remove(filepath)
            
            return jsonify({'review': review})
        except Exception as e:
            return jsonify({'error': str(e)}), 500
    
    return jsonify({'error': 'Invalid file type'}), 400

if __name__ == '__main__':
    app.run(debug=True, host='0.0.0.0', port=5000)