app.py

import gradio as gr
from transformers import pipeline
import PyPDF2

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

def summarize_pdf(pdf_file):
    try:
        # Extract text from the uploaded PDF
        pdf_reader = PyPDF2.PdfReader(pdf_file)
        text = ""
        for page in pdf_reader.pages:
            text += page.extract_text()
        
        # Check if text was extracted
        if not text.strip():
            return "❌ Could not extract text from the PDF. Please upload a valid document."

        # Summarize the extracted text
        summary = summarizer(text, max_length=300, min_length=50, do_sample=False)
        return summary[0]['summary_text']

    except Exception as e:
        return f"❌ An error occurred: {str(e)}"

# Create the Gradio interface
interface = gr.Interface(
    fn=summarize_pdf,
    inputs=gr.inputs.File(label="Upload PDF"),
    outputs=gr.outputs.Textbox(label="Summary"),
    title="PDF Summarizer",
    description="Upload a PDF file to extract and summarize its content using state-of-the-art AI."
)

interface.launch()