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 pdf_to_text(pdf_file):
    """Extract text from a PDF file."""
    text = ""
    try:
        with open(pdf_file, 'rb') as file:
            reader = PyPDF2.PdfReader(file)
            for page in reader.pages:
                page_text = page.extract_text()
                if page_text:  # Only add non-empty pages
                    text += page_text + "\n"
    except Exception as e:
        return f"Error reading PDF: {str(e)}"
    return text.strip()

def summarize_pdf(pdf_file):
    """Summarize the content of a PDF file."""
    text = pdf_to_text(pdf_file)
    if len(text) == 0:
        return "No text found in the PDF."

    # Check if the text is too short for summarization
    if len(text) < 50:  # Adjust this threshold if necessary
        return "The text extracted is too short for summarization."

    # Split text if it's too long
    max_input_length = 1024  # BART's maximum token length
    text_chunks = [text[i:i + max_input_length] for i in range(0, len(text), max_input_length)]

    # Attempt to summarize the text
    summaries = []
    for chunk in text_chunks:
        try:
            summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
            summaries.append(summary[0]['summary_text'])
        except Exception as e:
            return f"Error summarizing text: {str(e)}"

    return "\n\n".join(summaries)  # Join summaries from chunks

# Create a Gradio interface
interface = gr.Interface(
    fn=summarize_pdf,
    inputs=gr.File(label="Upload a PDF file"),
    outputs=gr.Textbox(label="Summary", lines=10),
    title="PDF Summarizer - by Atif Kazmi",
    description="Upload a PDF file to receive a summary."
)

# Launch the interface
if __name__ == "__main__":
    interface.launch()