app.py

import gradio as gr
from transformers import pipeline
import fitz  # PyMuPDF

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

# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
    doc = fitz.open(stream=pdf_file.read(), filetype="pdf")
    text = ""
    for page in doc:
        text += page.get_text()
    return text

# Combine everything into one function
def summarize_pdf(pdf_file):
    try:
        text = extract_text_from_pdf(pdf_file)
        if len(text.strip()) == 0:
            return "The PDF seems empty or text is not extractable."
        # Truncate long text (BART model has ~1024 token limit)
        text = text[:3000]
        summary = summarizer(text, max_length=150, min_length=40, do_sample=False)
        return summary[0]['summary_text']
    except Exception as e:
        return f"Error: {str(e)}"

# Gradio Interface
demo = gr.Interface(
    fn=summarize_pdf,
    inputs=gr.File(label="Upload PDF of Academic Notes"),
    outputs=gr.Textbox(label="Summarized Notes"),
    title="📄 Academic Note Summarizer (PDF)",
    description="Upload your academic notes in PDF format. The app will extract and summarize the content using a Hugging Face model."
)

demo.launch()