app.py

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

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

# Function to extract text from the uploaded PDF
def extract_text_from_pdf(pdf_file):
    doc = fitz.open(pdf_file.name)  # ✅ Use file path instead of .read()
    text = ""
    for page in doc:
        text += page.get_text()
    return text

# Function to summarize the extracted text
def summarize_pdf(pdf_file):
    try:
        text = extract_text_from_pdf(pdf_file)
        if len(text.strip()) == 0:
            return "❌ The PDF seems empty or has no extractable text."
        text = text[:3000]  # Truncate to fit within model's token limit
        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 UI
demo = gr.Interface(
    fn=summarize_pdf,
    inputs=gr.File(label="📄 Upload PDF of Academic Notes", type="file"),
    outputs=gr.Textbox(label="📝 Summarized Notes"),
    title="📚 Academic Note Summarizer",
    description="Upload a PDF of your academic notes. The app extracts and summarizes the content using a Hugging Face transformer model."
)

# Launch the app
demo.launch()