app.py

import fitz  # PyMuPDF
import gradio as gr

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[:3000]  # Show only the first 3000 characters for now

gr.Interface(
    fn=extract_text_from_pdf,
    inputs=gr.File(file_types=[".pdf"]),
    outputs="text",
    title="📄 JEE PDF Extractor"
).launch()