app.py

import torch
from transformers import pipeline
import streamlit as st
import fitz  # PyMuPDF for PDF text extraction

# Load pretrained model for simplification
simplifier = pipeline("summarization", model="facebook/bart-large-cnn")

def simplify_text(text):
    """Simplifies a given academic text using a pretrained model."""
    simplified = simplifier(text, max_length=96, min_length=30, do_sample=False)
    return simplified[0]['summary_text']

def extract_text_from_pdf(pdf_file):
    """Extracts text from an uploaded PDF file stream."""
    text = ""
    with fitz.open(stream=pdf_file.read(), filetype="pdf") as doc:
        for page in doc:
            text += page.get_text()
    return text

# Streamlit UI
st.title("Text Simplification with Pretrained Model")
option = st.radio("Choose input type:", ("Text Input", "Upload PDF"))

if option == "Text Input":
    user_text = st.text_area("Enter your text:")
    if st.button("Simplify") and user_text:
        simplified_text = simplify_text(user_text)
        st.subheader("Simplified Text:")
        st.text_area("Simplified Output", simplified_text, height=150)

elif option == "Upload PDF":
    uploaded_file = st.file_uploader("Upload a PDF", type=["pdf"])
    if uploaded_file:
        extracted_text = extract_text_from_pdf(uploaded_file)
        st.subheader("Extracted Text from PDF:")
        st.text_area("Extracted Text", extracted_text, height=200)

        if st.button("Simplify Extracted Text"):
            simplified_text = simplify_text(extracted_text[:1000])  # Limit length for model input
            st.subheader("Simplified Text:")
            st.text_area("Simplified Output", simplified_text, height=150)

st.write("\nMade by Harshitha")