from pypdf import PdfReader
import streamlit as st

def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_reader.pages:
            text += page.extract_text()
    return text

raw_text=""
with st.sidebar:
        st.title("Menu:")
        pdf_docs = st.file_uploader(
            "Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True
        )
        if st.button("Submit & Process"):
         with st.spinner("Processing..."):
            raw_text = get_pdf_text(pdf_docs)

# st.write(raw_text)

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

# Load the pre-trained tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn")
model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn")

# Tokenize the text
inputs = tokenizer(raw_text, return_tensors="pt", max_length=1024, truncation=True)

# Generate the summary
summary_ids = model.generate(inputs["input_ids"], num_beams=4, min_length=30, max_length=200, early_stopping=True)

# Decode the summary
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)

st.write("\n\nSummary:\n", summary)
st.write("\n\n\nOriginal text:\n", raw_text)