app1.py

import streamlit as st
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
import torch
import base64
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import PyPDFLoader

# Model and tokenizer loading
# model_name ="google/pegasus-large" # good
# model_name = "t5-large" # good
model_name = "facebook/bart-large"
tokenizer = AutoTokenizer.from_pretrained(model_name)
base_model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

# File loader and preprocessing
def file_preprocessing(file):
    loader = PyPDFLoader(file)
    pages = loader.load_and_split()
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=200, chunk_overlap=50)
    texts = text_splitter.split_documents(pages)
    final_texts = ""
    for text in texts:
        print(text)
        final_texts = final_texts + text.page_content
    return final_texts

# LLM pipeline
def llm_pipeline(filepath):
    pipe_sum = pipeline(
        'summarization',
        model=base_model,
        tokenizer=tokenizer,
        min_length=50
    )
    input_text = file_preprocessing(filepath)
    result = pipe_sum(input_text)
    result = result[0]['summary_text']
    return result

# Function to display the PDF of a given file
def displayPDF(file):
    # Opening file from file path
    with open(file, "rb") as f:
        base64_pdf = base64.b64encode(f.read()).decode('utf-8')
    # Embedding PDF in HTML
    pdf_display = F'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
    # Displ aying File
    st.markdown(pdf_display, unsafe_allow_html=True)

# Streamlit code
st.set_page_config(layout="wide")

def main():
    st.title("Document Summarization App")
    uploaded_file = st.file_uploader("Upload your PDF file", type=['pdf'])
    if uploaded_file is not None:
        if st.button("Summarize"):
            col1, col2 = st.columns(2)
            filepath = "data/" + uploaded_file.name
            with open(filepath, "wb") as temp_file:
                temp_file.write(uploaded_file.read())
            with col1:
                st.info("Uploaded File")
                pdf_view = displayPDF(filepath)
            with col2:
                summary = llm_pipeline(filepath)
                st.info("Summarization Complete")
                st.success(summary)

if __name__ == "__main__":
    main()