app.py

import streamlit as st 
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader
from transformers import T5Tokenizer, T5ForConditionalGeneration
from transformers import pipeline
import torch
import base64
import tempfile
import os


checkpoint = "MBZUAI/LaMini-Flan-T5-248M"
#model and tokenizer loading

tokenizer = T5Tokenizer.from_pretrained(checkpoint)
with tempfile.TemporaryDirectory() as offload_folder:
    base_model = T5ForConditionalGeneration.from_pretrained(checkpoint, device_map='auto', torch_dtype=torch.float32, offload_folder=offload_folder)

#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,
        max_length = 500, 
        min_length = 50)
    input_text = file_preprocessing(filepath)
    result = pipe_sum(input_text)
    result = result[0]['summary_text']
    return result

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"):
            col2 = st.columns(1)
            # Use a temporary filename directly
            with tempfile.NamedTemporaryFile(delete=False) as temp_file:
                temp_file.write(uploaded_file.read())
                temp_file.flush()  # Ensure contents are written to disk
                filepath = temp_file.name
                       
                try:
                    summary = llm_pipeline(filepath)
                    st.success(summary)  # Display only the summary
                except Exception as e:
                    st.error(f"An error occurred during summarization: {e}")
            # Clean up the temporary file
            os.remove(filepath)




if __name__ == "__main__":
    main()