docapp.py

import streamlit as st
from langchain.text_splitter import CharacterTextSplitter
from langchain.docstore.document import Document
from langchain.chains.summarize import load_summarize_chain
from langchain_community.llms import CTransformers
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from pypdf import PdfReader

# Page title
st.set_page_config(page_title='🦜🔗 Text Summarization App')
st.title('🦜🔗 Text Summarization App')

# Function to read all PDF files and return text
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

# Function to split the text into smaller chunks and convert it into document format
def chunks_and_document(txt):
    text_splitter = CharacterTextSplitter() 
    texts = text_splitter.split_text(txt) 
    docs = [Document(page_content=t) for t in texts] 
    return docs

# Loading the Llama 2's LLM
def load_llm():
    # We instantiate the callback with a streaming stdout handler
    callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])   

    # Loading the LLM model
    llm = CTransformers(
        model="llama-2-7b-chat.ggmlv3.q2_K.bin",
        model_type="llama",
        config={'max_new_tokens': 600,
                              'temperature': 0.5,
                              'context_length': 700}
    )
        
    return llm

# Function to apply the LLM model with our document 
def chains_and_response(docs):
    llm = load_llm()
    chain = load_summarize_chain(llm, chain_type='map_reduce')
    return chain.invoke(docs)

def main():
    # Initialize messages if not already present
    if "messages" not in st.session_state.keys():
        st.session_state.messages = []

    # Sidebar for uploading PDF files
    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..."):
                txt_input = get_pdf_text(pdf_docs)
                docs = chunks_and_document(txt_input)
                response = chains_and_response(docs)
                st.title('📝✅ Summarization Result')
                for res in response:
                    st.info(res)

main()