app.py

import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from css_template import css, bot_template, user_template
from langchain.llms import HuggingFaceHub
import os
# os.environ['FAISS_NO_AVX2'] = '1'

def method_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


def method_get_text_chunks(text):
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=7500, chunk_overlap=100)
    doc_splits = text_splitter.split_documents(text)
    return chunks


def method_get_vectorstore(text_chunks):
    # embeddings = OpenAIEmbeddings()
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore


def method_get_conversation_chain(vectorstore):
    #llm = ChatOpenAI()
    llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})

    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=vectorstore.as_retriever(),
        memory=memory
    )
    return conversation_chain


def method_handle_userinput(user_question):
    response = st.session_state.conversation({'question': user_question})
    st.session_state.chat_history = response['chat_history']

    for i, message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace(
                "{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace(
                "{{MSG}}", message.content), unsafe_allow_html=True)


def main():
    load_dotenv()
    st.set_page_config(page_title="Converse with multiple PDFs",page_icon=":books:")
    st.write(css, unsafe_allow_html=True)

    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header("Converse with multiple PDFs :books:")
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        method_handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Documents Upload")
        pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Submit'", accept_multiple_files=True)
        if st.button("Submit"):
            with st.spinner("Processing"):
                # get pdf text
                raw_text = method_get_pdf_text(pdf_docs)
                # get the text chunks
                text_chunks = method_get_text_chunks(raw_text)
                # create vector store
                vectorstore = method_get_vectorstore(text_chunks)
                st.write(text_chunks)
                # create conversation chain
                st.session_state.conversation = method_get_conversation_chain(vectorstore)
                


if __name__ == '__main__':
    main()