app.py

import streamlit as st
from dotenv import load_dotenv
from pypdf import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template


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


def get_vectorstore(text_chunks):
    embeddings = OpenAIEmbeddings()
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore


def get_text_chunks(raw_text):
    text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len)
    chunks = text_splitter.split_text(raw_text)
    return chunks


def get_conversation_chain(vectorstore):
    llm = ChatOpenAI()
    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 handle_user_input(user_question):
    if st.session_state.conversation is None:
        st.error("Please upload file(s) and Process them before asking questions.")
        return

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

    # Reverse the chat history
    reversed_messages = st.session_state.chat_history[::-1]

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


def main():
    load_dotenv()
    st.set_page_config(page_title='Chat with Documents', 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

    if "input_disabled_state" not in st.session_state:
        st.session_state.input_disabled_state = True

    st.header("Chat with multiple PDFs :books:")
    user_question = st.text_input("Ask a question about your documents:",
                                  disabled=st.session_state.input_disabled_state)

    if user_question:
        handle_user_input(user_question)

    with st.sidebar:
        st.subheader("Your Documents")
        pdf_docs = st.file_uploader("Upload Your PDF Documents", accept_multiple_files=True)

        if not pdf_docs:
            st.error("Please upload PDF documents to continue")

        if st.button("Process"):
            with st.spinner("Processing"):
                # Get PDF Text
                raw_text = get_pdf_text(pdf_docs)

                # Get the text chunks
                text_chunks = get_text_chunks(raw_text)

                # Create the vector store with embeddings
                vectorstore = get_vectorstore(text_chunks)

                # Conversation Chain
                st.session_state.conversation = get_conversation_chain(vectorstore)

    st.session_state.input_disabled_state = False


if __name__ == '__main__':
    main()