app.py

import base64
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
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 htmlTemplates import css, bot_template, user_template
from langchain.llms import HuggingFaceHub


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


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


def 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 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 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 displayPDF(upl_file):
    # Read file as bytes:
    bytes_data = upl_file.getvalue()

    # Convert to utf-8
    base64_pdf = base64.b64encode(bytes_data).decode("utf-8")

    # Embed PDF in HTML
    # pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width={str(width)} height={str(width*4/3)} type="application/pdf"></iframe>'
    pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="700" height="1000" type="application/pdf"></iframe>'
    # Display file
    st.markdown(pdf_display, unsafe_allow_html=True)


def main():
    st.set_page_config(
        page_title="Chat with multiple PDFs", page_icon=":books:", layout="wide"
    )
    load_dotenv()
    st.write(css, unsafe_allow_html=True)
    col1, col2 = st.columns(spec=[4, 3])
    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
    with col2:
        st.header("Chat with multiple PDFs :books:")
        user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'")

        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 vector store
                vectorstore = get_vectorstore(text_chunks)

                # create conversation chain
                st.session_state.conversation = get_conversation_chain(vectorstore)

    if pdf_docs:
        with col1:
            displayPDF(pdf_docs)


if __name__ == "__main__":
    main()