import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.chat_models import ChatOpenAI

from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template, hide_st_style, footer
from langchain_community.llms import HuggingFaceHub
from matplotlib import style


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


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()
    print("HuggingFaceInstructEmbeddings")
    model_kwargs = {'device': 'cpu', 'weights_only': True}
    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl", model_kwargs=model_kwargs)
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    print("FAISS.from_texts")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    print("returning vectorstore")
    return vectorstore


def get_conversation_chain(vectorstore):
    # llm = ChatOpenAI()
    llm = HuggingFaceHub(repo_id="google/flan-t5-base", 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):
    if st.session_state.conversation is None:
        st.error("Please upload PDF data before starting the chat.")
        return

    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="Talk with PDF",
                       page_icon="icon.png")
    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("Chat with AI with Custom Data 🚀")
    user_question = st.text_input("Ask a question about your Data:")

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader(
            "Upload your Data here  in PDF format and click on 'Process'", accept_multiple_files=True, type=['pdf'])

        if st.button("Process"):
            if pdf_docs is None:
                st.error("Please upload at least one PDF file.")
            else:
                with st.spinner("Processing"):
                    print("get_pdf_text")
                    raw_text = get_pdf_text(pdf_docs)
                    print("get_text_chunks")
                    text_chunks = get_text_chunks(raw_text)
                    print("get_vectorstore")
                    vectorstore = get_vectorstore(text_chunks)
                    print("get_conversation_chain")
                    st.session_state.conversation = get_conversation_chain(
                        vectorstore)
                    print("success")
                    st.success("Your Data has been processed successfully")

    if user_question:
        handle_userinput(user_question)

    st.markdown(hide_st_style, unsafe_allow_html=True)
    st.markdown(footer, unsafe_allow_html=True)


if __name__ == '__main__':
    main()