import streamlit as st
import os
from streamlit_chat import message
import tempfile
#from langchain_community.documentloader.csv_loader import CSVLoader
from langchain_community.document_loaders.csv_loader import CSVLoader
from langchain_community.embeddings import HuggingFaceEmbeddings
#from langchain_community.embeddings import HuggingFaceBgeEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
#from langchain_community.llms import CTransformers
from langchain_community.llms.ctransformers import CTransformers

from langchain.chains.conversational_retrieval.base import ConversationalRetrievalChain
                                                            
#from langchain.chains.conversational_retrieval.base import ConversationalRetreievalChain


DB_FAISS_PATH = 'vectorstore/db_faiss'
TEMP_DIR = 'temp'
if not os.path.exists(TEMP_DIR):
    os.makedirs(TEMP_DIR)
    
def load_llm():
    # load model from hugging face repo
    llm = CTransformers(
        model = 'TheBloke/Llama-2-7B-Chat-GGML',
        model_type = 'llama',
        max_new_token = 512,
        temperature = 0.5
    )
    return llm

st.title("Chat with CSV using Llma 2")
st.markdown("<h1 style='text-align: center; color: blue;'>Chat with your PDF 📄 </h1>", unsafe_allow_html=True)
st.markdown("<h3 style='text-align: center; color: grey;'>Built by <a href='https://github.com/DrKareemKAmal'>MindSparks ❤️ </a></h3>", unsafe_allow_html=True)

uploaded_file = st.sidebar.file_uploader('Upload your data', type=['csv'])

if uploaded_file:
    # with tempfile.NamedTemporaryFile(delete=False)as temp_file :
    #     temp_file.write(uploaded_file.getvalue())
    #     tempfile_path = temp_file.name
    file_path = os.path.join(TEMP_DIR, uploaded_file.name)
    with open(file_path, "wb") as f:
        f.write(uploaded_file.getvalue())

    st.write(f"Uploaded file: {uploaded_file.name}")
    st.write("Processing CSV file...")
    
    loader = CSVLoader(file_path = file_path, encoding = 'utf-8',
                        csv_args = {'delimiter': ','} )
    data = loader.load()
    #st.json(data)

    text_splitter = RecursiveCharacterTextSplitter(chunk_size = 500 , chunk_overlap = 20)
    text_chunks = text_splitter.split_documents(data)
    st.write (f"Total text chunks : {len(text_chunks)}")

    embeddings = HuggingFaceEmbeddings(
        model_name = 'sentence-transformers/all-MiniLM-L6-v2',
        # model_kwargs = {'device': 'cpu'}
    )


    db = FAISS.from_documents(text_chunks, embeddings)
    db.save_local (DB_FAISS_PATH)
    llm = load_llm()

    chain = ConversationalRetrievalChain.from_llm(llm= llm , retriever = db.as_retriever())

    def conversational_chat(query):
        result  = chain({"question": query ,
                         "chat_history": st.session_state['history']})
        st.session_state['history'].append((query , result['answer']))
        return result['answer']
    
    if 'history' not in st.session_state :
        st.session_state['history'] = []

    if 'generated' not in st.session_state :
        st.session_state['generated'] = ['Hello, Ask me anything about ' + uploaded_file.name]

    if 'past' not in st.session_state :
        st.session_state['past'] = ['Hey !']

    # Container for the chat history
    response_container = st.container()
    container = st.container()

    with container :
        with st.form(key = 'my_form',
                     clear_on_submit=True):
            user_input = st.text_input('Query:', placeholder= "Talk to youur CSV Data here ")
            submit_button = st.form_submit_button(label = 'chat')

        if submit_button and user_input :
            output = conversational_chat(user_input)

            st.session_state['past'].append(user_input)
            st.session_state['generated'].append(output)

        if st.session_state['generated'] :
            with response_container:
                for i in range(len(st.session_state['generated'])):
                    message(st.session_state['past'][i], is_user = True , key=str(i) + '_user',
                            avatar_style='big-smile')
                    message(st.session_state['generated'][i], key = str(i), avatar_style='thumb')