import streamlit as st
import pandas as pd
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, Chroma
from langchain.embeddings import HuggingFaceEmbeddings  # General embeddings from HuggingFace models.
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, LlamaCpp, CTransformers  # For loading transformer models.
from langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader
import tempfile  # 임시 파일을 생성하기 위한 라이브러리입니다.
import os
import json



# PDF 문서로부터 텍스트를 추출하는 함수입니다.
def get_pdf_text(pdf_docs):
    text = ''
    
    pdf_reader = PdfReader(pdf_docs)
    for page in pdf_reader.pages:
        text += page.extract_text()

    return text

# 과제
# 아래 텍스트 추출 함수를 작성

def get_text_file(txt_docs):
    text = txt_docs.read().decode("utf-8")
    return text


def get_csv_file(csv_docs):
    text = ''
    data = pd.read_csv(csv_docs)
    for index, row in data.iterrows():
        row_text = ' '.join(f"{col}: {row[col]}" for col in data.columns)
        text += row_text + '\n'
    return text


def get_json_file(json_docs):
    text = ''
    json_data = json.load(json_docs)

    for key, values in json_data.items():
        for value in values:
            text += f"{key}: {value}\n"
    return text


# 문서들을 처리하여 텍스트 청크로 나누는 함수입니다.
def get_text_chunks(documents):
    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )

    combined_text = "\n".join(documents)

    chunks = text_splitter.split_text(combined_text)
    return chunks


# 텍스트 청크들로부터 벡터 스토어를 생성하는 함수입니다.
def get_vectorstore(text_chunks):
    # OpenAI 임베딩 모델을 로드합니다. (Embedding models - Ada v2)

    embeddings = OpenAIEmbeddings()
    vectorstore = FAISS.from_texts(text_chunks, embeddings)  # FAISS 벡터 스토어를 생성합니다.

    return vectorstore  # 생성된 벡터 스토어를 반환합니다.


def get_conversation_chain(vectorstore):
    gpt_model_name = 'gpt-3.5-turbo'
    llm = ChatOpenAI(model_name=gpt_model_name)  # gpt-3.5 모델 로드

    # 대화 기록을 저장하기 위한 메모리를 생성합니다.
    memory = ConversationBufferMemory(
        memory_key='chat_history', return_messages=True)
    # 대화 검색 체인을 생성합니다.
    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=vectorstore.as_retriever(),
        memory=memory
    )
    return conversation_chain


# 사용자 입력을 처리하는 함수입니다.
def handle_userinput(user_question):
    # 대화 체인을 사용하여 사용자 질문에 대한 응답을 생성합니다.
    response = st.session_state.conversation({'question': user_question})
    # 대화 기록을 저장합니다.
    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="Chat with multiple Files",
                       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("Chat with multiple Files :")
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        openai_key = st.text_input("Paste your OpenAI API key (sk-...)")
        if openai_key:
            os.environ["OPENAI_API_KEY"] = openai_key

        st.subheader("Your documents")
        docs = st.file_uploader(
            "Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                # get pdf text
                doc_list = []

                for file in docs:
                    try:
                        if file.type == 'text/plain':
                            text = get_text_file(file)
                        elif file.type in ['application/octet-stream', 'application/pdf']:
                            text = get_pdf_text(file)
                        elif file.type == 'text/csv':
                            text = get_csv_file(file)
                        elif file.type == 'application/json':
                            text = get_json_file(file)
                        else:
                            text = "Unsupported file format"
                    
                        print(f"File processed: {file.name}, Text length: {len(text)}")
                        doc_list.append(text)
                    except Exception as e:
                        print(f"Error processing file {file.name}: {e}")


                # get the text chunks
                combined_documents = "\n".join(doc_list)
                text_chunks = get_text_chunks(combined_documents)

                # create vector store
                vectorstore = get_vectorstore(text_chunks)

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


if __name__ == '__main__':
    main()