import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.llms import HuggingFaceHub, ctransformers


def get_pdf_text(pdf_docs):
    text = ""
    try:
        for pdf in pdf_docs:
            pdf_reader = PdfReader(pdf)
            for page in pdf_reader.pages:
                text += page.extract_text()
    except Exception as e:
        st.error(f"Error reading PDFs: {e}")
    return text


def get_text_chunks(text):
    try:
        text_splitter = CharacterTextSplitter(
            separator="\n",
            chunk_size=800,
            chunk_overlap=0,
            length_function=len
        )
        chunks = text_splitter.split_text(text)
    except Exception as e:
        st.error(f"Error splitting text into chunks: {e}")
        chunks = []
    return chunks


def get_vectorstore(text_chunks):
    try:
        embeddings = HuggingFaceInstructEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
        vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    except Exception as e:
        st.error(f"Error creating vector store: {e}")
        vectorstore = None
    return vectorstore


def get_Hub_llm():
    try:
        llm = HuggingFaceHub(
            repo_id="HuggingFaceH4/zephyr-7b-beta",
            model_kwargs={
                "temperature": 0.1,
                "max_length": 2048,
                "top_k": 50,
                "num_return_sequences": 3,
                "task": "text-generation",
                "top_p": 0.95
            }
        )
    except Exception as e:
        st.error(f"Error loading Hub LLM: {e}")
        llm = None
    return llm


def get_local_llm():
    try:
        llm = ctransformers.CTransformers(
            model="C:/llama-2-7b-chat.ggmlv3.q4_0.bin",
            model_type="llama",
            max_new_tokens=1024,
            max_length=4096,
            temperature=0.1
        )
    except Exception as e:
        st.error(f"Error loading local LLM: {e}")
        llm = None
    return llm


def get_conversation_chain(vectorstore, llm):
    try:
        memory = ConversationBufferMemory(
            memory_key='chat_history',
            return_messages=True,
            input_key="question",
            output_key="answer")
        if vectorstore:
            conversation_chain = ConversationalRetrievalChain.from_llm(
                llm=llm,
                chain_type="stuff",
                verbose=True,
                retriever=vectorstore.as_retriever(search_kwargs={"k": 3, "search_type": "similarity"}),
                memory=memory,
                output_key='answer',
                return_source_documents=False
            )
        else:
            conversation_chain = ConversationalRetrievalChain.from_llm(
                llm=llm,
                chain_type="stuff",
                verbose=True,
                memory=memory,
                output_key='answer',
                return_source_documents=False
            )
    except Exception as e:
        st.error(f"Error creating conversation chain: {e}")
        conversation_chain = None
    return conversation_chain


def handle_userinput(user_question):
    if st.session_state.conversation is None:
        st.error("Conversation chain is not initialized.")
        return

    try:
        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:
                with st.chat_message("User"):
                    st.write(message.content)
            else:
                with st.chat_message("assistant"):
                    st.write(message.content)
    except Exception as e:
        st.error(f"Error handling user input: {e}")


def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple PDFs",
                       page_icon=":books:")
    
    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 PDFs ")
    
    user_question = st.chat_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'", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                try:
                    # get pdf text
                    raw_text = get_pdf_text(pdf_docs)
                
                    # get the text chunks
                    text_chunks = get_text_chunks(raw_text)

                    if not text_chunks:
                        st.error("No text found in the PDFs or text splitting failed.")
                        return

                    # create vector store
                    vectorstore = get_vectorstore(text_chunks)

                    if not vectorstore:
                        st.error("Failed to create vector store.")
                        return

                    # create llm
                    llm = get_Hub_llm()

                    if not llm:
                        st.error("Failed to load LLM.")
                        return

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

                    if not st.session_state.conversation:
                        st.error("Failed to create conversation chain.")

                except Exception as e:
                    st.error(f"An error occurred during processing: {e}")


if __name__ == '__main__':
    main()