import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.llms import HuggingFaceHub
from htmltemplates import css, bot_template, user_template

def get_text_chunks(text):
        text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=1000,
            chunk_overlap=200,
            length_function=len
        )
        chunks = text_splitter.split_text(text)
        return chunks

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_vectorstore(text_chunks):
    try:
        embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
        vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
        return vectorstore
    except Exception as e:
        st.error(f"Error in get_vectorstore: {e}")
        return None

def get_conversation_chain(vectorstore):
    try:
        llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature": 0.8, "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
    except Exception as e:
        st.error(f"Error in get_conversation_chain: {e}")
        return None

def handle_userinput(user_question):
    if st.session_state.conversation:
        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:
                    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)
        except Exception as e:
            st.error(f"Error in handle_userinput: {e}")
    else:
        st.error("Conversation chain is not initialized. Please upload and process documents first.")

def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with your PDFs", 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 = []

    st.header("Chat with your 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", accept_multiple_files=True)
        if st.button("Enter"):
            with st.spinner("Processing"):
                # Get PDF text
                raw_text = get_pdf_text(pdf_docs)
                # Get text chunks
                text_chunks = get_text_chunks(raw_text)
                if text_chunks:
                    # Create vector store
                    vectorstore = get_vectorstore(text_chunks)
                    if vectorstore:
                        # Initialize conversation chain
                        st.session_state.conversation = get_conversation_chain(vectorstore)
                        if st.session_state.conversation:
                            st.success("Conversation chain initialized successfully.")

if __name__ == "__main__":
    main()