import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter

from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template


from langchain_community.embeddings import OpenAIEmbeddings,HuggingFaceInstructEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.chat_models import ChatOpenAI
from langchain_community.llms import HuggingFaceHub
from langchain_community.embeddings import OllamaEmbeddings
from langchain_community.chat_models import ChatOllama
from langchain_core.documents import Document
import os

VECTOR_DIR = "vectorstore"
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_pdf_chunks_with_metadata(pdf_docs):
    all_chunks = []
    splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)

    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        text = ""
        for page in pdf_reader.pages:
            text += page.extract_text()
        
        chunks = splitter.split_text(text)

        # Add PDF file name as metadata for each chunk
        doc_chunks = [Document(page_content=chunk, metadata={"source": pdf.name}) for chunk in chunks]
        all_chunks.extend(doc_chunks)

    return all_chunks


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()
    embeddings = OllamaEmbeddings(model="nomic-embed-text")
    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

def get_vectorstore(docs_with_metadata):
    embeddings = OllamaEmbeddings(model="nomic-embed-text")

    if os.path.exists(VECTOR_DIR):
        vectorstore = FAISS.load_local(VECTOR_DIR, embeddings, allow_dangerous_deserialization=True)
    else:
        vectorstore = FAISS.from_documents(docs_with_metadata, embedding=embeddings)
        vectorstore.save_local(VECTOR_DIR)

    return vectorstore


def get_conversation_chain(vectorstore):
    #llm = ChatOpenAI()
    llm = ChatOllama(
        base_url = 'http://127.0.0.1:11434',
        model = "llama3:8b"
        #model = "deepseek-r1:8b"
    )
    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", 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):
#     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 handle_userinput(user_question):
    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:
            # User message
            st.write(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            # Bot message with optional source metadata
            content = message.content
            if hasattr(message, 'metadata') and message.metadata.get("source"):
                content += f"\n\n📄 *Source: {message.metadata['source']}*"
            st.write(bot_template.replace("{{MSG}}", content), unsafe_allow_html=True)



def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple 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 = None

    st.header("Chat with multiple 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 and click on 'Process'", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                # get pdf text
                # raw_text = get_pdf_text(pdf_docs)

                # # get the text chunks
                # text_chunks = get_text_chunks(raw_text)

                # # create vector store
                # vectorstore = get_vectorstore(text_chunks)
                docs_with_metadata = get_pdf_chunks_with_metadata(pdf_docs)
                vectorstore = get_vectorstore(docs_with_metadata)

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


if __name__ == '__main__':
    main()