import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
import os
from langchain import LLMChain
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain.llms import HuggingFaceHub
from langchain.embeddings import HuggingFaceInferenceAPIEmbeddings
import google.generativeai as genai
from langchain.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
import time
from dotenv import load_dotenv

genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
os.environ["HUGGINGFACEHUB_API_TOKEN"] = os.getenv("HF_TOKEN")

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_text_chunks(text):
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=700, chunk_overlap=200)
    chunks = text_splitter.split_text(text)
    return chunks

def get_vector_store(text_chunks):
    HF_TOKEN = os.getenv("HF_TOKEN")
    embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=HF_TOKEN, model_name="BAAI/bge-base-en-v1.5")
    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
    vector_store.save_local("faiss_index")

def get_conversational_chain():
    prompt_template = """
    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
    provided context just say, "answer is not available in the Provided PDF", don't provide the wrong answer\n\n
    Context:\n {context}?\n
    Question: \n{question}\n

    Answer:
    """
    # model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.1)
    model = HuggingFaceHub(repo_id="google/gemma-1.1-7b-it",
                            model_kwargs={"temperature": 0.2,"max_new_tokens":512, "return_only_answer":True})
    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
    chain = LLMChain(llm=model, prompt=prompt)
    return chain

def user_input(user_question):
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
    docs = new_db.similarity_search(user_question)
    chain = get_conversational_chain()
    response = chain({"context": docs, "question": user_question}, return_only_outputs=True)
    return response

# def response_generator(response):
#     for word in response.split():
#         yield word + " "
#         time.sleep(0.05)

# Streamlit app initialization
st.title("Chat With PDF 📄")

if 'messages' not in st.session_state:
    st.session_state.messages = [{'role': 'assistant', "content": 'Hello! Upload a PDF and ask me anything about its content.'}]

with st.sidebar:
    st.title("Menu:")
    uploaded_file = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
    if st.button("Submit & Process"):
        with st.spinner("Processing..."):
            raw_text = get_pdf_text(uploaded_file)
            text_chunks = get_text_chunks(raw_text)
            get_vector_store(text_chunks)
            st.success("Done")

user_prompt = st.chat_input("Ask me anything about the content of the PDF:")
if user_prompt:
    st.session_state.messages.append({'role': 'user', "content": user_prompt})
    response = user_input(user_prompt)
    # answer = response_generator(response)
    st.session_state.messages.append({'role': 'assistant', "content": response})

for message in st.session_state.messages:
    with st.chat_message(message['role']):
        st.write(message['content'])