import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
from langchain_community.vectorstores import FAISS  # Updated import
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv
import os
import google.generativeai as genai

load_dotenv()

# Configure Generative AI API key
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))

def get_pdf_text(pdf_docs):
    """Extract text from PDF documents."""
    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):
    """Split text into manageable chunks."""
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
    chunks = text_splitter.split_text(text)
    return chunks

def get_vector_store(text_chunks):
    """Generate embeddings and create FAISS index."""
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
    vector_store.save_local("faiss_index")

def get_conversational_chain():
    """Load conversational chain for question answering."""
    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 context", 
    don't provide the wrong answer\n\n
    Context:\n {context}?\n
    Question: \n{question}\n

    Answer:
    """

    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
    return chain

def user_input(user_question):
    """Process user input and generate response."""
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    
    # Load FAISS index with the necessary flag
    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
    docs = new_db.similarity_search(user_question)

    # Load conversational chain
    chain = get_conversational_chain()

    # Generate response
    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
    
    return response["output_text"]

def main():
    """Main Streamlit application function."""
    st.set_page_config("Chat PDF")
    st.header("📄📄 Chat with Multi_PDFs 📄📄")

    user_question = st.text_input("Ask a Question from the PDF Files")

    if user_question:
        response = user_input(user_question)
        st.write("Reply: ", response)

    with st.sidebar:
        st.title("Menu:")
        pdf_docs = 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(pdf_docs)
                text_chunks = get_text_chunks(raw_text)
                get_vector_store(text_chunks)
                st.success("Done")

if __name__ == "__main__":
    main()