import os
import streamlit as st
import google.generativeai as genai

from dotenv import load_dotenv
from PyPDF2 import PdfReader # read the PDF file
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_google_genai import GoogleGenerativeAIEmbeddings # converting text to vectors
from langchain.vectorstores import FAISS # for vector embeddings
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain # helps for prompts
from langchain.prompts import PromptTemplate


load_dotenv()
genai.configure(api_key=os.getenv('GOOGLE_API_KEY'))
                                  
# read the pdf, and extract the text
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

# divide the text into chunks
def get_text_chunks(text):
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
    chunks = text_splitter.split_text(text)
    return chunks

# convert the text to vectors
def get_vector_store(text_chunks):
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
    vector_store.save_local("faiss_index") # save the vector as local, can also save it on Pinecone, DataStax

# creating chain for conversational
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 context", don't provide the wrong answer\n\n
                    Context:\n {context}?\n
                    Question: \n{question}\n
                    Answer:
                    """
            model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.8)
            prompt = PromptTemplate(template=prompt_template, input_variables=['context','question'])
            chain = load_qa_chain(model, chain_type='stuff',prompt=prompt) #stuff for internal summerization
            return chain


# user question besed on the textbox and calling the other functions
def user_input(user_question):
     embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")

     new_db = FAISS.load_local("faiss_index",embeddings) # load the embedding from local
     docs = new_db.similarity_search(user_question)
     chain = get_conversational_chain()

     response = chain(
          {'input_documents': docs, "question": user_question},
          return_only_outputs=True
     )
     print(response)
     st.write("Reply: ", response["output_text"])

# creating the streamlit Application
def main():
    st.set_page_config("Chat PDF")
    st.header("Chat with PDF using Gemini💁")

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

    if user_question:
        user_input(user_question)

    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()