# app.py
import os
import base64
import streamlit as st
from PyPDF2 import PdfReader
from dotenv import load_dotenv

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.prompts import PromptTemplate
from langchain.chains.question_answering import load_qa_chain
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI

import google.generativeai as genai

# ==========================
# Load Environment Variables
# ==========================
load_dotenv()
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))


# ==========================
# Helper Functions
# ==========================

# Extract text from PDFs
def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_reader.pages:
            if page.extract_text():
                text += page.extract_text()
    return text


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


# Create FAISS vector database
def get_vector_store(text_chunks):
    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
    vector_store.save_local("faiss_index")


# Create QA Chain
def get_conversational_chain():
    prompt_template = """
    Answer the question as detailed as possible from the provided context. 
    If the answer is not in the provided context, just say 
    "Answer is not available in the context". 
    Do not provide incorrect answers.
    
    Context:\n{context}\n
    Question:\n{question}\n
    Answer:
    """

    model = ChatGoogleGenerativeAI(
        model="models/gemini-2.0-flash",
        temperature=0.3
    )

    prompt = PromptTemplate(
        template=prompt_template,
        input_variables=["context", "question"]
    )

    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
    return chain


# Handle user question
def user_input(user_question):
    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    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(
        {"input_documents": docs, "question": user_question},
        return_only_outputs=True
    )

    st.write("### Reply:")
    st.write(response["output_text"])


# ==========================
# Streamlit UI
# ==========================
def main():
    st.set_page_config(page_title="Chat with PDF 💁", layout="wide")
    st.header("📄 Chat with your PDF using Gemini + FAISS")

    # User question input
    user_question = st.text_input("Ask a question about the uploaded PDFs:")

    if user_question:
        user_input(user_question)

    # Sidebar for uploading PDFs
    with st.sidebar:
        st.title("📂 Menu")
        pdf_docs = st.file_uploader(
            "Upload PDF files and click on 'Submit & Process'",
            accept_multiple_files=True,
            type=["pdf"]
        )

        if st.button("Submit & Process"):
            if pdf_docs:
                with st.spinner("Processing PDFs..."):
                    raw_text = get_pdf_text(pdf_docs)
                    text_chunks = get_text_chunks(raw_text)
                    get_vector_store(text_chunks)
                    st.success("✅ Processing complete! You can now ask questions.")
            else:
                st.warning("⚠️ Please upload at least one PDF file.")


if __name__ == "__main__":
    main()