import gradio as gr
import os
import subprocess
import fitz
from dotenv import load_dotenv
from langchain_community.document_loaders import UnstructuredPDFLoader
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings
from langchain_text_splitters import CharacterTextSplitter
from langchain_groq import ChatGroq
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from gtts import gTTS
import sys
import pytesseract
from pdf2image import convert_from_path
from huggingface_hub import Repository, login
from huggingface_hub import hf_hub_download
from langchain.schema import Document




# Load environment variables
load_dotenv()
secret_key = os.getenv("GROQ_API_KEY")
hf_key = os.getenv("HF_TOKEN")

os.environ["GROQ_API_KEY"] = secret_key
login(token=hf_key,add_to_git_credential=True)

embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-mpnet-base-v2")

# Ensure the necessary folders exist
UPLOAD_FOLDER = 'uploads/'
AUDIO_FOLDER = 'audio/'
for folder in [UPLOAD_FOLDER, AUDIO_FOLDER]:
    if not os.path.exists(folder):
        os.makedirs(folder)

def load_pdf(file_path):
    """Load and preprocess Arabic text from a PDF file."""
    try:
        pages = convert_from_path(file_path, 500)
    except Exception as e:
        print(f"Error loading PDF: {e}")
        return []

    documents = []
    for pageNum, imgBlob in enumerate(pages):
        try:
            text = pytesseract.image_to_string(imgBlob, lang="ara")
            documents.append(text)
        except Exception as e:
            print(f"Error processing page {pageNum}: {e}")
            documents.append("")  # Append empty string for pages where OCR failed

    return documents

def prepare_vectorstore(data):
    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=20, separator="\n")
    # Create Document objects from the input data
    documents = [Document(page_content=text) for text in data]
    
    # Split the documents into chunks
    chunks = text_splitter.split_documents(documents)
    
    # Create the vector store
    vectorstore = FAISS.from_documents(chunks, embeddings)
    return vectorstore

def create_chain(vectorstore):
    llm = ChatGroq(model="gemma2-9b-it", temperature=0)
    retriever = vectorstore.as_retriever()
    memory = ConversationBufferMemory(llm=llm, output_key="answer", memory_key="chat_history", return_messages=True)
    chain = ConversationalRetrievalChain.from_llm(
        llm=llm,
        retriever=retriever,
        memory=memory,
        verbose=False,
        chain_type="map_reduce"
    )
    return chain
    
custom_css = """
body {
    font-family: 'Noto Kufi Arabic', sans-serif;
    background: linear-gradient(135deg, #799351 0%, #A67B5B 100%);
    background-size: cover;
    background-position: center;
    background-attachment: fixed;
}

.gradio-container {
    max-width: 800px !important;
    margin: auto !important;
    background: rgba(255, 255, 255, 0.9);
    border-radius: 20px;
    box-shadow: 0 8px 32px 0 rgba(31, 38, 135, 0.37);
    backdrop-filter: blur(4px);
    border: 1px solid rgba(255, 255, 255, 0.18);
    padding: 20px;
}

h1, h2, h3 {
    color: #1A4D2E;
    font-weight: bold;
    text-align: center;
}

p {
    color: #A89F91;
}

.gradio-button {
    background-color: #5F6F65 !important;
    color: #FFFFFF !important;
}

.gradio-button:hover {
    background-color: #FFFFFF !important;
    color: #5F6F65 !important;
}

.chat-message {
    border-radius: 10px;
    padding: 10px;
    margin-bottom: 10px;
}

.chat-message.user {
    background-color: #E7F0DC;
}

.chat-message.bot {
    background-color: #F7EED3;
}

.chat-message::before {
    content: '';
    display: inline-block;
    width: 24px;
    height: 24px;
    background-size: contain;
    background-repeat: no-repeat;
    margin-right: 10px;
    vertical-align: middle;
}

.chat-message.user::before {
    content: '👤';
}

.chat-message.bot::before {
    content: '🤖';
}
"""

def main():
    # Create the Gradio interface
    with gr.Blocks(css=custom_css) as demo:
        pdf_input = gr.File(label="Upload PDF")
        chat_input = gr.Textbox(label="Your question")
        chat_output = gr.Textbox(label="Assistant's response")
        audio_output = gr.Audio(label="Audio response")
        submit_button = gr.Button("Submit")

        # Define the logic for processing the PDF and generating responses
        def process_pdf_and_chat(pdf_file, user_input):
            data = load_pdf(pdf_file)
            vectorstore = prepare_vectorstore(data)
            chain = create_chain(vectorstore)

            prompt = f"""
            You are an expert Arabic-language assistant specialized in analyzing and responding to queries about Arabic PDF documents. Your responses should be precise, informative, and reflect the professional tone and structure expected in formal Arabic communication. Focus on extracting and presenting relevant information from the document clearly and systematically, while avoiding colloquial or informal language.

            When responding, ensure the following:
               - Your answer directly reflects the content of the document.
               - If the requested information is not available in the document, clearly state that.
               - Keep your response concise yet comprehensive, addressing the question fully.
               - Always respond in formal Arabic, without using English.\n

            Question: {user_input}\n
            Helpful Answer:"""

            response = chain({"question": prompt})
            assistant_response = response["answer"]

            # Generate a unique identifier for the audio file
            audio_id = str(uuid.uuid4())

            # Create audio file
            tts = gTTS(text=assistant_response, lang='ar')
            audio_file = f"{audio_id}.mp3"
            tts.save(audio_file)

            return assistant_response, audio_file

        # Connect the button to the processing function
        submit_button.click(process_pdf_and_chat, inputs=[pdf_input, chat_input], outputs=[chat_output, audio_output])

    # Launch the Gradio app
    demo.launch()

if __name__ == '__main__':
    main()