import gradio as gr
import requests
from fpdf import FPDF
import nltk
from nltk.tokenize import sent_tokenize
import random
import os

# Ensure nltk resources are downloaded
nltk.download("punkt")

# Function to send audio to Groq API and get transcription
def transcribe(audio_path):
    # Read audio file in binary mode
    with open(audio_path, "rb") as audio_file:
        audio_data = audio_file.read()

    # Groq API endpoint for audio transcription
    groq_api_endpoint = "https://api.groq.com/openai/v1/audio/transcriptions"

    headers = {
        "Authorization": "Bearer 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",  # Replace with your actual API key
    }

    files = {
        'file': ('audio.wav', audio_data, 'audio/wav'),
    }
    data = {
        'model': 'whisper-large-v3-turbo',
        'response_format': 'json',
        'language': 'en',
    }

    # Send audio to Groq API
    response = requests.post(groq_api_endpoint, headers=headers, files=files, data=data)

    if response.status_code == 200:
        result = response.json()
        transcript = result.get("text", "No transcription available.")
        return generate_notes(transcript)
    else:
        error_msg = response.json().get("error", {}).get("message", "Unknown error.")
        print(f"API Error: {error_msg}")
        return None  # Indicate failure

# Function to generate notes and questions
def generate_notes(transcript):
    # Split transcript into sentences
    sentences = sent_tokenize(transcript)

    # Generate long and short questions
    long_questions = [f"What is meant by '{sentence}'?" for sentence in sentences[:5]]
    short_questions = [f"Define '{sentence.split()[0]}'." for sentence in sentences[:5]]

    # Generate MCQs
    mcqs = []
    for sentence in sentences[:5]:
        mcq = {
            "question": f"What is '{sentence.split()[0]}'?",
            "options": [sentence.split()[0]] + random.sample(["Option 1", "Option 2", "Option 3"], 3),
            "answer": sentence.split()[0]
        }
        mcqs.append(mcq)

    # Create PDF
    pdf_path = create_pdf(transcript, long_questions, short_questions, mcqs)
    return pdf_path

# Function to create and save PDF
def create_pdf(transcript, long_questions, short_questions, mcqs):
    pdf = FPDF()
    pdf.add_page()
    
    # Title
    pdf.set_font("Arial", "B", 16)
    pdf.cell(200, 10, "Transcription Notes", ln=True, align="C")

    # Transcription
    pdf.set_font("Arial", "", 12)
    pdf.multi_cell(0, 10, f"Transcription:\n{transcript}\n\n")

    # Long Questions
    pdf.set_font("Arial", "B", 14)
    pdf.cell(200, 10, "Long Questions", ln=True)
    pdf.set_font("Arial", "", 12)
    for question in long_questions:
        pdf.multi_cell(0, 10, f"- {question}\n")

    # Short Questions
    pdf.set_font("Arial", "B", 14)
    pdf.cell(200, 10, "Short Questions", ln=True)
    pdf.set_font("Arial", "", 12)
    for question in short_questions:
        pdf.multi_cell(0, 10, f"- {question}\n")

    # MCQs
    pdf.set_font("Arial", "B", 14)
    pdf.cell(200, 10, "Multiple Choice Questions (MCQs)", ln=True)
    pdf.set_font("Arial", "", 12)
    for mcq in mcqs:
        pdf.multi_cell(0, 10, f"Q: {mcq['question']}")
        for option in mcq["options"]:
            pdf.multi_cell(0, 10, f"   - {option}")
        pdf.multi_cell(0, 10, f"Answer: {mcq['answer']}\n")

    # Save PDF
    pdf_path = "/mnt/data/transcription_notes.pdf"
    pdf.output(pdf_path)
    
    return pdf_path

# Gradio interface
def gradio_interface(audio_path):
    pdf_path = transcribe(audio_path)
    if pdf_path:
        return pdf_path
    else:
        return "Error: Unable to process the audio file. Please check the API key and try again."

iface = gr.Interface(
    fn=gradio_interface,
    inputs=gr.Audio(type="filepath"),
    outputs=gr.File(label="Download PDF with Notes and Questions"),
    title="Voice to Text Converter and Notes Generator",
)

iface.launch()