app.py

import gradio as gr
import openai
import base64 # image ---> base64
from PIL import Image
import io
import fitz  # PyMuPDF for PDF handling

# Extract text from PDF
def extract_text_from_pdf(pdf_file):
    try:
        text = ""
        pdf_document = fitz.open(pdf_file)
        for page_num in range(len(pdf_document)):
            page = pdf_document[page_num]
            text += page.get_text()
        pdf_document.close()
        return text
    except Exception as e:
        return f"Error extracting text from PDF: {str(e)}"

### mcq quiz from pdf file

def generate_mcq_quiz(pdf_content, num_questions, openai_api_key, model_choice):
    if not openai_api_key:
        return "Error: No API key provided."
    openai.api_key = openai_api_key
    limited_content = pdf_content[:8000]
    prompt = f"""Based on the following document content, generate {num_questions} multiple-choice quiz questions. #system prompt for mcq quiz gen
For each question:
1. Write a clear question
2. Give 4 options (A, B, C, D)
3. Indicate the correct answer
4. Briefly explain why the answer is correct
Document:
{limited_content}
"""
    try:
        response = openai.ChatCompletion.create(
            model=model_choice,
            messages=[{"role": "user", "content": prompt}]
        )
        return response.choices[0].message.content
    except Exception as e:
        return f"Error generating quiz: {str(e)}"

# Convert image to base64
def get_base64_string_from_image(pil_image):
    buffered = io.BytesIO()
    pil_image.save(buffered, format="PNG")
    return base64.b64encode(buffered.getvalue()).decode("utf-8")

### STS - speech to text (whisper-1)
def transcribe_audio(audio, openai_api_key):
    if not openai_api_key:
        return "Error: No API key provided."
    openai.api_key = openai_api_key
    try:
        with open(audio, 'rb') as f:
            audio_bytes = f.read()
        file_obj = io.BytesIO(audio_bytes)
        file_obj.name = 'audio.wav'
        transcription = openai.Audio.transcribe(file=file_obj, model="whisper-1") ## (ami vaat khai) in a recording:  transcription.text: ami vaat khai
        return transcription.text
    except Exception as e:
        return f"Error transcribing audio: {str(e)}"

# Generate response for text/image/pdf
def generate_response(input_text, image, pdf_content, openai_api_key, reasoning_effort, model_choice):
    if not openai_api_key:
        return "Error: No API key provided."
    openai.api_key = openai_api_key

    if pdf_content and input_text:
        input_text = f"Based on the document below, answer the question:\n\n{input_text}\n\nDocument:\n{pdf_content}" # what does this pdf is about? ### all word extracted
    elif image:
        image_b64 = get_base64_string_from_image(image)
        input_text = f"data:image/png;base64,{image_b64}"

    try:
        response = openai.ChatCompletion.create(
            model=model_choice,
            messages=[{"role": "user", "content": input_text}],
            max_completion_tokens=2000
        )
        return response.choices[0].message.content
    except Exception as e:
        return f"Error calling OpenAI API: {str(e)}"


# Chatbot logic
def chatbot(input_text, image, audio, pdf_file, openai_api_key, reasoning_effort, model_choice, pdf_content, num_quiz_questions, pdf_quiz_mode, history):
    if history is None:
        history = []

    if audio:
        input_text = transcribe_audio(audio, openai_api_key)

    new_pdf_content = pdf_content
    if pdf_file:
        new_pdf_content = extract_text_from_pdf(pdf_file)

    if pdf_quiz_mode:
        if new_pdf_content:
            quiz = generate_mcq_quiz(new_pdf_content, int(num_quiz_questions), openai_api_key, model_choice)
            history.append((f"📘 Generated {num_quiz_questions} quiz questions", quiz))
        else:
            history.append(("No PDF detected", "Please upload a PDF file first."))
    else:
        response = generate_response(input_text, image, new_pdf_content, openai_api_key, reasoning_effort, model_choice)
        if input_text:
            history.append((input_text, response))
        elif image:
            history.append(("🖼️ [Image Uploaded]", response))
        elif pdf_file:
            history.append(("📄 [PDF Uploaded]", response))
        else:
            history.append(("No input", "Please provide input."))

    return "", None, None, None, new_pdf_content, history

# Reset all fields
def clear_history():
    return "", None, None, None, "", []

# Extract text when PDF uploaded
def process_pdf(pdf_file):
    if pdf_file is None:
        return ""
    return extract_text_from_pdf(pdf_file)

# Switch between input modes
def update_input_type(choice):
    if choice == "Text":
        return gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(value=False)
    elif choice == "Image":
        return gr.update(visible=True), gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(value=False)
    elif choice == "Voice":
        return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(value=False)
    elif choice == "PDF":
        return gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(visible=False), gr.update(value=False)
    elif choice == "PDF(QUIZ)":
        return gr.update(visible=False), gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(visible=True), gr.update(value=True)

# Build Gradio interface
def create_interface():
    with gr.Blocks() as demo:
        gr.Markdown("## 🧠 Multimodal Chatbot — Text | Image | Voice | PDF | Quiz")

        pdf_content = gr.State("")

        openai_api_key = gr.Textbox(label="🔑 OpenAI API Key", type="password", placeholder="sk-...")

        input_type = gr.Radio(
            ["Text", "Image", "Voice", "PDF", "PDF(QUIZ)"], 
            label="Choose Input Type", 
            value="Text"
        )

        input_text = gr.Textbox(label="Enter your question or text", lines=2, visible=True)
        image_input = gr.Image(label="Upload Image", type="pil", visible=False)
        audio_input = gr.Audio(label="Upload/Record Audio", type="filepath", visible=False)
        pdf_input = gr.File(label="Upload PDF", file_types=[".pdf"], visible=False)
        quiz_questions_slider = gr.Slider(1, 20, value=5, step=1, label="Number of Quiz Questions", visible=False)
        quiz_mode = gr.Checkbox(label="Quiz Mode", visible=False, value=False)

        with gr.Row():
            reasoning_effort = gr.Dropdown(["low", "medium", "high"], value="medium", label="Reasoning Effort")
            model_choice = gr.Dropdown(["o1", "o3-mini"], value="o1", label="Model")

        submit_btn = gr.Button("Submit")
        clear_btn = gr.Button("Clear Chat")

        chat_history = gr.Chatbot(label="Chat History")

        # Input type handling
        input_type.change(
            fn=update_input_type,
            inputs=[input_type],
            outputs=[input_text, image_input, audio_input, pdf_input, quiz_questions_slider, quiz_mode]
        )

        # PDF upload processing
        pdf_input.change(fn=process_pdf, inputs=[pdf_input], outputs=[pdf_content])

        # Submit
        submit_btn.click(
            fn=chatbot,
            inputs=[input_text, image_input, audio_input, pdf_input, openai_api_key, reasoning_effort, model_choice, pdf_content, quiz_questions_slider, quiz_mode, chat_history],
            outputs=[input_text, image_input, audio_input, pdf_input, pdf_content, chat_history]
        )

        # Clear
        clear_btn.click(fn=clear_history, inputs=[], outputs=[input_text, image_input, audio_input, pdf_input, pdf_content, chat_history])

    return demo


if __name__ == "__main__":
    demo = create_interface()
    demo.launch()