import gradio as gr
from huggingface_hub import InferenceClient
from AICoreAGIX_with_TB import AICoreAGIX # Ensure this imports your AICoreAGIX class

# Initialize the AI core
ai_core = AICoreAGIX()

def respond(message, history, system_message, max_tokens, temperature, top_p, image, audio):
    # Process the uploaded files
    if image and audio:
        # Save the uploaded files to disk or process them as needed
        image_path = "uploaded_image.png"
        audio_path = "uploaded_audio.wav"
        image.save(image_path)
        audio.save(audio_path)

        # Run TB diagnostics
        tb_result = ai_core.run_tb_diagnostics(image_path, audio_path, user_id=1)  # Replace with actual user_id handling

        # Incorporate TB diagnostic results into the response
        tb_message = f"TB Diagnostic Result: {tb_result['tb_risk']}\n"
        tb_message += f"Image Analysis: {tb_result['image_analysis']}\n"
        tb_message += f"Audio Analysis: {tb_result['audio_analysis']}\n"
        tb_message += f"Shareable Link: {tb_result['shareable_link']}\n\n"
    else:
        tb_message = "No TB diagnostic data provided.\n\n"

    # Existing chat functionality
    messages = [{"role": "system", "content": system_message}]
    for user_msg, bot_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if bot_msg:
            messages.append({"role": "assistant", "content": bot_msg})
    messages.append({"role": "user", "content": message})

    response = ""
    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content
        response += token
        yield tb_message + response

# Define the Gradio interface
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
        gr.inputs.Image(type="pil", label="Upload Saliva Microscopy Image"),
        gr.inputs.Audio(type="file", label="Upload Cough Audio Recording"),
    ],
)

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