app.py

import gradio as gr

examples = [
    "Give me a recipe for pizza with pineapple",
    "Write me a tweet about the new OpenVINO release",
    "Explain the difference between CPU and GPU",
    "Give five ideas for a great weekend with family",
    "Do Androids dream of Electric sheep?",
    "Who is Dolly?",
    "Please give me advice on how to write resume?",
    "Name 3 advantages to being a cat",
    "Write instructions on how to become a good AI engineer",
    "Write a love letter to my best friend",
]

def run_generation(user_text, top_p, temperature, top_k, max_new_tokens, performance):
    # Example response, replace with actual model call
    response = f"Generated text for: {user_text}"
    performance = "N/A"  # Replace with actual performance metrics if available
    return response, performance

def reset_textbox(*args):
    return "", "", ""

with gr.Blocks() as demo:
    gr.Markdown(
        "# Question Answering with OpenVINO\n"
        "Provide instruction which describes a task below or select among predefined examples and model writes response that performs requested task."
    )

    with gr.Row():
        with gr.Column(scale=4):
            user_text = gr.Textbox(
                placeholder="Write an email about an alpaca that likes flan",
                label="User instruction",
            )
            model_output = gr.Textbox(label="Model response", interactive=False)
            performance = gr.Textbox(label="Performance", lines=1, interactive=False)
            with gr.Column(scale=1):
                button_clear = gr.Button(value="Clear")
                button_submit = gr.Button(value="Submit")
            gr.Examples(examples, user_text)
        with gr.Column(scale=1):
            max_new_tokens = gr.Slider(
                minimum=1,
                maximum=1000,
                value=256,
                step=1,
                interactive=True,
                label="Max New Tokens",
            )
            top_p = gr.Slider(
                minimum=0.05,
                maximum=1.0,
                value=0.92,
                step=0.05,
                interactive=True,
                label="Top-p (nucleus sampling)",
            )
            top_k = gr.Slider(
                minimum=0,
                maximum=50,
                value=0,
                step=1,
                interactive=True,
                label="Top-k",
            )
            temperature = gr.Slider(
                minimum=0.1,
                maximum=5.0,
                value=0.8,
                step=0.1,
                interactive=True,
                label="Temperature",
            )

    user_text.submit(
        run_generation,
        [user_text, top_p, temperature, top_k, max_new_tokens, performance],
        [model_output, performance],
    )
    button_submit.click(
        run_generation,
        [user_text, top_p, temperature, top_k, max_new_tokens, performance],
        [model_output, performance],
    )
    button_clear.click(
        reset_textbox,
        [user_text, model_output, performance],
        [user_text, model_output, performance],
    )

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