app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Initialize the InferenceClient with the model name
# client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
client = InferenceClient("meta-llama/Llama-3.3-70B-Instruct")
# client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")

def respond(
    message,
    history,
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Create a list of messages with the system message and user input
    messages = [{"role": "system", "content": system_message}, {"role": "user", "content": message}]

    # Get the response from the model
    response = client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=False,
        temperature=temperature,
        top_p=top_p,
    )

    # Return the response
    return response.choices[0].message.content


# Create a ChatInterface with the respond function and additional inputs
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)",
        ),
    ],
)


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