app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Initialize Hugging Face client with your model
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history,
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # Prepare messages for the API call
    messages = [{"role": "system", "content": system_message}]
    messages.append({"role": "user", "content": message})

    # Make API call without streaming
    response = client.chat_completion(
        messages=messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=False,  # Streaming disabled
    )

    # Extract the response content
    response_text = response.choices[0].message['content']
    return response_text  # Directly return the response text


# Gradio interface setup
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()