import gradio as gr
from transformers import pipeline

# Initialize the inference client with the model ID
client = pipeline(model="bragour/Camel-7b-chat")

def respond(
    message,
    max_tokens,
    temperature,
    top_p,
):
    # Generate the response from the API
    result = client(
        message,
        max_new_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
    )
    
    response = result[0]['generated_text']

    return response

# Define the Gradio interface
demo = gr.Interface(
    fn=respond,
    inputs=[
        gr.Textbox(lines=2, placeholder="Type your message here...", label="Your 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)"),
    ],
    outputs=gr.Textbox(label="Response"),
)

if __name__ ==