app.py

import gradio as gr
import torch
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="text",
    outputs=["text"]
)
iface.launch(inline = False)

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