app.py

import gradio as gr
from huggingface_hub import InferenceClient
import os

# Get the Hugging Face API token from environment variables
API_TOKEN = os.getenv("HF_API_TOKEN")

# Initialize the Inference Client with the correct token
client = InferenceClient("abhillubillu/ai_gameapp", token=API_TOKEN)

def respond(message, history, system_message, max_tokens, temperature, top_p):
    messages = [{"role": "system", "content": system_message}]
    
    for user_msg, assistant_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if assistant_msg:
            messages.append({"role": "assistant", "content": assistant_msg})
    
    messages.append({"role": "user", "content": message})
    
    response = ""
    
    try:
        for message in client.chat_completion(
            messages,
            max_tokens=max_tokens,
            stream=True,
            temperature=temperature,
            top_p=top_p,
        ):
            token = message.choices[0].delta.content
            response += token
            yield response
    except Exception as e:
        yield f"Error: {str(e)}"

# Define the Gradio Chat Interface with 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(share=True)