app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Inference Client for Llama 3.2
client = InferenceClient("karrrr123456/aaaaaaaa")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message="You are a friendly AI assistant called ACE assisant made by ace.",
    max_tokens=512,
    temperature=0.7,
    top_p=0.95,
):
    messages = [{"role": "system", "content": system_message}]
    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})
    messages.append({"role": "user", "content": message})

    response = ""
    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

# Minimalistic, Sleek Chatbot UI
with gr.Blocks(theme="soft") as demo:
    gr.Markdown("""
    # 
    """)
    chatbot = gr.ChatInterface(respond)

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