app.py

import gradio as gr
from huggingface_hub import InferenceClient
import os

# 1. Setup the Client 
# Tip: Add your HF_TOKEN to the Space's "Variables and Secrets" settings 
# so you don't have to hardcode it!
HF_TOKEN = os.getenv("HF_TOKEN") 
client = InferenceClient(model="Qwen/Qwen2.5-7B-Instruct", token=HF_TOKEN)

def respond(
    message,
    history,
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]
    
    # Convert Gradio history to HF format
    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 = ""
    # Call the API
    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
        if token:
            response += token
            yield response

# 2. Setup the Interface
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are the CodeIgnite AI tutor. Help students learn coding by being encouraging and clear.", 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"),
    ],
)

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