app.py

import gradio as gr
from huggingface_hub import InferenceClient

def respond(message, history, system_message, max_tokens, temperature, top_p, hf_token):
    client = InferenceClient(token=hf_token, model="openai/gpt-oss-20b")

    messages = [{"role": "system", "content": system_message}] + history
    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 if message.choices and message.choices[0].delta.content else ""
        response += token
        yield response

chatbot = gr.ChatInterface(
    respond,
    type="messages",
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(1, 2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"),
        gr.Textbox(value="hf_YourTokenHere", label="HF Token")
    ],
)

if __name__ == "__main__":
    # This will launch both a web UI and a programmatic endpoint
    chatbot.launch(share=True)