app.py

import gradio as gr
from huggingface_hub import InferenceClient

# Load system prompt
with open("system_prompt.txt", "r") as f:
    SYSTEM_PROMPT = f.read()

def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    hf_token: gr.OAuthToken,
):
    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")

    messages = [{
        "role": "system",
        "content": system_message
    }]

    messages.extend(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,
    ):
        choices = message.choices
        token = ""
        if len(choices) and choices[0].delta.content:
            token = choices[0].delta.content

        response += token
        yield response


chatbot = gr.ChatInterface(
    respond,
    chatbot=gr.Chatbot(
        value=[
            {
                "role": "assistant",
                "content": "Hello! I'm Hedy Lamarr—or rather, a chatbot created to simulate a conversation using her knowledge and personality. I'm about as close as you can get to traveling back in time to speak with Hedy."
            }
        ]
    ),
    additional_inputs=[
        gr.Textbox(value=SYSTEM_PROMPT, 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)",
        ),
    ],
)

with gr.Blocks() as demo:
    with gr.Sidebar():
        gr.LoginButton()
    chatbot.render()

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