app.py

import os
import gradio as gr
from openai import OpenAI

# Initialize OpenAI client using Hugging Face router
hf_token = os.getenv("apikey")  # ensure your HF_TOKEN env var is set
client = OpenAI(
    base_url="https://router.huggingface.co/v1",
    api_key=hf_token,
)

# Function to handle chat responses

def respond(
    message: str,
    history: list[tuple[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
):
    # Build messages list with system prompt
    messages = [{"role": "system", "content": system_message}]

    # Append past conversation
    for user_msg, bot_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if bot_msg:
            messages.append({"role": "assistant", "content": bot_msg})

    # Add current user message
    messages.append({"role": "user", "content": message})

    response_text = ""
    # Stream completion
    completion = client.chat.completions.create(
        model="openai/gpt-oss-120b",
        messages=messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=True,
    )
    for chunk in completion:
        # chunk.choices[0].delta is a ChoiceDelta object with .content attribute
        delta = chunk.choices[0].delta.content or ""
        response_text += delta
        yield response_text

# Setup Gradio ChatInterface

demo = gr.ChatInterface(
    fn=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)