app.py

import os
import gradio as gr
from openai import OpenAI
from typing import List, Tuple

ENDPOINT_URL = "https://api.hyperbolic.xyz/v1"

OAI_API_KEY = os.getenv('HYPERBOLIC_XYZ_KEY')

client = OpenAI(base_url=ENDPOINT_URL,api_key=OAI_API_KEY)

def respond(
    message: str,
    history: List[Tuple[str, str]],
    system_message: str,
    max_tokens: int,
    temperature: float,
    top_p: float,
):
    # Prepare the conversation history
    messages = [{"role": "system", "content": system_message}]

    for user_msg, assistant_msg in history:
        if user_msg:
            messages.append({"role": "user", "content": user_msg})
        if assistant_msg:
            messages.append({"role": "assistant", "content": assistant_msg})

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

    # Stream the response from OpenAI
    response = ""
    for chunk in client.chat.completions.create(
        model="deepseek-ai/DeepSeek-V3",
        messages=messages,
        max_tokens=max_tokens,
        temperature=temperature,
        top_p=top_p,
        stream=True,
    ):
        token = chunk.choices[0].delta.content or ""
        response += token
        yield response


# Gradio ChatInterface with additional inputs for customization
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a helpful assistant.", 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()