app.py

import gradio as gr
from openai import OpenAI
import os

"""
Initialize the OpenAI client
"""
client = OpenAI(
    api_key="na",  
    base_url=os.environ['API_BASE']
)


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    """
    Respond to a user message using the OpenAI client with streaming enabled.
    """
    messages = [{"role": "system", "content": system_message}]

    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 = ""

    try:
        # Call the OpenAI client with streaming
        for message_chunk in client.chat.completions.create(
            model="DeepSeek R1 Distill Llama 8B",  # Replace with your model name
            messages=messages,
            max_tokens=max_tokens,
            temperature=temperature,
            top_p=top_p,
            stream=True,  # Enable streaming
            stop=["<|im_start|>", "<|im_end|>"]
        ):
            # Extract the streamed content, if it exists
            token = message_chunk.choices[0].delta.content
            if token:  # Only concatenate if content is not None
                response += token
                yield response
    except Exception as e:
        yield f"Error: {str(e)}"


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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)",
        ),
    ],
    title="Inference demo on AMD Instinct MI50",
    # description="tiiuae Falcon3 10B Q8 with llama.cpp",
    description="DevQuasar R1 8B Q8 with llama.cpp",
)


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