app.py

import socket
import subprocess
import gradio as gr
from openai import OpenAI


subprocess.Popen("bash /home/user/app/start.sh", shell=True)

client = OpenAI(
    base_url="http://0.0.0.0:8000/v1",
    api_key="sk-local",
    timeout=600
)


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]
    
    for user, assistant in history:
        if user:
            messages.append({"role": "user", "content": user})
        if assistant:
            messages.append({"role": "assistant", "content": assistant})

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

    try:
        stream = client.chat.completions.create(
            model="Deepseek-R1-0528-Qwen3-8B",  # ⚠️ Replace it with the name of the model loaded by your llama.cpp
            messages=messages,
            max_tokens=max_tokens,
            temperature=temperature,
            top_p=top_p,
            stream=True,
        )

        output = ""
        for chunk in stream:
            print(chunk)
            delta = chunk.choices[0].delta.content or ""
            output += delta
            yield output

    except Exception as e:
        print(f"[Error] {e}")
        yield "⚠️ Llama.cpp server error"

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly assistant.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=4096, 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()