app.py

import os
import subprocess
import threading
import time
import gradio as gr
from huggingface_hub import InferenceClient

def start_cloudflare_tunnel():
    print("正在下载并配置 Cloudflare 隧道，请稍候...")
    
    os.system("wget -q https://github.com/cloudflare/cloudflared/releases/latest/download/cloudflared-linux-amd64 -O /tmp/cloudflared")
    os.system("chmod +x /tmp/cloudflared")
    
    print("Cloudflare downloaded...")
    
    process = subprocess.Popen(
        ["/tmp/cloudflared", "tunnel", "--url", "http://127.0.0.1:7860"],
        stdout=subprocess.PIPE, stderr=subprocess.PIPE
    )
    
    for line in process.stderr:
        line_str = line.decode('utf-8', errors='ignore')
        if "trycloudflare.com" in line_str:
            start_idx = line_str.find("https://")
            if start_idx != -1:
                url = line_str[start_idx:].strip()
                print("\n" + "="*50)
                print(f"🎉 Success! Address:\n👉 {url} 👈")
                print("="*50 + "\n")
                break

threading.Thread(target=start_cloudflare_tunnel, daemon=True).start()


def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    hf_token: gr.OAuthToken,
):
    """
    For more information on `huggingface_hub` Inference API support, please check the docs: 
    https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
    """
    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,
    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)",
        ),
    ],
)

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

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