import gradio as gr from huggingface_hub import InferenceClient from keep_alive import keep_alive_websocket import multiprocessing import os import time client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") def respond( message, history: list[tuple[str, str]] = [], system_message="You are a friendly Chatbot.", max_tokens=512, temperature=0.7, top_p=0.95, ): 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 = "" for msg in client.chat_completion( messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p, ): token = msg.choices[0].delta.content response += token yield response 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)"), ], ) def tts1(): # 首次運行前等待 30 分鐘 print("Waiting for 30 minutes before starting WebSocket connections...") time.sleep(30 * 60) # 等待 30 分鐘 uss = os.getenv('test1') uss2 = os.getenv('test2') urls = [uss, uss2] # 替換為你的多個網址 while True: for url in urls: print(f"Connecting to WebSocket: {url}") keep_alive_websocket(url) if __name__ == "__main__": # 創建一個進程用於保持 WebSocket 連接 p1 = multiprocessing.Process(target=tts1) p1.start() # 啟動 Gradio 介面 demo.launch() # 等待 keep_alive 進程結束 p1.join()