app.py

import gradio as gr
from huggingface_hub import InferenceClient
import os

# 从环境变量读取 token
HF_TOKEN = os.environ.get("HF_TOKEN")

client = InferenceClient(
    provider="zai-org",
    api_key=HF_TOKEN,
)

def chat_function(message, history):
    messages = []
    for human, assistant in history:
        messages.append({"role": "user", "content": human})
        messages.append({"role": "assistant", "content": assistant})
    messages.append({"role": "user", "content": message})

    response = client.chat.completions.create(
        model="zai-org/GLM-5.1",
        messages=messages,
        max_tokens=512,
    )
    return response.choices[0].message.content

with gr.Blocks() as demo:
    gr.ChatInterface(fn=chat_function)

demo.launch(server_name="0.0.0.0", server_port=7860)