Update app.py

app.py

@@ -1,18 +1,30 @@
 import gradio as gr
-from transformers import pipeline
+from huggingface_hub import InferenceClient
+import os
 
-# 加载对话模型
-chatbot = pipeline("text-generation", model="zai-org/GLM-5.1")
+# 从环境变量读取 token
+HF_TOKEN = os.environ.get("HF_TOKEN")
 
-# 定义聊天函数
-def chat_function(input_text):
-    conversation = chatbot(input_text)
-    return conversation[-1]["generated_text"]
+client = InferenceClient(
+    provider="zai-org",
+    api_key=HF_TOKEN,
+)
 
-# 使用 Gradio 创建聊天 API
-def create_chat_api():
-    with gr.Interface(fn=chat_function, inputs="text", outputs="text", title="Chatbot API") as demo:
-        demo.launch()
+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})
 
-# 启动服务
-create_chat_api()
+    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)