Update app.py

app.py

@@ -3,11 +3,11 @@ from huggingface_hub import InferenceClient
 import os
 import json
 
-api_key=os.environ.get('qwen_API_KEY')
+api_key = os.environ.get('qwen_API_KEY')
 """
 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("Qwen/Qwen2.5-72B-Instruct",token=api_key)
+client = InferenceClient("Qwen/Qwen2.5-72B-Instruct", token=api_key)
 
 def respond(
     message,
@@ -29,18 +29,20 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p
-    ):
-        token = message.choices[0].delta.content
+    try:
+        async for message in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p
+        ):
+            token = message.choices[0].delta.content
+            response += token
+            yield response
+    except Exception as e:
+        yield f"An error occurred: {e}"
 
-        response += token
-        yield response
-        
 example_prompts = [
     ["How to cook Kung Pao chicken the tastiest?"],
     ["Help me create an email expressing my greetings to an old friend."],
@@ -60,7 +62,6 @@ demo = gr.ChatInterface(
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
     chatbot=gr.Chatbot(show_label=True, show_copy_button=True)
-
 )
 
 if __name__ == "__main__":