Update app.py

app.py

@@ -140,15 +140,19 @@ def respond(
 
     # Generate response using the InferenceClient
     response = ""
-    for message in client.chat_completion(
-        messages=messages,
-        max_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
+    try:
+        for message in client.chat_completion(
+            messages=messages,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            print("DEBUG: message:", message)  # Debugging statement
+            token = message.choices[0].delta.content
+            response += token
+            yield response
+    except Exception as e:
+        print("Error during chat completion:", e)
 
     # Append the response to history
     history.append((message, response))
@@ -182,4 +186,4 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    demo.launch(share=True)
+    demo.launch()