Update app.py

app.py

@@ -22,29 +22,24 @@ def user(user_message, history: list):
 
 
 def bot(history: list, user_message):
-    # Use OpenVINO to generate a response
-    full_response = ""  # Store the complete response
+    full_response = ""
 
-    def streamer(subword):  # Local streamer function
-        nonlocal full_response  # Allow modification of outer scope variable
-        full_response += subword  # Accumulate the subword
-        history[-1]['content'] = full_response  # Update chatbot content
+    def streamer(subword):
+        nonlocal full_response
+        full_response += subword
+        history[-1]['content'] = full_response
         yield history
         return ov_genai.StreamingStatus.RUNNING
 
-
-    # Initialize the bot message in history
     history.append({"role": "assistant", "content": ""})
 
-    # Generate the response using the streaming function
-    for updated_history in pipe.generate(user_message, streamer=streamer, max_new_tokens=100):
-        yield updated_history
-
-    # Alternatively, without the step-by-step updates, you can just do this:
-    # full_response = pipe.generate(user_message, max_new_tokens=100) # but this will skip the steaming
-    # history[-1]['content'] = full_response
-    # yield history
-
+    try:
+        for updated_history in pipe.generate(user_message, streamer=streamer, max_new_tokens=100):
+            yield updated_history
+    except Exception as e:
+        print(f"Error during OpenVINO generation: {e}") # Log the error!
+        history[-1]['content'] = "An error occurred while generating the response."
+        yield history
 
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot(type="messages")