Update app.py

app.py

@@ -2,32 +2,37 @@ from huggingface_hub import InferenceClient
 import gradio as gr
 import random
 
-# Initialize the inference client
-client = InferenceClient("google/gemma-1.1-7b-it")  # Replace with a smaller model if needed
+client = InferenceClient("google/gemma-1.1-7b-it")  # Use a smaller model for smoother results
 
-# Define the response function
 def respond(message, history):
     messages = [{"role": "system", "content": "You are a mean chatbot."}]
     
-    # Convert history to OpenAI-style messages
+    # Convert chat history to messages
     if history:
         for user_msg, bot_msg in history:
             messages.append({"role": "user", "content": user_msg})
             messages.append({"role": "assistant", "content": bot_msg})
-    
+
     messages.append({"role": "user", "content": message})
 
     response = ""
-    
-    # Call the model with streaming response
-    for chunk in client.chat_completion(messages, max_tokens=100, stream=True):
-        if chunk.choices and chunk.choices[0].delta:
-            token = chunk.choices[0].delta.get("content", "")
-            response += token
-            yield response
-
-# Set up the Gradio chat interface
+
+    try:
+        for chunk in client.chat_completion(messages, max_tokens=100, stream=True):
+            if chunk.choices and chunk.choices[0].delta:
+                token = chunk.choices[0].delta.get("content", "")
+                response += token
+                yield response  # streaming response
+
+    except StopIteration:
+        pass  # not strictly needed, but included for clarity
+
+    # Final yield to make sure a value is returned
+    if not response:
+        yield "..."
+
+# Set up the Gradio interface
 chatbot = gr.ChatInterface(fn=respond, chatbot=gr.Chatbot(), title="Mean Chatbot")
 
-# Launch the chatbot
 chatbot.launch(debug=True)
+