Update app.py

app.py

@@ -82,7 +82,6 @@ def think(request):
 
         #if reasoning != "":
         #    messages.append({"role": "assistant", "content": "<think>\n" + reasoning + "</think>\n"})
-        print(messages)
         payload = {
             "model": model,
             "messages": messages,
@@ -136,7 +135,7 @@ def chat_with_openai(message: str, history: list, temperature: float, max_new_to
 
     if not fast_mode:
         # Immediately yield a "thinking" status message.
-        yield "HealthAssistant is Thinking! Please wait, your response will output shortly... This may take 30-60 seconds...\n\n"
+        yield "HealthAssistant is Thinking! Please wait, your response will output shortly. This may take 30-60 seconds...\n\n"
 
         think_result = think(conversation)
     
@@ -198,7 +197,7 @@ with gr.Blocks(css=css) as demo:
     gr.HTML(DESCRIPTION)
 
     # Add the checkbox directly to the layout
-    fast_mode_checkbox = gr.Checkbox(label="Fast Mode (Skips Reasoning, Provides Immediate Responses)", value=False)
+    fast_mode_checkbox = gr.Checkbox(label="Fast Mode (Skips Reasoning. Provides Immediate, Less Accurate Responses.)", value=False)
 
     gr.ChatInterface(
         fn=chat_with_openai,