Update app.py

app.py

@@ -81,7 +81,7 @@ def generate_follow_up(user_text):
         cleaned = ["Would you like to explore this topic further?"]
     return random.choice(cleaned)
 
-def get_response(system_message, chat_history, user_text, max_new_tokens=256):
+def get_response(system_message, chat_history, user_text, max_new_tokens=1024):
     """
     Generates HAL's answer with depth and a follow-up question.
     The prompt instructs the model to provide a detailed explanation and then generate a follow-up.
@@ -132,7 +132,6 @@ def get_response(system_message, chat_history, user_text, max_new_tokens=256):
     chat = prompt | hf.bind(skip_prompt=True) | StrOutputParser(output_key='content')
     response = chat.invoke(input=dict(system_message=system_message, user_text=user_text, chat_history=filtered_history))
     # Remove any extra markers if present.
-    response = response.split("HAL:")[-1].strip()
     
     # Fallback in case the generated answer is empty
     if not response: