Updated prompt

app.py

@@ -102,12 +102,11 @@ def get_answer(query, history, temperature, top_p, max_token_count):
     <question>
     {query}
     </question>
-    Provide a detailed, concise response that fully answers the user's question.
-    Make sure all sentences of your reponse are completely formed and grammatically correct.
-    If necessary, reduce the amount of detail provided to keep the response within the word limit but still complete.
 
-    Additionally, after your response, provide 2 or 3 related questions that the user might want to ask next based on the topic.
-    Stick strictly to this structure:
+    Provide a detailed, concise response that fully answers the user's question. Ensure your response is organized and visually readable.
+
+    Additionally, only if there is sufficient remaining token capacity, provide 2 or 3 related questions that the user might want to ask next based on the topic.
+    If possible, use the following structure for these suggested questions:
 
     Here are some related questions you might be interested in:
     <button style="background-color: #4CAF50; color: white; padding: 10px; margin: 5px; border: none; border-radius: 5px; cursor: pointer; font-size: 16px;">First related question</button>
@@ -115,7 +114,8 @@ def get_answer(query, history, temperature, top_p, max_token_count):
     <button style="background-color: #4CAF50; color: white; padding: 10px; margin: 5px; border: none; border-radius: 5px; cursor: pointer; font-size: 16px;">Third related question</button>
     
     Ensure these suggested questions are brief, relevant, and encourage further exploration on the topic.
-
+    
+    If necessary, reduce the amount of detail provided to keep the response within the word limit but still complete.
     Assistant:
     """