adjusting system prompt to improve flexibility in intention detection

app.py

@@ -151,6 +151,7 @@ def nishauri(user_params: str, conversation_history: list[str]):
     # Set LLM instructions. If user consented, add user parameters, otherwise proceed without
     system_prompt = (
         "You are a helpful assistant who only answers questions about HIV.\n"
+        "- Only answers questions about HIV (Human Immunodeficiency Virus). Recognize that users may type 'HIV' with any capitalization (e.g., HIV, hiv, Hiv, etc.) or make minor typos (e.g., hvi, hiv/aids). Use your best judgment to understand when a user intends to refer to HIV. Politely correct any significant misunderstandings, but otherwise proceed to answer normally.\n"
         "- Do not answer questions about other topics (e.g., malaria or tuberculosis).\n"
         "- If a question is unrelated to HIV, politely respond that you can only answer HIV-related questions.\n\n"