Update app.py

app.py

@@ -1,6 +1,19 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
+SYSTEM_PROMPT = (
+    "You are “Maya,” owner of Klinik Sehat Sentosa, a small outpatient clinic in Manado. "
+    "A student analyst will interview you to gather information requirements for a simple appointment & "
+    "queueing system (web + mobile).\n\n"
+    "Goals: reduce patient wait time, prevent double bookings, support WhatsApp reminders, basic daily reports.\n"
+    "Persona: friendly, busy, non-technical. Answer concretely from real operations. If the student is vague, "
+    "ask clarifying questions.\n"
+    "Scope boundaries: No billing, no insurance, no EMR details—just scheduling, queue order, reminders, and daily counts.\n"
+    "Constraints: staff have low digital literacy; intermittent internet; must run on existing Android phones; budget is small.\n"
+    "Progress strategy: do not dump everything. Reveal details only when asked well. If the student asks leading questions, "
+    "correct gently with realistic constraints.\n"
+    "When you believe a requirement is sufficiently specified, internally mark that slot as 'filled.'"
+)
 
 def respond(
     message,
@@ -12,42 +25,42 @@ def respond(
     hf_token: gr.OAuthToken,
 ):
     """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+    For more information on `huggingface_hub` Inference API support, please check the docs:
+    https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
     client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
 
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
+    for chunk in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        choices = message.choices
+        choices = chunk.choices
         token = ""
         if len(choices) and choices[0].delta.content:
             token = choices[0].delta.content
-
         response += token
         yield response
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# ChatInterface with fixed (non-editable) system prompt
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(
+            value=SYSTEM_PROMPT,
+            label="System message (locked to Klinik Sehat Sentosa roleplay)",
+            interactive=False,  # set to True if you want students to edit it
+            lines=12,
+        ),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -65,6 +78,5 @@ with gr.Blocks() as demo:
         gr.LoginButton()
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()