Update app.py

app.py

@@ -479,7 +479,7 @@ class LlamaGenerator(BaseGenerator):
         Returns:
             str: Generated response
         """
-        prompt = self._construct_prompt(
+        prompt = self.prompt_builder.format(
             context,
             user_input,
             chat_history,
@@ -763,7 +763,7 @@ async def generate_stream(
             config = request.config or GenerationConfig()
             
             async for token in generator.generate_stream(
-                prompt=generator._construct_prompt(
+                prompt=generator.prompt_builder.format(
                     context=request.context or "",
                     user_input=user_input,
                     chat_history=chat_history