Clean up instructions and implementation; reorganize notebooks

llama_stack/providers/remote/safety/nvidia/nvidia.py

@@ -12,8 +12,8 @@ import requests
 from llama_stack.apis.inference import Message
 from llama_stack.apis.safety import RunShieldResponse, Safety, SafetyViolation, ViolationLevel
 from llama_stack.apis.shields import Shield
-from llama_stack.distribution.library_client import convert_pydantic_to_json_value
 from llama_stack.providers.datatypes import ShieldsProtocolPrivate
+from llama_stack.providers.utils.inference.openai_compat import convert_message_to_openai_dict_new
 
 from .config import NVIDIASafetyConfig
 
@@ -28,7 +28,6 @@ class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):
         Args:
             config (NVIDIASafetyConfig): The configuration containing the guardrails service URL and config ID.
         """
-        print(f"Initializing NVIDIASafetyAdapter({config.guardrails_service_url})...")
         self.config = config
 
     async def initialize(self) -> None:
@@ -127,9 +126,10 @@ class NeMoGuardrails:
         Raises:
             requests.HTTPError: If the POST request fails.
         """
+        messages = [await convert_message_to_openai_dict_new(message) for message in messages]
         request_data = {
             "model": self.model,
-            "messages": convert_pydantic_to_json_value(messages),
+            "messages": messages,
             "temperature": self.temperature,
             "top_p": 1,
             "frequency_penalty": 0,
@@ -140,6 +140,8 @@ class NeMoGuardrails:
                 "config_id": self.config_id,
             },
         }
+        print("request_data")
+        print(request_data)
         response = await self._guardrails_post(path="/v1/guardrail/checks", data=request_data)
 
         if response["status"] == "blocked":