Merge branch 'main' into nvidia-e2e-notebook

llama_stack/providers/remote/safety/bedrock/bedrock.py

@@ -6,7 +6,7 @@
 
 import json
 import logging
-from typing import Any, Dict, List
+from typing import Any
 
 from llama_stack.apis.inference import Message
 from llama_stack.apis.safety import (
@@ -53,7 +53,7 @@ class BedrockSafetyAdapter(Safety, ShieldsProtocolPrivate):
             )
 
     async def run_shield(
-        self, shield_id: str, messages: List[Message], params: Dict[str, Any] = None
+        self, shield_id: str, messages: list[Message], params: dict[str, Any] = None
     ) -> RunShieldResponse:
         shield = await self.shield_store.get_shield(shield_id)
         if not shield:

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

@@ -4,7 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 import os
-from typing import Any, Dict, Optional
+from typing import Any
 
 from pydantic import BaseModel, Field
 
@@ -27,13 +27,13 @@ class NVIDIASafetyConfig(BaseModel):
         default_factory=lambda: os.getenv("GUARDRAILS_SERVICE_URL", "http://0.0.0.0:7331"),
         description="The url for accessing the Guardrails service",
     )
-    config_id: Optional[str] = Field(
+    config_id: str | None = Field(
         default_factory=lambda: os.getenv("NVIDIA_GUARDRAILS_CONFIG_ID", "self-check"),
         description="Guardrails configuration ID to use from the Guardrails configuration store",
     )
 
     @classmethod
-    def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
+    def sample_run_config(cls, **kwargs) -> dict[str, Any]:
         return {
             "guardrails_service_url": "${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}",
             "config_id": "${env.NVIDIA_GUARDRAILS_CONFIG_ID:self-check}",

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

@@ -5,7 +5,7 @@
 # the root directory of this source tree.
 
 import logging
-from typing import Any, List, Optional
+from typing import Any
 
 import requests
 
@@ -41,7 +41,7 @@ class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):
             raise ValueError("Shield model not provided.")
 
     async def run_shield(
-        self, shield_id: str, messages: List[Message], params: Optional[dict[str, Any]] = None
+        self, shield_id: str, messages: list[Message], params: dict[str, Any] | None = None
     ) -> RunShieldResponse:
         """
         Run a safety shield check against the provided messages.
@@ -112,7 +112,7 @@ class NeMoGuardrails:
         response.raise_for_status()
         return response.json()
 
-    async def run(self, messages: List[Message]) -> RunShieldResponse:
+    async def run(self, messages: list[Message]) -> RunShieldResponse:
         """
         Queries the /v1/guardrails/checks endpoint of the NeMo guardrails deployed API.