phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 13:09:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

doc update for NVIDIA Inference provider

Browse source
This commit is contained in:
Jiayi 2025-08-21 12:00:55 -07:00
parent 58e164b8bc
commit 5bdaffd9e5
2 changed files with 76 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/safety/nvidia/nvidia.py
View file

@ -9,7 +9,7 @@ from typing import Any
import requests
from llama_stack.apis.inference import Message
from llama_stack.apis.safety import RunShieldResponse, Safety, SafetyViolation, ViolationLevel
from llama_stack.apis.safety import ModerationObject, RunShieldResponse, Safety, SafetyViolation, ViolationLevel
from llama_stack.apis.shields import Shield
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import ShieldsProtocolPrivate
@ -67,6 +67,9 @@ class NVIDIASafetyAdapter(Safety, ShieldsProtocolPrivate):
self.shield = NeMoGuardrails(self.config, shield.shield_id)
return await self.shield.run(messages)
async def run_moderation(self, input: str | list[str], model: str) -> ModerationObject:
raise NotImplementedError("NVIDIA safety provider currently does not implement run_moderation")
class NeMoGuardrails:
"""