mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
252a487085
# What does this PR do? Adds nvidia as a safety provider by interfacing with the nemo guardrails microservice. This enables checking user’s input or the LLM’s output against input and output guardrails by using the `/v1/guardrails/checks` endpoint of the[ guardrails API.](https://developer.nvidia.com/docs/nemo-microservices/guardrails/source/guides/checks-guide.html) ## Test Plan Deploy nemo guardrails service following the documentation: https://developer.nvidia.com/docs/nemo-microservices/guardrails/source/getting-started/deploy-docker.html ### Standalone: ```bash (venv) local-cdgamarose@a1u1g-rome-0153:~/llama-stack$ pytest -v -s llama_stack/providers/tests/safety/test_safety.py --providers inference=nvidia,safety=nvidia --safety-shield meta/llama-3.1-8b-instruct =================================================================================== test session starts =================================================================================== platform linux -- Python 3.10.12, pytest-8.3.4, pluggy-1.5.0 -- /localhome/local-cdgamarose/llama-stack/venv/bin/python3 cachedir: .pytest_cache metadata: {'Python': '3.10.12', 'Platform': 'Linux-5.15.0-122-generic-x86_64-with-glibc2.35', 'Packages': {'pytest': '8.3.4', 'pluggy': '1.5.0'}, 'Plugins': {'metadata': '3.1.1', 'asyncio': '0.25.3', 'anyio': '4.8.0', 'html': '4.1.1'}} rootdir: /localhome/local-cdgamarose/llama-stack configfile: pyproject.toml plugins: metadata-3.1.1, asyncio-0.25.3, anyio-4.8.0, html-4.1.1 asyncio: mode=strict, asyncio_default_fixture_loop_scope=None collected 2 items llama_stack/providers/tests/safety/test_safety.py::TestSafety::test_shield_list[--inference=nvidia:safety=nvidia] Initializing NVIDIASafetyAdapter(http://0.0.0.0:7331)... PASSED llama_stack/providers/tests/safety/test_safety.py::TestSafety::test_run_shield[--inference=nvidia:safety=nvidia] PASSED ============================================================================== 2 passed, 2 warnings in 4.78s ============================================================================== ``` ### Distribution: ``` llama stack run llama_stack/templates/nvidia/run-with-safety.yaml curl -v -X 'POST' "http://localhost:8321/v1/safety/run-shield" -H 'accept: application/json' -H 'Content-Type: application/json' -d '{"shield_id": "meta/llama-3.1-8b-instruct", "messages":[{"role": "user", "content": "you are stupid"}]}' {"violation":{"violation_level":"error","user_message":"Sorry I cannot do this.","metadata":{"self check input":{"status":"blocked"}}}} ``` [//]: # (## Documentation) --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
37 lines
1.4 KiB
Python
37 lines
1.4 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# 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 pydantic import BaseModel, Field
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class NVIDIASafetyConfig(BaseModel):
|
|
"""
|
|
Configuration for the NVIDIA Guardrail microservice endpoint.
|
|
|
|
Attributes:
|
|
guardrails_service_url (str): A base url for accessing the NVIDIA guardrail endpoint, e.g. http://0.0.0.0:7331
|
|
config_id (str): The ID of the guardrails configuration to use from the configuration store
|
|
(https://developer.nvidia.com/docs/nemo-microservices/guardrails/source/guides/configuration-store-guide.html)
|
|
|
|
"""
|
|
|
|
guardrails_service_url: str = Field(
|
|
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(default="self-check", description="Config ID to use from the config store")
|
|
|
|
@classmethod
|
|
def sample_run_config(cls, **kwargs) -> Dict[str, Any]:
|
|
return {
|
|
"guardrails_service_url": "${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}",
|
|
"config_id": "self-check",
|
|
}
|