mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-28 06:58:53 +00:00
# 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>
709 lines
12 KiB
JSON
709 lines
12 KiB
JSON
{
|
|
"bedrock": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"boto3",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn"
|
|
],
|
|
"cerebras": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"cerebras_cloud_sdk",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"ci-tests": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"fastapi",
|
|
"fire",
|
|
"fireworks-ai",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"sqlite-vec",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"dell": [
|
|
"aiohttp",
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"huggingface_hub",
|
|
"matplotlib",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"dev": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"fastapi",
|
|
"fire",
|
|
"fireworks-ai",
|
|
"httpx",
|
|
"litellm",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"sqlite-vec",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"fireworks": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"fireworks-ai",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"groq": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"litellm",
|
|
"matplotlib",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn"
|
|
],
|
|
"hf-endpoint": [
|
|
"aiohttp",
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"huggingface_hub",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn"
|
|
],
|
|
"hf-serverless": [
|
|
"aiohttp",
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"huggingface_hub",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"meta-reference-gpu": [
|
|
"accelerate",
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"fairscale",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"lm-format-enforcer",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentence-transformers",
|
|
"sentencepiece",
|
|
"torch",
|
|
"torchvision",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"zmq"
|
|
],
|
|
"meta-reference-quantized-gpu": [
|
|
"accelerate",
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"fairscale",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fbgemm-gpu",
|
|
"fire",
|
|
"httpx",
|
|
"lm-format-enforcer",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentence-transformers",
|
|
"sentencepiece",
|
|
"torch",
|
|
"torchao==0.5.0",
|
|
"torchvision",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"zmq"
|
|
],
|
|
"nvidia": [
|
|
"aiosqlite",
|
|
"blobfile",
|
|
"chardet",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn"
|
|
],
|
|
"ollama": [
|
|
"aiohttp",
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"ollama",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn"
|
|
],
|
|
"open-benchmark": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"litellm",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"sqlite-vec",
|
|
"together",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn"
|
|
],
|
|
"passthrough": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"remote-vllm": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"sambanova": [
|
|
"aiosqlite",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"uvicorn"
|
|
],
|
|
"tgi": [
|
|
"aiohttp",
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"huggingface_hub",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"together": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"together",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
],
|
|
"vllm-gpu": [
|
|
"aiosqlite",
|
|
"autoevals",
|
|
"blobfile",
|
|
"chardet",
|
|
"chromadb-client",
|
|
"datasets",
|
|
"faiss-cpu",
|
|
"fastapi",
|
|
"fire",
|
|
"httpx",
|
|
"matplotlib",
|
|
"mcp",
|
|
"nltk",
|
|
"numpy",
|
|
"openai",
|
|
"opentelemetry-exporter-otlp-proto-http",
|
|
"opentelemetry-sdk",
|
|
"pandas",
|
|
"pillow",
|
|
"psycopg2-binary",
|
|
"pymongo",
|
|
"pypdf",
|
|
"redis",
|
|
"requests",
|
|
"scikit-learn",
|
|
"scipy",
|
|
"sentencepiece",
|
|
"tqdm",
|
|
"transformers",
|
|
"tree_sitter",
|
|
"uvicorn",
|
|
"vllm",
|
|
"sentence-transformers --no-deps",
|
|
"torch torchvision --index-url https://download.pytorch.org/whl/cpu"
|
|
]
|
|
}
|