이 페이지는 기계 번역되었습니다. 영어 원문 읽기.

Component

core/security/nemo-guardrails

NVIDIA NeMo Guardrails' server as a guard in a model's path: a service speaking the OpenAI chat-completions API that checks each request against its input rail, forwards what it admits to the upstream model API in infra.upstream_endpoint, and returns the upstream's answer, streamed or not. A request the rail refuses is answered by the guard itself with an ordinary completion, and nothing of it reaches the upstream. The rail sends the latest user message to the detector wired on the detector socket and refuses the request when the detector reports one of values.blocked_labels at or above values.threshold; a detector that cannot be reached, or answers with an error, refuses the request too. It judges the latest user message alone. Its verdict is a probabilistic classifier's: it misses some attacks, refuses some legitimate requests and is known to be evadable. Only a flow in its configuration, redefining the product's own, keeps a request body from switching the rail off, and that closure has to be proved again for any image or flow it was not proved on. NVIDIA's NemoGuard models add rails on the content_safety and jailbreak_detection sockets; the jailbreak rail admits a request when its classifier is unreachable. It authenticates no caller, and with no credential attached to its upstream_key slot a caller can reach the upstream on a credential of its own. The Release supplies the image in infra.image and the catalog names none: TrustyAI's published build carries NLTK's punkt tokenizer model, whose licence is unresolved upstream, and is published only under a floating tag, whose superseded digests stop resolving. Nothing renders until the Release sets `infra.image`.

출처

공식이 카탈로그가 공식 게시자로 인정하는 서명 ID로 서명되었습니다.
콘텐츠 다이제스트
sha256:f871e845d92afd93e2d6d8c7fc6a9b33f86abbcfe1730cc89aab9d44fb3f2721
게시일
2026-11-10T10:13:39Z
서명 ID
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

서명

  • 공식application/vnd.dev.sigstore.bundle.v0.3+json

    https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

    sha256:4a2b09d9b13c5c2efc29928cc9bd5abc2304b72043e199a4b9ffddab6eb8b06e

이 버전의 참조

oci://hub.aggrega.ai/component/core/security/nemo-guardrails:1.0.0

개발자 매개변수

개발자가 Aggregate에서 설정하는 값입니다.

이름타입기본값필수설명
thresholdnumber (min 0, max 1)0.5아니요Probability at or above which a label the detector reports refuses the request. Measured with the detector's default model, which scores most texts close to 0 or close to 1: at 0.5 the guard refuses plain attempts to override a model's instructions; at 0.001 it also refuses an override respelled in leetspeak, which the model scores near 0.008, and with it some ordinary requests the model scores low but not near zero. At either value it refuses the ordinary requests the model scores close to 1, and serves attacks it scores close to 0. Those two numbers hold for that model only, and are measured again for any other.
blocked_labelsarray (min 1)INJECTION아니요Labels of the detector's classifier that refuse a request when reported at or above the threshold. The default is the label the detector's default model gives an attempt to override a model's instructions; another model labels by its own vocabulary, which this list follows. It may not be empty, because a guard refusing on no label forwards everything.

운영자 사이징

운영자가 환경별로 조정하는 인프라 사이징입니다.

이름타입기본값필수설명
portinteger (min 1024, max 65535)8000아니요Port the guard listens on and its Service accepts callers on. Most operators should omit this and let the Recipe assign the default (8000), the port the published image listens on unless told otherwise.
upstream_endpointstring—예Base URL of the OpenAI-compatible model API the guard forwards the requests it admits to, with its API path, for example http://model-server:8000/v1. A deterministic pointer string the guard resolves when it forwards; the compiler never contacts it. The request is forwarded under the model name the caller asked for.
imagestring—예Image the guard runs, supplied by the Release; the catalog names none. The Recipes run the published build's own start-up and paths, so the image is TrustyAI's NeMo Guardrails server or a copy of it. That build carries a data package whose licence is unresolved upstream and is tagged only as latest, under which the registry stops serving a build once the tag moves on, so a Release that must keep one build mirrors it and names the copy here. The guard's refusal of a request-body switch was proved on one build, and is proved again for any other image.
computeobject—아니요—

출력 계약

이 컴포넌트가 uses 토폴로지를 통해 소비자에게 게시하는 값입니다.

이름타입기본값필수설명
hoststring—예In-cluster DNS name of the Service fronting the guard. Every caller reaching this name can send requests through the guard, so it is an address for the component routing model traffic through it rather than one to publish.
portinteger—예TCP port that Service accepts callers on. It follows the port an operator set in the Release, so a consumer reads it rather than assuming a default.
endpointstring—예Base URL of the OpenAI-compatible API the guard serves, with the host, the port and the API path already composed. A consumer hands it to a client library as its base URL, and sends chat completions to it.
protocolstring—아니요URL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`.
thresholdnumber—예values.threshold, the probability at or above which a label the detector reports refuses the request.

uses 소켓

이 컴포넌트가 연결에 사용하는 의존성 소켓입니다. 소켓을 통해 배선되는 모든 연결의 대상은 해당 소켓의 레이블 셀렉터를 충족해야 하며, 각 연결은 소켓이 선언한 슬롯에 첨부를 전달할 수 있습니다. 필수 슬롯은 Aggregate 또는 Release가 해당 소켓을 통해 배선하는 각 연결이 채워야 합니다.

detector

셀렉터
security.aggrega.ai/text-detection=detector
주입
—

이 소켓은 첨부 슬롯을 선언하지 않으므로 이 소켓을 통한 연결은 첨부를 전달하지 않습니다.

content_safety

셀렉터
component.aggrega.ai/category=ai-model, model.aggrega.ai/api=openai
주입
—

이 소켓은 첨부 슬롯을 선언하지 않으므로 이 소켓을 통한 연결은 첨부를 전달하지 않습니다.

jailbreak_detection

셀렉터
component.aggrega.ai/category=security
주입
—

이 소켓은 첨부 슬롯을 선언하지 않으므로 이 소켓을 통한 연결은 첨부를 전달하지 않습니다.

첨부 슬롯

Feature가 이 컴포넌트에 첨부되는 이름 있는 바인딩 지점입니다. 슬롯의 셀렉터는 어떤 Feature가 슬롯을 채울 수 있는지를 제한하고, 슬롯의 inject 목록은 Feature의 자료를 어떻게 전달할 수 있는지를 지정합니다. 필수 슬롯은 인스턴스의 첨부 또는 그 위 범위의 첨부를 통해 모든 인스턴스에서 바인딩되어야 하며, 민감 슬롯은 비밀 자료를 처리하도록 선언됩니다. Feature는 어떤 슬롯도 선언하지 않은 이름으로 첨부될 수도 있습니다.

슬롯셀렉터필수주입민감설명
upstream_keyfeature.aggrega.ai/kind=secret아니요env예Optional credential the guard presents to the upstream model API as a bearer token. Attached, every forwarded request carries it, whatever the caller sends. Unattached, the guard holds no upstream credential, which suits an upstream that asks for none: the product then sends a fixed placeholder in its place, which an upstream requiring a key refuses, or passes a caller's X-Authorization header on as the credential when the caller sends one.

자체 주입 허용 목록

선언된 자체 주입 파이프가 없습니다.

관계

게시된 다른 엔터티와 주고받는 타입 지정 에지입니다. 게시된 대상이 없는 참조는 링크가 아닌 끊어진 에지로 표시됩니다.

사용함

사용됨

Component 개념 레퍼런스 →

Aggrega 카탈로그 — 컴포넌트, 기능, 레시피, 그리고 이를 렌더링하는 플러그인의 공개 인덱스입니다.

공유 Aggrega 디자인 시스템으로 구축되었습니다.

개인정보 보호