Component
core/security/trustyai-huggingface-detector
TrustyAI's Hugging Face detector: a service that runs one text classifier from the Hugging Face Hub and reports what it detects in the texts a caller sends. For each text posted to its content route with a threshold, it answers with every label the classifier scores at or above it, never the classifier's first label, read as the one for harmless text. It changes nothing and forwards nothing: what to do about a detection is the caller's decision, and core/security/nemo-guardrails is one such caller. The classifier is values.model at values.model_revision. The default, protectai/deberta-v3-base-prompt-injection-v2 (Apache-2.0), labels each text SAFE or INJECTION, and its own model card states that the project which published it is archived and no longer maintained. Another model labels and scores differently, so a caller's labels and thresholds follow it. The verdict misses some attacks and flags some ordinary requests. The weights are fetched where the service runs, never at build time. It authenticates no caller and every text reaches it as sent, so it is published on an in-cluster address only. Its own metrics, in the Prometheus format at /metrics on the same port, are published as `metrics_endpoint`. The Release supplies the image in infra.image and the catalog names none: TrustyAI's published build carries NVIDIA's proprietary CUDA runtime, whose licence agreement limits its use to systems with NVIDIA GPUs, and is published only under a floating tag, whose superseded digests stop resolving. Nothing renders until the Release sets `infra.image`.
Asal-usul
- Digest konten
- sha256:8f985fb76602947f3d871a7625d6614d76375528aa12e151d26a51559254d630
- Dipublikasikan
- 2026-11-10T10:13:59Z
- Identitas penandatangan
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Tanda tangan
- Resmiapplication/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:c34f4d9c71225ccd5e22a7d802c196dda140050af22eb57aa716bedbe73525f8
Referensi pada versi ini
oci://hub.aggrega.ai/component/core/security/trustyai-huggingface-detector:1.0.0Parameter pengembang
Nilai yang ditetapkan pengembang di Aggregate.
| Nama | Tipe | Bawaan | Wajib | Deskripsi |
|---|---|---|---|---|
| model | string | protectai/deberta-v3-base-prompt-injection-v2 | tidak | Hugging Face model id of the sequence-classification model the service runs. The default is a prompt-injection classifier labelling each text SAFE or INJECTION; another model labels by its own vocabulary, which a caller's refusal labels must then follow. |
| model_revision | string | 90c9989b1a342275dd0d1a95aad283c04e075671 | tidak | Revision of values.model to fetch — a commit id, a tag or a branch. The default is the commit of the default model whose scores a caller's thresholds are measured against; set it together with values.model, and main follows the repository's newest revision. |
Penentuan ukuran oleh operator
Ukuran infrastruktur yang disesuaikan operator untuk setiap lingkungan.
| Nama | Tipe | Bawaan | Wajib | Deskripsi |
|---|---|---|---|---|
| port | integer (min 1024, max 65535) | 8000 | tidak | Port the service 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. |
| image | string | — | ya | Image the service and its weights-pull step run, supplied by the Release; the catalog names none. The Recipes run the published build's own server command, log configuration and Hugging Face command-line tool, so the image is TrustyAI's Hugging Face detector or a copy of it. That build carries NVIDIA's proprietary CUDA runtime, whose licence agreement limits its use to systems with NVIDIA GPUs, 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. |
| compute | object | — | tidak | — |
| model_cache | object | — | tidak | The volume the pull step writes the weights to and the server reads them from. |
Kontrak keluaran
Nilai yang dipublikasikan komponen ini kepada konsumen melalui topologi uses.
| Nama | Tipe | Bawaan | Wajib | Deskripsi |
|---|---|---|---|---|
| host | string | — | ya | In-cluster DNS name of the Service fronting the detector. Every caller reaching this name can submit text, so it is an address for the component that calls the service rather than one to publish. |
| port | integer | — | ya | TCP 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. |
| endpoint | string | — | ya | Base URL of the detector's HTTP API, with the host and the port already composed and no path. A caller posts the texts to check to the content route under it. |
| model | string | — | ya | Hugging Face model id of the classifier the service loaded, so a caller can record which model gave a verdict. |
| protocol | string | — | tidak | URL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`. |
| metrics_endpoint | string | — | tidak | The full address Prometheus scrapes this component's metrics at — scheme, host, port and path, `http://<host>:<port>/metrics` on the port callers reach. Empty where the component serves none reachable. |
Soket uses
Soket dependensi yang menjadi jalur koneksi komponen ini. Target setiap koneksi yang dihubungkan melalui sebuah soket harus memenuhi selektor labelnya, dan setiap koneksi dapat membawa lampiran pada slot yang dideklarasikan soket tersebut. Slot wajib harus diisi oleh setiap koneksi yang dihubungkan oleh Aggregate atau Release melalui soket tersebut.
Tidak ada soket uses yang dideklarasikan.
Slot lampiran
Titik pengikatan bernama tempat sebuah Feature dilampirkan ke komponen ini. Selektor sebuah slot membatasi Feature mana yang dapat mengisinya, dan daftar injeksinya menyebutkan cara materi Feature dapat dikirimkan. Slot wajib harus terikat pada setiap instans, melalui lampiran pada instans tersebut atau pada cakupan di atasnya, dan slot sensitif dideklarasikan untuk menangani materi rahasia. Sebuah Feature juga dapat dilampirkan dengan nama yang tidak dideklarasikan oleh slot mana pun.
| Slot | Selektor | Wajib | Injeksi | Sensitif | Deskripsi |
|---|---|---|---|---|---|
| model_pull_token | feature.aggrega.ai/kind=secret | tidak | env | ya | Optional Hugging Face Hub access token for a gated model. When attached, the weights-pull step receives it as an environment variable, and the server itself never does; unattached, weights are pulled anonymously, which the default model allows. |
Daftar izin injeksi mandiri
Tidak ada pipa injeksi mandiri yang dideklarasikan.
Relasi
Sisi bertipe ke dan dari entitas lain yang dipublikasikan. Referensi tanpa target yang dipublikasikan ditampilkan sebagai sisi yang terputus, bukan sebagai tautan.
Menggunakan
Entitas ini tidak menggunakan apa pun di katalog.
Digunakan oleh
menggunakan soket «auth_core»
menggunakan soket «auth_core»
menggunakan soket «auth_core»
menggunakan soket «auth_core»
menggunakan soket «upstream»
menggunakan soket «forward_target»
menggunakan soket «scrape_target»
menggunakan soket «store»
menggunakan soket «detector»
menggunakan soket «detector»
menggunakan soket «jailbreak_detection»
berlaku untuk
berlaku untuk
berlaku untuk
berlaku untuk
berlaku untuk
berlaku untuk
berlaku untuk
mengimplementasikan
mengimplementasikan