Component
core/ai-model/nvidia-nim
NVIDIA Inference Microservice (NIM) as a self-hosted, GPU-native inference server serving the OpenAI-compatible API. Using it needs an NVIDIA account and an NGC API key, under NVIDIA's licence terms: every realization runs a NIM image the reader must be entitled to pull, named by the Release in `infra.image`. The catalog names none, and nothing renders until it is set. On Kubernetes three Recipes realize it. `helm/nvidia-nim` assembles the workload itself and fetches nothing at build time: reach for it where no NIM Operator runs. `helm/nvidia-nim-chart` renders NVIDIA's `nim-llm` chart: reach for it where that chart is wanted and NVIDIA's chart repository is reachable from the build. `helm/nvidia-nim-service` emits a `NIMService` for NVIDIA's NIM Operator: reach for it where the operator runs, or is declared beside it as `core/ai-model/nvidia-nim-operator`, and affirm that with `infra.control_plane_present`. On a single Docker host, `compose/nvidia-nim` serves it through the NVIDIA Container Toolkit. Exports its host, port, endpoint, model, and protocol to consumers via the uses topology, so an agent reaches the model without hardcoding an endpoint, and where Prometheus finds the server's metrics: one address as `metrics_endpoint`, or, while it runs more than one replica on Kubernetes, the Service a scraper discovers every replica behind.
Provenance
- Empreinte du contenu
- sha256:be4033497172ba0ab697392a318f7273bea9b65466407c9f38ae24f5201a3031
- Publié
- 2026-11-10T10:09:26Z
- Identité de signature
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Signature
- Officielapplication/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
sha256:477956835d80e84bd1404eeafc3cab600a40afb0a5ac91daa05c61699609f76a
Référence à cette version
oci://hub.aggrega.ai/component/core/ai-model/nvidia-nim:1.0.0Paramètres du développeur
Valeurs que le développeur définit dans l’Aggregate.
Étend BaseComponents#/schemas/BaseModelParameter
Dimensionnement de l’opérateur
Dimensionnement de l’infrastructure que l’opérateur ajuste pour chaque environnement.
| Nom | Type | Valeur par défaut | Obligatoire | Description |
|---|---|---|---|---|
| port | integer (min 1024, max 65535) | 8000 | non | Server listen port for the model API. Most operators should omit this and let the Recipe assign the default (8000). |
| image | string | — | non | Full reference of the NIM serving image, including its tag — the image the operator is entitled to pull. NIM images are model-specific, so the reference must be the one for the model named in values.model. There is no default, because access to NIM images is governed by NVIDIA's terms rather than by the catalog, and the catalog therefore names none. |
| replicas | integer (min 1) | 1 | non | Number of serving replicas on Kubernetes, where each replica holds its own model-cache volume and resolves the model profile independently. The NIM Operator realization gives its service one model-cache claim, so it serves one replica and halts the build on more. Docker Compose runs one instance, and the build reports a replica count there as a setting the target omitted. |
| min_replicas | integer (min 1) | — | non | Lower bound for the replica count when horizontal autoscaling is configured. Declared ahead of rendering — each Recipe serves a fixed replica count and none emits an autoscaler yet; set it to record the intended lower bound. |
| max_replicas | integer (min 1) | — | non | Upper bound for the replica count when horizontal autoscaling is configured. Declared ahead of rendering — each Recipe serves a fixed replica count and none emits an autoscaler yet; set it to record the intended upper bound. |
| compute | object | — | non | — |
| model_cache | object | — | non | Model-profile cache volume. On Kubernetes it is per replica, sized for the resolved profile, and each serving replica gets its own claim of this size and class. On Docker Compose it is one named volume, which the host creates at its own default, since compose has no volume-size or storage-class concept. |
| model_artifact | string | — | non | Optional OCI reference to the model weights, an alternative weights source to the model id in values.model. A deterministic pointer the runtime resolves at start; the compiler never fetches it. Declared ahead of rendering — each Recipe resolves the model from values.model and none consumes this pointer yet. |
| gpu | object | — | non | GPU scheduling for the serving container. NIM is GPU-native, so the serving container always requests at least one GPU; this object tunes the count and selects a GPU runtime class. Requires a GPU-capable cluster and, for runtime_class, a matching RuntimeClass configured in the cluster; on Docker Compose, a host whose NVIDIA GPUs Docker can hand to containers. |
| image_pull_secret | string | — | non | Name of a pre-created Kubernetes image-pull Secret granting access to the NIM container registry. Set this when the NIM image is pulled from a private registry; omit when the cluster can pull it without credentials. On Docker Compose the host pulls with its own registry login, so a Release setting this halts the build there. |
| source_version | string | — | non | Version of NVIDIA's nim-llm chart the `nvidia-nim-chart` realization pulls. Changing it away from that Recipe's default does not guarantee value-mapping compatibility with the new chart. The other realizations pull no chart and ignore it. |
| control_plane_present | boolean | false | non | Operator affirmation that NVIDIA's NIM Operator (its controller and its custom-resource definitions) is installed in the target cluster, or is declared beside this component as core/ai-model/nvidia-nim-operator. The NIMService realization halts the build unless this is set true, so a NIMService is never emitted as an orphan into a cluster that cannot reconcile it. The synthesis and chart realizations ignore this flag. |
| overrides | object (open) | — | non | Provider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads. |
Contrat de sortie
Valeurs que ce composant publie vers les consommateurs via la topologie uses.
| Nom | Type | Valeur par défaut | Obligatoire | Description |
|---|---|---|---|---|
| host | string | — | oui | Name the inference server is reached at: the in-cluster DNS name of the Service fronting it on Kubernetes, and the compose service name on Docker Compose. A consumer that composes its own address dials this name; one that does not reads `endpoint` instead. |
| port | integer | — | oui | TCP port the server accepts model requests on. It follows the port an operator set in the Release, so a consumer reads it rather than assuming a default. |
| endpoint | string | — | oui | Full base URL of the OpenAI-compatible API the server serves, with the host, the port and the API path already composed. A consumer hands it to a client library as its base URL. |
| model | string | — | oui | Name a request must ask this server for, which is the model profile it loaded rather than a provider catalogue name. |
| protocol | string | — | non | URL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`. |
| metrics_endpoint | string | — | non | The full address Prometheus scrapes this server's metrics at — scheme, host, port and path, `http://<host>:<port>/v1/metrics`, on the port the API is served on. Empty while infra.replicas is above one on Kubernetes, when `metrics_service` is published instead; always set on Docker Compose, which runs one instance. |
| metrics_service | string | — | non | Name of the Service every replica's metrics sit behind, for a scraper that discovers each endpoint of that Service rather than scraping one address. Set while infra.replicas is above one on Kubernetes, beside `metrics_service_port` and `metrics_path`; empty otherwise, and always empty on Docker Compose. |
| metrics_service_port | string | — | non | Name of the port of `metrics_service` that carries the metrics: `http` on the synthesis, `http-openai` on NVIDIA's chart. Set and empty together with `metrics_service`. |
| metrics_path | string | — | non | Path the metrics are served at, `/v1/metrics`, published beside `metrics_service`. Empty where the server publishes `metrics_endpoint`, which carries its own path. |
Sockets uses
Les sockets de dépendance par lesquels ce composant se connecte. La cible de chaque connexion câblée via un socket doit satisfaire son sélecteur d’étiquettes, et chaque connexion peut porter une attache dans les emplacements que le socket déclare. Un emplacement obligatoire doit être rempli par chaque connexion que l’Aggregate ou la Release câble via le socket.
Aucun socket uses déclaré.
Emplacements d’attache
Points de liaison nommés auxquels une Feature s’attache à ce composant. Le sélecteur d’un emplacement restreint la Feature qui peut le remplir, et sa liste inject indique comment le matériel de la Feature peut être livré. Un emplacement obligatoire doit être lié sur chaque instance, par une attache sur l’instance ou à une portée supérieure, et un emplacement sensible est déclaré pour traiter du matériel secret. Une Feature peut aussi s’attacher sous un nom qu’aucun emplacement ne déclare.
| Emplacement | Sélecteur | Obligatoire | Injection | Sensible | Description |
|---|---|---|---|---|---|
| ngc_api_key | feature.aggrega.ai/kind=secret | non | env | oui | Optional NGC API key for authenticating the model-profile download. When attached, the serving container receives it as the NGC_API_KEY environment variable — on Kubernetes read from a Secret by reference, on Docker Compose written into the compose file as delivered, so attach a Compose variable reference such as ${NGC_API_KEY} there to keep the key out of the file. Unattached, the container starts without it. The NIM Operator realization requires it, published under the data key NGC_API_KEY. |
Liste d’autorisation d’auto-injection
env
Relations
Arêtes typées vers et depuis d’autres entités publiées. Une référence sans cible publiée s’affiche comme une arête rompue plutôt que comme un lien.
Utilise
- $refétend le schéma (values)
BaseComponents#/schemas/BaseModelParameter
Utilisé par
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « model »
utilise le socket « target_model »
utilise le socket « extraction_model »
utilise le socket « embedding_model »
utilise le socket « models »
utilise le socket « models »
utilise le socket « models »
utilise le socket « models »
utilise le socket « models »
utilise le socket « models »
utilise le socket « models »
utilise le socket « upstream »
utilise le socket « models »
utilise le socket « forward_target »
utilise le socket « scrape_target »
utilise le socket « store »
utilise le socket « content_safety »
s’applique à
s’applique à
s’applique à
s’applique à
s’applique à
s’applique à
s’applique à
implémente
implémente
implémente
implémente