Component
core/ai-model/tgi
Text Generation Inference running in-cluster as a self-hosted inference server. A Recipe synthesizes the runtime directly: a weights-pull initContainer resolves the model pointer into a model-cache volume the serving container mounts, and a ClusterIP Service fronts the API. The model value is a deterministic pointer resolved at pod start, never fetched at compile time. Exports its host, port, endpoint, model, and protocol to consumers via the uses topology, so an agent reaches the model without hardcoding an endpoint. Each Recipe also publishes where Prometheus finds the server's metrics: one address as `metrics_endpoint`, or, while the Kubernetes realization runs more than one replica, the Service a scraper discovers every replica behind. On a cluster running the Prometheus Operator, `core/prometheus-exporter` attached with its port set to `http` emits a ServiceMonitor for it instead.
Procedência
- Digest do conteúdo
- sha256:19e35931d9753f81e3143869dcffd919cf89b93a2770da756bbadc8066853021
- Publicado
- 2026-11-10T10:09:37Z
- Identidade de assinatura
- https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main
Assinatura
- Oficialapplication/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
sha256:46a2f0e5c8b71d3f5bff94a62a3523fdb3f5b0b89eac6aac1b53f1705bdd5090
Referência nesta versão
oci://hub.aggrega.ai/component/core/ai-model/tgi:1.0.0Parâmetros do desenvolvedor
Valores que o desenvolvedor define no Aggregate.
Estende BaseComponents#/schemas/BaseModelParameter
Dimensionamento do operador
Dimensionamento de infraestrutura que o operador ajusta por ambiente.
| Nome | Tipo | Padrão | Obrigatório | Descrição |
|---|---|---|---|---|
| port | integer (min 1024, max 65535) | 8080 | não | Server listen port for the model API. Most operators should omit this and let the Recipe assign the default (8080). |
| engine_version | string | 3.0.1 | não | Text Generation Inference runtime image tag. Selects the image tag on the synthesized serving and weights-pull containers. |
| replicas | integer (min 1) | 1 | não | Number of serving replicas. Each replica holds its own model-cache volume and pulls the weights independently. |
| min_replicas | integer (min 1) | — | não | Lower bound for the replica count when horizontal autoscaling is configured. Declared ahead of rendering — the synth recipes serve a fixed replica count and do not yet emit an autoscaler; set it to record the intended lower bound. |
| max_replicas | integer (min 1) | — | não | Upper bound for the replica count when horizontal autoscaling is configured. Declared ahead of rendering — the synth recipes serve a fixed replica count and do not yet emit an autoscaler; set it to record the intended upper bound. |
| compute | object | — | não | — |
| model_cache | object | — | não | Per-replica model-weights cache volume. Sized for the pulled model; each serving replica gets its own claim. |
| model_artifact | string | — | não | Optional OCI reference to the model weights, an alternative weights source to the Hugging Face model id in values.model. A deterministic pointer the runtime resolves at pod start; the compiler never fetches it. Declared ahead of rendering — the synth recipes resolve weights from values.model and do not yet consume this pointer. |
| overrides | object (open) | — | não | Provider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads. |
| gpu | object | — | não | Optional GPU scheduling for the serving container. When set, the Recipe requests GPUs as the extended resource nvidia.com/gpu and, when a runtime class is named, schedules the pod under it. Requires a GPU-capable cluster and, for runtime_class, a matching RuntimeClass configured in the cluster. Omit the whole object to serve on CPU. |
Contrato de saída
Valores que este componente publica para os consumidores pela topologia uses.
| Nome | Tipo | Padrão | Obrigatório | Descrição |
|---|---|---|---|---|
| host | string | — | sim | In-cluster DNS name of the Service fronting the inference server. A consumer that composes its own address dials this name; one that does not reads `endpoint` instead. |
| port | integer | — | sim | TCP port that Service accepts generation requests on. It follows the port an operator set in the Release, so a consumer reads it rather than assuming a default. |
| endpoint | string | — | sim | Full base URL of the generation API, 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 | — | sim | Name a request must ask this server for, which is the model whose weights it loaded rather than a provider catalogue name. |
| protocol | string | — | não | URL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`. |
| metrics_endpoint | string | — | não | The full address Prometheus scrapes this server's metrics at — scheme, host, port and path, `http://<host>:<port>/metrics`, on the port the API is served on. Empty while the Kubernetes realization runs more than one replica, which then publishes `metrics_service` instead. |
| metrics_service | string | — | não | 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 by the Kubernetes realization while infra.replicas is above one, beside `metrics_service_port` and `metrics_path`; empty otherwise. |
| metrics_service_port | string | — | não | Name of the port of `metrics_service` that carries the metrics, `http`. Set and empty together with `metrics_service`. |
| metrics_path | string | — | não | Path the metrics are served at, `/metrics`, published beside `metrics_service`. Empty where the server publishes `metrics_endpoint`, which carries its own path. |
Sockets uses
Os sockets de dependência pelos quais este componente se conecta. O destino de cada conexão ligada por um socket deve satisfazer o seletor de rótulos dele, e cada conexão pode carregar um acoplamento nos slots que o socket declara. Cada conexão que o Aggregate ou a Release liga pelo socket deve preencher os slots obrigatórios.
Nenhum socket uses declarado.
Slots de acoplamento
Pontos de vinculação nomeados nos quais uma Feature se acopla a este componente. O seletor de um slot restringe qual Feature pode preenchê-lo, e sua lista inject indica como o material da Feature pode ser entregue. Um slot obrigatório deve estar vinculado em cada instância, por um acoplamento na instância ou em um escopo acima dela, e um slot sensível é declarado para lidar com material secreto. Uma Feature também pode se acoplar com um nome que nenhum slot declara.
| Slot | Seletor | Obrigatório | Injeção | Sensível | Descrição |
|---|---|---|---|---|---|
| model_pull_token | feature.aggrega.ai/kind=secret | não | env | sim | Optional model-registry pull credential for gated model weights. When attached, the weights-pull initContainer receives it as an environment variable; unattached, weights are pulled anonymously. |
| api_key | feature.aggrega.ai/kind=secret | não | env | sim | Optional key the server requires of every caller. When attached, the Recipe delivers it as API_KEY, the variable Text Generation Inference reads at startup, and each generation request must then carry it as a bearer token in the Authorization header. The server checks this one key, so every caller must present the same key. Text Generation Inference accepts the key whatever its letter case, so two keys differing only in case are one key to it, and a key's strength is judged on its case-folded form. Unattached, the server requires none. |
Lista de permissões de autoinjeção
env
Relações
Arestas tipadas de e para outras entidades publicadas. Uma referência sem destino publicado é exibida como uma aresta quebrada em vez de um link.
Usa
- $refestende o esquema (values)
BaseComponents#/schemas/BaseModelParameter
Usado por
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «model»
usa o socket «target_model»
usa o socket «extraction_model»
usa o socket «embedding_model»
usa o socket «models»
usa o socket «models»
usa o socket «models»
usa o socket «models»
usa o socket «models»
usa o socket «models»
usa o socket «models»
usa o socket «upstream»
usa o socket «models»
usa o socket «forward_target»
usa o socket «scrape_target»
usa o socket «store»
usa o socket «content_safety»
aplica-se a
aplica-se a
aplica-se a
aplica-se a
aplica-se a
aplica-se a
aplica-se a
implementa
implementa