Эта страница переведена автоматически. Читать английский оригинал.

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.

Происхождение

ОфициальныйПодписано идентичностью подписи, которую этот каталог признаёт официальным издателем.
Дайджест содержимого
sha256:19e35931d9753f81e3143869dcffd919cf89b93a2770da756bbadc8066853021
Опубликовано
2026-11-10T10:09:37Z
Идентичность подписи
https://token.actions.githubusercontent.com/https://github.com/aggrega-ai/aggrega-hub/.github/workflows/catalog-publish-sign.yml@refs/heads/main

Подпись

  • Официальныйapplication/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

Ссылка на эту версию

oci://hub.aggrega.ai/component/core/ai-model/tgi:1.0.0

Параметры разработчика

Значения, которые разработчик задаёт в сущности Aggregate.

Расширяет BaseComponents#/schemas/BaseModelParameter

Размеры, задаваемые оператором

Размеры инфраструктуры, которые оператор настраивает для каждого окружения.

ИмяТипПо умолчаниюОбязательныйОписание
portinteger (min 1024, max 65535)8080нетServer listen port for the model API. Most operators should omit this and let the Recipe assign the default (8080).
engine_versionstring3.0.1нетText Generation Inference runtime image tag. Selects the image tag on the synthesized serving and weights-pull containers.
replicasinteger (min 1)1нетNumber of serving replicas. Each replica holds its own model-cache volume and pulls the weights independently.
min_replicasinteger (min 1)—нетLower 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_replicasinteger (min 1)—нетUpper 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.
computeobject—нет—
model_cacheobject—нетPer-replica model-weights cache volume. Sized for the pulled model; each serving replica gets its own claim.
model_artifactstring—нетOptional 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.
overridesobject (open)—нетProvider-specific overrides. Accepts any nested structure. Each Recipe documents which keys it reads.
gpuobject—нетOptional 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.

Контракт выходных значений

Значения, которые этот компонент публикует для потребителей через топологию uses.

ИмяТипПо умолчаниюОбязательныйОписание
hoststring—даIn-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.
portinteger—даTCP 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.
endpointstring—даFull 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.
modelstring—даName a request must ask this server for, which is the model whose weights it loaded rather than a provider catalogue name.
protocolstring—нетURL scheme to reach `host` and `port` over, for a consumer composing its own address rather than reading `endpoint`.
metrics_endpointstring—нетThe 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_servicestring—нетName 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_portstring—нетName of the port of `metrics_service` that carries the metrics, `http`. Set and empty together with `metrics_service`.
metrics_pathstring—нетPath the metrics are served at, `/metrics`, published beside `metrics_service`. Empty where the server publishes `metrics_endpoint`, which carries its own path.

Сокеты uses

Сокеты зависимостей, через которые подключается этот компонент. Цель каждого соединения, проведённого через сокет, должна удовлетворять его селектору меток, и каждое соединение может нести подключение в слотах, которые объявляет сокет. Обязательный слот должен заполнить каждое соединение, которое сущность Aggregate или сущность Release проводит через сокет.

Сокеты uses не объявлены.

Слоты подключения

Именованные точки привязки, в которых Feature подключается к этому компоненту. Селектор слота ограничивает, какая сущность Feature может его заполнить, а его список внедрения указывает, как могут доставляться материалы сущности Feature. Обязательный слот должен быть привязан в каждом экземпляре — подключением в самом экземпляре или в области выше него, — а конфиденциальный слот объявляется для работы с секретными материалами. Feature также может подключаться под именем, которое не объявляет ни один слот.

СлотСелекторОбязательныйВнедрениеКонфиденциальныйОписание
model_pull_tokenfeature.aggrega.ai/kind=secretнетenvдаOptional 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_keyfeature.aggrega.ai/kind=secretнетenvдаOptional 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.

Список разрешённых самовнедрений

env

Связи

Типизированные рёбра к другим опубликованным сущностям и от них. Ссылка без опубликованной цели отображается как разорванное ребро, а не как ссылка.

Использует

Используется в

Справочник по понятию Component →

Каталог Aggrega — открытый указатель компонентов, функций, рецептов и плагинов, которые их рендерят.

Создано на общей дизайн-системе Aggrega.

Конфиденциальность