ModelDeploymentCreateParams

class nemo_microservices.types.deployment.ModelDeploymentCreateParams

Bases: TypedDict

config: Required[str | DeploymentConfigParam]

The deployment configuration.

async_enabled: bool

Whether the async mode is enabled.

custom_fields: object

A set of custom fields that the user can define and use for various purposes.

description: str

The description of the entity.

hf_token: str

Hugging Face authentication token for accessing private models and repositories. This token will be stored as a Kubernetes secret and mounted as an environment variable (HF_TOKEN) in the NIM deployment. The secret will be automatically cleaned up when the model deployment is deleted.

models: List[str]

The models served by this deployment.

name: str

The name of the identity.

Must be unique inside the namespace. If not specified, it will be the same as the automatically generated id.

namespace: str

The if of the namespace of the entity.

This can be missing for namespace entities or in deployments that don’t use namespaces.

ownership: Ownership

Information about ownership of an entity.

If the entity is a namespace, the access_policies will typically apply to all entities inside the namespace.

project: str

The id of project associated with this entity.