Struct ModelService

pub struct ModelService { /* private fields */ }

Available on crate feature model-service only.

Implements a client for the Vertex AI API.

Example

let client = ModelService::builder().build().await?;
// use `client` to make requests to the Vertex AI API.

Service Description

A service for managing Vertex AI’s machine learning Models.

Configuration

To configure ModelService use the with_* methods in the type returned by builder(). The default configuration should work for most applications. Common configuration changes include

• with_endpoint(): by default this client uses the global default endpoint (https://aiplatform.googleapis.com). Applications using regional endpoints or running in restricted networks (e.g. a network configured override this default.
• with_credentials(): by default this client uses Application Default Credentials. Applications using custom authentication may need to override this default.

Pooling and Cloning

ModelService holds a connection pool internally, it is advised to create one and the reuse it. You do not need to wrap ModelService in an Rc or Arc to reuse it, because it already uses an Arc internally.

Implementations

impl ModelService

pub fn builder() -> ClientBuilder

Returns a builder for ModelService.

let client = ModelService::builder().build().await?;

pub fn from_stub<T>(stub: T) -> Self

where T: ModelService + 'static,

Creates a new client from the provided stub.

The most common case for calling this function is in tests mocking the client’s behavior.

pub fn upload_model(&self) -> UploadModel

Uploads a Model artifact into Vertex AI.

Long running operations

This method is used to start, and/or poll a long-running Operation. The Working with long-running operations chapter in the user guide covers these operations in detail.

pub fn get_model(&self) -> GetModel

Gets a Model.

pub fn list_models(&self) -> ListModels

Lists Models in a Location.

pub fn list_model_versions(&self) -> ListModelVersions

Lists versions of the specified model.

pub fn list_model_version_checkpoints(&self) -> ListModelVersionCheckpoints

Lists checkpoints of the specified model version.

pub fn update_model(&self) -> UpdateModel

Updates a Model.

pub fn update_explanation_dataset(&self) -> UpdateExplanationDataset

Incrementally update the dataset used for an examples model.

Long running operations

This method is used to start, and/or poll a long-running Operation. The Working with long-running operations chapter in the user guide covers these operations in detail.

pub fn delete_model(&self) -> DeleteModel

Deletes a Model.

A model cannot be deleted if any Endpoint resource has a DeployedModel based on the model in its deployed_models field.

Long running operations

This method is used to start, and/or poll a long-running Operation. The Working with long-running operations chapter in the user guide covers these operations in detail.

pub fn delete_model_version(&self) -> DeleteModelVersion

Deletes a Model version.

Model version can only be deleted if there are no DeployedModels created from it. Deleting the only version in the Model is not allowed. Use DeleteModel for deleting the Model instead.

Long running operations

This method is used to start, and/or poll a long-running Operation. The Working with long-running operations chapter in the user guide covers these operations in detail.

pub fn merge_version_aliases(&self) -> MergeVersionAliases

Merges a set of aliases for a Model version.

pub fn export_model(&self) -> ExportModel

Exports a trained, exportable Model to a location specified by the user. A Model is considered to be exportable if it has at least one supported export format.

Long running operations

This method is used to start, and/or poll a long-running Operation. The Working with long-running operations chapter in the user guide covers these operations in detail.

pub fn copy_model(&self) -> CopyModel

Copies an already existing Vertex AI Model into the specified Location. The source Model must exist in the same Project. When copying custom Models, the users themselves are responsible for Model.metadata content to be region-agnostic, as well as making sure that any resources (e.g. files) it depends on remain accessible.

Long running operations

This method is used to start, and/or poll a long-running Operation. The Working with long-running operations chapter in the user guide covers these operations in detail.

pub fn import_model_evaluation(&self) -> ImportModelEvaluation

Imports an externally generated ModelEvaluation.

pub fn batch_import_model_evaluation_slices( &self, ) -> BatchImportModelEvaluationSlices

Imports a list of externally generated ModelEvaluationSlice.

pub fn batch_import_evaluated_annotations( &self, ) -> BatchImportEvaluatedAnnotations

Imports a list of externally generated EvaluatedAnnotations.

pub fn get_model_evaluation(&self) -> GetModelEvaluation

Gets a ModelEvaluation.

pub fn list_model_evaluations(&self) -> ListModelEvaluations

Lists ModelEvaluations in a Model.

pub fn get_model_evaluation_slice(&self) -> GetModelEvaluationSlice

Gets a ModelEvaluationSlice.

pub fn list_model_evaluation_slices(&self) -> ListModelEvaluationSlices

Lists ModelEvaluationSlices in a ModelEvaluation.

pub fn list_locations(&self) -> ListLocations

Lists information about the supported locations for this service.

pub fn get_location(&self) -> GetLocation

Gets information about a location.

pub fn set_iam_policy(&self) -> SetIamPolicy

Sets the access control policy on the specified resource. Replaces any existing policy.

Can return NOT_FOUND, INVALID_ARGUMENT, and PERMISSION_DENIED errors.

pub fn get_iam_policy(&self) -> GetIamPolicy

Gets the access control policy for a resource. Returns an empty policy if the resource exists and does not have a policy set.

pub fn test_iam_permissions(&self) -> TestIamPermissions

Returns permissions that a caller has on the specified resource. If the resource does not exist, this will return an empty set of permissions, not a NOT_FOUND error.

Note: This operation is designed to be used for building permission-aware UIs and command-line tools, not for authorization checking. This operation may “fail open” without warning.

pub fn list_operations(&self) -> ListOperations

Provides the Operations service functionality in this service.

pub fn get_operation(&self) -> GetOperation

Provides the Operations service functionality in this service.

pub fn delete_operation(&self) -> DeleteOperation

Provides the Operations service functionality in this service.

pub fn cancel_operation(&self) -> CancelOperation

Provides the Operations service functionality in this service.

pub fn wait_operation(&self) -> WaitOperation

Provides the Operations service functionality in this service.

Trait Implementations

impl Clone for ModelService

fn clone(&self) -> ModelService

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ModelService

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.