REST Resource: projects.locations.endpoints

Resource: Endpoint

Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.

Fields
name string

Output only. The resource name of the Endpoint.

displayName string

Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.

description string

The description of the Endpoint.

deployedModels[] object (DeployedModel)

Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.

trafficSplit map (key: string, value: integer)

A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel.

If a DeployedModel's id is not listed in this map, then it receives no traffic.

The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.

etag string

Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.

labels map (key: string, value: string)

The labels with user-defined metadata to organize your endpoints.

label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed.

See https://goo.gl/xmQnxf for more information and examples of labels.

createTime string (Timestamp format)

Output only. timestamp when this Endpoint was created.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

updateTime string (Timestamp format)

Output only. timestamp when this Endpoint was last updated.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

encryptionSpec object (EncryptionSpec)

Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.

network string

Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered.

Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network.

Only one of the fields, network or enablePrivateServiceConnect, can be set.

Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.

enablePrivateServiceConnect
(deprecated)
boolean

Deprecated: If true, expose the Endpoint via private service connect.

Only one of the fields, network or enablePrivateServiceConnect, can be set.

privateServiceConnectConfig object (PrivateServiceConnectConfig)

Optional. Configuration for private service connect.

network and privateServiceConnectConfig are mutually exclusive.

modelDeploymentMonitoringJob string

Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{modelDeploymentMonitoringJob}

predictRequestResponseLoggingConfig object (PredictRequestResponseLoggingConfig)

Configures the request-response logging for online prediction.

dedicatedEndpointEnabled boolean

If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.

dedicatedEndpointDns string

Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.

clientConnectionConfig object (ClientConnectionConfig)

Configurations that are applied to the endpoint for online prediction.

satisfiesPzs boolean

Output only. reserved for future use.

satisfiesPzi boolean

Output only. reserved for future use.

JSON representation
{
  "name": string,
  "displayName": string,
  "description": string,
  "deployedModels": [
    {
      object (DeployedModel)
    }
  ],
  "trafficSplit": {
    string: integer,
    ...
  },
  "etag": string,
  "labels": {
    string: string,
    ...
  },
  "createTime": string,
  "updateTime": string,
  "encryptionSpec": {
    object (EncryptionSpec)
  },
  "network": string,
  "enablePrivateServiceConnect": boolean,
  "privateServiceConnectConfig": {
    object (PrivateServiceConnectConfig)
  },
  "modelDeploymentMonitoringJob": string,
  "predictRequestResponseLoggingConfig": {
    object (PredictRequestResponseLoggingConfig)
  },
  "dedicatedEndpointEnabled": boolean,
  "dedicatedEndpointDns": string,
  "clientConnectionConfig": {
    object (ClientConnectionConfig)
  },
  "satisfiesPzs": boolean,
  "satisfiesPzi": boolean
}

DeployedModel

A deployment of a Model. endpoints contain one or more DeployedModels.

Fields
id string

Immutable. The id of the DeployedModel. If not provided upon deployment, Vertex AI will generate a value for this id.

This value should be 1-10 characters, and valid characters are /[0-9]/.

model string

Required. The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint.

The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.

modelVersionId string

Output only. The version id of the model that is deployed.

displayName string

The display name of the DeployedModel. If not provided upon creation, the Model's displayName is used.

createTime string (Timestamp format)

Output only. timestamp when the DeployedModel was created.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

explanationSpec object (ExplanationSpec)

Explanation configuration for this DeployedModel.

When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanationSpec are optional in the request. If a field of explanationSpec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanationSpec will be used for the explanation configuration.

disableExplanations boolean

If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanationSpec.

serviceAccount string

The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project.

Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.

enableContainerLogging boolean

If true, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging.

Only supported for custom-trained Models and AutoML Tabular Models.

enableAccessLogging boolean

If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request.

Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.

privateEndpoints object (PrivateEndpoints)

Output only. Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.

fasterDeploymentConfig object (FasterDeploymentConfig)

Configuration for faster model deployment.

status object (Status)

Output only. Runtime status of the deployed model.

systemLabels map (key: string, value: string)

System labels to apply to Model Garden deployments. System labels are managed by Google for internal use only.

prediction_resources Union type
The prediction (for example, the machine) resources that the DeployedModel uses. The user is billed for the resources (at least their minimal amount) even if the DeployedModel receives no traffic. Not all Models support all resources types. See Model.supported_deployment_resources_types. Required except for Large Model Deploy use cases. prediction_resources can be only one of the following:
dedicatedResources object (DedicatedResources)

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

automaticResources object (AutomaticResources)

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

sharedResources string

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deploymentResourcePool}

JSON representation
{
  "id": string,
  "model": string,
  "modelVersionId": string,
  "displayName": string,
  "createTime": string,
  "explanationSpec": {
    object (ExplanationSpec)
  },
  "disableExplanations": boolean,
  "serviceAccount": string,
  "enableContainerLogging": boolean,
  "enableAccessLogging": boolean,
  "privateEndpoints": {
    object (PrivateEndpoints)
  },
  "fasterDeploymentConfig": {
    object (FasterDeploymentConfig)
  },
  "status": {
    object (Status)
  },
  "systemLabels": {
    string: string,
    ...
  },

  // prediction_resources
  "dedicatedResources": {
    object (DedicatedResources)
  },
  "automaticResources": {
    object (AutomaticResources)
  },
  "sharedResources": string
  // Union type
}

PrivateEndpoints

PrivateEndpoints proto is used to provide paths for users to send requests privately. To send request via private service access, use predictHttpUri, explainHttpUri or healthHttpUri. To send request via private service connect, use serviceAttachment.

Fields
predictHttpUri string

Output only. Http(s) path to send prediction requests.

explainHttpUri string

Output only. Http(s) path to send explain requests.

healthHttpUri string

Output only. Http(s) path to send health check requests.

serviceAttachment string

Output only. The name of the service attachment resource. Populated if private service connect is enabled.

JSON representation
{
  "predictHttpUri": string,
  "explainHttpUri": string,
  "healthHttpUri": string,
  "serviceAttachment": string
}

FasterDeploymentConfig

Configuration for faster model deployment.

Fields
fastTryoutEnabled boolean

If true, enable fast tryout feature for this deployed model.

JSON representation
{
  "fastTryoutEnabled": boolean
}

Status

Runtime status of the deployed model.

Fields
message string

Output only. The latest deployed model's status message (if any).

lastUpdateTime string (Timestamp format)

Output only. The time at which the status was last updated.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

availableReplicaCount integer

Output only. The number of available replicas of the deployed model.

JSON representation
{
  "message": string,
  "lastUpdateTime": string,
  "availableReplicaCount": integer
}

PredictRequestResponseLoggingConfig

Configuration for logging request-response to a BigQuery table.

Fields
enabled boolean

If logging is enabled or not.

samplingRate number

Percentage of requests to be logged, expressed as a fraction in range(0,1].

bigqueryDestination object (BigQueryDestination)

BigQuery table for logging. If only given a project, a new dataset will be created with name logging_<endpoint-display-name>_<endpoint-id> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging

JSON representation
{
  "enabled": boolean,
  "samplingRate": number,
  "bigqueryDestination": {
    object (BigQueryDestination)
  }
}

ClientConnectionConfig

Configurations (e.g. inference timeout) that are applied on your endpoints.

Fields
inferenceTimeout string (Duration format)

Customizable online prediction request timeout.

A duration in seconds with up to nine fractional digits, ending with 's'. Example: "3.5s".

JSON representation
{
  "inferenceTimeout": string
}

Methods

computeTokens

Return a list of tokens based on the input text.

countTokens

Perform a token counting.

create

Creates an Endpoint.

delete

Deletes an Endpoint.

deployModel

Deploys a Model into this Endpoint, creating a DeployedModel within it.

directPredict

Perform an unary online prediction request to a gRPC model server for Vertex first-party products and frameworks.

directRawPredict

Perform an unary online prediction request to a gRPC model server for custom containers.

explain

Perform an online explanation.

generateContent

Generate content with multimodal inputs.

get

Gets an Endpoint.

getIamPolicy

Gets the access control policy for a resource.

list

Lists Endpoints in a Location.

mutateDeployedModel

Updates an existing deployed model.

patch

Updates an Endpoint.

predict

Perform an online prediction.

rawPredict

Perform an online prediction with an arbitrary HTTP payload.

serverStreamingPredict

Perform a server-side streaming online prediction request for Vertex LLM streaming.

setIamPolicy

Sets the access control policy on the specified resource.

streamGenerateContent

Generate content with multimodal inputs with streaming support.

streamRawPredict

Perform a streaming online prediction with an arbitrary HTTP payload.

testIamPermissions

Returns permissions that a caller has on the specified resource.

undeployModel

Undeploys a Model from an Endpoint, removing a DeployedModel from it, and freeing all resources it's using.