gcp.vertex.AiEndpoint
Explore with Pulumi AI
Models are deployed into it, and afterwards Endpoint is called to obtain predictions and explanations.
To get more information about Endpoint, see:
- API documentation
- How-to Guides
Example Usage
Vertex Ai Endpoint Network
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Gcp = Pulumi.Gcp;
return await Deployment.RunAsync(() =>
{
var vertexNetwork = Gcp.Compute.GetNetwork.Invoke(new()
{
Name = "network-name",
});
var vertexRange = new Gcp.Compute.GlobalAddress("vertexRange", new()
{
Purpose = "VPC_PEERING",
AddressType = "INTERNAL",
PrefixLength = 24,
Network = vertexNetwork.Apply(getNetworkResult => getNetworkResult.Id),
});
var vertexVpcConnection = new Gcp.ServiceNetworking.Connection("vertexVpcConnection", new()
{
Network = vertexNetwork.Apply(getNetworkResult => getNetworkResult.Id),
Service = "servicenetworking.googleapis.com",
ReservedPeeringRanges = new[]
{
vertexRange.Name,
},
});
var project = Gcp.Organizations.GetProject.Invoke();
var endpoint = new Gcp.Vertex.AiEndpoint("endpoint", new()
{
DisplayName = "sample-endpoint",
Description = "A sample vertex endpoint",
Location = "us-central1",
Region = "us-central1",
Labels =
{
{ "label-one", "value-one" },
},
Network = Output.Tuple(project, vertexNetwork).Apply(values =>
{
var project = values.Item1;
var vertexNetwork = values.Item2;
return $"projects/{project.Apply(getProjectResult => getProjectResult.Number)}/global/networks/{vertexNetwork.Apply(getNetworkResult => getNetworkResult.Name)}";
}),
EncryptionSpec = new Gcp.Vertex.Inputs.AiEndpointEncryptionSpecArgs
{
KmsKeyName = "kms-name",
},
}, new CustomResourceOptions
{
DependsOn = new[]
{
vertexVpcConnection,
},
});
var cryptoKey = new Gcp.Kms.CryptoKeyIAMMember("cryptoKey", new()
{
CryptoKeyId = "kms-name",
Role = "roles/cloudkms.cryptoKeyEncrypterDecrypter",
Member = $"serviceAccount:service-{project.Apply(getProjectResult => getProjectResult.Number)}@gcp-sa-aiplatform.iam.gserviceaccount.com",
});
});
package main
import (
"fmt"
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/compute"
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/kms"
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/organizations"
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/servicenetworking"
"github.com/pulumi/pulumi-gcp/sdk/v6/go/gcp/vertex"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
vertexNetwork, err := compute.LookupNetwork(ctx, &compute.LookupNetworkArgs{
Name: "network-name",
}, nil)
if err != nil {
return err
}
vertexRange, err := compute.NewGlobalAddress(ctx, "vertexRange", &compute.GlobalAddressArgs{
Purpose: pulumi.String("VPC_PEERING"),
AddressType: pulumi.String("INTERNAL"),
PrefixLength: pulumi.Int(24),
Network: *pulumi.String(vertexNetwork.Id),
})
if err != nil {
return err
}
vertexVpcConnection, err := servicenetworking.NewConnection(ctx, "vertexVpcConnection", &servicenetworking.ConnectionArgs{
Network: *pulumi.String(vertexNetwork.Id),
Service: pulumi.String("servicenetworking.googleapis.com"),
ReservedPeeringRanges: pulumi.StringArray{
vertexRange.Name,
},
})
if err != nil {
return err
}
project, err := organizations.LookupProject(ctx, nil, nil)
if err != nil {
return err
}
_, err = vertex.NewAiEndpoint(ctx, "endpoint", &vertex.AiEndpointArgs{
DisplayName: pulumi.String("sample-endpoint"),
Description: pulumi.String("A sample vertex endpoint"),
Location: pulumi.String("us-central1"),
Region: pulumi.String("us-central1"),
Labels: pulumi.StringMap{
"label-one": pulumi.String("value-one"),
},
Network: pulumi.String(fmt.Sprintf("projects/%v/global/networks/%v", project.Number, vertexNetwork.Name)),
EncryptionSpec: &vertex.AiEndpointEncryptionSpecArgs{
KmsKeyName: pulumi.String("kms-name"),
},
}, pulumi.DependsOn([]pulumi.Resource{
vertexVpcConnection,
}))
if err != nil {
return err
}
_, err = kms.NewCryptoKeyIAMMember(ctx, "cryptoKey", &kms.CryptoKeyIAMMemberArgs{
CryptoKeyId: pulumi.String("kms-name"),
Role: pulumi.String("roles/cloudkms.cryptoKeyEncrypterDecrypter"),
Member: pulumi.String(fmt.Sprintf("serviceAccount:service-%v@gcp-sa-aiplatform.iam.gserviceaccount.com", project.Number)),
})
if err != nil {
return err
}
return nil
})
}
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.compute.ComputeFunctions;
import com.pulumi.gcp.compute.inputs.GetNetworkArgs;
import com.pulumi.gcp.compute.GlobalAddress;
import com.pulumi.gcp.compute.GlobalAddressArgs;
import com.pulumi.gcp.servicenetworking.Connection;
import com.pulumi.gcp.servicenetworking.ConnectionArgs;
import com.pulumi.gcp.organizations.OrganizationsFunctions;
import com.pulumi.gcp.organizations.inputs.GetProjectArgs;
import com.pulumi.gcp.vertex.AiEndpoint;
import com.pulumi.gcp.vertex.AiEndpointArgs;
import com.pulumi.gcp.vertex.inputs.AiEndpointEncryptionSpecArgs;
import com.pulumi.gcp.kms.CryptoKeyIAMMember;
import com.pulumi.gcp.kms.CryptoKeyIAMMemberArgs;
import com.pulumi.resources.CustomResourceOptions;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;
public class App {
public static void main(String[] args) {
Pulumi.run(App::stack);
}
public static void stack(Context ctx) {
final var vertexNetwork = ComputeFunctions.getNetwork(GetNetworkArgs.builder()
.name("network-name")
.build());
var vertexRange = new GlobalAddress("vertexRange", GlobalAddressArgs.builder()
.purpose("VPC_PEERING")
.addressType("INTERNAL")
.prefixLength(24)
.network(vertexNetwork.applyValue(getNetworkResult -> getNetworkResult.id()))
.build());
var vertexVpcConnection = new Connection("vertexVpcConnection", ConnectionArgs.builder()
.network(vertexNetwork.applyValue(getNetworkResult -> getNetworkResult.id()))
.service("servicenetworking.googleapis.com")
.reservedPeeringRanges(vertexRange.name())
.build());
final var project = OrganizationsFunctions.getProject();
var endpoint = new AiEndpoint("endpoint", AiEndpointArgs.builder()
.displayName("sample-endpoint")
.description("A sample vertex endpoint")
.location("us-central1")
.region("us-central1")
.labels(Map.of("label-one", "value-one"))
.network(String.format("projects/%s/global/networks/%s", project.applyValue(getProjectResult -> getProjectResult.number()),vertexNetwork.applyValue(getNetworkResult -> getNetworkResult.name())))
.encryptionSpec(AiEndpointEncryptionSpecArgs.builder()
.kmsKeyName("kms-name")
.build())
.build(), CustomResourceOptions.builder()
.dependsOn(vertexVpcConnection)
.build());
var cryptoKey = new CryptoKeyIAMMember("cryptoKey", CryptoKeyIAMMemberArgs.builder()
.cryptoKeyId("kms-name")
.role("roles/cloudkms.cryptoKeyEncrypterDecrypter")
.member(String.format("serviceAccount:service-%s@gcp-sa-aiplatform.iam.gserviceaccount.com", project.applyValue(getProjectResult -> getProjectResult.number())))
.build());
}
}
import pulumi
import pulumi_gcp as gcp
vertex_network = gcp.compute.get_network(name="network-name")
vertex_range = gcp.compute.GlobalAddress("vertexRange",
purpose="VPC_PEERING",
address_type="INTERNAL",
prefix_length=24,
network=vertex_network.id)
vertex_vpc_connection = gcp.servicenetworking.Connection("vertexVpcConnection",
network=vertex_network.id,
service="servicenetworking.googleapis.com",
reserved_peering_ranges=[vertex_range.name])
project = gcp.organizations.get_project()
endpoint = gcp.vertex.AiEndpoint("endpoint",
display_name="sample-endpoint",
description="A sample vertex endpoint",
location="us-central1",
region="us-central1",
labels={
"label-one": "value-one",
},
network=f"projects/{project.number}/global/networks/{vertex_network.name}",
encryption_spec=gcp.vertex.AiEndpointEncryptionSpecArgs(
kms_key_name="kms-name",
),
opts=pulumi.ResourceOptions(depends_on=[vertex_vpc_connection]))
crypto_key = gcp.kms.CryptoKeyIAMMember("cryptoKey",
crypto_key_id="kms-name",
role="roles/cloudkms.cryptoKeyEncrypterDecrypter",
member=f"serviceAccount:service-{project.number}@gcp-sa-aiplatform.iam.gserviceaccount.com")
import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";
const vertexNetwork = gcp.compute.getNetwork({
name: "network-name",
});
const vertexRange = new gcp.compute.GlobalAddress("vertexRange", {
purpose: "VPC_PEERING",
addressType: "INTERNAL",
prefixLength: 24,
network: vertexNetwork.then(vertexNetwork => vertexNetwork.id),
});
const vertexVpcConnection = new gcp.servicenetworking.Connection("vertexVpcConnection", {
network: vertexNetwork.then(vertexNetwork => vertexNetwork.id),
service: "servicenetworking.googleapis.com",
reservedPeeringRanges: [vertexRange.name],
});
const project = gcp.organizations.getProject({});
const endpoint = new gcp.vertex.AiEndpoint("endpoint", {
displayName: "sample-endpoint",
description: "A sample vertex endpoint",
location: "us-central1",
region: "us-central1",
labels: {
"label-one": "value-one",
},
network: Promise.all([project, vertexNetwork]).then(([project, vertexNetwork]) => `projects/${project.number}/global/networks/${vertexNetwork.name}`),
encryptionSpec: {
kmsKeyName: "kms-name",
},
}, {
dependsOn: [vertexVpcConnection],
});
const cryptoKey = new gcp.kms.CryptoKeyIAMMember("cryptoKey", {
cryptoKeyId: "kms-name",
role: "roles/cloudkms.cryptoKeyEncrypterDecrypter",
member: project.then(project => `serviceAccount:service-${project.number}@gcp-sa-aiplatform.iam.gserviceaccount.com`),
});
resources:
endpoint:
type: gcp:vertex:AiEndpoint
properties:
displayName: sample-endpoint
description: A sample vertex endpoint
location: us-central1
region: us-central1
labels:
label-one: value-one
network: projects/${project.number}/global/networks/${vertexNetwork.name}
encryptionSpec:
kmsKeyName: kms-name
options:
dependson:
- ${vertexVpcConnection}
vertexVpcConnection:
type: gcp:servicenetworking:Connection
properties:
network: ${vertexNetwork.id}
service: servicenetworking.googleapis.com
reservedPeeringRanges:
- ${vertexRange.name}
vertexRange:
type: gcp:compute:GlobalAddress
properties:
purpose: VPC_PEERING
addressType: INTERNAL
prefixLength: 24
network: ${vertexNetwork.id}
cryptoKey:
type: gcp:kms:CryptoKeyIAMMember
properties:
cryptoKeyId: kms-name
role: roles/cloudkms.cryptoKeyEncrypterDecrypter
member: serviceAccount:service-${project.number}@gcp-sa-aiplatform.iam.gserviceaccount.com
variables:
vertexNetwork:
fn::invoke:
Function: gcp:compute:getNetwork
Arguments:
name: network-name
project:
fn::invoke:
Function: gcp:organizations:getProject
Arguments: {}
Create AiEndpoint Resource
new AiEndpoint(name: string, args: AiEndpointArgs, opts?: CustomResourceOptions);
@overload
def AiEndpoint(resource_name: str,
opts: Optional[ResourceOptions] = None,
description: Optional[str] = None,
display_name: Optional[str] = None,
encryption_spec: Optional[AiEndpointEncryptionSpecArgs] = None,
labels: Optional[Mapping[str, str]] = None,
location: Optional[str] = None,
name: Optional[str] = None,
network: Optional[str] = None,
project: Optional[str] = None,
region: Optional[str] = None)
@overload
def AiEndpoint(resource_name: str,
args: AiEndpointArgs,
opts: Optional[ResourceOptions] = None)
func NewAiEndpoint(ctx *Context, name string, args AiEndpointArgs, opts ...ResourceOption) (*AiEndpoint, error)
public AiEndpoint(string name, AiEndpointArgs args, CustomResourceOptions? opts = null)
public AiEndpoint(String name, AiEndpointArgs args)
public AiEndpoint(String name, AiEndpointArgs args, CustomResourceOptions options)
type: gcp:vertex:AiEndpoint
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args AiEndpointArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args AiEndpointArgs
- The arguments to resource properties.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resource.
- args AiEndpointArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args AiEndpointArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args AiEndpointArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
AiEndpoint Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
The AiEndpoint resource accepts the following input properties:
- Display
Name 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.
- Location string
The location for the resource
- Description string
The description of the Endpoint.
- Encryption
Spec AiEndpoint Encryption Spec 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. Structure is documented below.
- Labels Dictionary<string, 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.
- Name string
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- Network string
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- Region string
The region for the resource
- Display
Name 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.
- Location string
The location for the resource
- Description string
The description of the Endpoint.
- Encryption
Spec AiEndpoint Encryption Spec Args 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. Structure is documented below.
- Labels map[string]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.
- Name string
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- Network string
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- Region string
The region for the resource
- display
Name 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.
- location String
The location for the resource
- description String
The description of the Endpoint.
- encryption
Spec AiEndpoint Encryption Spec 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. Structure is documented below.
- labels Map<String,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.
- name String
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network String
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region String
The region for the resource
- display
Name 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.
- location string
The location for the resource
- description string
The description of the Endpoint.
- encryption
Spec AiEndpoint Encryption Spec 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. Structure is documented below.
- labels {[key: string]: 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.
- name string
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network string
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region string
The region for the resource
- display_
name str Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
- location str
The location for the resource
- description str
The description of the Endpoint.
- encryption_
spec AiEndpoint Encryption Spec Args 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. Structure is documented below.
- labels Mapping[str, str]
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.
- name str
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network str
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project str
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region str
The region for the resource
- display
Name 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.
- location String
The location for the resource
- description String
The description of the Endpoint.
- encryption
Spec Property Map 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. Structure is documented below.
- labels Map<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.
- name String
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network String
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region String
The region for the resource
Outputs
All input properties are implicitly available as output properties. Additionally, the AiEndpoint resource produces the following output properties:
- Create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- Deployed
Models List<AiEndpoint Deployed Model> Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- Etag string
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- Id string
The provider-assigned unique ID for this managed resource.
- Model
Deployment stringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- Update
Time string Output only. Timestamp when this Endpoint was last updated.
- Create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- Deployed
Models []AiEndpoint Deployed Model Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- Etag string
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- Id string
The provider-assigned unique ID for this managed resource.
- Model
Deployment stringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- Update
Time string Output only. Timestamp when this Endpoint was last updated.
- create
Time String (Output) Output only. Timestamp when the DeployedModel was created.
- deployed
Models List<AiEndpoint Deployed Model> Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- etag String
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- id String
The provider-assigned unique ID for this managed resource.
- model
Deployment StringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- update
Time String Output only. Timestamp when this Endpoint was last updated.
- create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- deployed
Models AiEndpoint Deployed Model[] Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- etag string
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- id string
The provider-assigned unique ID for this managed resource.
- model
Deployment stringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- update
Time string Output only. Timestamp when this Endpoint was last updated.
- create_
time str (Output) Output only. Timestamp when the DeployedModel was created.
- deployed_
models Sequence[AiEndpoint Deployed Model] Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- etag str
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- id str
The provider-assigned unique ID for this managed resource.
- model_
deployment_ strmonitoring_ job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- update_
time str Output only. Timestamp when this Endpoint was last updated.
- create
Time String (Output) Output only. Timestamp when the DeployedModel was created.
- deployed
Models List<Property Map> Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- etag String
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- id String
The provider-assigned unique ID for this managed resource.
- model
Deployment StringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- update
Time String Output only. Timestamp when this Endpoint was last updated.
Look up Existing AiEndpoint Resource
Get an existing AiEndpoint resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.
public static get(name: string, id: Input<ID>, state?: AiEndpointState, opts?: CustomResourceOptions): AiEndpoint
@staticmethod
def get(resource_name: str,
id: str,
opts: Optional[ResourceOptions] = None,
create_time: Optional[str] = None,
deployed_models: Optional[Sequence[AiEndpointDeployedModelArgs]] = None,
description: Optional[str] = None,
display_name: Optional[str] = None,
encryption_spec: Optional[AiEndpointEncryptionSpecArgs] = None,
etag: Optional[str] = None,
labels: Optional[Mapping[str, str]] = None,
location: Optional[str] = None,
model_deployment_monitoring_job: Optional[str] = None,
name: Optional[str] = None,
network: Optional[str] = None,
project: Optional[str] = None,
region: Optional[str] = None,
update_time: Optional[str] = None) -> AiEndpoint
func GetAiEndpoint(ctx *Context, name string, id IDInput, state *AiEndpointState, opts ...ResourceOption) (*AiEndpoint, error)
public static AiEndpoint Get(string name, Input<string> id, AiEndpointState? state, CustomResourceOptions? opts = null)
public static AiEndpoint get(String name, Output<String> id, AiEndpointState state, CustomResourceOptions options)
Resource lookup is not supported in YAML
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- resource_name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- name
- The unique name of the resulting resource.
- id
- The unique provider ID of the resource to lookup.
- state
- Any extra arguments used during the lookup.
- opts
- A bag of options that control this resource's behavior.
- Create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- Deployed
Models List<AiEndpoint Deployed Model> Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- Description string
The description of the Endpoint.
- Display
Name 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.
- Encryption
Spec AiEndpoint Encryption Spec 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. Structure is documented below.
- Etag string
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- Labels Dictionary<string, 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.
- Location string
The location for the resource
- Model
Deployment stringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- Name string
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- Network string
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- Region string
The region for the resource
- Update
Time string Output only. Timestamp when this Endpoint was last updated.
- Create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- Deployed
Models []AiEndpoint Deployed Model Args Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- Description string
The description of the Endpoint.
- Display
Name 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.
- Encryption
Spec AiEndpoint Encryption Spec Args 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. Structure is documented below.
- Etag string
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- Labels map[string]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.
- Location string
The location for the resource
- Model
Deployment stringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- Name string
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- Network string
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- Project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- Region string
The region for the resource
- Update
Time string Output only. Timestamp when this Endpoint was last updated.
- create
Time String (Output) Output only. Timestamp when the DeployedModel was created.
- deployed
Models List<AiEndpoint Deployed Model> Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- description String
The description of the Endpoint.
- display
Name 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.
- encryption
Spec AiEndpoint Encryption Spec 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. Structure is documented below.
- etag String
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- labels Map<String,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.
- location String
The location for the resource
- model
Deployment StringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- name String
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network String
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region String
The region for the resource
- update
Time String Output only. Timestamp when this Endpoint was last updated.
- create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- deployed
Models AiEndpoint Deployed Model[] Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- description string
The description of the Endpoint.
- display
Name 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.
- encryption
Spec AiEndpoint Encryption Spec 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. Structure is documented below.
- etag string
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- labels {[key: string]: 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.
- location string
The location for the resource
- model
Deployment stringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- name string
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network string
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project string
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region string
The region for the resource
- update
Time string Output only. Timestamp when this Endpoint was last updated.
- create_
time str (Output) Output only. Timestamp when the DeployedModel was created.
- deployed_
models Sequence[AiEndpoint Deployed Model Args] Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- description str
The description of the Endpoint.
- display_
name str Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
- encryption_
spec AiEndpoint Encryption Spec Args 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. Structure is documented below.
- etag str
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- labels Mapping[str, str]
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.
- location str
The location for the resource
- model_
deployment_ strmonitoring_ job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- name str
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network str
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project str
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region str
The region for the resource
- update_
time str Output only. Timestamp when this Endpoint was last updated.
- create
Time String (Output) Output only. Timestamp when the DeployedModel was created.
- deployed
Models List<Property Map> Output only. The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively. Models can also be deployed and undeployed using the Cloud Console. Structure is documented below.
- description String
The description of the Endpoint.
- display
Name 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.
- encryption
Spec Property Map 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. Structure is documented below.
- etag String
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
- labels Map<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.
- location String
The location for the resource
- model
Deployment StringMonitoring Job Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by CreateModelDeploymentMonitoringJob. Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
- name String
The resource name of the Endpoint. The name must be numeric with no leading zeros and can be at most 10 digits.
- network String
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 enable_private_service_connect, can be set. Format:
projects/{project}/global/networks/{network}
. Where{project}
is a project number, as in12345
, and{network}
is network name.- project String
The ID of the project in which the resource belongs. If it is not provided, the provider project is used.
- region String
The region for the resource
- update
Time String Output only. Timestamp when this Endpoint was last updated.
Supporting Types
AiEndpointDeployedModel, AiEndpointDeployedModelArgs
- Automatic
Resources List<AiEndpoint Deployed Model Automatic Resource> (Output) A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Structure is documented below.
- Create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- Dedicated
Resources List<AiEndpoint Deployed Model Dedicated Resource> (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
- Display
Name 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.
- Enable
Access boolLogging (Output) These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that Stackdriver 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.
- Enable
Container boolLogging (Output) If true, the container of the DeployedModel instances will send
stderr
andstdout
streams to Stackdriver Logging. Only supported for custom-trained Models and AutoML Tabular Models.- Id string
(Output) 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
(Output) The 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.
- Model
Version stringId (Output) Output only. The version ID of the model that is deployed.
- Private
Endpoints List<AiEndpoint Deployed Model Private Endpoint> (Output) 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. Structure is documented below.
- Service
Account string (Output) 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.- string
(Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
- Automatic
Resources []AiEndpoint Deployed Model Automatic Resource (Output) A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Structure is documented below.
- Create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- Dedicated
Resources []AiEndpoint Deployed Model Dedicated Resource (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
- Display
Name 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.
- Enable
Access boolLogging (Output) These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that Stackdriver 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.
- Enable
Container boolLogging (Output) If true, the container of the DeployedModel instances will send
stderr
andstdout
streams to Stackdriver Logging. Only supported for custom-trained Models and AutoML Tabular Models.- Id string
(Output) 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
(Output) The 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.
- Model
Version stringId (Output) Output only. The version ID of the model that is deployed.
- Private
Endpoints []AiEndpoint Deployed Model Private Endpoint (Output) 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. Structure is documented below.
- Service
Account string (Output) 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.- string
(Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
- automatic
Resources List<AiEndpoint Deployed Model Automatic Resource> (Output) A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Structure is documented below.
- create
Time String (Output) Output only. Timestamp when the DeployedModel was created.
- dedicated
Resources List<AiEndpoint Deployed Model Dedicated Resource> (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
- display
Name 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.
- enable
Access BooleanLogging (Output) These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that Stackdriver 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.
- enable
Container BooleanLogging (Output) If true, the container of the DeployedModel instances will send
stderr
andstdout
streams to Stackdriver Logging. Only supported for custom-trained Models and AutoML Tabular Models.- id String
(Output) 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
(Output) The 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.
- model
Version StringId (Output) Output only. The version ID of the model that is deployed.
- private
Endpoints List<AiEndpoint Deployed Model Private Endpoint> (Output) 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. Structure is documented below.
- service
Account String (Output) 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.- String
(Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
- automatic
Resources AiEndpoint Deployed Model Automatic Resource[] (Output) A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Structure is documented below.
- create
Time string (Output) Output only. Timestamp when the DeployedModel was created.
- dedicated
Resources AiEndpoint Deployed Model Dedicated Resource[] (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
- display
Name 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.
- enable
Access booleanLogging (Output) These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that Stackdriver 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.
- enable
Container booleanLogging (Output) If true, the container of the DeployedModel instances will send
stderr
andstdout
streams to Stackdriver Logging. Only supported for custom-trained Models and AutoML Tabular Models.- id string
(Output) 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
(Output) The 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.
- model
Version stringId (Output) Output only. The version ID of the model that is deployed.
- private
Endpoints AiEndpoint Deployed Model Private Endpoint[] (Output) 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. Structure is documented below.
- service
Account string (Output) 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.- string
(Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
- automatic_
resources Sequence[AiEndpoint Deployed Model Automatic Resource] (Output) A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Structure is documented below.
- create_
time str (Output) Output only. Timestamp when the DeployedModel was created.
- dedicated_
resources Sequence[AiEndpoint Deployed Model Dedicated Resource] (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
- display_
name str Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
- enable_
access_ boollogging (Output) These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that Stackdriver 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.
- enable_
container_ boollogging (Output) If true, the container of the DeployedModel instances will send
stderr
andstdout
streams to Stackdriver Logging. Only supported for custom-trained Models and AutoML Tabular Models.- id str
(Output) 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 str
(Output) The 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.
- model_
version_ strid (Output) Output only. The version ID of the model that is deployed.
- private_
endpoints Sequence[AiEndpoint Deployed Model Private Endpoint] (Output) 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. Structure is documented below.
- service_
account str (Output) 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.- str
(Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
- automatic
Resources List<Property Map> (Output) A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration. Structure is documented below.
- create
Time String (Output) Output only. Timestamp when the DeployedModel was created.
- dedicated
Resources List<Property Map> (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
- display
Name 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.
- enable
Access BooleanLogging (Output) These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that Stackdriver 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.
- enable
Container BooleanLogging (Output) If true, the container of the DeployedModel instances will send
stderr
andstdout
streams to Stackdriver Logging. Only supported for custom-trained Models and AutoML Tabular Models.- id String
(Output) 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
(Output) The 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.
- model
Version StringId (Output) Output only. The version ID of the model that is deployed.
- private
Endpoints List<Property Map> (Output) 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. Structure is documented below.
- service
Account String (Output) 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.- String
(Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
AiEndpointDeployedModelAutomaticResource, AiEndpointDeployedModelAutomaticResourceArgs
- Max
Replica intCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- Min
Replica intCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- Max
Replica intCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- Min
Replica intCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- max
Replica IntegerCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min
Replica IntegerCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- max
Replica numberCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min
Replica numberCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- max_
replica_ intcount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min_
replica_ intcount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- max
Replica NumberCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min
Replica NumberCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
AiEndpointDeployedModelDedicatedResource, AiEndpointDeployedModelDedicatedResourceArgs
- Autoscaling
Metric List<AiSpecs Endpoint Deployed Model Dedicated Resource Autoscaling Metric Spec> (Output) The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to
aiplatform.googleapis.com/prediction/online/cpu/utilization
and autoscaling_metric_specs.target to80
. Structure is documented below.- Machine
Specs List<AiEndpoint Deployed Model Dedicated Resource Machine Spec> (Output) The specification of a single machine used by the prediction. Structure is documented below.
- Max
Replica intCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- Min
Replica intCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- Autoscaling
Metric []AiSpecs Endpoint Deployed Model Dedicated Resource Autoscaling Metric Spec (Output) The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to
aiplatform.googleapis.com/prediction/online/cpu/utilization
and autoscaling_metric_specs.target to80
. Structure is documented below.- Machine
Specs []AiEndpoint Deployed Model Dedicated Resource Machine Spec (Output) The specification of a single machine used by the prediction. Structure is documented below.
- Max
Replica intCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- Min
Replica intCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- autoscaling
Metric List<AiSpecs Endpoint Deployed Model Dedicated Resource Autoscaling Metric Spec> (Output) The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to
aiplatform.googleapis.com/prediction/online/cpu/utilization
and autoscaling_metric_specs.target to80
. Structure is documented below.- machine
Specs List<AiEndpoint Deployed Model Dedicated Resource Machine Spec> (Output) The specification of a single machine used by the prediction. Structure is documented below.
- max
Replica IntegerCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min
Replica IntegerCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- autoscaling
Metric AiSpecs Endpoint Deployed Model Dedicated Resource Autoscaling Metric Spec[] (Output) The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to
aiplatform.googleapis.com/prediction/online/cpu/utilization
and autoscaling_metric_specs.target to80
. Structure is documented below.- machine
Specs AiEndpoint Deployed Model Dedicated Resource Machine Spec[] (Output) The specification of a single machine used by the prediction. Structure is documented below.
- max
Replica numberCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min
Replica numberCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- autoscaling_
metric_ Sequence[Aispecs Endpoint Deployed Model Dedicated Resource Autoscaling Metric Spec] (Output) The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to
aiplatform.googleapis.com/prediction/online/cpu/utilization
and autoscaling_metric_specs.target to80
. Structure is documented below.- machine_
specs Sequence[AiEndpoint Deployed Model Dedicated Resource Machine Spec] (Output) The specification of a single machine used by the prediction. Structure is documented below.
- max_
replica_ intcount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min_
replica_ intcount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
- autoscaling
Metric List<Property Map>Specs (Output) The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to
aiplatform.googleapis.com/prediction/online/cpu/utilization
and autoscaling_metric_specs.target to80
. Structure is documented below.- machine
Specs List<Property Map> (Output) The specification of a single machine used by the prediction. Structure is documented below.
- max
Replica NumberCount (Output) The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
- min
Replica NumberCount (Output) The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
AiEndpointDeployedModelDedicatedResourceAutoscalingMetricSpec, AiEndpointDeployedModelDedicatedResourceAutoscalingMetricSpecArgs
- Metric
Name string (Output) The resource metric name. Supported metrics: * For Online Prediction: *
aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
*aiplatform.googleapis.com/prediction/online/cpu/utilization
- Target int
(Output) The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
- Metric
Name string (Output) The resource metric name. Supported metrics: * For Online Prediction: *
aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
*aiplatform.googleapis.com/prediction/online/cpu/utilization
- Target int
(Output) The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
- metric
Name String (Output) The resource metric name. Supported metrics: * For Online Prediction: *
aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
*aiplatform.googleapis.com/prediction/online/cpu/utilization
- target Integer
(Output) The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
- metric
Name string (Output) The resource metric name. Supported metrics: * For Online Prediction: *
aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
*aiplatform.googleapis.com/prediction/online/cpu/utilization
- target number
(Output) The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
- metric_
name str (Output) The resource metric name. Supported metrics: * For Online Prediction: *
aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
*aiplatform.googleapis.com/prediction/online/cpu/utilization
- target int
(Output) The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
- metric
Name String (Output) The resource metric name. Supported metrics: * For Online Prediction: *
aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle
*aiplatform.googleapis.com/prediction/online/cpu/utilization
- target Number
(Output) The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
AiEndpointDeployedModelDedicatedResourceMachineSpec, AiEndpointDeployedModelDedicatedResourceMachineSpecArgs
- Accelerator
Count int (Output) The number of accelerators to attach to the machine.
- Accelerator
Type string (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
- Machine
Type string (Output) The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. TODO(rsurowka): Try to better unify the required vs optional.
- Accelerator
Count int (Output) The number of accelerators to attach to the machine.
- Accelerator
Type string (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
- Machine
Type string (Output) The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. TODO(rsurowka): Try to better unify the required vs optional.
- accelerator
Count Integer (Output) The number of accelerators to attach to the machine.
- accelerator
Type String (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
- machine
Type String (Output) The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. TODO(rsurowka): Try to better unify the required vs optional.
- accelerator
Count number (Output) The number of accelerators to attach to the machine.
- accelerator
Type string (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
- machine
Type string (Output) The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. TODO(rsurowka): Try to better unify the required vs optional.
- accelerator_
count int (Output) The number of accelerators to attach to the machine.
- accelerator_
type str (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
- machine_
type str (Output) The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. TODO(rsurowka): Try to better unify the required vs optional.
- accelerator
Count Number (Output) The number of accelerators to attach to the machine.
- accelerator
Type String (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
- machine
Type String (Output) The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. TODO(rsurowka): Try to better unify the required vs optional.
AiEndpointDeployedModelPrivateEndpoint, AiEndpointDeployedModelPrivateEndpointArgs
- Explain
Http stringUri (Output) Output only. Http(s) path to send explain requests.
- Health
Http stringUri (Output) Output only. Http(s) path to send health check requests.
- Predict
Http stringUri (Output) Output only. Http(s) path to send prediction requests.
- Service
Attachment string (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
- Explain
Http stringUri (Output) Output only. Http(s) path to send explain requests.
- Health
Http stringUri (Output) Output only. Http(s) path to send health check requests.
- Predict
Http stringUri (Output) Output only. Http(s) path to send prediction requests.
- Service
Attachment string (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
- explain
Http StringUri (Output) Output only. Http(s) path to send explain requests.
- health
Http StringUri (Output) Output only. Http(s) path to send health check requests.
- predict
Http StringUri (Output) Output only. Http(s) path to send prediction requests.
- service
Attachment String (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
- explain
Http stringUri (Output) Output only. Http(s) path to send explain requests.
- health
Http stringUri (Output) Output only. Http(s) path to send health check requests.
- predict
Http stringUri (Output) Output only. Http(s) path to send prediction requests.
- service
Attachment string (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
- explain_
http_ struri (Output) Output only. Http(s) path to send explain requests.
- health_
http_ struri (Output) Output only. Http(s) path to send health check requests.
- predict_
http_ struri (Output) Output only. Http(s) path to send prediction requests.
- service_
attachment str (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
- explain
Http StringUri (Output) Output only. Http(s) path to send explain requests.
- health
Http StringUri (Output) Output only. Http(s) path to send health check requests.
- predict
Http StringUri (Output) Output only. Http(s) path to send prediction requests.
- service
Attachment String (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
AiEndpointEncryptionSpec, AiEndpointEncryptionSpecArgs
- Kms
Key stringName Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- Kms
Key stringName Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key StringName Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key stringName Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms_
key_ strname Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key StringName Required. The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
Import
Endpoint can be imported using any of these accepted formats
$ pulumi import gcp:vertex/aiEndpoint:AiEndpoint default projects/{{project}}/locations/{{location}}/endpoints/{{name}}
$ pulumi import gcp:vertex/aiEndpoint:AiEndpoint default {{project}}/{{location}}/{{name}}
$ pulumi import gcp:vertex/aiEndpoint:AiEndpoint default {{location}}/{{name}}
Package Details
- Repository
- Google Cloud (GCP) Classic pulumi/pulumi-gcp
- License
- Apache-2.0
- Notes
This Pulumi package is based on the
google-beta
Terraform Provider.