1. Packages
  2. Google Cloud (GCP) Classic
  3. API Docs
  4. vertex
  5. AiEndpoint
Google Cloud Classic v7.29.0 published on Wednesday, Jun 26, 2024 by Pulumi

gcp.vertex.AiEndpoint

Explore with Pulumi AI

gcp logo
Google Cloud Classic v7.29.0 published on Wednesday, Jun 26, 2024 by Pulumi

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

    To get more information about Endpoint, see:

    Example Usage

    Vertex Ai Endpoint Network

    import * as pulumi from "@pulumi/pulumi";
    import * as gcp from "@pulumi/gcp";
    
    const vertexNetwork = new gcp.compute.Network("vertex_network", {name: "network-name"});
    const vertexRange = new gcp.compute.GlobalAddress("vertex_range", {
        name: "address-name",
        purpose: "VPC_PEERING",
        addressType: "INTERNAL",
        prefixLength: 24,
        network: vertexNetwork.id,
    });
    const vertexVpcConnection = new gcp.servicenetworking.Connection("vertex_vpc_connection", {
        network: vertexNetwork.id,
        service: "servicenetworking.googleapis.com",
        reservedPeeringRanges: [vertexRange.name],
    });
    const project = gcp.organizations.getProject({});
    const endpoint = new gcp.vertex.AiEndpoint("endpoint", {
        name: "endpoint-name",
        displayName: "sample-endpoint",
        description: "A sample vertex endpoint",
        location: "us-central1",
        region: "us-central1",
        labels: {
            "label-one": "value-one",
        },
        network: pulumi.all([project, vertexNetwork.name]).apply(([project, name]) => `projects/${project.number}/global/networks/${name}`),
        encryptionSpec: {
            kmsKeyName: "kms-name",
        },
    }, {
        dependsOn: [vertexVpcConnection],
    });
    const cryptoKey = new gcp.kms.CryptoKeyIAMMember("crypto_key", {
        cryptoKeyId: "kms-name",
        role: "roles/cloudkms.cryptoKeyEncrypterDecrypter",
        member: project.then(project => `serviceAccount:service-${project.number}@gcp-sa-aiplatform.iam.gserviceaccount.com`),
    });
    
    import pulumi
    import pulumi_gcp as gcp
    
    vertex_network = gcp.compute.Network("vertex_network", name="network-name")
    vertex_range = gcp.compute.GlobalAddress("vertex_range",
        name="address-name",
        purpose="VPC_PEERING",
        address_type="INTERNAL",
        prefix_length=24,
        network=vertex_network.id)
    vertex_vpc_connection = gcp.servicenetworking.Connection("vertex_vpc_connection",
        network=vertex_network.id,
        service="servicenetworking.googleapis.com",
        reserved_peering_ranges=[vertex_range.name])
    project = gcp.organizations.get_project()
    endpoint = gcp.vertex.AiEndpoint("endpoint",
        name="endpoint-name",
        display_name="sample-endpoint",
        description="A sample vertex endpoint",
        location="us-central1",
        region="us-central1",
        labels={
            "label-one": "value-one",
        },
        network=vertex_network.name.apply(lambda name: f"projects/{project.number}/global/networks/{name}"),
        encryption_spec=gcp.vertex.AiEndpointEncryptionSpecArgs(
            kms_key_name="kms-name",
        ),
        opts = pulumi.ResourceOptions(depends_on=[vertex_vpc_connection]))
    crypto_key = gcp.kms.CryptoKeyIAMMember("crypto_key",
        crypto_key_id="kms-name",
        role="roles/cloudkms.cryptoKeyEncrypterDecrypter",
        member=f"serviceAccount:service-{project.number}@gcp-sa-aiplatform.iam.gserviceaccount.com")
    
    package main
    
    import (
    	"fmt"
    
    	"github.com/pulumi/pulumi-gcp/sdk/v7/go/gcp/compute"
    	"github.com/pulumi/pulumi-gcp/sdk/v7/go/gcp/kms"
    	"github.com/pulumi/pulumi-gcp/sdk/v7/go/gcp/organizations"
    	"github.com/pulumi/pulumi-gcp/sdk/v7/go/gcp/servicenetworking"
    	"github.com/pulumi/pulumi-gcp/sdk/v7/go/gcp/vertex"
    	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
    )
    
    func main() {
    	pulumi.Run(func(ctx *pulumi.Context) error {
    		vertexNetwork, err := compute.NewNetwork(ctx, "vertex_network", &compute.NetworkArgs{
    			Name: pulumi.String("network-name"),
    		})
    		if err != nil {
    			return err
    		}
    		vertexRange, err := compute.NewGlobalAddress(ctx, "vertex_range", &compute.GlobalAddressArgs{
    			Name:         pulumi.String("address-name"),
    			Purpose:      pulumi.String("VPC_PEERING"),
    			AddressType:  pulumi.String("INTERNAL"),
    			PrefixLength: pulumi.Int(24),
    			Network:      vertexNetwork.ID(),
    		})
    		if err != nil {
    			return err
    		}
    		vertexVpcConnection, err := servicenetworking.NewConnection(ctx, "vertex_vpc_connection", &servicenetworking.ConnectionArgs{
    			Network: 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{
    			Name:        pulumi.String("endpoint-name"),
    			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: vertexNetwork.Name.ApplyT(func(name string) (string, error) {
    				return fmt.Sprintf("projects/%v/global/networks/%v", project.Number, name), nil
    			}).(pulumi.StringOutput),
    			EncryptionSpec: &vertex.AiEndpointEncryptionSpecArgs{
    				KmsKeyName: pulumi.String("kms-name"),
    			},
    		}, pulumi.DependsOn([]pulumi.Resource{
    			vertexVpcConnection,
    		}))
    		if err != nil {
    			return err
    		}
    		_, err = kms.NewCryptoKeyIAMMember(ctx, "crypto_key", &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
    	})
    }
    
    using System.Collections.Generic;
    using System.Linq;
    using Pulumi;
    using Gcp = Pulumi.Gcp;
    
    return await Deployment.RunAsync(() => 
    {
        var vertexNetwork = new Gcp.Compute.Network("vertex_network", new()
        {
            Name = "network-name",
        });
    
        var vertexRange = new Gcp.Compute.GlobalAddress("vertex_range", new()
        {
            Name = "address-name",
            Purpose = "VPC_PEERING",
            AddressType = "INTERNAL",
            PrefixLength = 24,
            Network = vertexNetwork.Id,
        });
    
        var vertexVpcConnection = new Gcp.ServiceNetworking.Connection("vertex_vpc_connection", new()
        {
            Network = vertexNetwork.Id,
            Service = "servicenetworking.googleapis.com",
            ReservedPeeringRanges = new[]
            {
                vertexRange.Name,
            },
        });
    
        var project = Gcp.Organizations.GetProject.Invoke();
    
        var endpoint = new Gcp.Vertex.AiEndpoint("endpoint", new()
        {
            Name = "endpoint-name",
            DisplayName = "sample-endpoint",
            Description = "A sample vertex endpoint",
            Location = "us-central1",
            Region = "us-central1",
            Labels = 
            {
                { "label-one", "value-one" },
            },
            Network = Output.Tuple(project, vertexNetwork.Name).Apply(values =>
            {
                var project = values.Item1;
                var name = values.Item2;
                return $"projects/{project.Apply(getProjectResult => getProjectResult.Number)}/global/networks/{name}";
            }),
            EncryptionSpec = new Gcp.Vertex.Inputs.AiEndpointEncryptionSpecArgs
            {
                KmsKeyName = "kms-name",
            },
        }, new CustomResourceOptions
        {
            DependsOn =
            {
                vertexVpcConnection,
            },
        });
    
        var cryptoKey = new Gcp.Kms.CryptoKeyIAMMember("crypto_key", new()
        {
            CryptoKeyId = "kms-name",
            Role = "roles/cloudkms.cryptoKeyEncrypterDecrypter",
            Member = $"serviceAccount:service-{project.Apply(getProjectResult => getProjectResult.Number)}@gcp-sa-aiplatform.iam.gserviceaccount.com",
        });
    
    });
    
    package generated_program;
    
    import com.pulumi.Context;
    import com.pulumi.Pulumi;
    import com.pulumi.core.Output;
    import com.pulumi.gcp.compute.Network;
    import com.pulumi.gcp.compute.NetworkArgs;
    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) {
            var vertexNetwork = new Network("vertexNetwork", NetworkArgs.builder()
                .name("network-name")
                .build());
    
            var vertexRange = new GlobalAddress("vertexRange", GlobalAddressArgs.builder()
                .name("address-name")
                .purpose("VPC_PEERING")
                .addressType("INTERNAL")
                .prefixLength(24)
                .network(vertexNetwork.id())
                .build());
    
            var vertexVpcConnection = new Connection("vertexVpcConnection", ConnectionArgs.builder()
                .network(vertexNetwork.id())
                .service("servicenetworking.googleapis.com")
                .reservedPeeringRanges(vertexRange.name())
                .build());
    
            final var project = OrganizationsFunctions.getProject();
    
            var endpoint = new AiEndpoint("endpoint", AiEndpointArgs.builder()
                .name("endpoint-name")
                .displayName("sample-endpoint")
                .description("A sample vertex endpoint")
                .location("us-central1")
                .region("us-central1")
                .labels(Map.of("label-one", "value-one"))
                .network(vertexNetwork.name().applyValue(name -> String.format("projects/%s/global/networks/%s", project.applyValue(getProjectResult -> getProjectResult.number()),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());
    
        }
    }
    
    resources:
      endpoint:
        type: gcp:vertex:AiEndpoint
        properties:
          name: endpoint-name
          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
        name: vertex_vpc_connection
        properties:
          network: ${vertexNetwork.id}
          service: servicenetworking.googleapis.com
          reservedPeeringRanges:
            - ${vertexRange.name}
      vertexRange:
        type: gcp:compute:GlobalAddress
        name: vertex_range
        properties:
          name: address-name
          purpose: VPC_PEERING
          addressType: INTERNAL
          prefixLength: 24
          network: ${vertexNetwork.id}
      vertexNetwork:
        type: gcp:compute:Network
        name: vertex_network
        properties:
          name: network-name
      cryptoKey:
        type: gcp:kms:CryptoKeyIAMMember
        name: crypto_key
        properties:
          cryptoKeyId: kms-name
          role: roles/cloudkms.cryptoKeyEncrypterDecrypter
          member: serviceAccount:service-${project.number}@gcp-sa-aiplatform.iam.gserviceaccount.com
    variables:
      project:
        fn::invoke:
          Function: gcp:organizations:getProject
          Arguments: {}
    

    Create AiEndpoint Resource

    Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

    Constructor syntax

    new AiEndpoint(name: string, args: AiEndpointArgs, opts?: CustomResourceOptions);
    @overload
    def AiEndpoint(resource_name: str,
                   args: AiEndpointArgs,
                   opts: Optional[ResourceOptions] = None)
    
    @overload
    def AiEndpoint(resource_name: str,
                   opts: Optional[ResourceOptions] = None,
                   display_name: Optional[str] = None,
                   location: Optional[str] = None,
                   description: Optional[str] = None,
                   encryption_spec: Optional[AiEndpointEncryptionSpecArgs] = None,
                   labels: Optional[Mapping[str, str]] = None,
                   name: Optional[str] = None,
                   network: Optional[str] = None,
                   project: Optional[str] = None,
                   region: Optional[str] = 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.
    
    

    Parameters

    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.

    Constructor example

    The following reference example uses placeholder values for all input properties.

    var aiEndpointResource = new Gcp.Vertex.AiEndpoint("aiEndpointResource", new()
    {
        DisplayName = "string",
        Location = "string",
        Description = "string",
        EncryptionSpec = new Gcp.Vertex.Inputs.AiEndpointEncryptionSpecArgs
        {
            KmsKeyName = "string",
        },
        Labels = 
        {
            { "string", "string" },
        },
        Name = "string",
        Network = "string",
        Project = "string",
        Region = "string",
    });
    
    example, err := vertex.NewAiEndpoint(ctx, "aiEndpointResource", &vertex.AiEndpointArgs{
    	DisplayName: pulumi.String("string"),
    	Location:    pulumi.String("string"),
    	Description: pulumi.String("string"),
    	EncryptionSpec: &vertex.AiEndpointEncryptionSpecArgs{
    		KmsKeyName: pulumi.String("string"),
    	},
    	Labels: pulumi.StringMap{
    		"string": pulumi.String("string"),
    	},
    	Name:    pulumi.String("string"),
    	Network: pulumi.String("string"),
    	Project: pulumi.String("string"),
    	Region:  pulumi.String("string"),
    })
    
    var aiEndpointResource = new AiEndpoint("aiEndpointResource", AiEndpointArgs.builder()
        .displayName("string")
        .location("string")
        .description("string")
        .encryptionSpec(AiEndpointEncryptionSpecArgs.builder()
            .kmsKeyName("string")
            .build())
        .labels(Map.of("string", "string"))
        .name("string")
        .network("string")
        .project("string")
        .region("string")
        .build());
    
    ai_endpoint_resource = gcp.vertex.AiEndpoint("aiEndpointResource",
        display_name="string",
        location="string",
        description="string",
        encryption_spec=gcp.vertex.AiEndpointEncryptionSpecArgs(
            kms_key_name="string",
        ),
        labels={
            "string": "string",
        },
        name="string",
        network="string",
        project="string",
        region="string")
    
    const aiEndpointResource = new gcp.vertex.AiEndpoint("aiEndpointResource", {
        displayName: "string",
        location: "string",
        description: "string",
        encryptionSpec: {
            kmsKeyName: "string",
        },
        labels: {
            string: "string",
        },
        name: "string",
        network: "string",
        project: "string",
        region: "string",
    });
    
    type: gcp:vertex:AiEndpoint
    properties:
        description: string
        displayName: string
        encryptionSpec:
            kmsKeyName: string
        labels:
            string: string
        location: string
        name: string
        network: string
        project: string
        region: string
    

    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:

    DisplayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    Location string
    The location for the resource


    Description string
    The description of the Endpoint.
    EncryptionSpec AiEndpointEncryptionSpec
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    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 in 12345, 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
    DisplayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    Location string
    The location for the resource


    Description string
    The description of the Endpoint.
    EncryptionSpec AiEndpointEncryptionSpecArgs
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    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 in 12345, 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
    displayName String
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    location String
    The location for the resource


    description String
    The description of the Endpoint.
    encryptionSpec AiEndpointEncryptionSpec
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    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 in 12345, 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
    displayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    location string
    The location for the resource


    description string
    The description of the Endpoint.
    encryptionSpec AiEndpointEncryptionSpec
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    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 in 12345, 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 AiEndpointEncryptionSpecArgs
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    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 in 12345, 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
    displayName String
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    location String
    The location for the resource


    description String
    The description of the Endpoint.
    encryptionSpec 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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    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 in 12345, 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:

    CreateTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    DeployedModels List<AiEndpointDeployedModel>
    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.
    EffectiveLabels Dictionary<string, string>
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    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.
    ModelDeploymentMonitoringJob string
    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}
    PulumiLabels Dictionary<string, string>
    The combination of labels configured directly on the resource and default labels configured on the provider.
    UpdateTime string
    Output only. Timestamp when this Endpoint was last updated.
    CreateTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    DeployedModels []AiEndpointDeployedModel
    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.
    EffectiveLabels map[string]string
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    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.
    ModelDeploymentMonitoringJob string
    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}
    PulumiLabels map[string]string
    The combination of labels configured directly on the resource and default labels configured on the provider.
    UpdateTime string
    Output only. Timestamp when this Endpoint was last updated.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    deployedModels List<AiEndpointDeployedModel>
    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.
    effectiveLabels Map<String,String>
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    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.
    modelDeploymentMonitoringJob String
    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}
    pulumiLabels Map<String,String>
    The combination of labels configured directly on the resource and default labels configured on the provider.
    updateTime String
    Output only. Timestamp when this Endpoint was last updated.
    createTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    deployedModels AiEndpointDeployedModel[]
    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.
    effectiveLabels {[key: string]: string}
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    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.
    modelDeploymentMonitoringJob string
    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}
    pulumiLabels {[key: string]: string}
    The combination of labels configured directly on the resource and default labels configured on the provider.
    updateTime 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[AiEndpointDeployedModel]
    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.
    effective_labels Mapping[str, str]
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    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_monitoring_job str
    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}
    pulumi_labels Mapping[str, str]
    The combination of labels configured directly on the resource and default labels configured on the provider.
    update_time str
    Output only. Timestamp when this Endpoint was last updated.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    deployedModels 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.
    effectiveLabels Map<String>
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    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.
    modelDeploymentMonitoringJob String
    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}
    pulumiLabels Map<String>
    The combination of labels configured directly on the resource and default labels configured on the provider.
    updateTime 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,
            effective_labels: Optional[Mapping[str, 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,
            pulumi_labels: Optional[Mapping[str, 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.
    The following state arguments are supported:
    CreateTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    DeployedModels List<AiEndpointDeployedModel>
    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.
    DisplayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    EffectiveLabels Dictionary<string, string>
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    EncryptionSpec AiEndpointEncryptionSpec
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    Location string
    The location for the resource


    ModelDeploymentMonitoringJob string
    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 in 12345, 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.
    PulumiLabels Dictionary<string, string>
    The combination of labels configured directly on the resource and default labels configured on the provider.
    Region string
    The region for the resource
    UpdateTime string
    Output only. Timestamp when this Endpoint was last updated.
    CreateTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    DeployedModels []AiEndpointDeployedModelArgs
    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.
    DisplayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    EffectiveLabels map[string]string
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    EncryptionSpec AiEndpointEncryptionSpecArgs
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    Location string
    The location for the resource


    ModelDeploymentMonitoringJob string
    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 in 12345, 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.
    PulumiLabels map[string]string
    The combination of labels configured directly on the resource and default labels configured on the provider.
    Region string
    The region for the resource
    UpdateTime string
    Output only. Timestamp when this Endpoint was last updated.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    deployedModels List<AiEndpointDeployedModel>
    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.
    displayName String
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    effectiveLabels Map<String,String>
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    encryptionSpec AiEndpointEncryptionSpec
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    location String
    The location for the resource


    modelDeploymentMonitoringJob String
    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 in 12345, 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.
    pulumiLabels Map<String,String>
    The combination of labels configured directly on the resource and default labels configured on the provider.
    region String
    The region for the resource
    updateTime String
    Output only. Timestamp when this Endpoint was last updated.
    createTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    deployedModels AiEndpointDeployedModel[]
    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.
    displayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    effectiveLabels {[key: string]: string}
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    encryptionSpec AiEndpointEncryptionSpec
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    location string
    The location for the resource


    modelDeploymentMonitoringJob string
    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 in 12345, 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.
    pulumiLabels {[key: string]: string}
    The combination of labels configured directly on the resource and default labels configured on the provider.
    region string
    The region for the resource
    updateTime 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[AiEndpointDeployedModelArgs]
    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.
    effective_labels Mapping[str, str]
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    encryption_spec AiEndpointEncryptionSpecArgs
    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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    location str
    The location for the resource


    model_deployment_monitoring_job str
    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 in 12345, 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.
    pulumi_labels Mapping[str, str]
    The combination of labels configured directly on the resource and default labels configured on the provider.
    region str
    The region for the resource
    update_time str
    Output only. Timestamp when this Endpoint was last updated.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    deployedModels 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.
    displayName String
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    effectiveLabels Map<String>
    All of labels (key/value pairs) present on the resource in GCP, including the labels configured through Pulumi, other clients and services.
    encryptionSpec 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. Note: This field is non-authoritative, and will only manage the labels present in your configuration. Please refer to the field effective_labels for all of the labels present on the resource.
    location String
    The location for the resource


    modelDeploymentMonitoringJob String
    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 in 12345, 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.
    pulumiLabels Map<String>
    The combination of labels configured directly on the resource and default labels configured on the provider.
    region String
    The region for the resource
    updateTime String
    Output only. Timestamp when this Endpoint was last updated.

    Supporting Types

    AiEndpointDeployedModel, AiEndpointDeployedModelArgs

    AutomaticResources List<AiEndpointDeployedModelAutomaticResource>
    (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.
    CreateTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    DedicatedResources List<AiEndpointDeployedModelDedicatedResource>
    (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
    DisplayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    EnableAccessLogging bool
    (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.
    EnableContainerLogging bool
    (Output) If true, the container of the DeployedModel instances will send stderr and stdout 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.
    ModelVersionId string
    (Output) Output only. The version ID of the model that is deployed.
    PrivateEndpoints List<AiEndpointDeployedModelPrivateEndpoint>
    (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.
    ServiceAccount 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.
    SharedResources string
    (Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
    AutomaticResources []AiEndpointDeployedModelAutomaticResource
    (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.
    CreateTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    DedicatedResources []AiEndpointDeployedModelDedicatedResource
    (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
    DisplayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    EnableAccessLogging bool
    (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.
    EnableContainerLogging bool
    (Output) If true, the container of the DeployedModel instances will send stderr and stdout 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.
    ModelVersionId string
    (Output) Output only. The version ID of the model that is deployed.
    PrivateEndpoints []AiEndpointDeployedModelPrivateEndpoint
    (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.
    ServiceAccount 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.
    SharedResources string
    (Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
    automaticResources List<AiEndpointDeployedModelAutomaticResource>
    (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.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    dedicatedResources List<AiEndpointDeployedModelDedicatedResource>
    (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
    displayName String
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    enableAccessLogging Boolean
    (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.
    enableContainerLogging Boolean
    (Output) If true, the container of the DeployedModel instances will send stderr and stdout 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.
    modelVersionId String
    (Output) Output only. The version ID of the model that is deployed.
    privateEndpoints List<AiEndpointDeployedModelPrivateEndpoint>
    (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.
    serviceAccount 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.
    sharedResources String
    (Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
    automaticResources AiEndpointDeployedModelAutomaticResource[]
    (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.
    createTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    dedicatedResources AiEndpointDeployedModelDedicatedResource[]
    (Output) A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration. Structure is documented below.
    displayName string
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    enableAccessLogging boolean
    (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.
    enableContainerLogging boolean
    (Output) If true, the container of the DeployedModel instances will send stderr and stdout 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.
    modelVersionId string
    (Output) Output only. The version ID of the model that is deployed.
    privateEndpoints AiEndpointDeployedModelPrivateEndpoint[]
    (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.
    serviceAccount 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.
    sharedResources string
    (Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
    automatic_resources Sequence[AiEndpointDeployedModelAutomaticResource]
    (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[AiEndpointDeployedModelDedicatedResource]
    (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_logging bool
    (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_logging bool
    (Output) If true, the container of the DeployedModel instances will send stderr and stdout 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_id str
    (Output) Output only. The version ID of the model that is deployed.
    private_endpoints Sequence[AiEndpointDeployedModelPrivateEndpoint]
    (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.
    shared_resources str
    (Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
    automaticResources 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.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    dedicatedResources 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.
    displayName String
    Required. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    enableAccessLogging Boolean
    (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.
    enableContainerLogging Boolean
    (Output) If true, the container of the DeployedModel instances will send stderr and stdout 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.
    modelVersionId String
    (Output) Output only. The version ID of the model that is deployed.
    privateEndpoints 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.
    serviceAccount 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.
    sharedResources String
    (Output) The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

    AiEndpointDeployedModelAutomaticResource, AiEndpointDeployedModelAutomaticResourceArgs

    MaxReplicaCount int
    (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.
    MinReplicaCount int
    (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.
    MaxReplicaCount int
    (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.
    MinReplicaCount int
    (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.
    maxReplicaCount Integer
    (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.
    minReplicaCount Integer
    (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.
    maxReplicaCount number
    (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.
    minReplicaCount number
    (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_count int
    (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_count int
    (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.
    maxReplicaCount Number
    (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.
    minReplicaCount Number
    (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

    AutoscalingMetricSpecs List<AiEndpointDeployedModelDedicatedResourceAutoscalingMetricSpec>
    (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 to 80. Structure is documented below.
    MachineSpecs List<AiEndpointDeployedModelDedicatedResourceMachineSpec>
    (Output) The specification of a single machine used by the prediction. Structure is documented below.
    MaxReplicaCount int
    (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.
    MinReplicaCount int
    (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.
    AutoscalingMetricSpecs []AiEndpointDeployedModelDedicatedResourceAutoscalingMetricSpec
    (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 to 80. Structure is documented below.
    MachineSpecs []AiEndpointDeployedModelDedicatedResourceMachineSpec
    (Output) The specification of a single machine used by the prediction. Structure is documented below.
    MaxReplicaCount int
    (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.
    MinReplicaCount int
    (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.
    autoscalingMetricSpecs List<AiEndpointDeployedModelDedicatedResourceAutoscalingMetricSpec>
    (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 to 80. Structure is documented below.
    machineSpecs List<AiEndpointDeployedModelDedicatedResourceMachineSpec>
    (Output) The specification of a single machine used by the prediction. Structure is documented below.
    maxReplicaCount Integer
    (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.
    minReplicaCount Integer
    (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.
    autoscalingMetricSpecs AiEndpointDeployedModelDedicatedResourceAutoscalingMetricSpec[]
    (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 to 80. Structure is documented below.
    machineSpecs AiEndpointDeployedModelDedicatedResourceMachineSpec[]
    (Output) The specification of a single machine used by the prediction. Structure is documented below.
    maxReplicaCount number
    (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.
    minReplicaCount number
    (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_specs Sequence[AiEndpointDeployedModelDedicatedResourceAutoscalingMetricSpec]
    (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 to 80. Structure is documented below.
    machine_specs Sequence[AiEndpointDeployedModelDedicatedResourceMachineSpec]
    (Output) The specification of a single machine used by the prediction. Structure is documented below.
    max_replica_count int
    (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_count int
    (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.
    autoscalingMetricSpecs List<Property Map>
    (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 to 80. Structure is documented below.
    machineSpecs List<Property Map>
    (Output) The specification of a single machine used by the prediction. Structure is documented below.
    maxReplicaCount Number
    (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.
    minReplicaCount Number
    (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

    MetricName 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.
    MetricName 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.
    metricName 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.
    metricName 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.
    metricName 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

    AcceleratorCount int
    (Output) The number of accelerators to attach to the machine.
    AcceleratorType string
    (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
    MachineType 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.
    AcceleratorCount int
    (Output) The number of accelerators to attach to the machine.
    AcceleratorType string
    (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
    MachineType 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.
    acceleratorCount Integer
    (Output) The number of accelerators to attach to the machine.
    acceleratorType String
    (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
    machineType 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.
    acceleratorCount number
    (Output) The number of accelerators to attach to the machine.
    acceleratorType string
    (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
    machineType 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.
    acceleratorCount Number
    (Output) The number of accelerators to attach to the machine.
    acceleratorType String
    (Output) The type of accelerator(s) that may be attached to the machine as per accelerator_count. See possible values here.
    machineType 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

    ExplainHttpUri string
    (Output) Output only. Http(s) path to send explain requests.
    HealthHttpUri string
    (Output) Output only. Http(s) path to send health check requests.
    PredictHttpUri string
    (Output) Output only. Http(s) path to send prediction requests.
    ServiceAttachment string
    (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
    ExplainHttpUri string
    (Output) Output only. Http(s) path to send explain requests.
    HealthHttpUri string
    (Output) Output only. Http(s) path to send health check requests.
    PredictHttpUri string
    (Output) Output only. Http(s) path to send prediction requests.
    ServiceAttachment string
    (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
    explainHttpUri String
    (Output) Output only. Http(s) path to send explain requests.
    healthHttpUri String
    (Output) Output only. Http(s) path to send health check requests.
    predictHttpUri String
    (Output) Output only. Http(s) path to send prediction requests.
    serviceAttachment String
    (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
    explainHttpUri string
    (Output) Output only. Http(s) path to send explain requests.
    healthHttpUri string
    (Output) Output only. Http(s) path to send health check requests.
    predictHttpUri string
    (Output) Output only. Http(s) path to send prediction requests.
    serviceAttachment string
    (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.
    explain_http_uri str
    (Output) Output only. Http(s) path to send explain requests.
    health_http_uri str
    (Output) Output only. Http(s) path to send health check requests.
    predict_http_uri str
    (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.
    explainHttpUri String
    (Output) Output only. Http(s) path to send explain requests.
    healthHttpUri String
    (Output) Output only. Http(s) path to send health check requests.
    predictHttpUri String
    (Output) Output only. Http(s) path to send prediction requests.
    serviceAttachment String
    (Output) Output only. The name of the service attachment resource. Populated if private service connect is enabled.

    AiEndpointEncryptionSpec, AiEndpointEncryptionSpecArgs

    KmsKeyName string
    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.
    KmsKeyName string
    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.
    kmsKeyName String
    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.
    kmsKeyName string
    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_name str
    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.
    kmsKeyName String
    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:

    • projects/{{project}}/locations/{{location}}/endpoints/{{name}}

    • {{project}}/{{location}}/{{name}}

    • {{location}}/{{name}}

    When using the pulumi import command, Endpoint can be imported using one of the formats above. For example:

    $ 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}}
    

    To learn more about importing existing cloud resources, see Importing resources.

    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.
    gcp logo
    Google Cloud Classic v7.29.0 published on Wednesday, Jun 26, 2024 by Pulumi