Docs Home Pulumi IaC Pulumi ESC Pulumi Cloud Packages Tutorials
  1. Packages
  2. Google Cloud (GCP) Classic
  3. API Docs
  4. vertex
  5. AiEndpoint
Google Cloud v8.22.0 published on Thursday, Mar 13, 2025 by Pulumi
pulumi/pulumi-gcp

gcp.vertex.AiEndpoint

Explore with Pulumi AI

gcp logo
Google Cloud v8.22.0 published on Thursday, Mar 13, 2025 by Pulumi
pulumi/pulumi-gcp

    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 bqDataset = new gcp.bigquery.Dataset("bq_dataset", {
    datasetId: "some_dataset",
    friendlyName: "logging dataset",
    description: "This is a dataset that requests are logged to",
    location: "US",
    deleteContentsOnDestroy: true,
});
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",
    },
    predictRequestResponseLoggingConfig: {
        bigqueryDestination: {
            outputUri: pulumi.all([project, bqDataset.datasetId]).apply(([project, datasetId]) => `bq://${project.projectId}.${datasetId}.request_response_logging`),
        },
        enabled: true,
        samplingRate: 0.1,
    },
    trafficSplit: JSON.stringify({
        "12345": 100,
    }),
}, {
    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 json
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])
bq_dataset = gcp.bigquery.Dataset("bq_dataset",
    dataset_id="some_dataset",
    friendly_name="logging dataset",
    description="This is a dataset that requests are logged to",
    location="US",
    delete_contents_on_destroy=True)
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={
        "kms_key_name": "kms-name",
    },
    predict_request_response_logging_config={
        "bigquery_destination": {
            "output_uri": bq_dataset.dataset_id.apply(lambda dataset_id: f"bq://{project.project_id}.{dataset_id}.request_response_logging"),
        },
        "enabled": True,
        "sampling_rate": 0.1,
    },
    traffic_split=json.dumps({
        "12345": 100,
    }),
    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 (
	"encoding/json"
	"fmt"

	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/bigquery"
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/compute"
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/kms"
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/organizations"
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/servicenetworking"
	"github.com/pulumi/pulumi-gcp/sdk/v8/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
		}
		bqDataset, err := bigquery.NewDataset(ctx, "bq_dataset", &bigquery.DatasetArgs{
			DatasetId:               pulumi.String("some_dataset"),
			FriendlyName:            pulumi.String("logging dataset"),
			Description:             pulumi.String("This is a dataset that requests are logged to"),
			Location:                pulumi.String("US"),
			DeleteContentsOnDestroy: pulumi.Bool(true),
		})
		if err != nil {
			return err
		}
		project, err := organizations.LookupProject(ctx, &organizations.LookupProjectArgs{}, nil)
		if err != nil {
			return err
		}
		tmpJSON0, err := json.Marshal(map[string]interface{}{
			"12345": 100,
		})
		if err != nil {
			return err
		}
		json0 := string(tmpJSON0)
		_, 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"),
			},
			PredictRequestResponseLoggingConfig: &vertex.AiEndpointPredictRequestResponseLoggingConfigArgs{
				BigqueryDestination: &vertex.AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs{
					OutputUri: bqDataset.DatasetId.ApplyT(func(datasetId string) (string, error) {
						return fmt.Sprintf("bq://%v.%v.request_response_logging", project.ProjectId, datasetId), nil
					}).(pulumi.StringOutput),
				},
				Enabled:      pulumi.Bool(true),
				SamplingRate: pulumi.Float64(0.1),
			},
			TrafficSplit: pulumi.String(json0),
		}, 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.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 System.Text.Json;
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 bqDataset = new Gcp.BigQuery.Dataset("bq_dataset", new()
    {
        DatasetId = "some_dataset",
        FriendlyName = "logging dataset",
        Description = "This is a dataset that requests are logged to",
        Location = "US",
        DeleteContentsOnDestroy = true,
    });

    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",
        },
        PredictRequestResponseLoggingConfig = new Gcp.Vertex.Inputs.AiEndpointPredictRequestResponseLoggingConfigArgs
        {
            BigqueryDestination = new Gcp.Vertex.Inputs.AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs
            {
                OutputUri = Output.Tuple(project, bqDataset.DatasetId).Apply(values =>
                {
                    var project = values.Item1;
                    var datasetId = values.Item2;
                    return $"bq://{project.Apply(getProjectResult => getProjectResult.ProjectId)}.{datasetId}.request_response_logging";
                }),
            },
            Enabled = true,
            SamplingRate = 0.1,
        },
        TrafficSplit = JsonSerializer.Serialize(new Dictionary<string, object?>
        {
            ["12345"] = 100,
        }),
    }, 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.bigquery.Dataset;
import com.pulumi.gcp.bigquery.DatasetArgs;
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.vertex.inputs.AiEndpointPredictRequestResponseLoggingConfigArgs;
import com.pulumi.gcp.vertex.inputs.AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs;
import com.pulumi.gcp.kms.CryptoKeyIAMMember;
import com.pulumi.gcp.kms.CryptoKeyIAMMemberArgs;
import static com.pulumi.codegen.internal.Serialization.*;
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());

        var bqDataset = new Dataset("bqDataset", DatasetArgs.builder()
            .datasetId("some_dataset")
            .friendlyName("logging dataset")
            .description("This is a dataset that requests are logged to")
            .location("US")
            .deleteContentsOnDestroy(true)
            .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())
            .predictRequestResponseLoggingConfig(AiEndpointPredictRequestResponseLoggingConfigArgs.builder()
                .bigqueryDestination(AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs.builder()
                    .outputUri(bqDataset.datasetId().applyValue(datasetId -> String.format("bq://%s.%s.request_response_logging", project.applyValue(getProjectResult -> getProjectResult.projectId()),datasetId)))
                    .build())
                .enabled(true)
                .samplingRate(0.1)
                .build())
            .trafficSplit(serializeJson(
                jsonObject(
                    jsonProperty("12345", 100)
                )))
            .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
      predictRequestResponseLoggingConfig:
        bigqueryDestination:
          outputUri: bq://${project.projectId}.${bqDataset.datasetId}.request_response_logging
        enabled: true
        samplingRate: 0.1
      trafficSplit:
        fn::toJSON:
          '12345': 100
    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
  bqDataset:
    type: gcp:bigquery:Dataset
    name: bq_dataset
    properties:
      datasetId: some_dataset
      friendlyName: logging dataset
      description: This is a dataset that requests are logged to
      location: US
      deleteContentsOnDestroy: true
variables:
  project:
    fn::invoke:
      function: gcp:organizations:getProject
      arguments: {}

    Vertex Ai Endpoint Private Service Connect

    import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";

const project = gcp.organizations.getProject({});
const endpoint = new gcp.vertex.AiEndpoint("endpoint", {
    name: "endpoint-name_9394",
    displayName: "sample-endpoint",
    description: "A sample vertex endpoint",
    location: "us-central1",
    region: "us-central1",
    labels: {
        "label-one": "value-one",
    },
    privateServiceConnectConfig: {
        enablePrivateServiceConnect: true,
        projectAllowlists: [project.then(project => project.projectId)],
        enableSecurePrivateServiceConnect: false,
    },
});

    import pulumi
import pulumi_gcp as gcp

project = gcp.organizations.get_project()
endpoint = gcp.vertex.AiEndpoint("endpoint",
    name="endpoint-name_9394",
    display_name="sample-endpoint",
    description="A sample vertex endpoint",
    location="us-central1",
    region="us-central1",
    labels={
        "label-one": "value-one",
    },
    private_service_connect_config={
        "enable_private_service_connect": True,
        "project_allowlists": [project.project_id],
        "enable_secure_private_service_connect": False,
    })

    package main

import (
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/organizations"
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/vertex"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		project, err := organizations.LookupProject(ctx, &organizations.LookupProjectArgs{}, nil)
		if err != nil {
			return err
		}
		_, err = vertex.NewAiEndpoint(ctx, "endpoint", &vertex.AiEndpointArgs{
			Name:        pulumi.String("endpoint-name_9394"),
			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"),
			},
			PrivateServiceConnectConfig: &vertex.AiEndpointPrivateServiceConnectConfigArgs{
				EnablePrivateServiceConnect: pulumi.Bool(true),
				ProjectAllowlists: pulumi.StringArray{
					pulumi.String(project.ProjectId),
				},
				EnableSecurePrivateServiceConnect: pulumi.Bool(false),
			},
		})
		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 project = Gcp.Organizations.GetProject.Invoke();

    var endpoint = new Gcp.Vertex.AiEndpoint("endpoint", new()
    {
        Name = "endpoint-name_9394",
        DisplayName = "sample-endpoint",
        Description = "A sample vertex endpoint",
        Location = "us-central1",
        Region = "us-central1",
        Labels = 
        {
            { "label-one", "value-one" },
        },
        PrivateServiceConnectConfig = new Gcp.Vertex.Inputs.AiEndpointPrivateServiceConnectConfigArgs
        {
            EnablePrivateServiceConnect = true,
            ProjectAllowlists = new[]
            {
                project.Apply(getProjectResult => getProjectResult.ProjectId),
            },
            EnableSecurePrivateServiceConnect = false,
        },
    });

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
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.AiEndpointPrivateServiceConnectConfigArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        final var project = OrganizationsFunctions.getProject();

        var endpoint = new AiEndpoint("endpoint", AiEndpointArgs.builder()
            .name("endpoint-name_9394")
            .displayName("sample-endpoint")
            .description("A sample vertex endpoint")
            .location("us-central1")
            .region("us-central1")
            .labels(Map.of("label-one", "value-one"))
            .privateServiceConnectConfig(AiEndpointPrivateServiceConnectConfigArgs.builder()
                .enablePrivateServiceConnect(true)
                .projectAllowlists(project.applyValue(getProjectResult -> getProjectResult.projectId()))
                .enableSecurePrivateServiceConnect(false)
                .build())
            .build());

    }
}

    resources:
  endpoint:
    type: gcp:vertex:AiEndpoint
    properties:
      name: endpoint-name_9394
      displayName: sample-endpoint
      description: A sample vertex endpoint
      location: us-central1
      region: us-central1
      labels:
        label-one: value-one
      privateServiceConnectConfig:
        enablePrivateServiceConnect: true
        projectAllowlists:
          - ${project.projectId}
        enableSecurePrivateServiceConnect: false
variables:
  project:
    fn::invoke:
      function: gcp:organizations:getProject
      arguments: {}

    Vertex Ai Endpoint Dedicated Endpoint

    import * as pulumi from "@pulumi/pulumi";
import * as gcp from "@pulumi/gcp";

const endpoint = new gcp.vertex.AiEndpoint("endpoint", {
    name: "endpoint-name_11380",
    displayName: "sample-endpoint",
    description: "A sample vertex endpoint",
    location: "us-central1",
    region: "us-central1",
    labels: {
        "label-one": "value-one",
    },
    dedicatedEndpointEnabled: true,
});
const project = gcp.organizations.getProject({});

    import pulumi
import pulumi_gcp as gcp

endpoint = gcp.vertex.AiEndpoint("endpoint",
    name="endpoint-name_11380",
    display_name="sample-endpoint",
    description="A sample vertex endpoint",
    location="us-central1",
    region="us-central1",
    labels={
        "label-one": "value-one",
    },
    dedicated_endpoint_enabled=True)
project = gcp.organizations.get_project()

    package main

import (
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/organizations"
	"github.com/pulumi/pulumi-gcp/sdk/v8/go/gcp/vertex"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := vertex.NewAiEndpoint(ctx, "endpoint", &vertex.AiEndpointArgs{
			Name:        pulumi.String("endpoint-name_11380"),
			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"),
			},
			DedicatedEndpointEnabled: pulumi.Bool(true),
		})
		if err != nil {
			return err
		}
		_, err = organizations.LookupProject(ctx, &organizations.LookupProjectArgs{}, nil)
		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 endpoint = new Gcp.Vertex.AiEndpoint("endpoint", new()
    {
        Name = "endpoint-name_11380",
        DisplayName = "sample-endpoint",
        Description = "A sample vertex endpoint",
        Location = "us-central1",
        Region = "us-central1",
        Labels = 
        {
            { "label-one", "value-one" },
        },
        DedicatedEndpointEnabled = true,
    });

    var project = Gcp.Organizations.GetProject.Invoke();

});

    package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.gcp.vertex.AiEndpoint;
import com.pulumi.gcp.vertex.AiEndpointArgs;
import com.pulumi.gcp.organizations.OrganizationsFunctions;
import com.pulumi.gcp.organizations.inputs.GetProjectArgs;
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 endpoint = new AiEndpoint("endpoint", AiEndpointArgs.builder()
            .name("endpoint-name_11380")
            .displayName("sample-endpoint")
            .description("A sample vertex endpoint")
            .location("us-central1")
            .region("us-central1")
            .labels(Map.of("label-one", "value-one"))
            .dedicatedEndpointEnabled(true)
            .build());

        final var project = OrganizationsFunctions.getProject();

    }
}

    resources:
  endpoint:
    type: gcp:vertex:AiEndpoint
    properties:
      name: endpoint-name_11380
      displayName: sample-endpoint
      description: A sample vertex endpoint
      location: us-central1
      region: us-central1
      labels:
        label-one: value-one
      dedicatedEndpointEnabled: true
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,
               name: Optional[str] = None,
               encryption_spec: Optional[AiEndpointEncryptionSpecArgs] = None,
               labels: Optional[Mapping[str, str]] = None,
               description: Optional[str] = None,
               dedicated_endpoint_enabled: Optional[bool] = None,
               network: Optional[str] = None,
               predict_request_response_logging_config: Optional[AiEndpointPredictRequestResponseLoggingConfigArgs] = None,
               private_service_connect_config: Optional[AiEndpointPrivateServiceConnectConfigArgs] = None,
               project: Optional[str] = None,
               region: Optional[str] = None,
               traffic_split: 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",
    Name = "string",
    EncryptionSpec = new Gcp.Vertex.Inputs.AiEndpointEncryptionSpecArgs
    {
        KmsKeyName = "string",
    },
    Labels = 
    {
        { "string", "string" },
    },
    Description = "string",
    DedicatedEndpointEnabled = false,
    Network = "string",
    PredictRequestResponseLoggingConfig = new Gcp.Vertex.Inputs.AiEndpointPredictRequestResponseLoggingConfigArgs
    {
        BigqueryDestination = new Gcp.Vertex.Inputs.AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs
        {
            OutputUri = "string",
        },
        Enabled = false,
        SamplingRate = 0,
    },
    PrivateServiceConnectConfig = new Gcp.Vertex.Inputs.AiEndpointPrivateServiceConnectConfigArgs
    {
        EnablePrivateServiceConnect = false,
        EnableSecurePrivateServiceConnect = false,
        ProjectAllowlists = new[]
        {
            "string",
        },
    },
    Project = "string",
    Region = "string",
    TrafficSplit = "string",
});

    example, err := vertex.NewAiEndpoint(ctx, "aiEndpointResource", &vertex.AiEndpointArgs{
	DisplayName: pulumi.String("string"),
	Location:    pulumi.String("string"),
	Name:        pulumi.String("string"),
	EncryptionSpec: &vertex.AiEndpointEncryptionSpecArgs{
		KmsKeyName: pulumi.String("string"),
	},
	Labels: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
	Description:              pulumi.String("string"),
	DedicatedEndpointEnabled: pulumi.Bool(false),
	Network:                  pulumi.String("string"),
	PredictRequestResponseLoggingConfig: &vertex.AiEndpointPredictRequestResponseLoggingConfigArgs{
		BigqueryDestination: &vertex.AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs{
			OutputUri: pulumi.String("string"),
		},
		Enabled:      pulumi.Bool(false),
		SamplingRate: pulumi.Float64(0),
	},
	PrivateServiceConnectConfig: &vertex.AiEndpointPrivateServiceConnectConfigArgs{
		EnablePrivateServiceConnect:       pulumi.Bool(false),
		EnableSecurePrivateServiceConnect: pulumi.Bool(false),
		ProjectAllowlists: pulumi.StringArray{
			pulumi.String("string"),
		},
	},
	Project:      pulumi.String("string"),
	Region:       pulumi.String("string"),
	TrafficSplit: pulumi.String("string"),
})

    var aiEndpointResource = new AiEndpoint("aiEndpointResource", AiEndpointArgs.builder()
    .displayName("string")
    .location("string")
    .name("string")
    .encryptionSpec(AiEndpointEncryptionSpecArgs.builder()
        .kmsKeyName("string")
        .build())
    .labels(Map.of("string", "string"))
    .description("string")
    .dedicatedEndpointEnabled(false)
    .network("string")
    .predictRequestResponseLoggingConfig(AiEndpointPredictRequestResponseLoggingConfigArgs.builder()
        .bigqueryDestination(AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs.builder()
            .outputUri("string")
            .build())
        .enabled(false)
        .samplingRate(0)
        .build())
    .privateServiceConnectConfig(AiEndpointPrivateServiceConnectConfigArgs.builder()
        .enablePrivateServiceConnect(false)
        .enableSecurePrivateServiceConnect(false)
        .projectAllowlists("string")
        .build())
    .project("string")
    .region("string")
    .trafficSplit("string")
    .build());

    ai_endpoint_resource = gcp.vertex.AiEndpoint("aiEndpointResource",
    display_name="string",
    location="string",
    name="string",
    encryption_spec={
        "kms_key_name": "string",
    },
    labels={
        "string": "string",
    },
    description="string",
    dedicated_endpoint_enabled=False,
    network="string",
    predict_request_response_logging_config={
        "bigquery_destination": {
            "output_uri": "string",
        },
        "enabled": False,
        "sampling_rate": 0,
    },
    private_service_connect_config={
        "enable_private_service_connect": False,
        "enable_secure_private_service_connect": False,
        "project_allowlists": ["string"],
    },
    project="string",
    region="string",
    traffic_split="string")

    const aiEndpointResource = new gcp.vertex.AiEndpoint("aiEndpointResource", {
    displayName: "string",
    location: "string",
    name: "string",
    encryptionSpec: {
        kmsKeyName: "string",
    },
    labels: {
        string: "string",
    },
    description: "string",
    dedicatedEndpointEnabled: false,
    network: "string",
    predictRequestResponseLoggingConfig: {
        bigqueryDestination: {
            outputUri: "string",
        },
        enabled: false,
        samplingRate: 0,
    },
    privateServiceConnectConfig: {
        enablePrivateServiceConnect: false,
        enableSecurePrivateServiceConnect: false,
        projectAllowlists: ["string"],
    },
    project: "string",
    region: "string",
    trafficSplit: "string",
});

    type: gcp:vertex:AiEndpoint
properties:
    dedicatedEndpointEnabled: false
    description: string
    displayName: string
    encryptionSpec:
        kmsKeyName: string
    labels:
        string: string
    location: string
    name: string
    network: string
    predictRequestResponseLoggingConfig:
        bigqueryDestination:
            outputUri: string
        enabled: false
        samplingRate: 0
    privateServiceConnectConfig:
        enablePrivateServiceConnect: false
        enableSecurePrivateServiceConnect: false
        projectAllowlists:
            - string
    project: string
    region: string
    trafficSplit: 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

    In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

    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

    DedicatedEndpointEnabled bool
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    PredictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction. Structure is documented below.
    PrivateServiceConnectConfig AiEndpointPrivateServiceConnectConfig
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    TrafficSplit string

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    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

    DedicatedEndpointEnabled bool
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    PredictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfigArgs
    Configures the request-response logging for online prediction. Structure is documented below.
    PrivateServiceConnectConfig AiEndpointPrivateServiceConnectConfigArgs
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    TrafficSplit string

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    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

    dedicatedEndpointEnabled Boolean
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction. Structure is documented below.
    privateServiceConnectConfig AiEndpointPrivateServiceConnectConfig
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    trafficSplit String

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    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

    dedicatedEndpointEnabled boolean
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction. Structure is documented below.
    privateServiceConnectConfig AiEndpointPrivateServiceConnectConfig
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    trafficSplit string

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    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

    dedicated_endpoint_enabled bool
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predict_request_response_logging_config AiEndpointPredictRequestResponseLoggingConfigArgs
    Configures the request-response logging for online prediction. Structure is documented below.
    private_service_connect_config AiEndpointPrivateServiceConnectConfigArgs
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    traffic_split str

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    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

    dedicatedEndpointEnabled Boolean
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predictRequestResponseLoggingConfig Property Map
    Configures the request-response logging for online prediction. Structure is documented below.
    privateServiceConnectConfig Property Map
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    trafficSplit String

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    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.
    DedicatedEndpointDns string
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    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.
    DedicatedEndpointDns string
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    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.
    dedicatedEndpointDns String
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    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.
    dedicatedEndpointDns string
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    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.
    dedicated_endpoint_dns str
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    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.
    dedicatedEndpointDns String
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    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,
        dedicated_endpoint_dns: Optional[str] = None,
        dedicated_endpoint_enabled: Optional[bool] = 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,
        predict_request_response_logging_config: Optional[AiEndpointPredictRequestResponseLoggingConfigArgs] = None,
        private_service_connect_config: Optional[AiEndpointPrivateServiceConnectConfigArgs] = None,
        project: Optional[str] = None,
        pulumi_labels: Optional[Mapping[str, str]] = None,
        region: Optional[str] = None,
        traffic_split: 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)
    resources:  _:    type: gcp:vertex:AiEndpoint    get:      id: ${id}
    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.
    DedicatedEndpointDns string
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    DedicatedEndpointEnabled bool
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    PredictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction. Structure is documented below.
    PrivateServiceConnectConfig AiEndpointPrivateServiceConnectConfig
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    TrafficSplit string

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    UpdateTime string
    Output only. Timestamp when this Endpoint was last updated.
    CreateTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    DedicatedEndpointDns string
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    DedicatedEndpointEnabled bool
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    PredictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfigArgs
    Configures the request-response logging for online prediction. Structure is documented below.
    PrivateServiceConnectConfig AiEndpointPrivateServiceConnectConfigArgs
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    TrafficSplit string

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    UpdateTime string
    Output only. Timestamp when this Endpoint was last updated.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    dedicatedEndpointDns String
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    dedicatedEndpointEnabled Boolean
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction. Structure is documented below.
    privateServiceConnectConfig AiEndpointPrivateServiceConnectConfig
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    trafficSplit String

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    updateTime String
    Output only. Timestamp when this Endpoint was last updated.
    createTime string
    (Output) Output only. Timestamp when the DeployedModel was created.
    dedicatedEndpointDns string
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    dedicatedEndpointEnabled boolean
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predictRequestResponseLoggingConfig AiEndpointPredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction. Structure is documented below.
    privateServiceConnectConfig AiEndpointPrivateServiceConnectConfig
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    trafficSplit string

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    updateTime string
    Output only. Timestamp when this Endpoint was last updated.
    create_time str
    (Output) Output only. Timestamp when the DeployedModel was created.
    dedicated_endpoint_dns str
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    dedicated_endpoint_enabled bool
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predict_request_response_logging_config AiEndpointPredictRequestResponseLoggingConfigArgs
    Configures the request-response logging for online prediction. Structure is documented below.
    private_service_connect_config AiEndpointPrivateServiceConnectConfigArgs
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    traffic_split str

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    update_time str
    Output only. Timestamp when this Endpoint was last updated.
    createTime String
    (Output) Output only. Timestamp when the DeployedModel was created.
    dedicatedEndpointDns String
    Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled is true. Format: https://{endpointId}.{region}-{projectNumber}.prediction.vertexai.goog.
    dedicatedEndpointEnabled Boolean
    If true, the endpoint will be exposed through a dedicated DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS will be isolated from other users' traffic and will have better performance and reliability. Note: Once you enabled dedicated endpoint, you won't be able to send request to the shared DNS {region}-aiplatform.googleapis.com. The limitation will be removed soon.
    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. Only one of the fields, network or privateServiceConnectConfig, can be set.
    predictRequestResponseLoggingConfig Property Map
    Configures the request-response logging for online prediction. Structure is documented below.
    privateServiceConnectConfig Property Map
    Configuration for private service connect. network and privateServiceConnectConfig are mutually exclusive. Structure is documented below.
    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
    trafficSplit String

    A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's id is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment. See the deployModel example and documentation for more information.

    Note: To set the map to empty, set "{}", apply, and then remove the field from your config.

    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.

    AiEndpointPredictRequestResponseLoggingConfig, AiEndpointPredictRequestResponseLoggingConfigArgs

    BigqueryDestination AiEndpointPredictRequestResponseLoggingConfigBigqueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging_<endpoint-display-name>_<endpoint-id> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging Structure is documented below.
    Enabled bool
    If logging is enabled or not.
    SamplingRate double
    Percentage of requests to be logged, expressed as a fraction in range(0,1]
    BigqueryDestination AiEndpointPredictRequestResponseLoggingConfigBigqueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging_<endpoint-display-name>_<endpoint-id> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging Structure is documented below.
    Enabled bool
    If logging is enabled or not.
    SamplingRate float64
    Percentage of requests to be logged, expressed as a fraction in range(0,1]
    bigqueryDestination AiEndpointPredictRequestResponseLoggingConfigBigqueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging_<endpoint-display-name>_<endpoint-id> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging Structure is documented below.
    enabled Boolean
    If logging is enabled or not.
    samplingRate Double
    Percentage of requests to be logged, expressed as a fraction in range(0,1]
    bigqueryDestination AiEndpointPredictRequestResponseLoggingConfigBigqueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging_<endpoint-display-name>_<endpoint-id> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging Structure is documented below.
    enabled boolean
    If logging is enabled or not.
    samplingRate number
    Percentage of requests to be logged, expressed as a fraction in range(0,1]
    bigquery_destination AiEndpointPredictRequestResponseLoggingConfigBigqueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging_<endpoint-display-name>_<endpoint-id> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging Structure is documented below.
    enabled bool
    If logging is enabled or not.
    sampling_rate float
    Percentage of requests to be logged, expressed as a fraction in range(0,1]
    bigqueryDestination Property Map
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging_<endpoint-display-name>_<endpoint-id> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging Structure is documented below.
    enabled Boolean
    If logging is enabled or not.
    samplingRate Number
    Percentage of requests to be logged, expressed as a fraction in range(0,1]

    AiEndpointPredictRequestResponseLoggingConfigBigqueryDestination, AiEndpointPredictRequestResponseLoggingConfigBigqueryDestinationArgs

    OutputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: - BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    OutputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: - BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri String
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: - BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: - BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    output_uri str
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: - BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri String
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: - BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.

    AiEndpointPrivateServiceConnectConfig, AiEndpointPrivateServiceConnectConfigArgs

    EnablePrivateServiceConnect bool
    Required. If true, expose the IndexEndpoint via private service connect.
    EnableSecurePrivateServiceConnect bool
    If set to true, enable secure private service connect with IAM authorization. Otherwise, private service connect will be done without authorization. Note latency will be slightly increased if authorization is enabled.
    ProjectAllowlists List<string>
    A list of Projects from which the forwarding rule will target the service attachment.
    EnablePrivateServiceConnect bool
    Required. If true, expose the IndexEndpoint via private service connect.
    EnableSecurePrivateServiceConnect bool
    If set to true, enable secure private service connect with IAM authorization. Otherwise, private service connect will be done without authorization. Note latency will be slightly increased if authorization is enabled.
    ProjectAllowlists []string
    A list of Projects from which the forwarding rule will target the service attachment.
    enablePrivateServiceConnect Boolean
    Required. If true, expose the IndexEndpoint via private service connect.
    enableSecurePrivateServiceConnect Boolean
    If set to true, enable secure private service connect with IAM authorization. Otherwise, private service connect will be done without authorization. Note latency will be slightly increased if authorization is enabled.
    projectAllowlists List<String>
    A list of Projects from which the forwarding rule will target the service attachment.
    enablePrivateServiceConnect boolean
    Required. If true, expose the IndexEndpoint via private service connect.
    enableSecurePrivateServiceConnect boolean
    If set to true, enable secure private service connect with IAM authorization. Otherwise, private service connect will be done without authorization. Note latency will be slightly increased if authorization is enabled.
    projectAllowlists string[]
    A list of Projects from which the forwarding rule will target the service attachment.
    enable_private_service_connect bool
    Required. If true, expose the IndexEndpoint via private service connect.
    enable_secure_private_service_connect bool
    If set to true, enable secure private service connect with IAM authorization. Otherwise, private service connect will be done without authorization. Note latency will be slightly increased if authorization is enabled.
    project_allowlists Sequence[str]
    A list of Projects from which the forwarding rule will target the service attachment.
    enablePrivateServiceConnect Boolean
    Required. If true, expose the IndexEndpoint via private service connect.
    enableSecurePrivateServiceConnect Boolean
    If set to true, enable secure private service connect with IAM authorization. Otherwise, private service connect will be done without authorization. Note latency will be slightly increased if authorization is enabled.
    projectAllowlists List<String>
    A list of Projects from which the forwarding rule will target the service attachment.

    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 v8.22.0 published on Thursday, Mar 13, 2025 by Pulumi
    pulumi/pulumi-gcp