com.pulumi.gcp.vertex.kotlin.inputs.AiIndexEndpointDeployedIndexAutomaticResourcesArgs.kt Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of pulumi-gcp-kotlin Show documentation
Build cloud applications and infrastructure by combining the safety and reliability of infrastructure as code with the power of the Kotlin programming language.
There is a newer version: 8.13.1.0
Show newest version
@file:Suppress("NAME_SHADOWING", "DEPRECATION")

package com.pulumi.gcp.vertex.kotlin.inputs

import com.pulumi.core.Output
import com.pulumi.core.Output.of
import com.pulumi.gcp.vertex.inputs.AiIndexEndpointDeployedIndexAutomaticResourcesArgs.builder
import com.pulumi.kotlin.ConvertibleToJava
import com.pulumi.kotlin.PulumiTagMarker
import kotlin.Int
import kotlin.Suppress
import kotlin.jvm.JvmName

/**
 *
 * @property maxReplicaCount The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If maxReplicaCount is not set, the default value is minReplicaCount. The max allowed replica count is 1000.
 * 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.
 * @property minReplicaCount The minimum number of replicas this DeployedModel will be always deployed on. If minReplicaCount is not set, the default value is 2 (we don't provide SLA when minReplicaCount=1).
 * If traffic against it increases, it may dynamically be deployed onto more replicas up to [maxReplicaCount](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/AutomaticResources#FIELDS.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.
 */
public data class AiIndexEndpointDeployedIndexAutomaticResourcesArgs(
    public val maxReplicaCount: Output? = null,
    public val minReplicaCount: Output? = null,
) :
    ConvertibleToJava {
    override fun toJava(): com.pulumi.gcp.vertex.inputs.AiIndexEndpointDeployedIndexAutomaticResourcesArgs =
        com.pulumi.gcp.vertex.inputs.AiIndexEndpointDeployedIndexAutomaticResourcesArgs.builder()
            .maxReplicaCount(maxReplicaCount?.applyValue({ args0 -> args0 }))
            .minReplicaCount(minReplicaCount?.applyValue({ args0 -> args0 })).build()
}

/**
 * Builder for [AiIndexEndpointDeployedIndexAutomaticResourcesArgs].
 */
@PulumiTagMarker
public class AiIndexEndpointDeployedIndexAutomaticResourcesArgsBuilder internal constructor() {
    private var maxReplicaCount: Output? = null

    private var minReplicaCount: Output? = null

    /**
     * @param value The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If maxReplicaCount is not set, the default value is minReplicaCount. The max allowed replica count is 1000.
     * 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.
     */
    @JvmName("sssalgptnsyrrdal")
    public suspend fun maxReplicaCount(`value`: Output) {
        this.maxReplicaCount = value
    }

    /**
     * @param value The minimum number of replicas this DeployedModel will be always deployed on. If minReplicaCount is not set, the default value is 2 (we don't provide SLA when minReplicaCount=1).
     * If traffic against it increases, it may dynamically be deployed onto more replicas up to [maxReplicaCount](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/AutomaticResources#FIELDS.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.
     */
    @JvmName("nyqojkdsvclretal")
    public suspend fun minReplicaCount(`value`: Output) {
        this.minReplicaCount = value
    }

    /**
     * @param value The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If maxReplicaCount is not set, the default value is minReplicaCount. The max allowed replica count is 1000.
     * 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.
     */
    @JvmName("nafiyasyxniwhxxp")
    public suspend fun maxReplicaCount(`value`: Int?) {
        val toBeMapped = value
        val mapped = toBeMapped?.let({ args0 -> of(args0) })
        this.maxReplicaCount = mapped
    }

    /**
     * @param value The minimum number of replicas this DeployedModel will be always deployed on. If minReplicaCount is not set, the default value is 2 (we don't provide SLA when minReplicaCount=1).
     * If traffic against it increases, it may dynamically be deployed onto more replicas up to [maxReplicaCount](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/AutomaticResources#FIELDS.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.
     */
    @JvmName("yktclanyghnrajnf")
    public suspend fun minReplicaCount(`value`: Int?) {
        val toBeMapped = value
        val mapped = toBeMapped?.let({ args0 -> of(args0) })
        this.minReplicaCount = mapped
    }

    internal fun build(): AiIndexEndpointDeployedIndexAutomaticResourcesArgs =
        AiIndexEndpointDeployedIndexAutomaticResourcesArgs(
            maxReplicaCount = maxReplicaCount,
            minReplicaCount = minReplicaCount,
        )
}