import * as pulumi from "@pulumi/pulumi"; import * as outputs from "../types/output"; /** * This data source provides details about a specific Model Deployment resource in Oracle Cloud Infrastructure Datascience service. * * Retrieves the model deployment for the specified `modelDeploymentId`. * * ## Example Usage * * ```typescript * import * as pulumi from "@pulumi/pulumi"; * import * as oci from "@pulumi/oci"; * * const testModelDeployment = oci.datascience.getModelDeployment({ * modelDeploymentId: testModelDeploymentOciDatascienceModelDeployment.id, * }); * ``` * * ## SINGLE_MODEL_FLEX Returned Contract * * The following attributes are returned for `deploymentType = SINGLE_MODEL_FLEX`. * * * `modelDeploymentConfigurationDetails` * * * `deploymentType` - `SINGLE_MODEL_FLEX` * * * `modelConfigurationDetails` - The single model configuration details. * * * `modelId` - The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of a model. * * * `infrastructureConfigurationDetails` - The infrastructure configuration details for managed compute cluster type compute target. * * * `infrastructureType` - `MANAGED_COMPUTE_CLUSTER` * * * `computeTargetId` - The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of a Compute Target. * * * `modelDeploymentResourceConfiguration` - Resource configuration details for model deploy on managed compute cluster type compute target. * * * `resourceRequestConfiguration` - Resource request configuration to run workload on managed compute cluster type compute target compute target. * * * `gpus` - The total number of gpus required to be allocated to the workload. * * * `memoryInGbs` - The memory in Gbs required to be allocated to run the workload. * * * `ocpus` - The ocpus required to be allocated to run the workload. * * * `resourceLimitConfiguration` - Resource limit configuration details for workload on managed compute cluster type compute target. * * * `memoryInGbs` - Burstable limit for memory. * * * `ocpus` - Burstable limit for cpu. * * * `scalingPolicy` - The scaling policy to apply to workloads on managed compute cluster type compute target. * * * `policyType` - The type of scaling policy. Supported values are `FIXED_SIZE` and `AUTOSCALING`. * * * `instanceCount` - Returned for `policy_type=FIXED_SIZE`. The number of instances for the workload. * * * `isEnabled` - Returned for `policy_type=AUTOSCALING`. Whether the autoscaling policy is enabled. * * * `autoScalingPolicies` - Returned for `policy_type=AUTOSCALING`. The list of autoscaling policy details. * * * `autoScalingPolicyType` - The type of autoscaling policy. The supported value is `THRESHOLD`. * * * `initialInstanceCount` - For a threshold-based autoscaling policy, this value is the initial number of workload instances to launch immediately after autoscaling is enabled. * * * `maximumInstanceCount` - For a threshold-based autoscaling policy, this value is the maximum number of workload instances allowed to increase to (scale out). * * * `minimumInstanceCount` - For a threshold-based autoscaling policy, this value is the minimum number of workload instances allowed to decrease to (scale in). This should be zero for scale-to-zero. * * * `rules` - The list of autoscaling policy rules. * * * `metricExpressionRuleType` - The metric expression for creating the alarm used to trigger autoscaling actions for workload. Supported values are `TARGET_PREDEFINED_EXPRESSION` and `TARGET_CUSTOM_EXPRESSION`. * * * `metricType` - Returned for `TARGET_PREDEFINED_EXPRESSION`. Metric type. * * * `scaleConfiguration` - The scaling configuration for the target-based workload rule. * * * `targetScalingConfigurationType` - The type of target scaling configuration. Supported values are `THRESHOLD` and `QUERY`. * * * `threshold` - A metric value at which the scaling operation will be triggered. * * * `query` - Returned for `TARGET_CUSTOM_EXPRESSION`. The Monitoring Query Language (MQL) expression to evaluate for the alarm. * * * `metricNamespace` - Returned for `TARGET_CUSTOM_EXPRESSION`. Namespace to read the metrics from. * * * `scaleInPolicy` - Workload scaling policy configuration for workloads on managed compute cluster type compute target. * * * `coolDownInSeconds` - The duration of time window used to restrict flapping of instance count when the metrics used for scaling keep fluctuating. * * * `instanceCountAdjustment` - The value used for adjusting the count of instances. * * * `pendingDuration` - The period of time that the alarm condition must persist before the alarm state changes. * * * `scaleOutPolicy` - Workload scaling policy configuration for workloads on managed compute cluster type compute target. * * * `coolDownInSeconds` - The duration of time window used to restrict flapping of instance count when the metrics used for scaling keep fluctuating. * * * `instanceCountAdjustment` - The value used for adjusting the count of instances. * * * `pendingDuration` - The period of time that the alarm condition must persist before the alarm state changes. */ export declare function getModelDeployment(args: GetModelDeploymentArgs, opts?: pulumi.InvokeOptions): Promise; /** * A collection of arguments for invoking getModelDeployment. */ export interface GetModelDeploymentArgs { /** * The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of the model deployment. */ modelDeploymentId: string; } /** * A collection of values returned by getModelDeployment. */ export interface GetModelDeploymentResult { /** * The log details for each category. */ readonly categoryLogDetails: outputs.DataScience.GetModelDeploymentCategoryLogDetail[]; /** * The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of the model deployment's compartment. */ readonly compartmentId: string; /** * The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of the user who created the model deployment. */ readonly createdBy: string; /** * Defined tags for this resource. Each key is predefined and scoped to a namespace. See [Resource Tags](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/resourcetags.htm). Example: `{"Operations.CostCenter": "42"}` */ readonly definedTags: { [key: string]: string; }; /** * A short description of the model deployment. */ readonly description: string; /** * A user-friendly display name for the resource. Does not have to be unique, and can be modified. Avoid entering confidential information. Example: `My ModelDeployment` */ readonly displayName: string; /** * Free-form tags for this resource. Each tag is a simple key-value pair with no predefined name, type, or namespace. See [Resource Tags](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/resourcetags.htm). Example: `{"Department": "Finance"}` */ readonly freeformTags: { [key: string]: string; }; /** * The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of the model deployment. */ readonly id: string; /** * Details about the state of the model deployment. */ readonly lifecycleDetails: string; /** * The model deployment configuration details. */ readonly modelDeploymentConfigurationDetails: outputs.DataScience.GetModelDeploymentModelDeploymentConfigurationDetail[]; readonly modelDeploymentId: string; /** * Model deployment system data. */ readonly modelDeploymentSystemDatas: outputs.DataScience.GetModelDeploymentModelDeploymentSystemData[]; /** * The URL to interact with the model deployment. */ readonly modelDeploymentUrl: string; readonly opcParentRptUrl: string; /** * The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of the project associated with the model deployment. */ readonly projectId: string; /** * The state of the model deployment. */ readonly state: string; /** * The date and time the resource was created, in the timestamp format defined by [RFC3339](https://tools.ietf.org/html/rfc3339). Example: 2019-08-25T21:10:29.41Z */ readonly timeCreated: string; } /** * This data source provides details about a specific Model Deployment resource in Oracle Cloud Infrastructure Datascience service. * * Retrieves the model deployment for the specified `modelDeploymentId`. * * ## Example Usage * * ```typescript * import * as pulumi from "@pulumi/pulumi"; * import * as oci from "@pulumi/oci"; * * const testModelDeployment = oci.datascience.getModelDeployment({ * modelDeploymentId: testModelDeploymentOciDatascienceModelDeployment.id, * }); * ``` * * ## SINGLE_MODEL_FLEX Returned Contract * * The following attributes are returned for `deploymentType = SINGLE_MODEL_FLEX`. * * * `modelDeploymentConfigurationDetails` * * * `deploymentType` - `SINGLE_MODEL_FLEX` * * * `modelConfigurationDetails` - The single model configuration details. * * * `modelId` - The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of a model. * * * `infrastructureConfigurationDetails` - The infrastructure configuration details for managed compute cluster type compute target. * * * `infrastructureType` - `MANAGED_COMPUTE_CLUSTER` * * * `computeTargetId` - The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of a Compute Target. * * * `modelDeploymentResourceConfiguration` - Resource configuration details for model deploy on managed compute cluster type compute target. * * * `resourceRequestConfiguration` - Resource request configuration to run workload on managed compute cluster type compute target compute target. * * * `gpus` - The total number of gpus required to be allocated to the workload. * * * `memoryInGbs` - The memory in Gbs required to be allocated to run the workload. * * * `ocpus` - The ocpus required to be allocated to run the workload. * * * `resourceLimitConfiguration` - Resource limit configuration details for workload on managed compute cluster type compute target. * * * `memoryInGbs` - Burstable limit for memory. * * * `ocpus` - Burstable limit for cpu. * * * `scalingPolicy` - The scaling policy to apply to workloads on managed compute cluster type compute target. * * * `policyType` - The type of scaling policy. Supported values are `FIXED_SIZE` and `AUTOSCALING`. * * * `instanceCount` - Returned for `policy_type=FIXED_SIZE`. The number of instances for the workload. * * * `isEnabled` - Returned for `policy_type=AUTOSCALING`. Whether the autoscaling policy is enabled. * * * `autoScalingPolicies` - Returned for `policy_type=AUTOSCALING`. The list of autoscaling policy details. * * * `autoScalingPolicyType` - The type of autoscaling policy. The supported value is `THRESHOLD`. * * * `initialInstanceCount` - For a threshold-based autoscaling policy, this value is the initial number of workload instances to launch immediately after autoscaling is enabled. * * * `maximumInstanceCount` - For a threshold-based autoscaling policy, this value is the maximum number of workload instances allowed to increase to (scale out). * * * `minimumInstanceCount` - For a threshold-based autoscaling policy, this value is the minimum number of workload instances allowed to decrease to (scale in). This should be zero for scale-to-zero. * * * `rules` - The list of autoscaling policy rules. * * * `metricExpressionRuleType` - The metric expression for creating the alarm used to trigger autoscaling actions for workload. Supported values are `TARGET_PREDEFINED_EXPRESSION` and `TARGET_CUSTOM_EXPRESSION`. * * * `metricType` - Returned for `TARGET_PREDEFINED_EXPRESSION`. Metric type. * * * `scaleConfiguration` - The scaling configuration for the target-based workload rule. * * * `targetScalingConfigurationType` - The type of target scaling configuration. Supported values are `THRESHOLD` and `QUERY`. * * * `threshold` - A metric value at which the scaling operation will be triggered. * * * `query` - Returned for `TARGET_CUSTOM_EXPRESSION`. The Monitoring Query Language (MQL) expression to evaluate for the alarm. * * * `metricNamespace` - Returned for `TARGET_CUSTOM_EXPRESSION`. Namespace to read the metrics from. * * * `scaleInPolicy` - Workload scaling policy configuration for workloads on managed compute cluster type compute target. * * * `coolDownInSeconds` - The duration of time window used to restrict flapping of instance count when the metrics used for scaling keep fluctuating. * * * `instanceCountAdjustment` - The value used for adjusting the count of instances. * * * `pendingDuration` - The period of time that the alarm condition must persist before the alarm state changes. * * * `scaleOutPolicy` - Workload scaling policy configuration for workloads on managed compute cluster type compute target. * * * `coolDownInSeconds` - The duration of time window used to restrict flapping of instance count when the metrics used for scaling keep fluctuating. * * * `instanceCountAdjustment` - The value used for adjusting the count of instances. * * * `pendingDuration` - The period of time that the alarm condition must persist before the alarm state changes. */ export declare function getModelDeploymentOutput(args: GetModelDeploymentOutputArgs, opts?: pulumi.InvokeOutputOptions): pulumi.Output; /** * A collection of arguments for invoking getModelDeployment. */ export interface GetModelDeploymentOutputArgs { /** * The [OCID](https://docs.cloud.oracle.com/iaas/Content/General/Concepts/identifiers.htm) of the model deployment. */ modelDeploymentId: pulumi.Input; } //# sourceMappingURL=getModelDeployment.d.ts.map