published on Thursday, May 28, 2026 by Pulumi
published on Thursday, May 28, 2026 by Pulumi
This data source provides the list of Model Deployments in Oracle Cloud Infrastructure Datascience service.
Lists all model deployments in the specified compartment. Only one parameter other than compartmentId may also be included in a query. The query must include compartmentId. If the query does not include compartmentId, or includes compartmentId but two or more other parameters an error is returned.
Example Usage
import * as pulumi from "@pulumi/pulumi";
import * as oci from "@pulumi/oci";
const testModelDeployments = oci.datascience.getModelDeployments({
compartmentId: compartmentId,
createdBy: modelDeploymentCreatedBy,
displayName: modelDeploymentDisplayName,
id: modelDeploymentId,
projectId: testProject.id,
state: modelDeploymentState,
});
import pulumi
import pulumi_oci as oci
test_model_deployments = oci.datascience.get_model_deployments(compartment_id=compartment_id,
created_by=model_deployment_created_by,
display_name=model_deployment_display_name,
id=model_deployment_id,
project_id=test_project["id"],
state=model_deployment_state)
package main
import (
"github.com/pulumi/pulumi-oci/sdk/v4/go/oci/datascience"
"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)
func main() {
pulumi.Run(func(ctx *pulumi.Context) error {
_, err := datascience.GetModelDeployments(ctx, &datascience.GetModelDeploymentsArgs{
CompartmentId: compartmentId,
CreatedBy: pulumi.StringRef(modelDeploymentCreatedBy),
DisplayName: pulumi.StringRef(modelDeploymentDisplayName),
Id: pulumi.StringRef(modelDeploymentId),
ProjectId: pulumi.StringRef(testProject.Id),
State: pulumi.StringRef(modelDeploymentState),
}, nil)
if err != nil {
return err
}
return nil
})
}
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Oci = Pulumi.Oci;
return await Deployment.RunAsync(() =>
{
var testModelDeployments = Oci.DataScience.GetModelDeployments.Invoke(new()
{
CompartmentId = compartmentId,
CreatedBy = modelDeploymentCreatedBy,
DisplayName = modelDeploymentDisplayName,
Id = modelDeploymentId,
ProjectId = testProject.Id,
State = modelDeploymentState,
});
});
package generated_program;
import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.oci.DataScience.DataScienceFunctions;
import com.pulumi.oci.DataScience.inputs.GetModelDeploymentsArgs;
import java.util.ArrayList;
import java.util.Arrays;
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 testModelDeployments = DataScienceFunctions.getModelDeployments(GetModelDeploymentsArgs.builder()
.compartmentId(compartmentId)
.createdBy(modelDeploymentCreatedBy)
.displayName(modelDeploymentDisplayName)
.id(modelDeploymentId)
.projectId(testProject.id())
.state(modelDeploymentState)
.build());
}
}
variables:
testModelDeployments:
fn::invoke:
function: oci:DataScience:getModelDeployments
arguments:
compartmentId: ${compartmentId}
createdBy: ${modelDeploymentCreatedBy}
displayName: ${modelDeploymentDisplayName}
id: ${modelDeploymentId}
projectId: ${testProject.id}
state: ${modelDeploymentState}
pulumi {
required_providers {
oci = {
source = "pulumi/oci"
}
}
}
data "oci_datascience_getmodeldeployments" "testModelDeployments" {
compartment_id = compartmentId
created_by = modelDeploymentCreatedBy
display_name = modelDeploymentDisplayName
id = modelDeploymentId
project_id = testProject.id
state = modelDeploymentState
}
SINGLE_MODEL_FLEX Returned Contract
The following attributes are returned for deploymentType = SINGLE_MODEL_FLEX.
modelDeploymentConfigurationDetailsdeploymentType-SINGLE_MODEL_FLEXmodelConfigurationDetails- The single model configuration details.modelId- The OCID of a model.
infrastructureConfigurationDetails- The infrastructure configuration details for managed compute cluster type compute target.infrastructureType-MANAGED_COMPUTE_CLUSTERcomputeTargetId- The OCID 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 areFIXED_SIZEandAUTOSCALING.instanceCount- Returned forpolicy_type=FIXED_SIZE. The number of instances for the workload.isEnabled- Returned forpolicy_type=AUTOSCALING. Whether the autoscaling policy is enabled.autoScalingPolicies- Returned forpolicy_type=AUTOSCALING. The list of autoscaling policy details.autoScalingPolicyType- The type of autoscaling policy. The supported value isTHRESHOLD.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 areTARGET_PREDEFINED_EXPRESSIONandTARGET_CUSTOM_EXPRESSION.metricType- Returned forTARGET_PREDEFINED_EXPRESSION. Metric type.scaleConfiguration- The scaling configuration for the target-based workload rule.targetScalingConfigurationType- The type of target scaling configuration. UseTHRESHOLDforTARGET_PREDEFINED_EXPRESSIONandQUERYforTARGET_CUSTOM_EXPRESSION.threshold- A metric value at which the scaling operation will be triggered.query- Returned forTARGET_CUSTOM_EXPRESSION. The Monitoring Query Language (MQL) expression to evaluate for the alarm.metricNamespace- Returned forTARGET_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.
Using getModelDeployments
Two invocation forms are available. The direct form accepts plain arguments and either blocks until the result value is available, or returns a Promise-wrapped result. The output form accepts Input-wrapped arguments and returns an Output-wrapped result.
function getModelDeployments(args: GetModelDeploymentsArgs, opts?: InvokeOptions): Promise<GetModelDeploymentsResult>
function getModelDeploymentsOutput(args: GetModelDeploymentsOutputArgs, opts?: InvokeOptions): Output<GetModelDeploymentsResult>def get_model_deployments(compartment_id: Optional[str] = None,
created_by: Optional[str] = None,
display_name: Optional[str] = None,
filters: Optional[Sequence[GetModelDeploymentsFilter]] = None,
id: Optional[str] = None,
project_id: Optional[str] = None,
state: Optional[str] = None,
opts: Optional[InvokeOptions] = None) -> GetModelDeploymentsResult
def get_model_deployments_output(compartment_id: pulumi.Input[Optional[str]] = None,
created_by: pulumi.Input[Optional[str]] = None,
display_name: pulumi.Input[Optional[str]] = None,
filters: pulumi.Input[Optional[Sequence[pulumi.Input[GetModelDeploymentsFilterArgs]]]] = None,
id: pulumi.Input[Optional[str]] = None,
project_id: pulumi.Input[Optional[str]] = None,
state: pulumi.Input[Optional[str]] = None,
opts: Optional[InvokeOptions] = None) -> Output[GetModelDeploymentsResult]func GetModelDeployments(ctx *Context, args *GetModelDeploymentsArgs, opts ...InvokeOption) (*GetModelDeploymentsResult, error)
func GetModelDeploymentsOutput(ctx *Context, args *GetModelDeploymentsOutputArgs, opts ...InvokeOption) GetModelDeploymentsResultOutput> Note: This function is named GetModelDeployments in the Go SDK.
public static class GetModelDeployments
{
public static Task<GetModelDeploymentsResult> InvokeAsync(GetModelDeploymentsArgs args, InvokeOptions? opts = null)
public static Output<GetModelDeploymentsResult> Invoke(GetModelDeploymentsInvokeArgs args, InvokeOptions? opts = null)
}public static CompletableFuture<GetModelDeploymentsResult> getModelDeployments(GetModelDeploymentsArgs args, InvokeOptions options)
public static Output<GetModelDeploymentsResult> getModelDeployments(GetModelDeploymentsArgs args, InvokeOptions options)
fn::invoke:
function: oci:DataScience/getModelDeployments:getModelDeployments
arguments:
# arguments dictionarydata "oci_datascience_getmodeldeployments" "name" {
# arguments
}The following arguments are supported:
- Compartment
Id string - Filter results by the OCID of the compartment.
- Created
By string - Filter results by the OCID of the user who created the resource.
- Display
Name string - Filter results by its user-friendly name.
- Filters
List<Get
Model Deployments Filter> - Id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- Project
Id string - Filter results by the OCID of the project.
- State string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- Compartment
Id string - Filter results by the OCID of the compartment.
- Created
By string - Filter results by the OCID of the user who created the resource.
- Display
Name string - Filter results by its user-friendly name.
- Filters
[]Get
Model Deployments Filter - Id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- Project
Id string - Filter results by the OCID of the project.
- State string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- compartment_
id string - Filter results by the OCID of the compartment.
- created_
by string - Filter results by the OCID of the user who created the resource.
- display_
name string - Filter results by its user-friendly name.
- filters list(object)
- id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- project_
id string - Filter results by the OCID of the project.
- state string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- compartment
Id String - Filter results by the OCID of the compartment.
- created
By String - Filter results by the OCID of the user who created the resource.
- display
Name String - Filter results by its user-friendly name.
- filters
List<Get
Model Deployments Filter> - id String
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- project
Id String - Filter results by the OCID of the project.
- state String
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- compartment
Id string - Filter results by the OCID of the compartment.
- created
By string - Filter results by the OCID of the user who created the resource.
- display
Name string - Filter results by its user-friendly name.
- filters
Get
Model Deployments Filter[] - id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- project
Id string - Filter results by the OCID of the project.
- state string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- compartment_
id str - Filter results by the OCID of the compartment.
- created_
by str - Filter results by the OCID of the user who created the resource.
- display_
name str - Filter results by its user-friendly name.
- filters
Sequence[Get
Model Deployments Filter] - id str
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- project_
id str - Filter results by the OCID of the project.
- state str
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- compartment
Id String - Filter results by the OCID of the compartment.
- created
By String - Filter results by the OCID of the user who created the resource.
- display
Name String - Filter results by its user-friendly name.
- filters List<Property Map>
- id String
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- project
Id String - Filter results by the OCID of the project.
- state String
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
getModelDeployments Result
The following output properties are available:
- Compartment
Id string - The OCID of the model deployment's compartment.
- Model
Deployments List<GetModel Deployments Model Deployment> - The list of model_deployments.
- Created
By string - The OCID of the user who created the model deployment.
- Display
Name 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 - Filters
List<Get
Model Deployments Filter> - Id string
- The OCID of the model deployment.
- Project
Id string - The OCID of the project associated with the model deployment.
- State string
- The state of the model deployment.
- Compartment
Id string - The OCID of the model deployment's compartment.
- Model
Deployments []GetModel Deployments Model Deployment - The list of model_deployments.
- Created
By string - The OCID of the user who created the model deployment.
- Display
Name 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 - Filters
[]Get
Model Deployments Filter - Id string
- The OCID of the model deployment.
- Project
Id string - The OCID of the project associated with the model deployment.
- State string
- The state of the model deployment.
- compartment_
id string - The OCID of the model deployment's compartment.
- model_
deployments list(object) - The list of model_deployments.
- created_
by string - The OCID of the user who created the model deployment.
- display_
name 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 - filters list(object)
- id string
- The OCID of the model deployment.
- project_
id string - The OCID of the project associated with the model deployment.
- state string
- The state of the model deployment.
- compartment
Id String - The OCID of the model deployment's compartment.
- model
Deployments List<GetModel Deployments Model Deployment> - The list of model_deployments.
- created
By String - The OCID of the user who created the model deployment.
- display
Name 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 - filters
List<Get
Model Deployments Filter> - id String
- The OCID of the model deployment.
- project
Id String - The OCID of the project associated with the model deployment.
- state String
- The state of the model deployment.
- compartment
Id string - The OCID of the model deployment's compartment.
- model
Deployments GetModel Deployments Model Deployment[] - The list of model_deployments.
- created
By string - The OCID of the user who created the model deployment.
- display
Name 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 - filters
Get
Model Deployments Filter[] - id string
- The OCID of the model deployment.
- project
Id string - The OCID of the project associated with the model deployment.
- state string
- The state of the model deployment.
- compartment_
id str - The OCID of the model deployment's compartment.
- model_
deployments Sequence[GetModel Deployments Model Deployment] - The list of model_deployments.
- created_
by str - The OCID of the user who created the model deployment.
- display_
name str - 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 - filters
Sequence[Get
Model Deployments Filter] - id str
- The OCID of the model deployment.
- project_
id str - The OCID of the project associated with the model deployment.
- state str
- The state of the model deployment.
- compartment
Id String - The OCID of the model deployment's compartment.
- model
Deployments List<Property Map> - The list of model_deployments.
- created
By String - The OCID of the user who created the model deployment.
- display
Name 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 - filters List<Property Map>
- id String
- The OCID of the model deployment.
- project
Id String - The OCID of the project associated with the model deployment.
- state String
- The state of the model deployment.
Supporting Types
GetModelDeploymentsFilter
GetModelDeploymentsModelDeployment
- Category
Log List<GetDetails Model Deployments Model Deployment Category Log Detail> - The log details for each category.
- Compartment
Id string - Filter results by the OCID of the compartment.
- Created
By string - Filter results by the OCID of the user who created the resource.
- Dictionary<string, string>
- Defined tags for this resource. Each key is predefined and scoped to a namespace. See Resource Tags. Example:
{"Operations.CostCenter": "42"} - Description string
- A short description of the model deployment.
- Display
Name string - Filter results by its user-friendly name.
- Dictionary<string, 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. Example:
{"Department": "Finance"} - Id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- Lifecycle
Details string - Details about the state of the model deployment.
- Model
Deployment List<GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail> - The model deployment configuration details.
- Model
Deployment List<GetSystem Datas Model Deployments Model Deployment Model Deployment System Data> - Model deployment system data.
- Model
Deployment stringUrl - The URL to interact with the model deployment.
- Opc
Parent stringRpt Url - Project
Id string - Filter results by the OCID of the project.
- State string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- Time
Created string - The date and time the resource was created, in the timestamp format defined by RFC3339. Example: 2019-08-25T21:10:29.41Z
- Category
Log []GetDetails Model Deployments Model Deployment Category Log Detail - The log details for each category.
- Compartment
Id string - Filter results by the OCID of the compartment.
- Created
By string - Filter results by the OCID of the user who created the resource.
- map[string]string
- Defined tags for this resource. Each key is predefined and scoped to a namespace. See Resource Tags. Example:
{"Operations.CostCenter": "42"} - Description string
- A short description of the model deployment.
- Display
Name string - Filter results by its user-friendly name.
- map[string]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. Example:
{"Department": "Finance"} - Id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- Lifecycle
Details string - Details about the state of the model deployment.
- Model
Deployment []GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail - The model deployment configuration details.
- Model
Deployment []GetSystem Datas Model Deployments Model Deployment Model Deployment System Data - Model deployment system data.
- Model
Deployment stringUrl - The URL to interact with the model deployment.
- Opc
Parent stringRpt Url - Project
Id string - Filter results by the OCID of the project.
- State string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- Time
Created string - The date and time the resource was created, in the timestamp format defined by RFC3339. Example: 2019-08-25T21:10:29.41Z
- category_
log_ list(object)details - The log details for each category.
- compartment_
id string - Filter results by the OCID of the compartment.
- created_
by string - Filter results by the OCID of the user who created the resource.
- map(string)
- Defined tags for this resource. Each key is predefined and scoped to a namespace. See Resource Tags. Example:
{"Operations.CostCenter": "42"} - description string
- A short description of the model deployment.
- display_
name string - Filter results by its user-friendly name.
- map(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. Example:
{"Department": "Finance"} - id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- lifecycle_
details string - Details about the state of the model deployment.
- model_
deployment_ list(object)configuration_ details - The model deployment configuration details.
- model_
deployment_ list(object)system_ datas - Model deployment system data.
- model_
deployment_ stringurl - The URL to interact with the model deployment.
- opc_
parent_ stringrpt_ url - project_
id string - Filter results by the OCID of the project.
- state string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- time_
created string - The date and time the resource was created, in the timestamp format defined by RFC3339. Example: 2019-08-25T21:10:29.41Z
- category
Log List<GetDetails Model Deployments Model Deployment Category Log Detail> - The log details for each category.
- compartment
Id String - Filter results by the OCID of the compartment.
- created
By String - Filter results by the OCID of the user who created the resource.
- Map<String,String>
- Defined tags for this resource. Each key is predefined and scoped to a namespace. See Resource Tags. Example:
{"Operations.CostCenter": "42"} - description String
- A short description of the model deployment.
- display
Name String - Filter results by its user-friendly name.
- Map<String,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. Example:
{"Department": "Finance"} - id String
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- lifecycle
Details String - Details about the state of the model deployment.
- model
Deployment List<GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail> - The model deployment configuration details.
- model
Deployment List<GetSystem Datas Model Deployments Model Deployment Model Deployment System Data> - Model deployment system data.
- model
Deployment StringUrl - The URL to interact with the model deployment.
- opc
Parent StringRpt Url - project
Id String - Filter results by the OCID of the project.
- state String
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- time
Created String - The date and time the resource was created, in the timestamp format defined by RFC3339. Example: 2019-08-25T21:10:29.41Z
- category
Log GetDetails Model Deployments Model Deployment Category Log Detail[] - The log details for each category.
- compartment
Id string - Filter results by the OCID of the compartment.
- created
By string - Filter results by the OCID of the user who created the resource.
- {[key: string]: string}
- Defined tags for this resource. Each key is predefined and scoped to a namespace. See Resource Tags. Example:
{"Operations.CostCenter": "42"} - description string
- A short description of the model deployment.
- display
Name string - Filter results by its user-friendly name.
- {[key: string]: 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. Example:
{"Department": "Finance"} - id string
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- lifecycle
Details string - Details about the state of the model deployment.
- model
Deployment GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail[] - The model deployment configuration details.
- model
Deployment GetSystem Datas Model Deployments Model Deployment Model Deployment System Data[] - Model deployment system data.
- model
Deployment stringUrl - The URL to interact with the model deployment.
- opc
Parent stringRpt Url - project
Id string - Filter results by the OCID of the project.
- state string
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- time
Created string - The date and time the resource was created, in the timestamp format defined by RFC3339. Example: 2019-08-25T21:10:29.41Z
- category_
log_ Sequence[Getdetails Model Deployments Model Deployment Category Log Detail] - The log details for each category.
- compartment_
id str - Filter results by the OCID of the compartment.
- created_
by str - Filter results by the OCID of the user who created the resource.
- Mapping[str, str]
- Defined tags for this resource. Each key is predefined and scoped to a namespace. See Resource Tags. Example:
{"Operations.CostCenter": "42"} - description str
- A short description of the model deployment.
- display_
name str - Filter results by its user-friendly name.
- Mapping[str, str]
- Free-form tags for this resource. Each tag is a simple key-value pair with no predefined name, type, or namespace. See Resource Tags. Example:
{"Department": "Finance"} - id str
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- lifecycle_
details str - Details about the state of the model deployment.
- model_
deployment_ Sequence[Getconfiguration_ details Model Deployments Model Deployment Model Deployment Configuration Detail] - The model deployment configuration details.
- model_
deployment_ Sequence[Getsystem_ datas Model Deployments Model Deployment Model Deployment System Data] - Model deployment system data.
- model_
deployment_ strurl - The URL to interact with the model deployment.
- opc_
parent_ strrpt_ url - project_
id str - Filter results by the OCID of the project.
- state str
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- time_
created str - The date and time the resource was created, in the timestamp format defined by RFC3339. Example: 2019-08-25T21:10:29.41Z
- category
Log List<Property Map>Details - The log details for each category.
- compartment
Id String - Filter results by the OCID of the compartment.
- created
By String - Filter results by the OCID of the user who created the resource.
- Map<String>
- Defined tags for this resource. Each key is predefined and scoped to a namespace. See Resource Tags. Example:
{"Operations.CostCenter": "42"} - description String
- A short description of the model deployment.
- display
Name String - Filter results by its user-friendly name.
- Map<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. Example:
{"Department": "Finance"} - id String
- Filter results by OCID. Must be an OCID of the correct type for the resource type.
- lifecycle
Details String - Details about the state of the model deployment.
- model
Deployment List<Property Map>Configuration Details - The model deployment configuration details.
- model
Deployment List<Property Map>System Datas - Model deployment system data.
- model
Deployment StringUrl - The URL to interact with the model deployment.
- opc
Parent StringRpt Url - project
Id String - Filter results by the OCID of the project.
- state String
- Filter results by the specified lifecycle state. Must be a valid state for the resource type.
- time
Created String - The date and time the resource was created, in the timestamp format defined by RFC3339. Example: 2019-08-25T21:10:29.41Z
GetModelDeploymentsModelDeploymentCategoryLogDetail
- Accesses
[]Get
Model Deployments Model Deployment Category Log Detail Access - The log details.
- Predicts
[]Get
Model Deployments Model Deployment Category Log Detail Predict - The log details.
- accesses list(object)
- The log details.
- predicts list(object)
- The log details.
- accesses
Get
Model Deployments Model Deployment Category Log Detail Access[] - The log details.
- predicts
Get
Model Deployments Model Deployment Category Log Detail Predict[] - The log details.
- accesses List<Property Map>
- The log details.
- predicts List<Property Map>
- The log details.
GetModelDeploymentsModelDeploymentCategoryLogDetailAccess
- Log
Group stringId - The OCID of a log group to work with.
- Log
Id string - The OCID of a log to work with.
- Log
Group stringId - The OCID of a log group to work with.
- Log
Id string - The OCID of a log to work with.
- log_
group_ stringid - The OCID of a log group to work with.
- log_
id string - The OCID of a log to work with.
- log
Group StringId - The OCID of a log group to work with.
- log
Id String - The OCID of a log to work with.
- log
Group stringId - The OCID of a log group to work with.
- log
Id string - The OCID of a log to work with.
- log_
group_ strid - The OCID of a log group to work with.
- log_
id str - The OCID of a log to work with.
- log
Group StringId - The OCID of a log group to work with.
- log
Id String - The OCID of a log to work with.
GetModelDeploymentsModelDeploymentCategoryLogDetailPredict
- Log
Group stringId - The OCID of a log group to work with.
- Log
Id string - The OCID of a log to work with.
- Log
Group stringId - The OCID of a log group to work with.
- Log
Id string - The OCID of a log to work with.
- log_
group_ stringid - The OCID of a log group to work with.
- log_
id string - The OCID of a log to work with.
- log
Group StringId - The OCID of a log group to work with.
- log
Id String - The OCID of a log to work with.
- log
Group stringId - The OCID of a log group to work with.
- log
Id string - The OCID of a log to work with.
- log_
group_ strid - The OCID of a log group to work with.
- log_
id str - The OCID of a log to work with.
- log
Group StringId - The OCID of a log group to work with.
- log
Id String - The OCID of a log to work with.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetail
- Deployment
Type string - The type of the model deployment.
- Environment
Configuration List<GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail> - The configuration to carry the environment details thats used in Model Deployment creation
- Infrastructure
Configuration List<GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail> - The infrastructure configuration details.
- Model
Configuration List<GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail> - The model configuration details.
- Model
Group List<GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Group Configuration Detail> - The model group configuration details.
- Deployment
Type string - The type of the model deployment.
- Environment
Configuration []GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail - The configuration to carry the environment details thats used in Model Deployment creation
- Infrastructure
Configuration []GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail - The infrastructure configuration details.
- Model
Configuration []GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail - The model configuration details.
- Model
Group []GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Group Configuration Detail - The model group configuration details.
- deployment_
type string - The type of the model deployment.
- environment_
configuration_ list(object)details - The configuration to carry the environment details thats used in Model Deployment creation
- infrastructure_
configuration_ list(object)details - The infrastructure configuration details.
- model_
configuration_ list(object)details - The model configuration details.
- model_
group_ list(object)configuration_ details - The model group configuration details.
- deployment
Type String - The type of the model deployment.
- environment
Configuration List<GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail> - The configuration to carry the environment details thats used in Model Deployment creation
- infrastructure
Configuration List<GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail> - The infrastructure configuration details.
- model
Configuration List<GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail> - The model configuration details.
- model
Group List<GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Group Configuration Detail> - The model group configuration details.
- deployment
Type string - The type of the model deployment.
- environment
Configuration GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail[] - The configuration to carry the environment details thats used in Model Deployment creation
- infrastructure
Configuration GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail[] - The infrastructure configuration details.
- model
Configuration GetDetails Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail[] - The model configuration details.
- model
Group GetConfiguration Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Group Configuration Detail[] - The model group configuration details.
- deployment_
type str - The type of the model deployment.
- environment_
configuration_ Sequence[Getdetails Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail] - The configuration to carry the environment details thats used in Model Deployment creation
- infrastructure_
configuration_ Sequence[Getdetails Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail] - The infrastructure configuration details.
- model_
configuration_ Sequence[Getdetails Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail] - The model configuration details.
- model_
group_ Sequence[Getconfiguration_ details Model Deployments Model Deployment Model Deployment Configuration Detail Model Group Configuration Detail] - The model group configuration details.
- deployment
Type String - The type of the model deployment.
- environment
Configuration List<Property Map>Details - The configuration to carry the environment details thats used in Model Deployment creation
- infrastructure
Configuration List<Property Map>Details - The infrastructure configuration details.
- model
Configuration List<Property Map>Details - The model configuration details.
- model
Group List<Property Map>Configuration Details - The model group configuration details.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailEnvironmentConfigurationDetail
- Cmds List<string>
- The container image run CMD as a list of strings. Use
CMDas arguments to theENTRYPOINTor the only command to run in the absence of anENTRYPOINT. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. - Custom
Http List<GetEndpoints Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail Custom Http Endpoint> - List of custom inference HTTP endpoints configured on the model deployment instance for inferencing.
- Default
Environment Dictionary<string, string>Variables - Service injected Environment variables set for the web server container and can not be set or modified by user.
- Entrypoints List<string>
- The container image run ENTRYPOINT as a list of strings. Accept the
CMDas extra arguments. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. More information on howCMDandENTRYPOINTinteract are here. - Environment
Configuration stringType - The environment configuration type
- Environment
Variables Dictionary<string, string> - Environment variables to set for the web server container. The size of envVars must be less than 2048 bytes. Key should be under 32 characters. Key should contain only letters, digits and underscore (_) Key should start with a letter. Key should have at least 2 characters. Key should not end with underscore eg.
TEST_Key if added cannot be empty. Value can be empty. No specific size limits on individual Values. But overall environment variables is limited to 2048 bytes. Key can't be reserved Model Deployment environment variables. - Health
Check intPort - The port on which the container HEALTHCHECK would listen. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447. - Image string
- The full path to the Oracle Container Repository (OCIR) registry, image, and tag in a canonical format. The container image is optional while using service managed open source foundation model. Acceptable format:
<region>.ocir.io/<registry>/<image>:<tag><region>.ocir.io/<registry>/<image>:<tag>@digest - Image
Digest string - The digest of the container image. For example,
sha256:881303a6b2738834d795a32b4a98eb0e5e3d1cad590a712d1e04f9b2fa90a030 - Image
Signature stringId - OCID of the container image signature
- Predict
Api stringSpecification - The chosen specification from predefined set of endpoints a user can access. For example, if the value is 'openai', the user can access OpenAI-compliant endpoints like /v1/completions, /v1/chat/completions, /v1/models, etc., for inference.
- Server
Port int - The port on which the web server serving the inference is running. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447.
- Cmds []string
- The container image run CMD as a list of strings. Use
CMDas arguments to theENTRYPOINTor the only command to run in the absence of anENTRYPOINT. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. - Custom
Http []GetEndpoints Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail Custom Http Endpoint - List of custom inference HTTP endpoints configured on the model deployment instance for inferencing.
- Default
Environment map[string]stringVariables - Service injected Environment variables set for the web server container and can not be set or modified by user.
- Entrypoints []string
- The container image run ENTRYPOINT as a list of strings. Accept the
CMDas extra arguments. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. More information on howCMDandENTRYPOINTinteract are here. - Environment
Configuration stringType - The environment configuration type
- Environment
Variables map[string]string - Environment variables to set for the web server container. The size of envVars must be less than 2048 bytes. Key should be under 32 characters. Key should contain only letters, digits and underscore (_) Key should start with a letter. Key should have at least 2 characters. Key should not end with underscore eg.
TEST_Key if added cannot be empty. Value can be empty. No specific size limits on individual Values. But overall environment variables is limited to 2048 bytes. Key can't be reserved Model Deployment environment variables. - Health
Check intPort - The port on which the container HEALTHCHECK would listen. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447. - Image string
- The full path to the Oracle Container Repository (OCIR) registry, image, and tag in a canonical format. The container image is optional while using service managed open source foundation model. Acceptable format:
<region>.ocir.io/<registry>/<image>:<tag><region>.ocir.io/<registry>/<image>:<tag>@digest - Image
Digest string - The digest of the container image. For example,
sha256:881303a6b2738834d795a32b4a98eb0e5e3d1cad590a712d1e04f9b2fa90a030 - Image
Signature stringId - OCID of the container image signature
- Predict
Api stringSpecification - The chosen specification from predefined set of endpoints a user can access. For example, if the value is 'openai', the user can access OpenAI-compliant endpoints like /v1/completions, /v1/chat/completions, /v1/models, etc., for inference.
- Server
Port int - The port on which the web server serving the inference is running. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447.
- cmds list(string)
- The container image run CMD as a list of strings. Use
CMDas arguments to theENTRYPOINTor the only command to run in the absence of anENTRYPOINT. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. - custom_
http_ list(object)endpoints - List of custom inference HTTP endpoints configured on the model deployment instance for inferencing.
- default_
environment_ map(string)variables - Service injected Environment variables set for the web server container and can not be set or modified by user.
- entrypoints list(string)
- The container image run ENTRYPOINT as a list of strings. Accept the
CMDas extra arguments. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. More information on howCMDandENTRYPOINTinteract are here. - environment_
configuration_ stringtype - The environment configuration type
- environment_
variables map(string) - Environment variables to set for the web server container. The size of envVars must be less than 2048 bytes. Key should be under 32 characters. Key should contain only letters, digits and underscore (_) Key should start with a letter. Key should have at least 2 characters. Key should not end with underscore eg.
TEST_Key if added cannot be empty. Value can be empty. No specific size limits on individual Values. But overall environment variables is limited to 2048 bytes. Key can't be reserved Model Deployment environment variables. - health_
check_ numberport - The port on which the container HEALTHCHECK would listen. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447. - image string
- The full path to the Oracle Container Repository (OCIR) registry, image, and tag in a canonical format. The container image is optional while using service managed open source foundation model. Acceptable format:
<region>.ocir.io/<registry>/<image>:<tag><region>.ocir.io/<registry>/<image>:<tag>@digest - image_
digest string - The digest of the container image. For example,
sha256:881303a6b2738834d795a32b4a98eb0e5e3d1cad590a712d1e04f9b2fa90a030 - image_
signature_ stringid - OCID of the container image signature
- predict_
api_ stringspecification - The chosen specification from predefined set of endpoints a user can access. For example, if the value is 'openai', the user can access OpenAI-compliant endpoints like /v1/completions, /v1/chat/completions, /v1/models, etc., for inference.
- server_
port number - The port on which the web server serving the inference is running. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447.
- cmds List<String>
- The container image run CMD as a list of strings. Use
CMDas arguments to theENTRYPOINTor the only command to run in the absence of anENTRYPOINT. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. - custom
Http List<GetEndpoints Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail Custom Http Endpoint> - List of custom inference HTTP endpoints configured on the model deployment instance for inferencing.
- default
Environment Map<String,String>Variables - Service injected Environment variables set for the web server container and can not be set or modified by user.
- entrypoints List<String>
- The container image run ENTRYPOINT as a list of strings. Accept the
CMDas extra arguments. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. More information on howCMDandENTRYPOINTinteract are here. - environment
Configuration StringType - The environment configuration type
- environment
Variables Map<String,String> - Environment variables to set for the web server container. The size of envVars must be less than 2048 bytes. Key should be under 32 characters. Key should contain only letters, digits and underscore (_) Key should start with a letter. Key should have at least 2 characters. Key should not end with underscore eg.
TEST_Key if added cannot be empty. Value can be empty. No specific size limits on individual Values. But overall environment variables is limited to 2048 bytes. Key can't be reserved Model Deployment environment variables. - health
Check IntegerPort - The port on which the container HEALTHCHECK would listen. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447. - image String
- The full path to the Oracle Container Repository (OCIR) registry, image, and tag in a canonical format. The container image is optional while using service managed open source foundation model. Acceptable format:
<region>.ocir.io/<registry>/<image>:<tag><region>.ocir.io/<registry>/<image>:<tag>@digest - image
Digest String - The digest of the container image. For example,
sha256:881303a6b2738834d795a32b4a98eb0e5e3d1cad590a712d1e04f9b2fa90a030 - image
Signature StringId - OCID of the container image signature
- predict
Api StringSpecification - The chosen specification from predefined set of endpoints a user can access. For example, if the value is 'openai', the user can access OpenAI-compliant endpoints like /v1/completions, /v1/chat/completions, /v1/models, etc., for inference.
- server
Port Integer - The port on which the web server serving the inference is running. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447.
- cmds string[]
- The container image run CMD as a list of strings. Use
CMDas arguments to theENTRYPOINTor the only command to run in the absence of anENTRYPOINT. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. - custom
Http GetEndpoints Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail Custom Http Endpoint[] - List of custom inference HTTP endpoints configured on the model deployment instance for inferencing.
- default
Environment {[key: string]: string}Variables - Service injected Environment variables set for the web server container and can not be set or modified by user.
- entrypoints string[]
- The container image run ENTRYPOINT as a list of strings. Accept the
CMDas extra arguments. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. More information on howCMDandENTRYPOINTinteract are here. - environment
Configuration stringType - The environment configuration type
- environment
Variables {[key: string]: string} - Environment variables to set for the web server container. The size of envVars must be less than 2048 bytes. Key should be under 32 characters. Key should contain only letters, digits and underscore (_) Key should start with a letter. Key should have at least 2 characters. Key should not end with underscore eg.
TEST_Key if added cannot be empty. Value can be empty. No specific size limits on individual Values. But overall environment variables is limited to 2048 bytes. Key can't be reserved Model Deployment environment variables. - health
Check numberPort - The port on which the container HEALTHCHECK would listen. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447. - image string
- The full path to the Oracle Container Repository (OCIR) registry, image, and tag in a canonical format. The container image is optional while using service managed open source foundation model. Acceptable format:
<region>.ocir.io/<registry>/<image>:<tag><region>.ocir.io/<registry>/<image>:<tag>@digest - image
Digest string - The digest of the container image. For example,
sha256:881303a6b2738834d795a32b4a98eb0e5e3d1cad590a712d1e04f9b2fa90a030 - image
Signature stringId - OCID of the container image signature
- predict
Api stringSpecification - The chosen specification from predefined set of endpoints a user can access. For example, if the value is 'openai', the user can access OpenAI-compliant endpoints like /v1/completions, /v1/chat/completions, /v1/models, etc., for inference.
- server
Port number - The port on which the web server serving the inference is running. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447.
- cmds Sequence[str]
- The container image run CMD as a list of strings. Use
CMDas arguments to theENTRYPOINTor the only command to run in the absence of anENTRYPOINT. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. - custom_
http_ Sequence[Getendpoints Model Deployments Model Deployment Model Deployment Configuration Detail Environment Configuration Detail Custom Http Endpoint] - List of custom inference HTTP endpoints configured on the model deployment instance for inferencing.
- default_
environment_ Mapping[str, str]variables - Service injected Environment variables set for the web server container and can not be set or modified by user.
- entrypoints Sequence[str]
- The container image run ENTRYPOINT as a list of strings. Accept the
CMDas extra arguments. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. More information on howCMDandENTRYPOINTinteract are here. - environment_
configuration_ strtype - The environment configuration type
- environment_
variables Mapping[str, str] - Environment variables to set for the web server container. The size of envVars must be less than 2048 bytes. Key should be under 32 characters. Key should contain only letters, digits and underscore (_) Key should start with a letter. Key should have at least 2 characters. Key should not end with underscore eg.
TEST_Key if added cannot be empty. Value can be empty. No specific size limits on individual Values. But overall environment variables is limited to 2048 bytes. Key can't be reserved Model Deployment environment variables. - health_
check_ intport - The port on which the container HEALTHCHECK would listen. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447. - image str
- The full path to the Oracle Container Repository (OCIR) registry, image, and tag in a canonical format. The container image is optional while using service managed open source foundation model. Acceptable format:
<region>.ocir.io/<registry>/<image>:<tag><region>.ocir.io/<registry>/<image>:<tag>@digest - image_
digest str - The digest of the container image. For example,
sha256:881303a6b2738834d795a32b4a98eb0e5e3d1cad590a712d1e04f9b2fa90a030 - image_
signature_ strid - OCID of the container image signature
- predict_
api_ strspecification - The chosen specification from predefined set of endpoints a user can access. For example, if the value is 'openai', the user can access OpenAI-compliant endpoints like /v1/completions, /v1/chat/completions, /v1/models, etc., for inference.
- server_
port int - The port on which the web server serving the inference is running. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447.
- cmds List<String>
- The container image run CMD as a list of strings. Use
CMDas arguments to theENTRYPOINTor the only command to run in the absence of anENTRYPOINT. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. - custom
Http List<Property Map>Endpoints - List of custom inference HTTP endpoints configured on the model deployment instance for inferencing.
- default
Environment Map<String>Variables - Service injected Environment variables set for the web server container and can not be set or modified by user.
- entrypoints List<String>
- The container image run ENTRYPOINT as a list of strings. Accept the
CMDas extra arguments. The combined size ofCMDandENTRYPOINTmust be less than 2048 bytes. More information on howCMDandENTRYPOINTinteract are here. - environment
Configuration StringType - The environment configuration type
- environment
Variables Map<String> - Environment variables to set for the web server container. The size of envVars must be less than 2048 bytes. Key should be under 32 characters. Key should contain only letters, digits and underscore (_) Key should start with a letter. Key should have at least 2 characters. Key should not end with underscore eg.
TEST_Key if added cannot be empty. Value can be empty. No specific size limits on individual Values. But overall environment variables is limited to 2048 bytes. Key can't be reserved Model Deployment environment variables. - health
Check NumberPort - The port on which the container HEALTHCHECK would listen. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447. - image String
- The full path to the Oracle Container Repository (OCIR) registry, image, and tag in a canonical format. The container image is optional while using service managed open source foundation model. Acceptable format:
<region>.ocir.io/<registry>/<image>:<tag><region>.ocir.io/<registry>/<image>:<tag>@digest - image
Digest String - The digest of the container image. For example,
sha256:881303a6b2738834d795a32b4a98eb0e5e3d1cad590a712d1e04f9b2fa90a030 - image
Signature StringId - OCID of the container image signature
- predict
Api StringSpecification - The chosen specification from predefined set of endpoints a user can access. For example, if the value is 'openai', the user can access OpenAI-compliant endpoints like /v1/completions, /v1/chat/completions, /v1/models, etc., for inference.
- server
Port Number - The port on which the web server serving the inference is running. The port can be anything between
1024and65535. The following ports cannot be used24224,8446,8447.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailEnvironmentConfigurationDetailCustomHttpEndpoint
- Endpoint
Uri stringSuffix - The suffix part of the endpoint that will be allowed for invocation.
- Http
Methods List<string> - List of HTTP methods acceptable by the URI.
- Endpoint
Uri stringSuffix - The suffix part of the endpoint that will be allowed for invocation.
- Http
Methods []string - List of HTTP methods acceptable by the URI.
- endpoint_
uri_ stringsuffix - The suffix part of the endpoint that will be allowed for invocation.
- http_
methods list(string) - List of HTTP methods acceptable by the URI.
- endpoint
Uri StringSuffix - The suffix part of the endpoint that will be allowed for invocation.
- http
Methods List<String> - List of HTTP methods acceptable by the URI.
- endpoint
Uri stringSuffix - The suffix part of the endpoint that will be allowed for invocation.
- http
Methods string[] - List of HTTP methods acceptable by the URI.
- endpoint_
uri_ strsuffix - The suffix part of the endpoint that will be allowed for invocation.
- http_
methods Sequence[str] - List of HTTP methods acceptable by the URI.
- endpoint
Uri StringSuffix - The suffix part of the endpoint that will be allowed for invocation.
- http
Methods List<String> - List of HTTP methods acceptable by the URI.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetail
- Bandwidth
Mbps int - The minimum network bandwidth for the model deployment.
- Compute
Target stringId - Infrastructure
Type string - The type of the model deployment infrastructure.
- Instance
Configurations List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration> - The model deployment instance configuration.
- Maximum
Bandwidth intMbps - The maximum network bandwidth for the model deployment.
- Model
Deployment List<GetResource Configurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration> - Scaling
Policies List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy> - The scaling policy to apply to each model of the deployment.
- Bandwidth
Mbps int - The minimum network bandwidth for the model deployment.
- Compute
Target stringId - Infrastructure
Type string - The type of the model deployment infrastructure.
- Instance
Configurations []GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration - The model deployment instance configuration.
- Maximum
Bandwidth intMbps - The maximum network bandwidth for the model deployment.
- Model
Deployment []GetResource Configurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration - Scaling
Policies []GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy - The scaling policy to apply to each model of the deployment.
- bandwidth_
mbps number - The minimum network bandwidth for the model deployment.
- compute_
target_ stringid - infrastructure_
type string - The type of the model deployment infrastructure.
- instance_
configurations list(object) - The model deployment instance configuration.
- maximum_
bandwidth_ numbermbps - The maximum network bandwidth for the model deployment.
- model_
deployment_ list(object)resource_ configurations - scaling_
policies list(object) - The scaling policy to apply to each model of the deployment.
- bandwidth
Mbps Integer - The minimum network bandwidth for the model deployment.
- compute
Target StringId - infrastructure
Type String - The type of the model deployment infrastructure.
- instance
Configurations List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration> - The model deployment instance configuration.
- maximum
Bandwidth IntegerMbps - The maximum network bandwidth for the model deployment.
- model
Deployment List<GetResource Configurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration> - scaling
Policies List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy> - The scaling policy to apply to each model of the deployment.
- bandwidth
Mbps number - The minimum network bandwidth for the model deployment.
- compute
Target stringId - infrastructure
Type string - The type of the model deployment infrastructure.
- instance
Configurations GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration[] - The model deployment instance configuration.
- maximum
Bandwidth numberMbps - The maximum network bandwidth for the model deployment.
- model
Deployment GetResource Configurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration[] - scaling
Policies GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy[] - The scaling policy to apply to each model of the deployment.
- bandwidth_
mbps int - The minimum network bandwidth for the model deployment.
- compute_
target_ strid - infrastructure_
type str - The type of the model deployment infrastructure.
- instance_
configurations Sequence[GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration] - The model deployment instance configuration.
- maximum_
bandwidth_ intmbps - The maximum network bandwidth for the model deployment.
- model_
deployment_ Sequence[Getresource_ configurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration] - scaling_
policies Sequence[GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy] - The scaling policy to apply to each model of the deployment.
- bandwidth
Mbps Number - The minimum network bandwidth for the model deployment.
- compute
Target StringId - infrastructure
Type String - The type of the model deployment infrastructure.
- instance
Configurations List<Property Map> - The model deployment instance configuration.
- maximum
Bandwidth NumberMbps - The maximum network bandwidth for the model deployment.
- model
Deployment List<Property Map>Resource Configurations - scaling
Policies List<Property Map> - The scaling policy to apply to each model of the deployment.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailInstanceConfiguration
- Instance
Shape stringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- Model
Deployment List<GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail> - Details for the model-deployment instance shape configuration.
- Network
Access stringType - Network Access type of model deployment.
- Private
Endpoint stringId - The OCID of a Data Science private endpoint.
- Subnet
Id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- Instance
Shape stringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- Model
Deployment []GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail - Details for the model-deployment instance shape configuration.
- Network
Access stringType - Network Access type of model deployment.
- Private
Endpoint stringId - The OCID of a Data Science private endpoint.
- Subnet
Id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance_
shape_ stringname - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model_
deployment_ list(object)instance_ shape_ config_ details - Details for the model-deployment instance shape configuration.
- network_
access_ stringtype - Network Access type of model deployment.
- private_
endpoint_ stringid - The OCID of a Data Science private endpoint.
- subnet_
id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance
Shape StringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model
Deployment List<GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail> - Details for the model-deployment instance shape configuration.
- network
Access StringType - Network Access type of model deployment.
- private
Endpoint StringId - The OCID of a Data Science private endpoint.
- subnet
Id String - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance
Shape stringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model
Deployment GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail[] - Details for the model-deployment instance shape configuration.
- network
Access stringType - Network Access type of model deployment.
- private
Endpoint stringId - The OCID of a Data Science private endpoint.
- subnet
Id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance_
shape_ strname - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model_
deployment_ Sequence[Getinstance_ shape_ config_ details Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail] - Details for the model-deployment instance shape configuration.
- network_
access_ strtype - Network Access type of model deployment.
- private_
endpoint_ strid - The OCID of a Data Science private endpoint.
- subnet_
id str - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance
Shape StringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model
Deployment List<Property Map>Instance Shape Config Details - Details for the model-deployment instance shape configuration.
- network
Access StringType - Network Access type of model deployment.
- private
Endpoint StringId - The OCID of a Data Science private endpoint.
- subnet
Id String - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailInstanceConfigurationModelDeploymentInstanceShapeConfigDetail
- Cpu
Baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - Memory
In doubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- Cpu
Baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - Memory
In float64Gbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus float64
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu_
baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory_
in_ numbergbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu
Baseline String - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory
In DoubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu
Baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory
In numberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu_
baseline str - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory_
in_ floatgbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus float
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu
Baseline String - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory
In NumberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailModelDeploymentResourceConfiguration
- Resource
Limit List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Limit Configuration> - Resource
Request List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Request Configuration>
- Resource
Limit []GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Limit Configuration - Resource
Request []GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Request Configuration
- resource
Limit List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Limit Configuration> - resource
Request List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Request Configuration>
- resource
Limit GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Limit Configuration[] - resource
Request GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Request Configuration[]
- resource_
limit_ Sequence[Getconfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Limit Configuration] - resource_
request_ Sequence[Getconfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Model Deployment Resource Configuration Resource Request Configuration]
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailModelDeploymentResourceConfigurationResourceLimitConfiguration
- Memory
In doubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- Memory
In float64Gbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus float64
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- memory_
in_ numbergbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- memory
In DoubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- memory
In numberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- memory_
in_ floatgbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus float
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- memory
In NumberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailModelDeploymentResourceConfigurationResourceRequestConfiguration
- Gpus int
- Memory
In doubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- Gpus int
- Memory
In float64Gbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus float64
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- gpus number
- memory_
in_ numbergbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- gpus Integer
- memory
In DoubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- gpus number
- memory
In numberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- gpus int
- memory_
in_ floatgbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus float
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- gpus Number
- memory
In NumberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicy
- Auto
Scaling List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy> - The list of autoscaling policy details.
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count int - The number of instances for the model deployment.
- Is
Enabled bool - Whether the autoscaling policy is enabled.
- Policy
Type string - The type of scaling policy.
- Auto
Scaling []GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy - The list of autoscaling policy details.
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count int - The number of instances for the model deployment.
- Is
Enabled bool - Whether the autoscaling policy is enabled.
- Policy
Type string - The type of scaling policy.
- auto_
scaling_ list(object)policies - The list of autoscaling policy details.
- cool_
down_ numberin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count number - The number of instances for the model deployment.
- is_
enabled bool - Whether the autoscaling policy is enabled.
- policy_
type string - The type of scaling policy.
- auto
Scaling List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy> - The list of autoscaling policy details.
- cool
Down IntegerIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count Integer - The number of instances for the model deployment.
- is
Enabled Boolean - Whether the autoscaling policy is enabled.
- policy
Type String - The type of scaling policy.
- auto
Scaling GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy[] - The list of autoscaling policy details.
- cool
Down numberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count number - The number of instances for the model deployment.
- is
Enabled boolean - Whether the autoscaling policy is enabled.
- policy
Type string - The type of scaling policy.
- auto_
scaling_ Sequence[Getpolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy] - The list of autoscaling policy details.
- cool_
down_ intin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count int - The number of instances for the model deployment.
- is_
enabled bool - Whether the autoscaling policy is enabled.
- policy_
type str - The type of scaling policy.
- auto
Scaling List<Property Map>Policies - The list of autoscaling policy details.
- cool
Down NumberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count Number - The number of instances for the model deployment.
- is
Enabled Boolean - Whether the autoscaling policy is enabled.
- policy
Type String - The type of scaling policy.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicyAutoScalingPolicy
- Auto
Scaling stringPolicy Type - The type of autoscaling policy.
- Initial
Instance intCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- Maximum
Instance intCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- Minimum
Instance intCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- Rules
List<Get
Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule> - The list of autoscaling policy rules.
- Scale
In List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale In Policy> - Scale
Out List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale Out Policy>
- Auto
Scaling stringPolicy Type - The type of autoscaling policy.
- Initial
Instance intCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- Maximum
Instance intCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- Minimum
Instance intCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- Rules
[]Get
Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule - The list of autoscaling policy rules.
- Scale
In []GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale In Policy - Scale
Out []GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale Out Policy
- auto_
scaling_ stringpolicy_ type - The type of autoscaling policy.
- initial_
instance_ numbercount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum_
instance_ numbercount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum_
instance_ numbercount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules list(object)
- The list of autoscaling policy rules.
- scale_
in_ list(object)policies - scale_
out_ list(object)policies
- auto
Scaling StringPolicy Type - The type of autoscaling policy.
- initial
Instance IntegerCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum
Instance IntegerCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum
Instance IntegerCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules
List<Get
Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule> - The list of autoscaling policy rules.
- scale
In List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale In Policy> - scale
Out List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale Out Policy>
- auto
Scaling stringPolicy Type - The type of autoscaling policy.
- initial
Instance numberCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum
Instance numberCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum
Instance numberCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules
Get
Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule[] - The list of autoscaling policy rules.
- scale
In GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale In Policy[] - scale
Out GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale Out Policy[]
- auto_
scaling_ strpolicy_ type - The type of autoscaling policy.
- initial_
instance_ intcount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum_
instance_ intcount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum_
instance_ intcount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules
Sequence[Get
Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule] - The list of autoscaling policy rules.
- scale_
in_ Sequence[Getpolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale In Policy] - scale_
out_ Sequence[Getpolicies Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Scale Out Policy]
- auto
Scaling StringPolicy Type - The type of autoscaling policy.
- initial
Instance NumberCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum
Instance NumberCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum
Instance NumberCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules List<Property Map>
- The list of autoscaling policy rules.
- scale
In List<Property Map>Policies - scale
Out List<Property Map>Policies
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicyAutoScalingPolicyRule
- Metric
Expression stringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- Metric
Type string - Metric type
- Scale
Configurations List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Configuration> - Scale
In List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration> - The scaling configuration for the predefined metric expression rule.
- Scale
Out List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration> - The scaling configuration for the predefined metric expression rule.
- Metric
Expression stringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- Metric
Type string - Metric type
- Scale
Configurations []GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Configuration - Scale
In []GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration - The scaling configuration for the predefined metric expression rule.
- Scale
Out []GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration - The scaling configuration for the predefined metric expression rule.
- metric_
expression_ stringrule_ type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric_
type string - Metric type
- scale_
configurations list(object) - scale_
in_ list(object)configurations - The scaling configuration for the predefined metric expression rule.
- scale_
out_ list(object)configurations - The scaling configuration for the predefined metric expression rule.
- metric
Expression StringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric
Type String - Metric type
- scale
Configurations List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Configuration> - scale
In List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration> - The scaling configuration for the predefined metric expression rule.
- scale
Out List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration> - The scaling configuration for the predefined metric expression rule.
- metric
Expression stringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric
Type string - Metric type
- scale
Configurations GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Configuration[] - scale
In GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration[] - The scaling configuration for the predefined metric expression rule.
- scale
Out GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration[] - The scaling configuration for the predefined metric expression rule.
- metric_
expression_ strrule_ type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric_
type str - Metric type
- scale_
configurations Sequence[GetModel Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Configuration] - scale_
in_ Sequence[Getconfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration] - The scaling configuration for the predefined metric expression rule.
- scale_
out_ Sequence[Getconfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Infrastructure Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration] - The scaling configuration for the predefined metric expression rule.
- metric
Expression StringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric
Type String - Metric type
- scale
Configurations List<Property Map> - scale
In List<Property Map>Configurations - The scaling configuration for the predefined metric expression rule.
- scale
Out List<Property Map>Configurations - The scaling configuration for the predefined metric expression rule.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicyAutoScalingPolicyRuleScaleConfiguration
- Metric
Namespace string - Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Target
Scaling stringConfiguration Type - Threshold double
- A metric value at which the scaling operation will be triggered.
- Metric
Namespace string - Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Target
Scaling stringConfiguration Type - Threshold float64
- A metric value at which the scaling operation will be triggered.
- metric_
namespace string - query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - target_
scaling_ stringconfiguration_ type - threshold number
- A metric value at which the scaling operation will be triggered.
- metric
Namespace String - query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - target
Scaling StringConfiguration Type - threshold Double
- A metric value at which the scaling operation will be triggered.
- metric
Namespace string - query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - target
Scaling stringConfiguration Type - threshold number
- A metric value at which the scaling operation will be triggered.
- metric_
namespace str - query str
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - target_
scaling_ strconfiguration_ type - threshold float
- A metric value at which the scaling operation will be triggered.
- metric
Namespace String - query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - target
Scaling StringConfiguration Type - threshold Number
- A metric value at which the scaling operation will be triggered.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicyAutoScalingPolicyRuleScaleInConfiguration
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- instance_
count_ numberadjustment - The value is used for adjusting the count of instances by.
- pending_
duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ stringtype - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance
Count IntegerAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Integer
- A metric value at which the scaling operation will be triggered.
- instance
Count numberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration stringType - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance_
count_ intadjustment - The value is used for adjusting the count of instances by.
- pending_
duration str - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query str
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ strtype - The type of scaling configuration.
- threshold int
- A metric value at which the scaling operation will be triggered.
- instance
Count NumberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Number
- A metric value at which the scaling operation will be triggered.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicyAutoScalingPolicyRuleScaleOutConfiguration
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- instance_
count_ numberadjustment - The value is used for adjusting the count of instances by.
- pending_
duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ stringtype - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance
Count IntegerAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Integer
- A metric value at which the scaling operation will be triggered.
- instance
Count numberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration stringType - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance_
count_ intadjustment - The value is used for adjusting the count of instances by.
- pending_
duration str - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query str
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ strtype - The type of scaling configuration.
- threshold int
- A metric value at which the scaling operation will be triggered.
- instance
Count NumberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Number
- A metric value at which the scaling operation will be triggered.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicyAutoScalingPolicyScaleInPolicy
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool_
down_ numberin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count_ numberadjustment - The value is used for adjusting the count of instances by.
- pending_
duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool
Down IntegerIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count IntegerAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool
Down numberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count numberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool_
down_ intin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count_ intadjustment - The value is used for adjusting the count of instances by.
- pending_
duration str - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool
Down NumberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count NumberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailInfrastructureConfigurationDetailScalingPolicyAutoScalingPolicyScaleOutPolicy
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool_
down_ numberin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count_ numberadjustment - The value is used for adjusting the count of instances by.
- pending_
duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool
Down IntegerIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count IntegerAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool
Down numberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count numberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool_
down_ intin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count_ intadjustment - The value is used for adjusting the count of instances by.
- pending_
duration str - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- cool
Down NumberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count NumberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetail
- Bandwidth
Mbps int - The minimum network bandwidth for the model deployment.
- Instance
Configurations List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration> - The model deployment instance configuration.
- Maximum
Bandwidth intMbps - The maximum network bandwidth for the model deployment.
- Model
Id string - The OCID of the model you want to deploy.
- Scaling
Policies List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy> - The scaling policy to apply to each model of the deployment.
- Bandwidth
Mbps int - The minimum network bandwidth for the model deployment.
- Instance
Configurations []GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration - The model deployment instance configuration.
- Maximum
Bandwidth intMbps - The maximum network bandwidth for the model deployment.
- Model
Id string - The OCID of the model you want to deploy.
- Scaling
Policies []GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy - The scaling policy to apply to each model of the deployment.
- bandwidth_
mbps number - The minimum network bandwidth for the model deployment.
- instance_
configurations list(object) - The model deployment instance configuration.
- maximum_
bandwidth_ numbermbps - The maximum network bandwidth for the model deployment.
- model_
id string - The OCID of the model you want to deploy.
- scaling_
policies list(object) - The scaling policy to apply to each model of the deployment.
- bandwidth
Mbps Integer - The minimum network bandwidth for the model deployment.
- instance
Configurations List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration> - The model deployment instance configuration.
- maximum
Bandwidth IntegerMbps - The maximum network bandwidth for the model deployment.
- model
Id String - The OCID of the model you want to deploy.
- scaling
Policies List<GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy> - The scaling policy to apply to each model of the deployment.
- bandwidth
Mbps number - The minimum network bandwidth for the model deployment.
- instance
Configurations GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration[] - The model deployment instance configuration.
- maximum
Bandwidth numberMbps - The maximum network bandwidth for the model deployment.
- model
Id string - The OCID of the model you want to deploy.
- scaling
Policies GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy[] - The scaling policy to apply to each model of the deployment.
- bandwidth_
mbps int - The minimum network bandwidth for the model deployment.
- instance_
configurations Sequence[GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration] - The model deployment instance configuration.
- maximum_
bandwidth_ intmbps - The maximum network bandwidth for the model deployment.
- model_
id str - The OCID of the model you want to deploy.
- scaling_
policies Sequence[GetModel Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy] - The scaling policy to apply to each model of the deployment.
- bandwidth
Mbps Number - The minimum network bandwidth for the model deployment.
- instance
Configurations List<Property Map> - The model deployment instance configuration.
- maximum
Bandwidth NumberMbps - The maximum network bandwidth for the model deployment.
- model
Id String - The OCID of the model you want to deploy.
- scaling
Policies List<Property Map> - The scaling policy to apply to each model of the deployment.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetailInstanceConfiguration
- Instance
Shape stringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- Model
Deployment List<GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail> - Details for the model-deployment instance shape configuration.
- Network
Access stringType - Network Access type of model deployment.
- Private
Endpoint stringId - The OCID of a Data Science private endpoint.
- Subnet
Id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- Instance
Shape stringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- Model
Deployment []GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail - Details for the model-deployment instance shape configuration.
- Network
Access stringType - Network Access type of model deployment.
- Private
Endpoint stringId - The OCID of a Data Science private endpoint.
- Subnet
Id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance_
shape_ stringname - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model_
deployment_ list(object)instance_ shape_ config_ details - Details for the model-deployment instance shape configuration.
- network_
access_ stringtype - Network Access type of model deployment.
- private_
endpoint_ stringid - The OCID of a Data Science private endpoint.
- subnet_
id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance
Shape StringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model
Deployment List<GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail> - Details for the model-deployment instance shape configuration.
- network
Access StringType - Network Access type of model deployment.
- private
Endpoint StringId - The OCID of a Data Science private endpoint.
- subnet
Id String - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance
Shape stringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model
Deployment GetInstance Shape Config Details Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail[] - Details for the model-deployment instance shape configuration.
- network
Access stringType - Network Access type of model deployment.
- private
Endpoint stringId - The OCID of a Data Science private endpoint.
- subnet
Id string - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance_
shape_ strname - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model_
deployment_ Sequence[Getinstance_ shape_ config_ details Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Instance Configuration Model Deployment Instance Shape Config Detail] - Details for the model-deployment instance shape configuration.
- network_
access_ strtype - Network Access type of model deployment.
- private_
endpoint_ strid - The OCID of a Data Science private endpoint.
- subnet_
id str - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
- instance
Shape StringName - The shape used to launch the model deployment instances. When using service managed open source foundation model, the supported shapes can be retrieved using get model api /models/{modelId}/definedMetadata/deploymentConfiguration/artifact/content.
- model
Deployment List<Property Map>Instance Shape Config Details - Details for the model-deployment instance shape configuration.
- network
Access StringType - Network Access type of model deployment.
- private
Endpoint StringId - The OCID of a Data Science private endpoint.
- subnet
Id String - A model deployment instance is provided with a VNIC for network access. This specifies the OCID of the subnet to create a VNIC in. The subnet should be in a VCN with a NAT/SGW gateway for egress.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetailInstanceConfigurationModelDeploymentInstanceShapeConfigDetail
- Cpu
Baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - Memory
In doubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- Cpu
Baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - Memory
In float64Gbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- Ocpus float64
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu_
baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory_
in_ numbergbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu
Baseline String - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory
In DoubleGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Double
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu
Baseline string - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory
In numberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu_
baseline str - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory_
in_ floatgbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus float
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
- cpu
Baseline String - The baseline OCPU utilization for a subcore burstable VM instance. If this attribute is left blank, it will default to
BASELINE_1_1. The following values are supported: BASELINE_1_8 - baseline usage is 1/8 of an OCPU. BASELINE_1_2 - baseline usage is 1/2 of an OCPU. BASELINE_1_1 - baseline usage is an entire OCPU. This represents a non-burstable instance. - memory
In NumberGbs - A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the memory to be specified with in the range of 6 to 1024 GB. VM.Standard3.Flex memory range is between 6 to 512 GB and VM.Optimized3.Flex memory range is between 6 to 256 GB.
- ocpus Number
- A model-deployment instance of type VM.Standard.E3.Flex or VM.Standard.E4.Flex allows the ocpu count to be specified with in the range of 1 to 64 ocpu. VM.Standard3.Flex OCPU range is between 1 to 32 ocpu and for VM.Optimized3.Flex OCPU range is 1 to 18 ocpu.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetailScalingPolicy
- Auto
Scaling List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy> - The list of autoscaling policy details.
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count int - The number of instances for the model deployment.
- Is
Enabled bool - Whether the autoscaling policy is enabled.
- Policy
Type string - The type of scaling policy.
- Auto
Scaling []GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy - The list of autoscaling policy details.
- Cool
Down intIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- Instance
Count int - The number of instances for the model deployment.
- Is
Enabled bool - Whether the autoscaling policy is enabled.
- Policy
Type string - The type of scaling policy.
- auto_
scaling_ list(object)policies - The list of autoscaling policy details.
- cool_
down_ numberin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count number - The number of instances for the model deployment.
- is_
enabled bool - Whether the autoscaling policy is enabled.
- policy_
type string - The type of scaling policy.
- auto
Scaling List<GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy> - The list of autoscaling policy details.
- cool
Down IntegerIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count Integer - The number of instances for the model deployment.
- is
Enabled Boolean - Whether the autoscaling policy is enabled.
- policy
Type String - The type of scaling policy.
- auto
Scaling GetPolicies Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy[] - The list of autoscaling policy details.
- cool
Down numberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count number - The number of instances for the model deployment.
- is
Enabled boolean - Whether the autoscaling policy is enabled.
- policy
Type string - The type of scaling policy.
- auto_
scaling_ Sequence[Getpolicies Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy] - The list of autoscaling policy details.
- cool_
down_ intin_ seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance_
count int - The number of instances for the model deployment.
- is_
enabled bool - Whether the autoscaling policy is enabled.
- policy_
type str - The type of scaling policy.
- auto
Scaling List<Property Map>Policies - The list of autoscaling policy details.
- cool
Down NumberIn Seconds - For threshold-based autoscaling policies, this value is the minimum period of time to wait between scaling actions. The cooldown period gives the system time to stabilize before rescaling. The minimum value is 300 seconds, which is also the default. The cooldown period starts when the model deployment becomes ACTIVE after the scaling operation.
- instance
Count Number - The number of instances for the model deployment.
- is
Enabled Boolean - Whether the autoscaling policy is enabled.
- policy
Type String - The type of scaling policy.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetailScalingPolicyAutoScalingPolicy
- Auto
Scaling stringPolicy Type - The type of autoscaling policy.
- Initial
Instance intCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- Maximum
Instance intCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- Minimum
Instance intCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- Rules
List<Get
Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule> - The list of autoscaling policy rules.
- Auto
Scaling stringPolicy Type - The type of autoscaling policy.
- Initial
Instance intCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- Maximum
Instance intCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- Minimum
Instance intCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- Rules
[]Get
Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule - The list of autoscaling policy rules.
- auto_
scaling_ stringpolicy_ type - The type of autoscaling policy.
- initial_
instance_ numbercount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum_
instance_ numbercount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum_
instance_ numbercount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules list(object)
- The list of autoscaling policy rules.
- auto
Scaling StringPolicy Type - The type of autoscaling policy.
- initial
Instance IntegerCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum
Instance IntegerCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum
Instance IntegerCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules
List<Get
Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule> - The list of autoscaling policy rules.
- auto
Scaling stringPolicy Type - The type of autoscaling policy.
- initial
Instance numberCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum
Instance numberCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum
Instance numberCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules
Get
Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule[] - The list of autoscaling policy rules.
- auto_
scaling_ strpolicy_ type - The type of autoscaling policy.
- initial_
instance_ intcount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum_
instance_ intcount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum_
instance_ intcount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules
Sequence[Get
Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule] - The list of autoscaling policy rules.
- auto
Scaling StringPolicy Type - The type of autoscaling policy.
- initial
Instance NumberCount - For a threshold-based autoscaling policy, this value is the initial number of instances to launch in the model deployment immediately after autoscaling is enabled. Note that anytime this value is updated, the number of instances will be reset to this value. After autoscaling retrieves performance metrics, the number of instances is automatically adjusted from this initial number to a number that is based on the limits that you set.
- maximum
Instance NumberCount - For a threshold-based autoscaling policy, this value is the maximum number of instances the model deployment is allowed to increase to (scale out).
- minimum
Instance NumberCount - For a threshold-based autoscaling policy, this value is the minimum number of instances the model deployment is allowed to decrease to (scale in).
- rules List<Property Map>
- The list of autoscaling policy rules.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetailScalingPolicyAutoScalingPolicyRule
- Metric
Expression stringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- Metric
Type string - Metric type
- Scale
In List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration> - The scaling configuration for the predefined metric expression rule.
- Scale
Out List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration> - The scaling configuration for the predefined metric expression rule.
- Metric
Expression stringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- Metric
Type string - Metric type
- Scale
In []GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration - The scaling configuration for the predefined metric expression rule.
- Scale
Out []GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration - The scaling configuration for the predefined metric expression rule.
- metric_
expression_ stringrule_ type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric_
type string - Metric type
- scale_
in_ list(object)configurations - The scaling configuration for the predefined metric expression rule.
- scale_
out_ list(object)configurations - The scaling configuration for the predefined metric expression rule.
- metric
Expression StringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric
Type String - Metric type
- scale
In List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration> - The scaling configuration for the predefined metric expression rule.
- scale
Out List<GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration> - The scaling configuration for the predefined metric expression rule.
- metric
Expression stringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric
Type string - Metric type
- scale
In GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration[] - The scaling configuration for the predefined metric expression rule.
- scale
Out GetConfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration[] - The scaling configuration for the predefined metric expression rule.
- metric_
expression_ strrule_ type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric_
type str - Metric type
- scale_
in_ Sequence[Getconfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale In Configuration] - The scaling configuration for the predefined metric expression rule.
- scale_
out_ Sequence[Getconfigurations Model Deployments Model Deployment Model Deployment Configuration Detail Model Configuration Detail Scaling Policy Auto Scaling Policy Rule Scale Out Configuration] - The scaling configuration for the predefined metric expression rule.
- metric
Expression StringRule Type - The metric expression for creating the alarm used to trigger autoscaling actions on the model deployment.
- metric
Type String - Metric type
- scale
In List<Property Map>Configurations - The scaling configuration for the predefined metric expression rule.
- scale
Out List<Property Map>Configurations - The scaling configuration for the predefined metric expression rule.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetailScalingPolicyAutoScalingPolicyRuleScaleInConfiguration
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- instance_
count_ numberadjustment - The value is used for adjusting the count of instances by.
- pending_
duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ stringtype - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance
Count IntegerAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Integer
- A metric value at which the scaling operation will be triggered.
- instance
Count numberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration stringType - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance_
count_ intadjustment - The value is used for adjusting the count of instances by.
- pending_
duration str - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query str
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ strtype - The type of scaling configuration.
- threshold int
- A metric value at which the scaling operation will be triggered.
- instance
Count NumberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Number
- A metric value at which the scaling operation will be triggered.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelConfigurationDetailScalingPolicyAutoScalingPolicyRuleScaleOutConfiguration
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- Instance
Count intAdjustment - The value is used for adjusting the count of instances by.
- Pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- Query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - Scaling
Configuration stringType - The type of scaling configuration.
- Threshold int
- A metric value at which the scaling operation will be triggered.
- instance_
count_ numberadjustment - The value is used for adjusting the count of instances by.
- pending_
duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ stringtype - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance
Count IntegerAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Integer
- A metric value at which the scaling operation will be triggered.
- instance
Count numberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration string - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query string
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration stringType - The type of scaling configuration.
- threshold number
- A metric value at which the scaling operation will be triggered.
- instance_
count_ intadjustment - The value is used for adjusting the count of instances by.
- pending_
duration str - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query str
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling_
configuration_ strtype - The type of scaling configuration.
- threshold int
- A metric value at which the scaling operation will be triggered.
- instance
Count NumberAdjustment - The value is used for adjusting the count of instances by.
- pending
Duration String - The period of time that the condition defined in the alarm must persist before the alarm state changes from "OK" to "FIRING" or vice versa. For example, a value of 5 minutes means that the alarm must persist in breaching the condition for five minutes before the alarm updates its state to "FIRING"; likewise, the alarm must persist in not breaching the condition for five minutes before the alarm updates its state to "OK."
- query String
- The Monitoring Query Language (MQL) expression to evaluate for the alarm. The Alarms feature of the Monitoring service interprets results for each returned time series as Boolean values, where zero represents false and a non-zero value represents true. A true value means that the trigger rule condition has been met. The query must specify a metric, statistic, interval, and trigger rule (threshold or absence). Supported values for interval:
1m-60m(also1h). You can optionally specify dimensions and grouping functions. Supported grouping functions:grouping(),groupBy(). - scaling
Configuration StringType - The type of scaling configuration.
- threshold Number
- A metric value at which the scaling operation will be triggered.
GetModelDeploymentsModelDeploymentModelDeploymentConfigurationDetailModelGroupConfigurationDetail
- Model
Group stringId - The OCID of the model group you want to deploy.
- Model
Group stringId - The OCID of the model group you want to deploy.
- model_
group_ stringid - The OCID of the model group you want to deploy.
- model
Group StringId - The OCID of the model group you want to deploy.
- model
Group stringId - The OCID of the model group you want to deploy.
- model_
group_ strid - The OCID of the model group you want to deploy.
- model
Group StringId - The OCID of the model group you want to deploy.
GetModelDeploymentsModelDeploymentModelDeploymentSystemData
- Current
Instance intCount - This value is the current count of the model deployment instances.
- Model
Type string - The type of the deployed model.
- System
Infra stringType - The infrastructure type of the model deployment.
- Current
Instance intCount - This value is the current count of the model deployment instances.
- Model
Type string - The type of the deployed model.
- System
Infra stringType - The infrastructure type of the model deployment.
- current_
instance_ numbercount - This value is the current count of the model deployment instances.
- model_
type string - The type of the deployed model.
- system_
infra_ stringtype - The infrastructure type of the model deployment.
- current
Instance IntegerCount - This value is the current count of the model deployment instances.
- model
Type String - The type of the deployed model.
- system
Infra StringType - The infrastructure type of the model deployment.
- current
Instance numberCount - This value is the current count of the model deployment instances.
- model
Type string - The type of the deployed model.
- system
Infra stringType - The infrastructure type of the model deployment.
- current_
instance_ intcount - This value is the current count of the model deployment instances.
- model_
type str - The type of the deployed model.
- system_
infra_ strtype - The infrastructure type of the model deployment.
- current
Instance NumberCount - This value is the current count of the model deployment instances.
- model
Type String - The type of the deployed model.
- system
Infra StringType - The infrastructure type of the model deployment.
Package Details
- Repository
- oci pulumi/pulumi-oci
- License
- Apache-2.0
- Notes
- This Pulumi package is based on the
ociTerraform Provider.
published on Thursday, May 28, 2026 by Pulumi