@aws-sdk/client-bedrock 3.943.0 → 3.944.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +8 -0
- package/dist-cjs/index.js +90 -3
- package/dist-es/Bedrock.js +2 -0
- package/dist-es/commands/UpdateCustomModelDeploymentCommand.js +16 -0
- package/dist-es/commands/index.js +1 -0
- package/dist-es/models/enums.js +11 -0
- package/dist-es/schemas/schemas_0.js +63 -3
- package/dist-types/Bedrock.d.ts +7 -0
- package/dist-types/BedrockClient.d.ts +3 -2
- package/dist-types/commands/CreateModelCustomizationJobCommand.d.ts +18 -1
- package/dist-types/commands/DeleteInferenceProfileCommand.d.ts +2 -1
- package/dist-types/commands/GetCustomModelCommand.d.ts +18 -1
- package/dist-types/commands/GetCustomModelDeploymentCommand.d.ts +4 -0
- package/dist-types/commands/GetInferenceProfileCommand.d.ts +1 -1
- package/dist-types/commands/GetModelCustomizationJobCommand.d.ts +18 -1
- package/dist-types/commands/ListCustomModelsCommand.d.ts +1 -1
- package/dist-types/commands/ListInferenceProfilesCommand.d.ts +1 -1
- package/dist-types/commands/ListModelCustomizationJobsCommand.d.ts +1 -1
- package/dist-types/commands/UpdateCustomModelDeploymentCommand.d.ts +90 -0
- package/dist-types/commands/index.d.ts +1 -0
- package/dist-types/models/enums.d.ts +27 -0
- package/dist-types/models/models_0.d.ts +166 -164
- package/dist-types/models/models_1.d.ts +163 -1
- package/dist-types/schemas/schemas_0.d.ts +8 -0
- package/dist-types/ts3.4/Bedrock.d.ts +17 -0
- package/dist-types/ts3.4/BedrockClient.d.ts +6 -0
- package/dist-types/ts3.4/commands/DeleteInferenceProfileCommand.d.ts +2 -4
- package/dist-types/ts3.4/commands/GetInferenceProfileCommand.d.ts +1 -1
- package/dist-types/ts3.4/commands/ListInferenceProfilesCommand.d.ts +1 -1
- package/dist-types/ts3.4/commands/UpdateCustomModelDeploymentCommand.d.ts +51 -0
- package/dist-types/ts3.4/commands/index.d.ts +1 -0
- package/dist-types/ts3.4/models/enums.d.ts +15 -0
- package/dist-types/ts3.4/models/models_0.d.ts +57 -39
- package/dist-types/ts3.4/models/models_1.d.ts +40 -0
- package/dist-types/ts3.4/schemas/schemas_0.d.ts +8 -0
- package/package.json +1 -1
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { DocumentType as __DocumentType } from "@smithy/types";
|
|
2
|
-
import { AgreementStatus, ApplicationType, AttributeType, AutomatedReasoningCheckLogicWarningType, AutomatedReasoningCheckResult, AutomatedReasoningPolicyAnnotationStatus, AutomatedReasoningPolicyBuildDocumentContentType, AutomatedReasoningPolicyBuildMessageType, AutomatedReasoningPolicyBuildResultAssetType, AutomatedReasoningPolicyBuildWorkflowStatus, AutomatedReasoningPolicyBuildWorkflowType, AutomatedReasoningPolicyTestRunResult, AutomatedReasoningPolicyTestRunStatus, ConfigurationOwner, CustomizationType, CustomModelDeploymentStatus, EvaluationJobStatus, EvaluationJobType, EvaluationTaskType, ExternalSourceType, GuardrailContentFilterAction, GuardrailContentFiltersTierName, GuardrailContentFilterType, GuardrailContextualGroundingAction, GuardrailContextualGroundingFilterType, GuardrailFilterStrength, GuardrailManagedWordsType, GuardrailModality, GuardrailPiiEntityType, GuardrailSensitiveInformationAction, GuardrailStatus, GuardrailTopicAction, GuardrailTopicsTierName, GuardrailTopicType, GuardrailWordAction, InferenceProfileStatus,
|
|
2
|
+
import { AgreementStatus, ApplicationType, AttributeType, AutomatedReasoningCheckLogicWarningType, AutomatedReasoningCheckResult, AutomatedReasoningPolicyAnnotationStatus, AutomatedReasoningPolicyBuildDocumentContentType, AutomatedReasoningPolicyBuildMessageType, AutomatedReasoningPolicyBuildResultAssetType, AutomatedReasoningPolicyBuildWorkflowStatus, AutomatedReasoningPolicyBuildWorkflowType, AutomatedReasoningPolicyTestRunResult, AutomatedReasoningPolicyTestRunStatus, ConfigurationOwner, CustomizationType, CustomModelDeploymentStatus, CustomModelDeploymentUpdateStatus, EvaluationJobStatus, EvaluationJobType, EvaluationTaskType, ExternalSourceType, GuardrailContentFilterAction, GuardrailContentFiltersTierName, GuardrailContentFilterType, GuardrailContextualGroundingAction, GuardrailContextualGroundingFilterType, GuardrailFilterStrength, GuardrailManagedWordsType, GuardrailModality, GuardrailPiiEntityType, GuardrailSensitiveInformationAction, GuardrailStatus, GuardrailTopicAction, GuardrailTopicsTierName, GuardrailTopicType, GuardrailWordAction, InferenceProfileStatus, InputTags, ModelStatus, PerformanceConfigLatency, QueryTransformationType, ReasoningEffort, RerankingMetadataSelectionMode, SortJobsBy, SortModelsBy, SortOrder, Status, VectorSearchRerankingConfigurationType } from "./enums";
|
|
3
3
|
/**
|
|
4
4
|
* <p>Account-level enforced guardrail input configuration.</p>
|
|
5
5
|
* @public
|
|
@@ -3570,6 +3570,22 @@ export interface GetCustomModelDeploymentRequest {
|
|
|
3570
3570
|
*/
|
|
3571
3571
|
customModelDeploymentIdentifier: string | undefined;
|
|
3572
3572
|
}
|
|
3573
|
+
/**
|
|
3574
|
+
* <p> Details about an update to a custom model deployment, including the new custom model resource ARN and current update status. </p>
|
|
3575
|
+
* @public
|
|
3576
|
+
*/
|
|
3577
|
+
export interface CustomModelDeploymentUpdateDetails {
|
|
3578
|
+
/**
|
|
3579
|
+
* <p> ARN of the new custom model being deployed as part of the update. </p>
|
|
3580
|
+
* @public
|
|
3581
|
+
*/
|
|
3582
|
+
modelArn: string | undefined;
|
|
3583
|
+
/**
|
|
3584
|
+
* <p> Current status of the deployment update. </p>
|
|
3585
|
+
* @public
|
|
3586
|
+
*/
|
|
3587
|
+
updateStatus: CustomModelDeploymentUpdateStatus | undefined;
|
|
3588
|
+
}
|
|
3573
3589
|
/**
|
|
3574
3590
|
* @public
|
|
3575
3591
|
*/
|
|
@@ -3604,6 +3620,11 @@ export interface GetCustomModelDeploymentResponse {
|
|
|
3604
3620
|
* @public
|
|
3605
3621
|
*/
|
|
3606
3622
|
description?: string | undefined;
|
|
3623
|
+
/**
|
|
3624
|
+
* <p> Details about any pending or completed updates to the custom model deployment, including the new model ARN and update status. </p>
|
|
3625
|
+
* @public
|
|
3626
|
+
*/
|
|
3627
|
+
updateDetails?: CustomModelDeploymentUpdateDetails | undefined;
|
|
3607
3628
|
/**
|
|
3608
3629
|
* <p>If the deployment status is <code>FAILED</code>, this field contains a message describing the failure reason.</p>
|
|
3609
3630
|
* @public
|
|
@@ -3721,6 +3742,31 @@ export interface ListCustomModelDeploymentsResponse {
|
|
|
3721
3742
|
*/
|
|
3722
3743
|
modelDeploymentSummaries?: CustomModelDeploymentSummary[] | undefined;
|
|
3723
3744
|
}
|
|
3745
|
+
/**
|
|
3746
|
+
* @public
|
|
3747
|
+
*/
|
|
3748
|
+
export interface UpdateCustomModelDeploymentRequest {
|
|
3749
|
+
/**
|
|
3750
|
+
* <p> ARN of the new custom model to deploy. This replaces the currently deployed model. </p>
|
|
3751
|
+
* @public
|
|
3752
|
+
*/
|
|
3753
|
+
modelArn: string | undefined;
|
|
3754
|
+
/**
|
|
3755
|
+
* <p> Identifier of the custom model deployment to update with the new custom model. </p>
|
|
3756
|
+
* @public
|
|
3757
|
+
*/
|
|
3758
|
+
customModelDeploymentIdentifier: string | undefined;
|
|
3759
|
+
}
|
|
3760
|
+
/**
|
|
3761
|
+
* @public
|
|
3762
|
+
*/
|
|
3763
|
+
export interface UpdateCustomModelDeploymentResponse {
|
|
3764
|
+
/**
|
|
3765
|
+
* <p> ARN of the custom model deployment being updated. </p>
|
|
3766
|
+
* @public
|
|
3767
|
+
*/
|
|
3768
|
+
customModelDeploymentArn: string | undefined;
|
|
3769
|
+
}
|
|
3724
3770
|
/**
|
|
3725
3771
|
* <p>The Amazon S3 data source of the model to import. </p>
|
|
3726
3772
|
* @public
|
|
@@ -3862,11 +3908,117 @@ export interface DistillationConfig {
|
|
|
3862
3908
|
*/
|
|
3863
3909
|
teacherModelConfig: TeacherModelConfig | undefined;
|
|
3864
3910
|
}
|
|
3911
|
+
/**
|
|
3912
|
+
* <p> Configuration for using an AWS Lambda function to grade model responses during reinforcement fine-tuning training. </p>
|
|
3913
|
+
* @public
|
|
3914
|
+
*/
|
|
3915
|
+
export interface LambdaGraderConfig {
|
|
3916
|
+
/**
|
|
3917
|
+
* <p> ARN of the AWS Lambda function that will evaluate model responses and return reward scores for RFT training. </p>
|
|
3918
|
+
* @public
|
|
3919
|
+
*/
|
|
3920
|
+
lambdaArn: string | undefined;
|
|
3921
|
+
}
|
|
3922
|
+
/**
|
|
3923
|
+
* <p> Configuration for the grader used in reinforcement fine-tuning to evaluate model responses and provide reward signals. </p>
|
|
3924
|
+
* @public
|
|
3925
|
+
*/
|
|
3926
|
+
export type GraderConfig = GraderConfig.LambdaGraderMember | GraderConfig.$UnknownMember;
|
|
3927
|
+
/**
|
|
3928
|
+
* @public
|
|
3929
|
+
*/
|
|
3930
|
+
export declare namespace GraderConfig {
|
|
3931
|
+
/**
|
|
3932
|
+
* <p> Configuration for using an AWS Lambda function as the grader for evaluating model responses and provide reward signals in reinforcement fine-tuning. </p>
|
|
3933
|
+
* @public
|
|
3934
|
+
*/
|
|
3935
|
+
interface LambdaGraderMember {
|
|
3936
|
+
lambdaGrader: LambdaGraderConfig;
|
|
3937
|
+
$unknown?: never;
|
|
3938
|
+
}
|
|
3939
|
+
/**
|
|
3940
|
+
* @public
|
|
3941
|
+
*/
|
|
3942
|
+
interface $UnknownMember {
|
|
3943
|
+
lambdaGrader?: never;
|
|
3944
|
+
$unknown: [string, any];
|
|
3945
|
+
}
|
|
3946
|
+
/**
|
|
3947
|
+
* @deprecated unused in schema-serde mode.
|
|
3948
|
+
*
|
|
3949
|
+
*/
|
|
3950
|
+
interface Visitor<T> {
|
|
3951
|
+
lambdaGrader: (value: LambdaGraderConfig) => T;
|
|
3952
|
+
_: (name: string, value: any) => T;
|
|
3953
|
+
}
|
|
3954
|
+
}
|
|
3955
|
+
/**
|
|
3956
|
+
* <p> Hyperparameters for controlling the reinforcement fine-tuning training process, including learning settings and evaluation intervals. </p>
|
|
3957
|
+
* @public
|
|
3958
|
+
*/
|
|
3959
|
+
export interface RFTHyperParameters {
|
|
3960
|
+
/**
|
|
3961
|
+
* <p> Number of training epochs to run during reinforcement fine-tuning. Higher values may improve performance but increase training time. </p>
|
|
3962
|
+
* @public
|
|
3963
|
+
*/
|
|
3964
|
+
epochCount?: number | undefined;
|
|
3965
|
+
/**
|
|
3966
|
+
* <p> Number of training samples processed in each batch during reinforcement fine-tuning (RFT) training. Larger batches may improve training stability. </p>
|
|
3967
|
+
* @public
|
|
3968
|
+
*/
|
|
3969
|
+
batchSize?: number | undefined;
|
|
3970
|
+
/**
|
|
3971
|
+
* <p> Learning rate for the reinforcement fine-tuning. Controls how quickly the model adapts to reward signals. </p>
|
|
3972
|
+
* @public
|
|
3973
|
+
*/
|
|
3974
|
+
learningRate?: number | undefined;
|
|
3975
|
+
/**
|
|
3976
|
+
* <p> Maximum length of input prompts during RFT training, measured in tokens. Longer prompts allow more context but increase memory usage and training-time. </p>
|
|
3977
|
+
* @public
|
|
3978
|
+
*/
|
|
3979
|
+
maxPromptLength?: number | undefined;
|
|
3980
|
+
/**
|
|
3981
|
+
* <p> Number of response samples generated per prompt during RFT training. More samples provide better reward signal estimation. </p>
|
|
3982
|
+
* @public
|
|
3983
|
+
*/
|
|
3984
|
+
trainingSamplePerPrompt?: number | undefined;
|
|
3985
|
+
/**
|
|
3986
|
+
* <p> Maximum number of tokens the model can generate in response to each prompt during RFT training. </p>
|
|
3987
|
+
* @public
|
|
3988
|
+
*/
|
|
3989
|
+
inferenceMaxTokens?: number | undefined;
|
|
3990
|
+
/**
|
|
3991
|
+
* <p> Level of reasoning effort applied during RFT training. Higher values may improve response quality but increase training time. </p>
|
|
3992
|
+
* @public
|
|
3993
|
+
*/
|
|
3994
|
+
reasoningEffort?: ReasoningEffort | undefined;
|
|
3995
|
+
/**
|
|
3996
|
+
* <p> Interval between evaluation runs during RFT training, measured in training steps. More frequent evaluation provides better monitoring. </p>
|
|
3997
|
+
* @public
|
|
3998
|
+
*/
|
|
3999
|
+
evalInterval?: number | undefined;
|
|
4000
|
+
}
|
|
4001
|
+
/**
|
|
4002
|
+
* <p> Configuration settings for reinforcement fine-tuning (RFT), including grader configuration and training hyperparameters. </p>
|
|
4003
|
+
* @public
|
|
4004
|
+
*/
|
|
4005
|
+
export interface RFTConfig {
|
|
4006
|
+
/**
|
|
4007
|
+
* <p> Configuration for the grader that evaluates model responses and provides reward signals during RFT training. </p>
|
|
4008
|
+
* @public
|
|
4009
|
+
*/
|
|
4010
|
+
graderConfig?: GraderConfig | undefined;
|
|
4011
|
+
/**
|
|
4012
|
+
* <p> Hyperparameters that control the reinforcement fine-tuning training process, including learning rate, batch size, and epoch count. </p>
|
|
4013
|
+
* @public
|
|
4014
|
+
*/
|
|
4015
|
+
hyperParameters?: RFTHyperParameters | undefined;
|
|
4016
|
+
}
|
|
3865
4017
|
/**
|
|
3866
4018
|
* <p>A model customization configuration</p>
|
|
3867
4019
|
* @public
|
|
3868
4020
|
*/
|
|
3869
|
-
export type CustomizationConfig = CustomizationConfig.DistillationConfigMember | CustomizationConfig.$UnknownMember;
|
|
4021
|
+
export type CustomizationConfig = CustomizationConfig.DistillationConfigMember | CustomizationConfig.RftConfigMember | CustomizationConfig.$UnknownMember;
|
|
3870
4022
|
/**
|
|
3871
4023
|
* @public
|
|
3872
4024
|
*/
|
|
@@ -3877,6 +4029,16 @@ export declare namespace CustomizationConfig {
|
|
|
3877
4029
|
*/
|
|
3878
4030
|
interface DistillationConfigMember {
|
|
3879
4031
|
distillationConfig: DistillationConfig;
|
|
4032
|
+
rftConfig?: never;
|
|
4033
|
+
$unknown?: never;
|
|
4034
|
+
}
|
|
4035
|
+
/**
|
|
4036
|
+
* <p> Configuration settings for reinforcement fine-tuning (RFT) model customization, including grader configuration and hyperparameters. </p>
|
|
4037
|
+
* @public
|
|
4038
|
+
*/
|
|
4039
|
+
interface RftConfigMember {
|
|
4040
|
+
distillationConfig?: never;
|
|
4041
|
+
rftConfig: RFTConfig;
|
|
3880
4042
|
$unknown?: never;
|
|
3881
4043
|
}
|
|
3882
4044
|
/**
|
|
@@ -3884,6 +4046,7 @@ export declare namespace CustomizationConfig {
|
|
|
3884
4046
|
*/
|
|
3885
4047
|
interface $UnknownMember {
|
|
3886
4048
|
distillationConfig?: never;
|
|
4049
|
+
rftConfig?: never;
|
|
3887
4050
|
$unknown: [string, any];
|
|
3888
4051
|
}
|
|
3889
4052
|
/**
|
|
@@ -3892,6 +4055,7 @@ export declare namespace CustomizationConfig {
|
|
|
3892
4055
|
*/
|
|
3893
4056
|
interface Visitor<T> {
|
|
3894
4057
|
distillationConfig: (value: DistillationConfig) => T;
|
|
4058
|
+
rftConfig: (value: RFTConfig) => T;
|
|
3895
4059
|
_: (name: string, value: any) => T;
|
|
3896
4060
|
}
|
|
3897
4061
|
}
|
|
@@ -6955,165 +7119,3 @@ export interface DeleteInferenceProfileRequest {
|
|
|
6955
7119
|
*/
|
|
6956
7120
|
inferenceProfileIdentifier: string | undefined;
|
|
6957
7121
|
}
|
|
6958
|
-
/**
|
|
6959
|
-
* @public
|
|
6960
|
-
*/
|
|
6961
|
-
export interface DeleteInferenceProfileResponse {
|
|
6962
|
-
}
|
|
6963
|
-
/**
|
|
6964
|
-
* @public
|
|
6965
|
-
*/
|
|
6966
|
-
export interface GetInferenceProfileRequest {
|
|
6967
|
-
/**
|
|
6968
|
-
* <p>The ID or Amazon Resource Name (ARN) of the inference profile.</p>
|
|
6969
|
-
* @public
|
|
6970
|
-
*/
|
|
6971
|
-
inferenceProfileIdentifier: string | undefined;
|
|
6972
|
-
}
|
|
6973
|
-
/**
|
|
6974
|
-
* <p>Contains information about a model.</p>
|
|
6975
|
-
* @public
|
|
6976
|
-
*/
|
|
6977
|
-
export interface InferenceProfileModel {
|
|
6978
|
-
/**
|
|
6979
|
-
* <p>The Amazon Resource Name (ARN) of the model.</p>
|
|
6980
|
-
* @public
|
|
6981
|
-
*/
|
|
6982
|
-
modelArn?: string | undefined;
|
|
6983
|
-
}
|
|
6984
|
-
/**
|
|
6985
|
-
* @public
|
|
6986
|
-
*/
|
|
6987
|
-
export interface GetInferenceProfileResponse {
|
|
6988
|
-
/**
|
|
6989
|
-
* <p>The name of the inference profile.</p>
|
|
6990
|
-
* @public
|
|
6991
|
-
*/
|
|
6992
|
-
inferenceProfileName: string | undefined;
|
|
6993
|
-
/**
|
|
6994
|
-
* <p>The description of the inference profile.</p>
|
|
6995
|
-
* @public
|
|
6996
|
-
*/
|
|
6997
|
-
description?: string | undefined;
|
|
6998
|
-
/**
|
|
6999
|
-
* <p>The time at which the inference profile was created.</p>
|
|
7000
|
-
* @public
|
|
7001
|
-
*/
|
|
7002
|
-
createdAt?: Date | undefined;
|
|
7003
|
-
/**
|
|
7004
|
-
* <p>The time at which the inference profile was last updated.</p>
|
|
7005
|
-
* @public
|
|
7006
|
-
*/
|
|
7007
|
-
updatedAt?: Date | undefined;
|
|
7008
|
-
/**
|
|
7009
|
-
* <p>The Amazon Resource Name (ARN) of the inference profile.</p>
|
|
7010
|
-
* @public
|
|
7011
|
-
*/
|
|
7012
|
-
inferenceProfileArn: string | undefined;
|
|
7013
|
-
/**
|
|
7014
|
-
* <p>A list of information about each model in the inference profile.</p>
|
|
7015
|
-
* @public
|
|
7016
|
-
*/
|
|
7017
|
-
models: InferenceProfileModel[] | undefined;
|
|
7018
|
-
/**
|
|
7019
|
-
* <p>The unique identifier of the inference profile.</p>
|
|
7020
|
-
* @public
|
|
7021
|
-
*/
|
|
7022
|
-
inferenceProfileId: string | undefined;
|
|
7023
|
-
/**
|
|
7024
|
-
* <p>The status of the inference profile. <code>ACTIVE</code> means that the inference profile is ready to be used.</p>
|
|
7025
|
-
* @public
|
|
7026
|
-
*/
|
|
7027
|
-
status: InferenceProfileStatus | undefined;
|
|
7028
|
-
/**
|
|
7029
|
-
* <p>The type of the inference profile. The following types are possible:</p> <ul> <li> <p> <code>SYSTEM_DEFINED</code> – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.</p> </li> <li> <p> <code>APPLICATION</code> – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.</p> </li> </ul>
|
|
7030
|
-
* @public
|
|
7031
|
-
*/
|
|
7032
|
-
type: InferenceProfileType | undefined;
|
|
7033
|
-
}
|
|
7034
|
-
/**
|
|
7035
|
-
* @public
|
|
7036
|
-
*/
|
|
7037
|
-
export interface ListInferenceProfilesRequest {
|
|
7038
|
-
/**
|
|
7039
|
-
* <p>The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the <code>nextToken</code> field when making another request to return the next batch of results.</p>
|
|
7040
|
-
* @public
|
|
7041
|
-
*/
|
|
7042
|
-
maxResults?: number | undefined;
|
|
7043
|
-
/**
|
|
7044
|
-
* <p>If the total number of results is greater than the <code>maxResults</code> value provided in the request, enter the token returned in the <code>nextToken</code> field in the response in this field to return the next batch of results.</p>
|
|
7045
|
-
* @public
|
|
7046
|
-
*/
|
|
7047
|
-
nextToken?: string | undefined;
|
|
7048
|
-
/**
|
|
7049
|
-
* <p>Filters for inference profiles that match the type you specify.</p> <ul> <li> <p> <code>SYSTEM_DEFINED</code> – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.</p> </li> <li> <p> <code>APPLICATION</code> – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.</p> </li> </ul>
|
|
7050
|
-
* @public
|
|
7051
|
-
*/
|
|
7052
|
-
typeEquals?: InferenceProfileType | undefined;
|
|
7053
|
-
}
|
|
7054
|
-
/**
|
|
7055
|
-
* <p>Contains information about an inference profile.</p>
|
|
7056
|
-
* @public
|
|
7057
|
-
*/
|
|
7058
|
-
export interface InferenceProfileSummary {
|
|
7059
|
-
/**
|
|
7060
|
-
* <p>The name of the inference profile.</p>
|
|
7061
|
-
* @public
|
|
7062
|
-
*/
|
|
7063
|
-
inferenceProfileName: string | undefined;
|
|
7064
|
-
/**
|
|
7065
|
-
* <p>The description of the inference profile.</p>
|
|
7066
|
-
* @public
|
|
7067
|
-
*/
|
|
7068
|
-
description?: string | undefined;
|
|
7069
|
-
/**
|
|
7070
|
-
* <p>The time at which the inference profile was created.</p>
|
|
7071
|
-
* @public
|
|
7072
|
-
*/
|
|
7073
|
-
createdAt?: Date | undefined;
|
|
7074
|
-
/**
|
|
7075
|
-
* <p>The time at which the inference profile was last updated.</p>
|
|
7076
|
-
* @public
|
|
7077
|
-
*/
|
|
7078
|
-
updatedAt?: Date | undefined;
|
|
7079
|
-
/**
|
|
7080
|
-
* <p>The Amazon Resource Name (ARN) of the inference profile.</p>
|
|
7081
|
-
* @public
|
|
7082
|
-
*/
|
|
7083
|
-
inferenceProfileArn: string | undefined;
|
|
7084
|
-
/**
|
|
7085
|
-
* <p>A list of information about each model in the inference profile.</p>
|
|
7086
|
-
* @public
|
|
7087
|
-
*/
|
|
7088
|
-
models: InferenceProfileModel[] | undefined;
|
|
7089
|
-
/**
|
|
7090
|
-
* <p>The unique identifier of the inference profile.</p>
|
|
7091
|
-
* @public
|
|
7092
|
-
*/
|
|
7093
|
-
inferenceProfileId: string | undefined;
|
|
7094
|
-
/**
|
|
7095
|
-
* <p>The status of the inference profile. <code>ACTIVE</code> means that the inference profile is ready to be used.</p>
|
|
7096
|
-
* @public
|
|
7097
|
-
*/
|
|
7098
|
-
status: InferenceProfileStatus | undefined;
|
|
7099
|
-
/**
|
|
7100
|
-
* <p>The type of the inference profile. The following types are possible:</p> <ul> <li> <p> <code>SYSTEM_DEFINED</code> – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.</p> </li> <li> <p> <code>APPLICATION</code> – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.</p> </li> </ul>
|
|
7101
|
-
* @public
|
|
7102
|
-
*/
|
|
7103
|
-
type: InferenceProfileType | undefined;
|
|
7104
|
-
}
|
|
7105
|
-
/**
|
|
7106
|
-
* @public
|
|
7107
|
-
*/
|
|
7108
|
-
export interface ListInferenceProfilesResponse {
|
|
7109
|
-
/**
|
|
7110
|
-
* <p>A list of information about each inference profile that you can use.</p>
|
|
7111
|
-
* @public
|
|
7112
|
-
*/
|
|
7113
|
-
inferenceProfileSummaries?: InferenceProfileSummary[] | undefined;
|
|
7114
|
-
/**
|
|
7115
|
-
* <p>If the total number of results is greater than the <code>maxResults</code> value provided in the request, use this token when making another request in the <code>nextToken</code> field to return the next batch of results.</p>
|
|
7116
|
-
* @public
|
|
7117
|
-
*/
|
|
7118
|
-
nextToken?: string | undefined;
|
|
7119
|
-
}
|
|
@@ -1,5 +1,167 @@
|
|
|
1
|
-
import { ApplicationType, AuthorizationStatus, CommitmentDuration, CustomizationType, EntitlementAvailability, EvaluationJobStatus, EvaluationJobType, FineTuningJobStatus, FoundationModelLifecycleStatus, InferenceType, JobStatusDetails, ModelCopyJobStatus, ModelCustomization, ModelCustomizationJobStatus, ModelImportJobStatus, ModelInvocationJobStatus, ModelModality, OfferType, PromptRouterStatus, PromptRouterType, ProvisionedModelStatus, RegionAvailability, RetrieveAndGenerateType, S3InputFormat, SearchType, SortByProvisionedModels, SortJobsBy, SortModelsBy, SortOrder } from "./enums";
|
|
1
|
+
import { ApplicationType, AuthorizationStatus, CommitmentDuration, CustomizationType, EntitlementAvailability, EvaluationJobStatus, EvaluationJobType, FineTuningJobStatus, FoundationModelLifecycleStatus, InferenceProfileStatus, InferenceProfileType, InferenceType, JobStatusDetails, ModelCopyJobStatus, ModelCustomization, ModelCustomizationJobStatus, ModelImportJobStatus, ModelInvocationJobStatus, ModelModality, OfferType, PromptRouterStatus, PromptRouterType, ProvisionedModelStatus, RegionAvailability, RetrieveAndGenerateType, S3InputFormat, SearchType, SortByProvisionedModels, SortJobsBy, SortModelsBy, SortOrder } from "./enums";
|
|
2
2
|
import { AgreementAvailability, CustomizationConfig, EvaluationConfig, EvaluationModelConfig, EvaluationOutputDataConfig, EvaluationPrecomputedRagSourceConfig, ExternalSourcesRetrieveAndGenerateConfiguration, FilterAttribute, GenerationConfiguration, ImplicitFilterConfiguration, ModelDataSource, OrchestrationConfiguration, OutputDataConfig, Tag, TrainingDataConfig, TrainingMetrics, ValidationDataConfig, ValidatorMetric, VectorSearchRerankingConfiguration, VpcConfig } from "./models_0";
|
|
3
|
+
/**
|
|
4
|
+
* @public
|
|
5
|
+
*/
|
|
6
|
+
export interface DeleteInferenceProfileResponse {
|
|
7
|
+
}
|
|
8
|
+
/**
|
|
9
|
+
* @public
|
|
10
|
+
*/
|
|
11
|
+
export interface GetInferenceProfileRequest {
|
|
12
|
+
/**
|
|
13
|
+
* <p>The ID or Amazon Resource Name (ARN) of the inference profile.</p>
|
|
14
|
+
* @public
|
|
15
|
+
*/
|
|
16
|
+
inferenceProfileIdentifier: string | undefined;
|
|
17
|
+
}
|
|
18
|
+
/**
|
|
19
|
+
* <p>Contains information about a model.</p>
|
|
20
|
+
* @public
|
|
21
|
+
*/
|
|
22
|
+
export interface InferenceProfileModel {
|
|
23
|
+
/**
|
|
24
|
+
* <p>The Amazon Resource Name (ARN) of the model.</p>
|
|
25
|
+
* @public
|
|
26
|
+
*/
|
|
27
|
+
modelArn?: string | undefined;
|
|
28
|
+
}
|
|
29
|
+
/**
|
|
30
|
+
* @public
|
|
31
|
+
*/
|
|
32
|
+
export interface GetInferenceProfileResponse {
|
|
33
|
+
/**
|
|
34
|
+
* <p>The name of the inference profile.</p>
|
|
35
|
+
* @public
|
|
36
|
+
*/
|
|
37
|
+
inferenceProfileName: string | undefined;
|
|
38
|
+
/**
|
|
39
|
+
* <p>The description of the inference profile.</p>
|
|
40
|
+
* @public
|
|
41
|
+
*/
|
|
42
|
+
description?: string | undefined;
|
|
43
|
+
/**
|
|
44
|
+
* <p>The time at which the inference profile was created.</p>
|
|
45
|
+
* @public
|
|
46
|
+
*/
|
|
47
|
+
createdAt?: Date | undefined;
|
|
48
|
+
/**
|
|
49
|
+
* <p>The time at which the inference profile was last updated.</p>
|
|
50
|
+
* @public
|
|
51
|
+
*/
|
|
52
|
+
updatedAt?: Date | undefined;
|
|
53
|
+
/**
|
|
54
|
+
* <p>The Amazon Resource Name (ARN) of the inference profile.</p>
|
|
55
|
+
* @public
|
|
56
|
+
*/
|
|
57
|
+
inferenceProfileArn: string | undefined;
|
|
58
|
+
/**
|
|
59
|
+
* <p>A list of information about each model in the inference profile.</p>
|
|
60
|
+
* @public
|
|
61
|
+
*/
|
|
62
|
+
models: InferenceProfileModel[] | undefined;
|
|
63
|
+
/**
|
|
64
|
+
* <p>The unique identifier of the inference profile.</p>
|
|
65
|
+
* @public
|
|
66
|
+
*/
|
|
67
|
+
inferenceProfileId: string | undefined;
|
|
68
|
+
/**
|
|
69
|
+
* <p>The status of the inference profile. <code>ACTIVE</code> means that the inference profile is ready to be used.</p>
|
|
70
|
+
* @public
|
|
71
|
+
*/
|
|
72
|
+
status: InferenceProfileStatus | undefined;
|
|
73
|
+
/**
|
|
74
|
+
* <p>The type of the inference profile. The following types are possible:</p> <ul> <li> <p> <code>SYSTEM_DEFINED</code> – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.</p> </li> <li> <p> <code>APPLICATION</code> – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.</p> </li> </ul>
|
|
75
|
+
* @public
|
|
76
|
+
*/
|
|
77
|
+
type: InferenceProfileType | undefined;
|
|
78
|
+
}
|
|
79
|
+
/**
|
|
80
|
+
* @public
|
|
81
|
+
*/
|
|
82
|
+
export interface ListInferenceProfilesRequest {
|
|
83
|
+
/**
|
|
84
|
+
* <p>The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the <code>nextToken</code> field when making another request to return the next batch of results.</p>
|
|
85
|
+
* @public
|
|
86
|
+
*/
|
|
87
|
+
maxResults?: number | undefined;
|
|
88
|
+
/**
|
|
89
|
+
* <p>If the total number of results is greater than the <code>maxResults</code> value provided in the request, enter the token returned in the <code>nextToken</code> field in the response in this field to return the next batch of results.</p>
|
|
90
|
+
* @public
|
|
91
|
+
*/
|
|
92
|
+
nextToken?: string | undefined;
|
|
93
|
+
/**
|
|
94
|
+
* <p>Filters for inference profiles that match the type you specify.</p> <ul> <li> <p> <code>SYSTEM_DEFINED</code> – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.</p> </li> <li> <p> <code>APPLICATION</code> – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.</p> </li> </ul>
|
|
95
|
+
* @public
|
|
96
|
+
*/
|
|
97
|
+
typeEquals?: InferenceProfileType | undefined;
|
|
98
|
+
}
|
|
99
|
+
/**
|
|
100
|
+
* <p>Contains information about an inference profile.</p>
|
|
101
|
+
* @public
|
|
102
|
+
*/
|
|
103
|
+
export interface InferenceProfileSummary {
|
|
104
|
+
/**
|
|
105
|
+
* <p>The name of the inference profile.</p>
|
|
106
|
+
* @public
|
|
107
|
+
*/
|
|
108
|
+
inferenceProfileName: string | undefined;
|
|
109
|
+
/**
|
|
110
|
+
* <p>The description of the inference profile.</p>
|
|
111
|
+
* @public
|
|
112
|
+
*/
|
|
113
|
+
description?: string | undefined;
|
|
114
|
+
/**
|
|
115
|
+
* <p>The time at which the inference profile was created.</p>
|
|
116
|
+
* @public
|
|
117
|
+
*/
|
|
118
|
+
createdAt?: Date | undefined;
|
|
119
|
+
/**
|
|
120
|
+
* <p>The time at which the inference profile was last updated.</p>
|
|
121
|
+
* @public
|
|
122
|
+
*/
|
|
123
|
+
updatedAt?: Date | undefined;
|
|
124
|
+
/**
|
|
125
|
+
* <p>The Amazon Resource Name (ARN) of the inference profile.</p>
|
|
126
|
+
* @public
|
|
127
|
+
*/
|
|
128
|
+
inferenceProfileArn: string | undefined;
|
|
129
|
+
/**
|
|
130
|
+
* <p>A list of information about each model in the inference profile.</p>
|
|
131
|
+
* @public
|
|
132
|
+
*/
|
|
133
|
+
models: InferenceProfileModel[] | undefined;
|
|
134
|
+
/**
|
|
135
|
+
* <p>The unique identifier of the inference profile.</p>
|
|
136
|
+
* @public
|
|
137
|
+
*/
|
|
138
|
+
inferenceProfileId: string | undefined;
|
|
139
|
+
/**
|
|
140
|
+
* <p>The status of the inference profile. <code>ACTIVE</code> means that the inference profile is ready to be used.</p>
|
|
141
|
+
* @public
|
|
142
|
+
*/
|
|
143
|
+
status: InferenceProfileStatus | undefined;
|
|
144
|
+
/**
|
|
145
|
+
* <p>The type of the inference profile. The following types are possible:</p> <ul> <li> <p> <code>SYSTEM_DEFINED</code> – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.</p> </li> <li> <p> <code>APPLICATION</code> – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.</p> </li> </ul>
|
|
146
|
+
* @public
|
|
147
|
+
*/
|
|
148
|
+
type: InferenceProfileType | undefined;
|
|
149
|
+
}
|
|
150
|
+
/**
|
|
151
|
+
* @public
|
|
152
|
+
*/
|
|
153
|
+
export interface ListInferenceProfilesResponse {
|
|
154
|
+
/**
|
|
155
|
+
* <p>A list of information about each inference profile that you can use.</p>
|
|
156
|
+
* @public
|
|
157
|
+
*/
|
|
158
|
+
inferenceProfileSummaries?: InferenceProfileSummary[] | undefined;
|
|
159
|
+
/**
|
|
160
|
+
* <p>If the total number of results is greater than the <code>maxResults</code> value provided in the request, use this token when making another request in the <code>nextToken</code> field to return the next batch of results.</p>
|
|
161
|
+
* @public
|
|
162
|
+
*/
|
|
163
|
+
nextToken?: string | undefined;
|
|
164
|
+
}
|
|
3
165
|
/**
|
|
4
166
|
* @public
|
|
5
167
|
*/
|
|
@@ -165,6 +165,7 @@ export declare var CustomMetricBedrockEvaluatorModel: StaticStructureSchema;
|
|
|
165
165
|
export declare var CustomMetricDefinition: StaticStructureSchema;
|
|
166
166
|
export declare var CustomMetricEvaluatorModelConfig: StaticStructureSchema;
|
|
167
167
|
export declare var CustomModelDeploymentSummary: StaticStructureSchema;
|
|
168
|
+
export declare var CustomModelDeploymentUpdateDetails: StaticStructureSchema;
|
|
168
169
|
export declare var CustomModelSummary: StaticStructureSchema;
|
|
169
170
|
export declare var CustomModelUnits: StaticStructureSchema;
|
|
170
171
|
export declare var DataProcessingDetails: StaticStructureSchema;
|
|
@@ -317,6 +318,7 @@ export declare var KbInferenceConfig: StaticStructureSchema;
|
|
|
317
318
|
export declare var KnowledgeBaseRetrievalConfiguration: StaticStructureSchema;
|
|
318
319
|
export declare var KnowledgeBaseRetrieveAndGenerateConfiguration: StaticStructureSchema;
|
|
319
320
|
export declare var KnowledgeBaseVectorSearchConfiguration: StaticStructureSchema;
|
|
321
|
+
export declare var LambdaGraderConfig: StaticStructureSchema;
|
|
320
322
|
export declare var LegalTerm: StaticStructureSchema;
|
|
321
323
|
export declare var ListAutomatedReasoningPoliciesRequest: StaticStructureSchema;
|
|
322
324
|
export declare var ListAutomatedReasoningPoliciesResponse: StaticStructureSchema;
|
|
@@ -395,6 +397,8 @@ export declare var ResourceInUseException: StaticErrorSchema;
|
|
|
395
397
|
export declare var ResourceNotFoundException: StaticErrorSchema;
|
|
396
398
|
export declare var RetrieveAndGenerateConfiguration: StaticStructureSchema;
|
|
397
399
|
export declare var RetrieveConfig: StaticStructureSchema;
|
|
400
|
+
export declare var RFTConfig: StaticStructureSchema;
|
|
401
|
+
export declare var RFTHyperParameters: StaticStructureSchema;
|
|
398
402
|
export declare var RoutingCriteria: StaticStructureSchema;
|
|
399
403
|
export declare var S3Config: StaticStructureSchema;
|
|
400
404
|
export declare var S3DataSource: StaticStructureSchema;
|
|
@@ -433,6 +437,8 @@ export declare var UpdateAutomatedReasoningPolicyRequest: StaticStructureSchema;
|
|
|
433
437
|
export declare var UpdateAutomatedReasoningPolicyResponse: StaticStructureSchema;
|
|
434
438
|
export declare var UpdateAutomatedReasoningPolicyTestCaseRequest: StaticStructureSchema;
|
|
435
439
|
export declare var UpdateAutomatedReasoningPolicyTestCaseResponse: StaticStructureSchema;
|
|
440
|
+
export declare var UpdateCustomModelDeploymentRequest: StaticStructureSchema;
|
|
441
|
+
export declare var UpdateCustomModelDeploymentResponse: StaticStructureSchema;
|
|
436
442
|
export declare var UpdateGuardrailRequest: StaticStructureSchema;
|
|
437
443
|
export declare var UpdateGuardrailResponse: StaticStructureSchema;
|
|
438
444
|
export declare var UpdateMarketplaceModelEndpointRequest: StaticStructureSchema;
|
|
@@ -573,6 +579,7 @@ export declare var EvaluationInferenceConfig: StaticStructureSchema;
|
|
|
573
579
|
export declare var EvaluationModelConfig: StaticStructureSchema;
|
|
574
580
|
export declare var EvaluationPrecomputedRagSourceConfig: StaticStructureSchema;
|
|
575
581
|
export declare var EvaluatorModelConfig: StaticStructureSchema;
|
|
582
|
+
export declare var GraderConfig: StaticStructureSchema;
|
|
576
583
|
export declare var InferenceProfileModelSource: StaticStructureSchema;
|
|
577
584
|
export declare var InvocationLogSource: StaticStructureSchema;
|
|
578
585
|
export declare var KnowledgeBaseConfig: StaticStructureSchema;
|
|
@@ -678,6 +685,7 @@ export declare var UntagResource: StaticOperationSchema;
|
|
|
678
685
|
export declare var UpdateAutomatedReasoningPolicy: StaticOperationSchema;
|
|
679
686
|
export declare var UpdateAutomatedReasoningPolicyAnnotations: StaticOperationSchema;
|
|
680
687
|
export declare var UpdateAutomatedReasoningPolicyTestCase: StaticOperationSchema;
|
|
688
|
+
export declare var UpdateCustomModelDeployment: StaticOperationSchema;
|
|
681
689
|
export declare var UpdateGuardrail: StaticOperationSchema;
|
|
682
690
|
export declare var UpdateMarketplaceModelEndpoint: StaticOperationSchema;
|
|
683
691
|
export declare var UpdateProvisionedModelThroughput: StaticOperationSchema;
|
|
@@ -376,6 +376,10 @@ import {
|
|
|
376
376
|
UpdateAutomatedReasoningPolicyTestCaseCommandInput,
|
|
377
377
|
UpdateAutomatedReasoningPolicyTestCaseCommandOutput,
|
|
378
378
|
} from "./commands/UpdateAutomatedReasoningPolicyTestCaseCommand";
|
|
379
|
+
import {
|
|
380
|
+
UpdateCustomModelDeploymentCommandInput,
|
|
381
|
+
UpdateCustomModelDeploymentCommandOutput,
|
|
382
|
+
} from "./commands/UpdateCustomModelDeploymentCommand";
|
|
379
383
|
import {
|
|
380
384
|
UpdateGuardrailCommandInput,
|
|
381
385
|
UpdateGuardrailCommandOutput,
|
|
@@ -1792,6 +1796,19 @@ export interface Bedrock {
|
|
|
1792
1796
|
data?: UpdateAutomatedReasoningPolicyTestCaseCommandOutput
|
|
1793
1797
|
) => void
|
|
1794
1798
|
): void;
|
|
1799
|
+
updateCustomModelDeployment(
|
|
1800
|
+
args: UpdateCustomModelDeploymentCommandInput,
|
|
1801
|
+
options?: __HttpHandlerOptions
|
|
1802
|
+
): Promise<UpdateCustomModelDeploymentCommandOutput>;
|
|
1803
|
+
updateCustomModelDeployment(
|
|
1804
|
+
args: UpdateCustomModelDeploymentCommandInput,
|
|
1805
|
+
cb: (err: any, data?: UpdateCustomModelDeploymentCommandOutput) => void
|
|
1806
|
+
): void;
|
|
1807
|
+
updateCustomModelDeployment(
|
|
1808
|
+
args: UpdateCustomModelDeploymentCommandInput,
|
|
1809
|
+
options: __HttpHandlerOptions,
|
|
1810
|
+
cb: (err: any, data?: UpdateCustomModelDeploymentCommandOutput) => void
|
|
1811
|
+
): void;
|
|
1795
1812
|
updateGuardrail(
|
|
1796
1813
|
args: UpdateGuardrailCommandInput,
|
|
1797
1814
|
options?: __HttpHandlerOptions
|
|
@@ -424,6 +424,10 @@ import {
|
|
|
424
424
|
UpdateAutomatedReasoningPolicyTestCaseCommandInput,
|
|
425
425
|
UpdateAutomatedReasoningPolicyTestCaseCommandOutput,
|
|
426
426
|
} from "./commands/UpdateAutomatedReasoningPolicyTestCaseCommand";
|
|
427
|
+
import {
|
|
428
|
+
UpdateCustomModelDeploymentCommandInput,
|
|
429
|
+
UpdateCustomModelDeploymentCommandOutput,
|
|
430
|
+
} from "./commands/UpdateCustomModelDeploymentCommand";
|
|
427
431
|
import {
|
|
428
432
|
UpdateGuardrailCommandInput,
|
|
429
433
|
UpdateGuardrailCommandOutput,
|
|
@@ -538,6 +542,7 @@ export type ServiceInputTypes =
|
|
|
538
542
|
| UpdateAutomatedReasoningPolicyAnnotationsCommandInput
|
|
539
543
|
| UpdateAutomatedReasoningPolicyCommandInput
|
|
540
544
|
| UpdateAutomatedReasoningPolicyTestCaseCommandInput
|
|
545
|
+
| UpdateCustomModelDeploymentCommandInput
|
|
541
546
|
| UpdateGuardrailCommandInput
|
|
542
547
|
| UpdateMarketplaceModelEndpointCommandInput
|
|
543
548
|
| UpdateProvisionedModelThroughputCommandInput;
|
|
@@ -636,6 +641,7 @@ export type ServiceOutputTypes =
|
|
|
636
641
|
| UpdateAutomatedReasoningPolicyAnnotationsCommandOutput
|
|
637
642
|
| UpdateAutomatedReasoningPolicyCommandOutput
|
|
638
643
|
| UpdateAutomatedReasoningPolicyTestCaseCommandOutput
|
|
644
|
+
| UpdateCustomModelDeploymentCommandOutput
|
|
639
645
|
| UpdateGuardrailCommandOutput
|
|
640
646
|
| UpdateMarketplaceModelEndpointCommandOutput
|
|
641
647
|
| UpdateProvisionedModelThroughputCommandOutput;
|
|
@@ -5,10 +5,8 @@ import {
|
|
|
5
5
|
ServiceInputTypes,
|
|
6
6
|
ServiceOutputTypes,
|
|
7
7
|
} from "../BedrockClient";
|
|
8
|
-
import {
|
|
9
|
-
|
|
10
|
-
DeleteInferenceProfileResponse,
|
|
11
|
-
} from "../models/models_0";
|
|
8
|
+
import { DeleteInferenceProfileRequest } from "../models/models_0";
|
|
9
|
+
import { DeleteInferenceProfileResponse } from "../models/models_1";
|
|
12
10
|
export { __MetadataBearer };
|
|
13
11
|
export { $Command };
|
|
14
12
|
export interface DeleteInferenceProfileCommandInput
|