aws-sdk-sagemaker 1.415.0 → 1.416.0
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.
- checksums.yaml +4 -4
- data/CHANGELOG.md +5 -0
- data/VERSION +1 -1
- data/lib/aws-sdk-sagemaker/client.rb +511 -27
- data/lib/aws-sdk-sagemaker/client_api.rb +232 -0
- data/lib/aws-sdk-sagemaker/errors.rb +16 -0
- data/lib/aws-sdk-sagemaker/types.rb +625 -3
- data/lib/aws-sdk-sagemaker.rb +1 -1
- data/sig/client.rbs +115 -10
- data/sig/errors.rbs +3 -0
- data/sig/params.rbs +30 -1
- data/sig/types.rbs +165 -16
- metadata +3 -3
|
@@ -4947,6 +4947,18 @@ module Aws::SageMaker
|
|
|
4947
4947
|
# @option params [Types::MetricsConfig] :metrics_config
|
|
4948
4948
|
# The configuration parameters for utilization metrics.
|
|
4949
4949
|
#
|
|
4950
|
+
# @option params [Types::CrossRegionTrafficConfig] :cross_region_traffic_config
|
|
4951
|
+
# The cross-Region traffic cap for the endpoint. The cap limits the
|
|
4952
|
+
# requests per second that the endpoint accepts from inference routers
|
|
4953
|
+
# in other Amazon Web Services Regions. If you don't specify it, these
|
|
4954
|
+
# requests aren't limited. You can't specify it with serverless
|
|
4955
|
+
# variants or with `AsyncInferenceConfig`. For information about the
|
|
4956
|
+
# cross-Region traffic cap, see [Limit requests from other Regions][1].
|
|
4957
|
+
#
|
|
4958
|
+
#
|
|
4959
|
+
#
|
|
4960
|
+
# [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/inference-router.html#inference-router-cross-region-limit
|
|
4961
|
+
#
|
|
4950
4962
|
# @return [Types::CreateEndpointConfigOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
|
4951
4963
|
#
|
|
4952
4964
|
# * {Types::CreateEndpointConfigOutput#endpoint_config_arn #endpoint_config_arn} => String
|
|
@@ -4995,7 +5007,7 @@ module Aws::SageMaker
|
|
|
4995
5007
|
# },
|
|
4996
5008
|
# },
|
|
4997
5009
|
# routing_config: {
|
|
4998
|
-
# routing_strategy: "LEAST_OUTSTANDING_REQUESTS", # required, accepts LEAST_OUTSTANDING_REQUESTS, RANDOM, PREFIX_AWARE
|
|
5010
|
+
# routing_strategy: "LEAST_OUTSTANDING_REQUESTS", # required, accepts LEAST_OUTSTANDING_REQUESTS, RANDOM, PREFIX_AWARE, KV_AWARE
|
|
4999
5011
|
# prefix_aware_routing_config: {
|
|
5000
5012
|
# prefix_length: 1,
|
|
5001
5013
|
# concurrency_threshold: 1,
|
|
@@ -5122,7 +5134,7 @@ module Aws::SageMaker
|
|
|
5122
5134
|
# },
|
|
5123
5135
|
# },
|
|
5124
5136
|
# routing_config: {
|
|
5125
|
-
# routing_strategy: "LEAST_OUTSTANDING_REQUESTS", # required, accepts LEAST_OUTSTANDING_REQUESTS, RANDOM, PREFIX_AWARE
|
|
5137
|
+
# routing_strategy: "LEAST_OUTSTANDING_REQUESTS", # required, accepts LEAST_OUTSTANDING_REQUESTS, RANDOM, PREFIX_AWARE, KV_AWARE
|
|
5126
5138
|
# prefix_aware_routing_config: {
|
|
5127
5139
|
# prefix_length: 1,
|
|
5128
5140
|
# concurrency_threshold: 1,
|
|
@@ -5151,6 +5163,10 @@ module Aws::SageMaker
|
|
|
5151
5163
|
# enable_detailed_observability: false,
|
|
5152
5164
|
# metric_publish_frequency_in_seconds: 1,
|
|
5153
5165
|
# },
|
|
5166
|
+
# cross_region_traffic_config: {
|
|
5167
|
+
# max_invocations_per_second_per_instance: 1, # required
|
|
5168
|
+
# max_cross_region_percent_per_endpoint: 1, # required
|
|
5169
|
+
# },
|
|
5154
5170
|
# })
|
|
5155
5171
|
#
|
|
5156
5172
|
# @example Response structure
|
|
@@ -7048,17 +7064,149 @@ module Aws::SageMaker
|
|
|
7048
7064
|
req.send_request(options)
|
|
7049
7065
|
end
|
|
7050
7066
|
|
|
7067
|
+
# Creates an inference router. An inference router is a Regional
|
|
7068
|
+
# SageMaker AI resource that sends each inference request to one of the
|
|
7069
|
+
# endpoints or inference components that you list for a routing target.
|
|
7070
|
+
# These destinations can be in any Amazon Web Services account, and in
|
|
7071
|
+
# any Amazon Web Services Region in the same partition as the router.
|
|
7072
|
+
#
|
|
7073
|
+
# The router's status is `Creating` until it's ready to use. SageMaker
|
|
7074
|
+
# AI checks that each endpoint is a real-time or asynchronous endpoint,
|
|
7075
|
+
# as the routing target requires, and rejects one of the wrong type. It
|
|
7076
|
+
# checks endpoints in other accounts with your credentials, so the
|
|
7077
|
+
# endpoint policy must allow `sagemaker:DescribeEndpoint`. SageMaker AI
|
|
7078
|
+
# accepts an endpoint that it can't check, for example one that
|
|
7079
|
+
# doesn't exist. Requests to it fail if it's the wrong type or
|
|
7080
|
+
# doesn't exist. To see the status of each destination, call
|
|
7081
|
+
# [DescribeInferenceRouter][1] and see the `RoutingStatus` of each
|
|
7082
|
+
# destination.
|
|
7083
|
+
#
|
|
7084
|
+
# To invoke the router, use `InvokeInferenceRouter` or
|
|
7085
|
+
# `InvokeInferenceRouterAsync`. For information about inference routers,
|
|
7086
|
+
# see [Route requests across Regions with inference routers][2].
|
|
7087
|
+
#
|
|
7088
|
+
#
|
|
7089
|
+
#
|
|
7090
|
+
# [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeInferenceRouter.html
|
|
7091
|
+
# [2]: https://docs.aws.amazon.com/sagemaker/latest/dg/inference-router.html
|
|
7092
|
+
#
|
|
7093
|
+
# @option params [required, String] :inference_router_name
|
|
7094
|
+
# The name of the inference router. The name must be unique within your
|
|
7095
|
+
# account in the current Amazon Web Services Region. The name is case
|
|
7096
|
+
# sensitive.
|
|
7097
|
+
#
|
|
7098
|
+
# @option params [required, Array<Types::RoutingTarget>] :routing_targets
|
|
7099
|
+
# The routing targets of the inference router. Each routing target is a
|
|
7100
|
+
# model that callers name when they invoke the router, and the
|
|
7101
|
+
# destinations that serve it.
|
|
7102
|
+
#
|
|
7103
|
+
# @option params [String] :client_token
|
|
7104
|
+
# A unique, case-sensitive identifier that you provide to ensure the
|
|
7105
|
+
# idempotency of the request. If you reuse a client token, use the same
|
|
7106
|
+
# request parameters. Otherwise, the request fails.
|
|
7107
|
+
#
|
|
7108
|
+
# **A suitable default value is auto-generated.** You should normally
|
|
7109
|
+
# not need to pass this option.**
|
|
7110
|
+
#
|
|
7111
|
+
# @option params [Array<Types::Tag>] :tags
|
|
7112
|
+
# A list of key-value pairs to apply to the inference router. For
|
|
7113
|
+
# information about tagging, see [Tagging Amazon Web Services
|
|
7114
|
+
# resources][1] in the *Amazon Web Services General Reference*.
|
|
7115
|
+
#
|
|
7116
|
+
#
|
|
7117
|
+
#
|
|
7118
|
+
# [1]: https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html
|
|
7119
|
+
#
|
|
7120
|
+
# @return [Types::CreateInferenceRouterOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
|
7121
|
+
#
|
|
7122
|
+
# * {Types::CreateInferenceRouterOutput#inference_router_arn #inference_router_arn} => String
|
|
7123
|
+
#
|
|
7124
|
+
# @example Request syntax with placeholder values
|
|
7125
|
+
#
|
|
7126
|
+
# resp = client.create_inference_router({
|
|
7127
|
+
# inference_router_name: "InferenceRouterName", # required
|
|
7128
|
+
# routing_targets: [ # required
|
|
7129
|
+
# {
|
|
7130
|
+
# name: "RoutingTargetName", # required
|
|
7131
|
+
# destinations: [ # required
|
|
7132
|
+
# {
|
|
7133
|
+
# resource_arn: "DestinationResourceArn", # required
|
|
7134
|
+
# routing_status: "Routable", # accepts Routable, Unroutable, Unknown
|
|
7135
|
+
# },
|
|
7136
|
+
# ],
|
|
7137
|
+
# async_inference_config: {
|
|
7138
|
+
# output_config: { # required
|
|
7139
|
+
# s3_output_path: "InferenceRouterS3Uri", # required
|
|
7140
|
+
# s3_failure_path: "InferenceRouterS3Uri", # required
|
|
7141
|
+
# kms_key_id: "KmsKeyId",
|
|
7142
|
+
# notification_config: {
|
|
7143
|
+
# success_topic: "InferenceRouterSnsTopicArn",
|
|
7144
|
+
# error_topic: "InferenceRouterSnsTopicArn",
|
|
7145
|
+
# },
|
|
7146
|
+
# },
|
|
7147
|
+
# client_config: {
|
|
7148
|
+
# max_time_in_backlog_seconds: 1,
|
|
7149
|
+
# },
|
|
7150
|
+
# },
|
|
7151
|
+
# routing_preference: "LocalRegionFirst", # accepts LocalRegionFirst, InstancePoolOrder
|
|
7152
|
+
# },
|
|
7153
|
+
# ],
|
|
7154
|
+
# client_token: "InferenceRouterClientToken",
|
|
7155
|
+
# tags: [
|
|
7156
|
+
# {
|
|
7157
|
+
# key: "TagKey", # required
|
|
7158
|
+
# value: "TagValue", # required
|
|
7159
|
+
# },
|
|
7160
|
+
# ],
|
|
7161
|
+
# })
|
|
7162
|
+
#
|
|
7163
|
+
# @example Response structure
|
|
7164
|
+
#
|
|
7165
|
+
# resp.inference_router_arn #=> String
|
|
7166
|
+
#
|
|
7167
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/CreateInferenceRouter AWS API Documentation
|
|
7168
|
+
#
|
|
7169
|
+
# @overload create_inference_router(params = {})
|
|
7170
|
+
# @param [Hash] params ({})
|
|
7171
|
+
def create_inference_router(params = {}, options = {})
|
|
7172
|
+
req = build_request(:create_inference_router, params)
|
|
7173
|
+
req.send_request(options)
|
|
7174
|
+
end
|
|
7175
|
+
|
|
7051
7176
|
# Creates a model customization job in Amazon SageMaker. A job runs a
|
|
7052
7177
|
# workload based on the job category and configuration you provide. You
|
|
7053
7178
|
# specify the job category, a schema-versioned configuration document,
|
|
7054
7179
|
# and an IAM role that grants Amazon SageMaker permission to access
|
|
7055
7180
|
# resources on your behalf.
|
|
7056
7181
|
#
|
|
7057
|
-
#
|
|
7058
|
-
#
|
|
7059
|
-
#
|
|
7060
|
-
#
|
|
7061
|
-
#
|
|
7182
|
+
# Specify one of the following job categories, which determines the type
|
|
7183
|
+
# of workload that the job runs:
|
|
7184
|
+
#
|
|
7185
|
+
# AgentRFT
|
|
7186
|
+
#
|
|
7187
|
+
# : Fine-tune a model using multi-turn reinforcement learning with
|
|
7188
|
+
# reward signals.
|
|
7189
|
+
#
|
|
7190
|
+
# AgentRFTEvaluation
|
|
7191
|
+
#
|
|
7192
|
+
# : Evaluate a fine-tuned or base model by running multi-turn rollouts
|
|
7193
|
+
# against a held-out prompt dataset. This category computes metrics
|
|
7194
|
+
# such as pass@k and mean reward.
|
|
7195
|
+
#
|
|
7196
|
+
# DataQualityEvaluation
|
|
7197
|
+
#
|
|
7198
|
+
# : Evaluate the quality of a generated or bring-your-own dataset using
|
|
7199
|
+
# quality metrics or your own specification.
|
|
7200
|
+
#
|
|
7201
|
+
# DataTransformation
|
|
7202
|
+
#
|
|
7203
|
+
# : Transform datasets into the format you need, for example for model
|
|
7204
|
+
# customization.
|
|
7205
|
+
#
|
|
7206
|
+
# SyntheticDataGeneration
|
|
7207
|
+
#
|
|
7208
|
+
# : Generate synthetic training and testing datasets from your context
|
|
7209
|
+
# data and specifications.
|
|
7062
7210
|
#
|
|
7063
7211
|
# Before creating a job, call `ListJobSchemaVersions` and
|
|
7064
7212
|
# `DescribeJobSchemaVersion` to retrieve the configuration schema for
|
|
@@ -7119,7 +7267,7 @@ module Aws::SageMaker
|
|
|
7119
7267
|
# resp = client.create_job({
|
|
7120
7268
|
# job_name: "JobName", # required
|
|
7121
7269
|
# role_arn: "RoleArn", # required
|
|
7122
|
-
# job_category: "AgentRFT", # required, accepts AgentRFT, AgentRFTEvaluation
|
|
7270
|
+
# job_category: "AgentRFT", # required, accepts AgentRFT, SyntheticDataGeneration, DataQualityEvaluation, AgentRFTEvaluation, DataTransformation
|
|
7123
7271
|
# job_config_schema_version: "JobSchemaVersion", # required
|
|
7124
7272
|
# job_config_document: "JobConfigDocument", # required
|
|
7125
7273
|
# tags: [
|
|
@@ -13184,6 +13332,42 @@ module Aws::SageMaker
|
|
|
13184
13332
|
req.send_request(options)
|
|
13185
13333
|
end
|
|
13186
13334
|
|
|
13335
|
+
# Deletes the resource-based policy that is attached to an endpoint.
|
|
13336
|
+
# After you delete the policy, other accounts can no longer send
|
|
13337
|
+
# requests to the endpoint through an inference router. The endpoint
|
|
13338
|
+
# continues to serve requests from your account. If the endpoint
|
|
13339
|
+
# doesn't have a policy, the operation succeeds.
|
|
13340
|
+
#
|
|
13341
|
+
# The change typically takes effect within 30 seconds, and can take up
|
|
13342
|
+
# to 5 minutes. To revoke access for one account only, use
|
|
13343
|
+
# [PutEndpointPolicy][1] to replace the policy with one that doesn't
|
|
13344
|
+
# include that account.
|
|
13345
|
+
#
|
|
13346
|
+
#
|
|
13347
|
+
#
|
|
13348
|
+
# [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_PutEndpointPolicy.html
|
|
13349
|
+
#
|
|
13350
|
+
# @option params [required, String] :endpoint_name
|
|
13351
|
+
# The name of the endpoint. The endpoint must be in your account and in
|
|
13352
|
+
# the current Amazon Web Services Region.
|
|
13353
|
+
#
|
|
13354
|
+
# @return [Struct] Returns an empty {Seahorse::Client::Response response}.
|
|
13355
|
+
#
|
|
13356
|
+
# @example Request syntax with placeholder values
|
|
13357
|
+
#
|
|
13358
|
+
# resp = client.delete_endpoint_policy({
|
|
13359
|
+
# endpoint_name: "EndpointName", # required
|
|
13360
|
+
# })
|
|
13361
|
+
#
|
|
13362
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DeleteEndpointPolicy AWS API Documentation
|
|
13363
|
+
#
|
|
13364
|
+
# @overload delete_endpoint_policy(params = {})
|
|
13365
|
+
# @param [Hash] params ({})
|
|
13366
|
+
def delete_endpoint_policy(params = {}, options = {})
|
|
13367
|
+
req = build_request(:delete_endpoint_policy, params)
|
|
13368
|
+
req.send_request(options)
|
|
13369
|
+
end
|
|
13370
|
+
|
|
13187
13371
|
# Deletes an SageMaker experiment. All trials associated with the
|
|
13188
13372
|
# experiment must be deleted first. Use the [ListTrials][1] API to get a
|
|
13189
13373
|
# list of the trials associated with the experiment.
|
|
@@ -13529,6 +13713,32 @@ module Aws::SageMaker
|
|
|
13529
13713
|
req.send_request(options)
|
|
13530
13714
|
end
|
|
13531
13715
|
|
|
13716
|
+
# Deletes an inference router. The endpoints and inference components
|
|
13717
|
+
# that the router sends requests to aren't deleted.
|
|
13718
|
+
#
|
|
13719
|
+
# If the router is being created, updated, or deleted, you get a
|
|
13720
|
+
# `ConflictException`.
|
|
13721
|
+
#
|
|
13722
|
+
# @option params [required, String] :inference_router_name
|
|
13723
|
+
# The name of the inference router to delete.
|
|
13724
|
+
#
|
|
13725
|
+
# @return [Struct] Returns an empty {Seahorse::Client::Response response}.
|
|
13726
|
+
#
|
|
13727
|
+
# @example Request syntax with placeholder values
|
|
13728
|
+
#
|
|
13729
|
+
# resp = client.delete_inference_router({
|
|
13730
|
+
# inference_router_name: "InferenceRouterName", # required
|
|
13731
|
+
# })
|
|
13732
|
+
#
|
|
13733
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DeleteInferenceRouter AWS API Documentation
|
|
13734
|
+
#
|
|
13735
|
+
# @overload delete_inference_router(params = {})
|
|
13736
|
+
# @param [Hash] params ({})
|
|
13737
|
+
def delete_inference_router(params = {}, options = {})
|
|
13738
|
+
req = build_request(:delete_inference_router, params)
|
|
13739
|
+
req.send_request(options)
|
|
13740
|
+
end
|
|
13741
|
+
|
|
13532
13742
|
# Deletes a job. This operation is idempotent. If the job is currently
|
|
13533
13743
|
# running, you must stop it before deleting it by calling `StopJob`.
|
|
13534
13744
|
#
|
|
@@ -13552,7 +13762,7 @@ module Aws::SageMaker
|
|
|
13552
13762
|
#
|
|
13553
13763
|
# resp = client.delete_job({
|
|
13554
13764
|
# job_name: "JobName", # required
|
|
13555
|
-
# job_category: "AgentRFT", # required, accepts AgentRFT, AgentRFTEvaluation
|
|
13765
|
+
# job_category: "AgentRFT", # required, accepts AgentRFT, SyntheticDataGeneration, DataQualityEvaluation, AgentRFTEvaluation, DataTransformation
|
|
13556
13766
|
# })
|
|
13557
13767
|
#
|
|
13558
13768
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DeleteJob AWS API Documentation
|
|
@@ -16878,6 +17088,7 @@ module Aws::SageMaker
|
|
|
16878
17088
|
# * {Types::DescribeEndpointOutput#explainer_config #explainer_config} => Types::ExplainerConfig
|
|
16879
17089
|
# * {Types::DescribeEndpointOutput#shadow_production_variants #shadow_production_variants} => Array<Types::ProductionVariantSummary>
|
|
16880
17090
|
# * {Types::DescribeEndpointOutput#metrics_config #metrics_config} => Types::MetricsConfig
|
|
17091
|
+
# * {Types::DescribeEndpointOutput#cross_region_traffic_config #cross_region_traffic_config} => Types::CrossRegionTrafficConfig
|
|
16881
17092
|
#
|
|
16882
17093
|
# @example Request syntax with placeholder values
|
|
16883
17094
|
#
|
|
@@ -16919,7 +17130,7 @@ module Aws::SageMaker
|
|
|
16919
17130
|
# resp.production_variants[0].managed_instance_scaling.scale_in_policy.strategy #=> String, one of "IDLE_RELEASE", "CONSOLIDATION"
|
|
16920
17131
|
# resp.production_variants[0].managed_instance_scaling.scale_in_policy.maximum_step_size #=> Integer
|
|
16921
17132
|
# resp.production_variants[0].managed_instance_scaling.scale_in_policy.cooldown_in_minutes #=> Integer
|
|
16922
|
-
# resp.production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE"
|
|
17133
|
+
# resp.production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE", "KV_AWARE"
|
|
16923
17134
|
# resp.production_variants[0].routing_config.prefix_aware_routing_config.prefix_length #=> Integer
|
|
16924
17135
|
# resp.production_variants[0].routing_config.prefix_aware_routing_config.concurrency_threshold #=> Integer
|
|
16925
17136
|
# resp.production_variants[0].capacity_reservation_config.ml_reservation_arn #=> String
|
|
@@ -17000,7 +17211,7 @@ module Aws::SageMaker
|
|
|
17000
17211
|
# resp.pending_deployment_summary.production_variants[0].managed_instance_scaling.scale_in_policy.strategy #=> String, one of "IDLE_RELEASE", "CONSOLIDATION"
|
|
17001
17212
|
# resp.pending_deployment_summary.production_variants[0].managed_instance_scaling.scale_in_policy.maximum_step_size #=> Integer
|
|
17002
17213
|
# resp.pending_deployment_summary.production_variants[0].managed_instance_scaling.scale_in_policy.cooldown_in_minutes #=> Integer
|
|
17003
|
-
# resp.pending_deployment_summary.production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE"
|
|
17214
|
+
# resp.pending_deployment_summary.production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE", "KV_AWARE"
|
|
17004
17215
|
# resp.pending_deployment_summary.production_variants[0].routing_config.prefix_aware_routing_config.prefix_length #=> Integer
|
|
17005
17216
|
# resp.pending_deployment_summary.production_variants[0].routing_config.prefix_aware_routing_config.concurrency_threshold #=> Integer
|
|
17006
17217
|
# resp.pending_deployment_summary.production_variants[0].accelerator_partition_layouts #=> Array
|
|
@@ -17038,7 +17249,7 @@ module Aws::SageMaker
|
|
|
17038
17249
|
# resp.pending_deployment_summary.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.strategy #=> String, one of "IDLE_RELEASE", "CONSOLIDATION"
|
|
17039
17250
|
# resp.pending_deployment_summary.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.maximum_step_size #=> Integer
|
|
17040
17251
|
# resp.pending_deployment_summary.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.cooldown_in_minutes #=> Integer
|
|
17041
|
-
# resp.pending_deployment_summary.shadow_production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE"
|
|
17252
|
+
# resp.pending_deployment_summary.shadow_production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE", "KV_AWARE"
|
|
17042
17253
|
# resp.pending_deployment_summary.shadow_production_variants[0].routing_config.prefix_aware_routing_config.prefix_length #=> Integer
|
|
17043
17254
|
# resp.pending_deployment_summary.shadow_production_variants[0].routing_config.prefix_aware_routing_config.concurrency_threshold #=> Integer
|
|
17044
17255
|
# resp.pending_deployment_summary.shadow_production_variants[0].accelerator_partition_layouts #=> Array
|
|
@@ -17096,7 +17307,7 @@ module Aws::SageMaker
|
|
|
17096
17307
|
# resp.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.strategy #=> String, one of "IDLE_RELEASE", "CONSOLIDATION"
|
|
17097
17308
|
# resp.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.maximum_step_size #=> Integer
|
|
17098
17309
|
# resp.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.cooldown_in_minutes #=> Integer
|
|
17099
|
-
# resp.shadow_production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE"
|
|
17310
|
+
# resp.shadow_production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE", "KV_AWARE"
|
|
17100
17311
|
# resp.shadow_production_variants[0].routing_config.prefix_aware_routing_config.prefix_length #=> Integer
|
|
17101
17312
|
# resp.shadow_production_variants[0].routing_config.prefix_aware_routing_config.concurrency_threshold #=> Integer
|
|
17102
17313
|
# resp.shadow_production_variants[0].capacity_reservation_config.ml_reservation_arn #=> String
|
|
@@ -17115,6 +17326,8 @@ module Aws::SageMaker
|
|
|
17115
17326
|
# resp.metrics_config.enable_enhanced_metrics #=> Boolean
|
|
17116
17327
|
# resp.metrics_config.enable_detailed_observability #=> Boolean
|
|
17117
17328
|
# resp.metrics_config.metric_publish_frequency_in_seconds #=> Integer
|
|
17329
|
+
# resp.cross_region_traffic_config.max_invocations_per_second_per_instance #=> Integer
|
|
17330
|
+
# resp.cross_region_traffic_config.max_cross_region_percent_per_endpoint #=> Integer
|
|
17118
17331
|
#
|
|
17119
17332
|
#
|
|
17120
17333
|
# The following waiters are defined for this operation (see {Client#wait_until} for detailed usage):
|
|
@@ -17152,6 +17365,7 @@ module Aws::SageMaker
|
|
|
17152
17365
|
# * {Types::DescribeEndpointConfigOutput#vpc_config #vpc_config} => Types::VpcConfig
|
|
17153
17366
|
# * {Types::DescribeEndpointConfigOutput#enable_network_isolation #enable_network_isolation} => Boolean
|
|
17154
17367
|
# * {Types::DescribeEndpointConfigOutput#metrics_config #metrics_config} => Types::MetricsConfig
|
|
17368
|
+
# * {Types::DescribeEndpointConfigOutput#cross_region_traffic_config #cross_region_traffic_config} => Types::CrossRegionTrafficConfig
|
|
17155
17369
|
#
|
|
17156
17370
|
# @example Request syntax with placeholder values
|
|
17157
17371
|
#
|
|
@@ -17190,7 +17404,7 @@ module Aws::SageMaker
|
|
|
17190
17404
|
# resp.production_variants[0].managed_instance_scaling.scale_in_policy.strategy #=> String, one of "IDLE_RELEASE", "CONSOLIDATION"
|
|
17191
17405
|
# resp.production_variants[0].managed_instance_scaling.scale_in_policy.maximum_step_size #=> Integer
|
|
17192
17406
|
# resp.production_variants[0].managed_instance_scaling.scale_in_policy.cooldown_in_minutes #=> Integer
|
|
17193
|
-
# resp.production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE"
|
|
17407
|
+
# resp.production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE", "KV_AWARE"
|
|
17194
17408
|
# resp.production_variants[0].routing_config.prefix_aware_routing_config.prefix_length #=> Integer
|
|
17195
17409
|
# resp.production_variants[0].routing_config.prefix_aware_routing_config.concurrency_threshold #=> Integer
|
|
17196
17410
|
# resp.production_variants[0].inference_ami_version #=> String, one of "al2-ami-sagemaker-inference-gpu-2", "al2-ami-sagemaker-inference-gpu-2-1", "al2-ami-sagemaker-inference-gpu-3-1", "al2-ami-sagemaker-inference-neuron-2", "al2023-ami-sagemaker-inference-gpu-4-1"
|
|
@@ -17269,7 +17483,7 @@ module Aws::SageMaker
|
|
|
17269
17483
|
# resp.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.strategy #=> String, one of "IDLE_RELEASE", "CONSOLIDATION"
|
|
17270
17484
|
# resp.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.maximum_step_size #=> Integer
|
|
17271
17485
|
# resp.shadow_production_variants[0].managed_instance_scaling.scale_in_policy.cooldown_in_minutes #=> Integer
|
|
17272
|
-
# resp.shadow_production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE"
|
|
17486
|
+
# resp.shadow_production_variants[0].routing_config.routing_strategy #=> String, one of "LEAST_OUTSTANDING_REQUESTS", "RANDOM", "PREFIX_AWARE", "KV_AWARE"
|
|
17273
17487
|
# resp.shadow_production_variants[0].routing_config.prefix_aware_routing_config.prefix_length #=> Integer
|
|
17274
17488
|
# resp.shadow_production_variants[0].routing_config.prefix_aware_routing_config.concurrency_threshold #=> Integer
|
|
17275
17489
|
# resp.shadow_production_variants[0].inference_ami_version #=> String, one of "al2-ami-sagemaker-inference-gpu-2", "al2-ami-sagemaker-inference-gpu-2-1", "al2-ami-sagemaker-inference-gpu-3-1", "al2-ami-sagemaker-inference-neuron-2", "al2023-ami-sagemaker-inference-gpu-4-1"
|
|
@@ -17287,6 +17501,8 @@ module Aws::SageMaker
|
|
|
17287
17501
|
# resp.metrics_config.enable_enhanced_metrics #=> Boolean
|
|
17288
17502
|
# resp.metrics_config.enable_detailed_observability #=> Boolean
|
|
17289
17503
|
# resp.metrics_config.metric_publish_frequency_in_seconds #=> Integer
|
|
17504
|
+
# resp.cross_region_traffic_config.max_invocations_per_second_per_instance #=> Integer
|
|
17505
|
+
# resp.cross_region_traffic_config.max_cross_region_percent_per_endpoint #=> Integer
|
|
17290
17506
|
#
|
|
17291
17507
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeEndpointConfig AWS API Documentation
|
|
17292
17508
|
#
|
|
@@ -18505,6 +18721,67 @@ module Aws::SageMaker
|
|
|
18505
18721
|
req.send_request(options)
|
|
18506
18722
|
end
|
|
18507
18723
|
|
|
18724
|
+
# Returns information about an inference router, including the routing
|
|
18725
|
+
# status of each destination.
|
|
18726
|
+
#
|
|
18727
|
+
# SageMaker AI checks each destination with your permissions when you
|
|
18728
|
+
# call this operation, so callers with different permissions can see a
|
|
18729
|
+
# different `RoutingStatus`. To get the router's tags, use
|
|
18730
|
+
# [ListTags][1].
|
|
18731
|
+
#
|
|
18732
|
+
#
|
|
18733
|
+
#
|
|
18734
|
+
# [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_ListTags.html
|
|
18735
|
+
#
|
|
18736
|
+
# @option params [required, String] :inference_router_name
|
|
18737
|
+
# The name of the inference router to describe.
|
|
18738
|
+
#
|
|
18739
|
+
# @return [Types::DescribeInferenceRouterOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
|
18740
|
+
#
|
|
18741
|
+
# * {Types::DescribeInferenceRouterOutput#inference_router_name #inference_router_name} => String
|
|
18742
|
+
# * {Types::DescribeInferenceRouterOutput#inference_router_arn #inference_router_arn} => String
|
|
18743
|
+
# * {Types::DescribeInferenceRouterOutput#routing_targets #routing_targets} => Array<Types::RoutingTarget>
|
|
18744
|
+
# * {Types::DescribeInferenceRouterOutput#status #status} => String
|
|
18745
|
+
# * {Types::DescribeInferenceRouterOutput#status_reason #status_reason} => String
|
|
18746
|
+
# * {Types::DescribeInferenceRouterOutput#creation_time #creation_time} => Time
|
|
18747
|
+
# * {Types::DescribeInferenceRouterOutput#last_modified_time #last_modified_time} => Time
|
|
18748
|
+
#
|
|
18749
|
+
# @example Request syntax with placeholder values
|
|
18750
|
+
#
|
|
18751
|
+
# resp = client.describe_inference_router({
|
|
18752
|
+
# inference_router_name: "InferenceRouterName", # required
|
|
18753
|
+
# })
|
|
18754
|
+
#
|
|
18755
|
+
# @example Response structure
|
|
18756
|
+
#
|
|
18757
|
+
# resp.inference_router_name #=> String
|
|
18758
|
+
# resp.inference_router_arn #=> String
|
|
18759
|
+
# resp.routing_targets #=> Array
|
|
18760
|
+
# resp.routing_targets[0].name #=> String
|
|
18761
|
+
# resp.routing_targets[0].destinations #=> Array
|
|
18762
|
+
# resp.routing_targets[0].destinations[0].resource_arn #=> String
|
|
18763
|
+
# resp.routing_targets[0].destinations[0].routing_status #=> String, one of "Routable", "Unroutable", "Unknown"
|
|
18764
|
+
# resp.routing_targets[0].async_inference_config.output_config.s3_output_path #=> String
|
|
18765
|
+
# resp.routing_targets[0].async_inference_config.output_config.s3_failure_path #=> String
|
|
18766
|
+
# resp.routing_targets[0].async_inference_config.output_config.kms_key_id #=> String
|
|
18767
|
+
# resp.routing_targets[0].async_inference_config.output_config.notification_config.success_topic #=> String
|
|
18768
|
+
# resp.routing_targets[0].async_inference_config.output_config.notification_config.error_topic #=> String
|
|
18769
|
+
# resp.routing_targets[0].async_inference_config.client_config.max_time_in_backlog_seconds #=> Integer
|
|
18770
|
+
# resp.routing_targets[0].routing_preference #=> String, one of "LocalRegionFirst", "InstancePoolOrder"
|
|
18771
|
+
# resp.status #=> String, one of "InService", "Creating", "Updating", "Failed", "Deleting"
|
|
18772
|
+
# resp.status_reason #=> String
|
|
18773
|
+
# resp.creation_time #=> Time
|
|
18774
|
+
# resp.last_modified_time #=> Time
|
|
18775
|
+
#
|
|
18776
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeInferenceRouter AWS API Documentation
|
|
18777
|
+
#
|
|
18778
|
+
# @overload describe_inference_router(params = {})
|
|
18779
|
+
# @param [Hash] params ({})
|
|
18780
|
+
def describe_inference_router(params = {}, options = {})
|
|
18781
|
+
req = build_request(:describe_inference_router, params)
|
|
18782
|
+
req.send_request(options)
|
|
18783
|
+
end
|
|
18784
|
+
|
|
18508
18785
|
# Returns detailed information about a job, including its current
|
|
18509
18786
|
# status, secondary status, configuration, and timestamps. Use
|
|
18510
18787
|
# `SecondaryStatus` for granular progress tracking and
|
|
@@ -18548,7 +18825,7 @@ module Aws::SageMaker
|
|
|
18548
18825
|
#
|
|
18549
18826
|
# resp = client.describe_job({
|
|
18550
18827
|
# job_name: "JobName", # required
|
|
18551
|
-
# job_category: "AgentRFT", # required, accepts AgentRFT, AgentRFTEvaluation
|
|
18828
|
+
# job_category: "AgentRFT", # required, accepts AgentRFT, SyntheticDataGeneration, DataQualityEvaluation, AgentRFTEvaluation, DataTransformation
|
|
18552
18829
|
# })
|
|
18553
18830
|
#
|
|
18554
18831
|
# @example Response structure
|
|
@@ -18556,16 +18833,16 @@ module Aws::SageMaker
|
|
|
18556
18833
|
# resp.job_name #=> String
|
|
18557
18834
|
# resp.job_arn #=> String
|
|
18558
18835
|
# resp.role_arn #=> String
|
|
18559
|
-
# resp.job_category #=> String, one of "AgentRFT", "AgentRFTEvaluation"
|
|
18836
|
+
# resp.job_category #=> String, one of "AgentRFT", "SyntheticDataGeneration", "DataQualityEvaluation", "AgentRFTEvaluation", "DataTransformation"
|
|
18560
18837
|
# resp.job_config_schema_version #=> String
|
|
18561
18838
|
# resp.job_config_document #=> String
|
|
18562
18839
|
# resp.creation_time #=> Time
|
|
18563
18840
|
# resp.last_modified_time #=> Time
|
|
18564
18841
|
# resp.end_time #=> Time
|
|
18565
18842
|
# resp.job_status #=> String, one of "InProgress", "Completed", "Failed", "Stopping", "Stopped", "Deleting", "DeleteFailed"
|
|
18566
|
-
# resp.secondary_status #=> String, one of "Starting", "Downloading", "Training", "Uploading", "Stopping", "Stopped", "MaxRuntimeExceeded", "Interrupted", "Failed", "Completed", "Restarting", "Pending", "Evaluating", "Deleting", "DeleteFailed"
|
|
18843
|
+
# resp.secondary_status #=> String, one of "Starting", "Downloading", "Training", "Uploading", "Stopping", "Stopped", "MaxRuntimeExceeded", "Interrupted", "Failed", "Completed", "Restarting", "Pending", "Generating", "PartialGeneration", "Evaluating", "Validating", "Preparing", "Executing", "Publishing", "Finalizing", "Transforming", "Deleting", "DeleteFailed"
|
|
18567
18844
|
# resp.secondary_status_transitions #=> Array
|
|
18568
|
-
# resp.secondary_status_transitions[0].status #=> String, one of "Starting", "Downloading", "Training", "Uploading", "Stopping", "Stopped", "MaxRuntimeExceeded", "Interrupted", "Failed", "Completed", "Restarting", "Pending", "Evaluating", "Deleting", "DeleteFailed"
|
|
18845
|
+
# resp.secondary_status_transitions[0].status #=> String, one of "Starting", "Downloading", "Training", "Uploading", "Stopping", "Stopped", "MaxRuntimeExceeded", "Interrupted", "Failed", "Completed", "Restarting", "Pending", "Generating", "PartialGeneration", "Evaluating", "Validating", "Preparing", "Executing", "Publishing", "Finalizing", "Transforming", "Deleting", "DeleteFailed"
|
|
18569
18846
|
# resp.secondary_status_transitions[0].start_time #=> Time
|
|
18570
18847
|
# resp.secondary_status_transitions[0].end_time #=> Time
|
|
18571
18848
|
# resp.secondary_status_transitions[0].status_message #=> String
|
|
@@ -18611,13 +18888,13 @@ module Aws::SageMaker
|
|
|
18611
18888
|
# @example Request syntax with placeholder values
|
|
18612
18889
|
#
|
|
18613
18890
|
# resp = client.describe_job_schema_version({
|
|
18614
|
-
# job_category: "AgentRFT", # required, accepts AgentRFT, AgentRFTEvaluation
|
|
18891
|
+
# job_category: "AgentRFT", # required, accepts AgentRFT, SyntheticDataGeneration, DataQualityEvaluation, AgentRFTEvaluation, DataTransformation
|
|
18615
18892
|
# job_config_schema_version: "JobSchemaVersion",
|
|
18616
18893
|
# })
|
|
18617
18894
|
#
|
|
18618
18895
|
# @example Response structure
|
|
18619
18896
|
#
|
|
18620
|
-
# resp.job_category #=> String, one of "AgentRFT", "AgentRFTEvaluation"
|
|
18897
|
+
# resp.job_category #=> String, one of "AgentRFT", "SyntheticDataGeneration", "DataQualityEvaluation", "AgentRFTEvaluation", "DataTransformation"
|
|
18621
18898
|
# resp.job_config_schema_version #=> String
|
|
18622
18899
|
# resp.job_config_schema #=> String
|
|
18623
18900
|
#
|
|
@@ -22100,6 +22377,40 @@ module Aws::SageMaker
|
|
|
22100
22377
|
req.send_request(options)
|
|
22101
22378
|
end
|
|
22102
22379
|
|
|
22380
|
+
# Returns the resource-based policy that is attached to an endpoint. If
|
|
22381
|
+
# the endpoint doesn't have a policy, you get a `ValidationException`.
|
|
22382
|
+
#
|
|
22383
|
+
# @option params [required, String] :endpoint_name
|
|
22384
|
+
# The name of the endpoint. The endpoint must be in your account and in
|
|
22385
|
+
# the current Amazon Web Services Region.
|
|
22386
|
+
#
|
|
22387
|
+
# @return [Types::GetEndpointPolicyResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
|
22388
|
+
#
|
|
22389
|
+
# * {Types::GetEndpointPolicyResponse#endpoint_name #endpoint_name} => String
|
|
22390
|
+
# * {Types::GetEndpointPolicyResponse#endpoint_arn #endpoint_arn} => String
|
|
22391
|
+
# * {Types::GetEndpointPolicyResponse#resource_policy #resource_policy} => String
|
|
22392
|
+
#
|
|
22393
|
+
# @example Request syntax with placeholder values
|
|
22394
|
+
#
|
|
22395
|
+
# resp = client.get_endpoint_policy({
|
|
22396
|
+
# endpoint_name: "EndpointName", # required
|
|
22397
|
+
# })
|
|
22398
|
+
#
|
|
22399
|
+
# @example Response structure
|
|
22400
|
+
#
|
|
22401
|
+
# resp.endpoint_name #=> String
|
|
22402
|
+
# resp.endpoint_arn #=> String
|
|
22403
|
+
# resp.resource_policy #=> String
|
|
22404
|
+
#
|
|
22405
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/GetEndpointPolicy AWS API Documentation
|
|
22406
|
+
#
|
|
22407
|
+
# @overload get_endpoint_policy(params = {})
|
|
22408
|
+
# @param [Hash] params ({})
|
|
22409
|
+
def get_endpoint_policy(params = {}, options = {})
|
|
22410
|
+
req = build_request(:get_endpoint_policy, params)
|
|
22411
|
+
req.send_request(options)
|
|
22412
|
+
end
|
|
22413
|
+
|
|
22103
22414
|
# The resource policy for the lineage group.
|
|
22104
22415
|
#
|
|
22105
22416
|
# @option params [required, String] :lineage_group_name
|
|
@@ -25985,6 +26296,49 @@ module Aws::SageMaker
|
|
|
25985
26296
|
req.send_request(options)
|
|
25986
26297
|
end
|
|
25987
26298
|
|
|
26299
|
+
# Lists the inference routers in your account in the current Amazon Web
|
|
26300
|
+
# Services Region. A router that you just created might not appear in
|
|
26301
|
+
# the list right away.
|
|
26302
|
+
#
|
|
26303
|
+
# @option params [Integer] :max_results
|
|
26304
|
+
# The maximum number of inference routers to return in the response.
|
|
26305
|
+
#
|
|
26306
|
+
# @option params [String] :next_token
|
|
26307
|
+
# If the previous response was truncated, you receive this token. To get
|
|
26308
|
+
# the next set of inference routers, use it in your next request.
|
|
26309
|
+
#
|
|
26310
|
+
# @return [Types::ListInferenceRoutersOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
|
26311
|
+
#
|
|
26312
|
+
# * {Types::ListInferenceRoutersOutput#inference_routers #inference_routers} => Array<Types::InferenceRouterSummary>
|
|
26313
|
+
# * {Types::ListInferenceRoutersOutput#next_token #next_token} => String
|
|
26314
|
+
#
|
|
26315
|
+
# The returned {Seahorse::Client::Response response} is a pageable response and is Enumerable. For details on usage see {Aws::PageableResponse PageableResponse}.
|
|
26316
|
+
#
|
|
26317
|
+
# @example Request syntax with placeholder values
|
|
26318
|
+
#
|
|
26319
|
+
# resp = client.list_inference_routers({
|
|
26320
|
+
# max_results: 1,
|
|
26321
|
+
# next_token: "NextToken",
|
|
26322
|
+
# })
|
|
26323
|
+
#
|
|
26324
|
+
# @example Response structure
|
|
26325
|
+
#
|
|
26326
|
+
# resp.inference_routers #=> Array
|
|
26327
|
+
# resp.inference_routers[0].inference_router_name #=> String
|
|
26328
|
+
# resp.inference_routers[0].inference_router_arn #=> String
|
|
26329
|
+
# resp.inference_routers[0].creation_time #=> Time
|
|
26330
|
+
# resp.inference_routers[0].last_modified_time #=> Time
|
|
26331
|
+
# resp.next_token #=> String
|
|
26332
|
+
#
|
|
26333
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/ListInferenceRouters AWS API Documentation
|
|
26334
|
+
#
|
|
26335
|
+
# @overload list_inference_routers(params = {})
|
|
26336
|
+
# @param [Hash] params ({})
|
|
26337
|
+
def list_inference_routers(params = {}, options = {})
|
|
26338
|
+
req = build_request(:list_inference_routers, params)
|
|
26339
|
+
req.send_request(options)
|
|
26340
|
+
end
|
|
26341
|
+
|
|
25988
26342
|
# Lists available configuration schema versions for a specified job
|
|
25989
26343
|
# category. Use the schema versions with `DescribeJobSchemaVersion` to
|
|
25990
26344
|
# retrieve the full schema document.
|
|
@@ -26016,7 +26370,7 @@ module Aws::SageMaker
|
|
|
26016
26370
|
# @example Request syntax with placeholder values
|
|
26017
26371
|
#
|
|
26018
26372
|
# resp = client.list_job_schema_versions({
|
|
26019
|
-
# job_category: "AgentRFT", # required, accepts AgentRFT, AgentRFTEvaluation
|
|
26373
|
+
# job_category: "AgentRFT", # required, accepts AgentRFT, SyntheticDataGeneration, DataQualityEvaluation, AgentRFTEvaluation, DataTransformation
|
|
26020
26374
|
# next_token: "NextToken",
|
|
26021
26375
|
# max_results: 1,
|
|
26022
26376
|
# })
|
|
@@ -26094,7 +26448,7 @@ module Aws::SageMaker
|
|
|
26094
26448
|
# @example Request syntax with placeholder values
|
|
26095
26449
|
#
|
|
26096
26450
|
# resp = client.list_jobs({
|
|
26097
|
-
# job_category: "AgentRFT", # required, accepts AgentRFT, AgentRFTEvaluation
|
|
26451
|
+
# job_category: "AgentRFT", # required, accepts AgentRFT, SyntheticDataGeneration, DataQualityEvaluation, AgentRFTEvaluation, DataTransformation
|
|
26098
26452
|
# next_token: "NextToken",
|
|
26099
26453
|
# max_results: 1,
|
|
26100
26454
|
# creation_time_after: Time.now,
|
|
@@ -26113,9 +26467,9 @@ module Aws::SageMaker
|
|
|
26113
26467
|
# resp.job_summaries #=> Array
|
|
26114
26468
|
# resp.job_summaries[0].job_arn #=> String
|
|
26115
26469
|
# resp.job_summaries[0].job_name #=> String
|
|
26116
|
-
# resp.job_summaries[0].job_category #=> String, one of "AgentRFT", "AgentRFTEvaluation"
|
|
26470
|
+
# resp.job_summaries[0].job_category #=> String, one of "AgentRFT", "SyntheticDataGeneration", "DataQualityEvaluation", "AgentRFTEvaluation", "DataTransformation"
|
|
26117
26471
|
# resp.job_summaries[0].job_status #=> String, one of "InProgress", "Completed", "Failed", "Stopping", "Stopped", "Deleting", "DeleteFailed"
|
|
26118
|
-
# resp.job_summaries[0].job_secondary_status #=> String, one of "Starting", "Downloading", "Training", "Uploading", "Stopping", "Stopped", "MaxRuntimeExceeded", "Interrupted", "Failed", "Completed", "Restarting", "Pending", "Evaluating", "Deleting", "DeleteFailed"
|
|
26472
|
+
# resp.job_summaries[0].job_secondary_status #=> String, one of "Starting", "Downloading", "Training", "Uploading", "Stopping", "Stopped", "MaxRuntimeExceeded", "Interrupted", "Failed", "Completed", "Restarting", "Pending", "Generating", "PartialGeneration", "Evaluating", "Validating", "Preparing", "Executing", "Publishing", "Finalizing", "Transforming", "Deleting", "DeleteFailed"
|
|
26119
26473
|
# resp.job_summaries[0].creation_time #=> Time
|
|
26120
26474
|
# resp.job_summaries[0].last_modified_time #=> Time
|
|
26121
26475
|
# resp.job_summaries[0].end_time #=> Time
|
|
@@ -29763,6 +30117,62 @@ module Aws::SageMaker
|
|
|
29763
30117
|
req.send_request(options)
|
|
29764
30118
|
end
|
|
29765
30119
|
|
|
30120
|
+
# Attaches a resource-based policy to an endpoint. With an endpoint
|
|
30121
|
+
# policy, you can allow other Amazon Web Services accounts to send
|
|
30122
|
+
# requests to your endpoint, or to inference components on it, through
|
|
30123
|
+
# an inference router. The policy that you specify replaces the
|
|
30124
|
+
# endpoint's existing policy, if it has one.
|
|
30125
|
+
#
|
|
30126
|
+
# You can't attach a policy to an endpoint whose status is `Deleting`
|
|
30127
|
+
# or `Failed`. SageMaker AI rejects a policy that doesn't follow the
|
|
30128
|
+
# endpoint policy rules. For information about the policy rules, see
|
|
30129
|
+
# [Use destinations in other accounts][1].
|
|
30130
|
+
#
|
|
30131
|
+
# Policy changes typically take effect within 30 seconds, and can take
|
|
30132
|
+
# up to 5 minutes. If you delete the endpoint, its policy is also
|
|
30133
|
+
# deleted, and a new endpoint with the same name has no policy.
|
|
30134
|
+
#
|
|
30135
|
+
#
|
|
30136
|
+
#
|
|
30137
|
+
# [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/inference-router-cross-account.html
|
|
30138
|
+
#
|
|
30139
|
+
# @option params [required, String] :endpoint_name
|
|
30140
|
+
# The name of the endpoint. The endpoint must be in your account and in
|
|
30141
|
+
# the current Amazon Web Services Region.
|
|
30142
|
+
#
|
|
30143
|
+
# @option params [required, String] :resource_policy
|
|
30144
|
+
# The endpoint policy, as a JSON policy document. The policy can contain
|
|
30145
|
+
# only ASCII characters. For information about the policy rules, see
|
|
30146
|
+
# [Use destinations in other accounts][1].
|
|
30147
|
+
#
|
|
30148
|
+
#
|
|
30149
|
+
#
|
|
30150
|
+
# [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/inference-router-cross-account.html
|
|
30151
|
+
#
|
|
30152
|
+
# @return [Types::PutEndpointPolicyResponse] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
|
30153
|
+
#
|
|
30154
|
+
# * {Types::PutEndpointPolicyResponse#endpoint_arn #endpoint_arn} => String
|
|
30155
|
+
#
|
|
30156
|
+
# @example Request syntax with placeholder values
|
|
30157
|
+
#
|
|
30158
|
+
# resp = client.put_endpoint_policy({
|
|
30159
|
+
# endpoint_name: "EndpointName", # required
|
|
30160
|
+
# resource_policy: "EndpointPolicyDocument", # required
|
|
30161
|
+
# })
|
|
30162
|
+
#
|
|
30163
|
+
# @example Response structure
|
|
30164
|
+
#
|
|
30165
|
+
# resp.endpoint_arn #=> String
|
|
30166
|
+
#
|
|
30167
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/PutEndpointPolicy AWS API Documentation
|
|
30168
|
+
#
|
|
30169
|
+
# @overload put_endpoint_policy(params = {})
|
|
30170
|
+
# @param [Hash] params ({})
|
|
30171
|
+
def put_endpoint_policy(params = {}, options = {})
|
|
30172
|
+
req = build_request(:put_endpoint_policy, params)
|
|
30173
|
+
req.send_request(options)
|
|
30174
|
+
end
|
|
30175
|
+
|
|
29766
30176
|
# Adds a resouce policy to control access to a model group. For
|
|
29767
30177
|
# information about resoure policies, see [Identity-based policies and
|
|
29768
30178
|
# resource-based policies][1] in the *Amazon Web Services Identity and
|
|
@@ -31023,7 +31433,7 @@ module Aws::SageMaker
|
|
|
31023
31433
|
#
|
|
31024
31434
|
# resp = client.stop_job({
|
|
31025
31435
|
# job_name: "JobName", # required
|
|
31026
|
-
# job_category: "AgentRFT", # required, accepts AgentRFT, AgentRFTEvaluation
|
|
31436
|
+
# job_category: "AgentRFT", # required, accepts AgentRFT, SyntheticDataGeneration, DataQualityEvaluation, AgentRFTEvaluation, DataTransformation
|
|
31027
31437
|
# })
|
|
31028
31438
|
#
|
|
31029
31439
|
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/StopJob AWS API Documentation
|
|
@@ -33707,6 +34117,80 @@ module Aws::SageMaker
|
|
|
33707
34117
|
req.send_request(options)
|
|
33708
34118
|
end
|
|
33709
34119
|
|
|
34120
|
+
# Updates the routing targets of an inference router. The routing
|
|
34121
|
+
# targets that you specify replace all of the router's existing routing
|
|
34122
|
+
# targets. To change one routing target, call
|
|
34123
|
+
# [DescribeInferenceRouter][1], edit the routing targets, and send all
|
|
34124
|
+
# of them.
|
|
34125
|
+
#
|
|
34126
|
+
# The update is applied in full or not at all, and each request uses
|
|
34127
|
+
# either the previous configuration or the new one. Updates typically
|
|
34128
|
+
# take effect within about 2 minutes.
|
|
34129
|
+
#
|
|
34130
|
+
# If the router is being created, updated, or deleted, or another
|
|
34131
|
+
# request changes it at the same time, you get a `ConflictException`.
|
|
34132
|
+
# Describe the router, and then send your update again.
|
|
34133
|
+
#
|
|
34134
|
+
#
|
|
34135
|
+
#
|
|
34136
|
+
# [1]: https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeInferenceRouter.html
|
|
34137
|
+
#
|
|
34138
|
+
# @option params [required, String] :inference_router_name
|
|
34139
|
+
# The name of the inference router to update.
|
|
34140
|
+
#
|
|
34141
|
+
# @option params [required, Array<Types::RoutingTarget>] :routing_targets
|
|
34142
|
+
# The complete list of routing targets for the inference router. To
|
|
34143
|
+
# remove the last routing target, delete the router.
|
|
34144
|
+
#
|
|
34145
|
+
# @return [Types::UpdateInferenceRouterOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
|
|
34146
|
+
#
|
|
34147
|
+
# * {Types::UpdateInferenceRouterOutput#inference_router_arn #inference_router_arn} => String
|
|
34148
|
+
#
|
|
34149
|
+
# @example Request syntax with placeholder values
|
|
34150
|
+
#
|
|
34151
|
+
# resp = client.update_inference_router({
|
|
34152
|
+
# inference_router_name: "InferenceRouterName", # required
|
|
34153
|
+
# routing_targets: [ # required
|
|
34154
|
+
# {
|
|
34155
|
+
# name: "RoutingTargetName", # required
|
|
34156
|
+
# destinations: [ # required
|
|
34157
|
+
# {
|
|
34158
|
+
# resource_arn: "DestinationResourceArn", # required
|
|
34159
|
+
# routing_status: "Routable", # accepts Routable, Unroutable, Unknown
|
|
34160
|
+
# },
|
|
34161
|
+
# ],
|
|
34162
|
+
# async_inference_config: {
|
|
34163
|
+
# output_config: { # required
|
|
34164
|
+
# s3_output_path: "InferenceRouterS3Uri", # required
|
|
34165
|
+
# s3_failure_path: "InferenceRouterS3Uri", # required
|
|
34166
|
+
# kms_key_id: "KmsKeyId",
|
|
34167
|
+
# notification_config: {
|
|
34168
|
+
# success_topic: "InferenceRouterSnsTopicArn",
|
|
34169
|
+
# error_topic: "InferenceRouterSnsTopicArn",
|
|
34170
|
+
# },
|
|
34171
|
+
# },
|
|
34172
|
+
# client_config: {
|
|
34173
|
+
# max_time_in_backlog_seconds: 1,
|
|
34174
|
+
# },
|
|
34175
|
+
# },
|
|
34176
|
+
# routing_preference: "LocalRegionFirst", # accepts LocalRegionFirst, InstancePoolOrder
|
|
34177
|
+
# },
|
|
34178
|
+
# ],
|
|
34179
|
+
# })
|
|
34180
|
+
#
|
|
34181
|
+
# @example Response structure
|
|
34182
|
+
#
|
|
34183
|
+
# resp.inference_router_arn #=> String
|
|
34184
|
+
#
|
|
34185
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/UpdateInferenceRouter AWS API Documentation
|
|
34186
|
+
#
|
|
34187
|
+
# @overload update_inference_router(params = {})
|
|
34188
|
+
# @param [Hash] params ({})
|
|
34189
|
+
def update_inference_router(params = {}, options = {})
|
|
34190
|
+
req = build_request(:update_inference_router, params)
|
|
34191
|
+
req.send_request(options)
|
|
34192
|
+
end
|
|
34193
|
+
|
|
33710
34194
|
# Updates an MLflow App.
|
|
33711
34195
|
#
|
|
33712
34196
|
# @option params [required, String] :arn
|
|
@@ -35809,7 +36293,7 @@ module Aws::SageMaker
|
|
|
35809
36293
|
tracer: tracer
|
|
35810
36294
|
)
|
|
35811
36295
|
context[:gem_name] = 'aws-sdk-sagemaker'
|
|
35812
|
-
context[:gem_version] = '1.
|
|
36296
|
+
context[:gem_version] = '1.416.0'
|
|
35813
36297
|
Seahorse::Client::Request.new(handlers, context)
|
|
35814
36298
|
end
|
|
35815
36299
|
|