-
Notifications
You must be signed in to change notification settings - Fork 121
/
zz_endpointconfiguration_types.go
executable file
·912 lines (651 loc) · 52.7 KB
/
zz_endpointconfiguration_types.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
// SPDX-FileCopyrightText: 2024 The Crossplane Authors <https://crossplane.io>
//
// SPDX-License-Identifier: Apache-2.0
// Code generated by upjet. DO NOT EDIT.
package v1beta1
import (
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
"k8s.io/apimachinery/pkg/runtime/schema"
v1 "github.com/crossplane/crossplane-runtime/apis/common/v1"
)
type AsyncInferenceConfigInitParameters struct {
// Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.
ClientConfig []ClientConfigInitParameters `json:"clientConfig,omitempty" tf:"client_config,omitempty"`
// Specifies the configuration for asynchronous inference invocation outputs.
OutputConfig []AsyncInferenceConfigOutputConfigInitParameters `json:"outputConfig,omitempty" tf:"output_config,omitempty"`
}
type AsyncInferenceConfigObservation struct {
// Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.
ClientConfig []ClientConfigObservation `json:"clientConfig,omitempty" tf:"client_config,omitempty"`
// Specifies the configuration for asynchronous inference invocation outputs.
OutputConfig []AsyncInferenceConfigOutputConfigObservation `json:"outputConfig,omitempty" tf:"output_config,omitempty"`
}
type AsyncInferenceConfigOutputConfigInitParameters struct {
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
// Specifies the configuration for notifications of inference results for asynchronous inference.
NotificationConfig []NotificationConfigInitParameters `json:"notificationConfig,omitempty" tf:"notification_config,omitempty"`
// The Amazon S3 location to upload failure inference responses to.
S3FailurePath *string `json:"s3FailurePath,omitempty" tf:"s3_failure_path,omitempty"`
// The Amazon S3 location to upload inference responses to.
S3OutputPath *string `json:"s3OutputPath,omitempty" tf:"s3_output_path,omitempty"`
}
type AsyncInferenceConfigOutputConfigObservation struct {
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
// Specifies the configuration for notifications of inference results for asynchronous inference.
NotificationConfig []NotificationConfigObservation `json:"notificationConfig,omitempty" tf:"notification_config,omitempty"`
// The Amazon S3 location to upload failure inference responses to.
S3FailurePath *string `json:"s3FailurePath,omitempty" tf:"s3_failure_path,omitempty"`
// The Amazon S3 location to upload inference responses to.
S3OutputPath *string `json:"s3OutputPath,omitempty" tf:"s3_output_path,omitempty"`
}
type AsyncInferenceConfigOutputConfigParameters struct {
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
// +kubebuilder:validation:Optional
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
// Specifies the configuration for notifications of inference results for asynchronous inference.
// +kubebuilder:validation:Optional
NotificationConfig []NotificationConfigParameters `json:"notificationConfig,omitempty" tf:"notification_config,omitempty"`
// The Amazon S3 location to upload failure inference responses to.
// +kubebuilder:validation:Optional
S3FailurePath *string `json:"s3FailurePath,omitempty" tf:"s3_failure_path,omitempty"`
// The Amazon S3 location to upload inference responses to.
// +kubebuilder:validation:Optional
S3OutputPath *string `json:"s3OutputPath" tf:"s3_output_path,omitempty"`
}
type AsyncInferenceConfigParameters struct {
// Configures the behavior of the client used by Amazon SageMaker to interact with the model container during asynchronous inference.
// +kubebuilder:validation:Optional
ClientConfig []ClientConfigParameters `json:"clientConfig,omitempty" tf:"client_config,omitempty"`
// Specifies the configuration for asynchronous inference invocation outputs.
// +kubebuilder:validation:Optional
OutputConfig []AsyncInferenceConfigOutputConfigParameters `json:"outputConfig" tf:"output_config,omitempty"`
}
type CaptureContentTypeHeaderInitParameters struct {
// The CSV content type headers to capture.
// +listType=set
CsvContentTypes []*string `json:"csvContentTypes,omitempty" tf:"csv_content_types,omitempty"`
// The JSON content type headers to capture.
// +listType=set
JSONContentTypes []*string `json:"jsonContentTypes,omitempty" tf:"json_content_types,omitempty"`
}
type CaptureContentTypeHeaderObservation struct {
// The CSV content type headers to capture.
// +listType=set
CsvContentTypes []*string `json:"csvContentTypes,omitempty" tf:"csv_content_types,omitempty"`
// The JSON content type headers to capture.
// +listType=set
JSONContentTypes []*string `json:"jsonContentTypes,omitempty" tf:"json_content_types,omitempty"`
}
type CaptureContentTypeHeaderParameters struct {
// The CSV content type headers to capture.
// +kubebuilder:validation:Optional
// +listType=set
CsvContentTypes []*string `json:"csvContentTypes,omitempty" tf:"csv_content_types,omitempty"`
// The JSON content type headers to capture.
// +kubebuilder:validation:Optional
// +listType=set
JSONContentTypes []*string `json:"jsonContentTypes,omitempty" tf:"json_content_types,omitempty"`
}
type CaptureOptionsInitParameters struct {
// Specifies the data to be captured. Should be one of Input or Output.
CaptureMode *string `json:"captureMode,omitempty" tf:"capture_mode,omitempty"`
}
type CaptureOptionsObservation struct {
// Specifies the data to be captured. Should be one of Input or Output.
CaptureMode *string `json:"captureMode,omitempty" tf:"capture_mode,omitempty"`
}
type CaptureOptionsParameters struct {
// Specifies the data to be captured. Should be one of Input or Output.
// +kubebuilder:validation:Optional
CaptureMode *string `json:"captureMode" tf:"capture_mode,omitempty"`
}
type ClientConfigInitParameters struct {
// The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.
MaxConcurrentInvocationsPerInstance *float64 `json:"maxConcurrentInvocationsPerInstance,omitempty" tf:"max_concurrent_invocations_per_instance,omitempty"`
}
type ClientConfigObservation struct {
// The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.
MaxConcurrentInvocationsPerInstance *float64 `json:"maxConcurrentInvocationsPerInstance,omitempty" tf:"max_concurrent_invocations_per_instance,omitempty"`
}
type ClientConfigParameters struct {
// The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, Amazon SageMaker will choose an optimal value for you.
// +kubebuilder:validation:Optional
MaxConcurrentInvocationsPerInstance *float64 `json:"maxConcurrentInvocationsPerInstance,omitempty" tf:"max_concurrent_invocations_per_instance,omitempty"`
}
type CoreDumpConfigInitParameters struct {
// The Amazon S3 bucket to send the core dump to.
DestinationS3URI *string `json:"destinationS3Uri,omitempty" tf:"destination_s3_uri,omitempty"`
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type CoreDumpConfigObservation struct {
// The Amazon S3 bucket to send the core dump to.
DestinationS3URI *string `json:"destinationS3Uri,omitempty" tf:"destination_s3_uri,omitempty"`
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type CoreDumpConfigParameters struct {
// The Amazon S3 bucket to send the core dump to.
// +kubebuilder:validation:Optional
DestinationS3URI *string `json:"destinationS3Uri" tf:"destination_s3_uri,omitempty"`
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.
// +kubebuilder:validation:Optional
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type DataCaptureConfigInitParameters struct {
// The content type headers to capture. Fields are documented below.
CaptureContentTypeHeader []CaptureContentTypeHeaderInitParameters `json:"captureContentTypeHeader,omitempty" tf:"capture_content_type_header,omitempty"`
// Specifies what data to capture. Fields are documented below.
CaptureOptions []CaptureOptionsInitParameters `json:"captureOptions,omitempty" tf:"capture_options,omitempty"`
// The URL for S3 location where the captured data is stored.
DestinationS3URI *string `json:"destinationS3Uri,omitempty" tf:"destination_s3_uri,omitempty"`
// Flag to enable data capture. Defaults to false.
EnableCapture *bool `json:"enableCapture,omitempty" tf:"enable_capture,omitempty"`
// Portion of data to capture. Should be between 0 and 100.
InitialSamplingPercentage *float64 `json:"initialSamplingPercentage,omitempty" tf:"initial_sampling_percentage,omitempty"`
// Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type DataCaptureConfigObservation struct {
// The content type headers to capture. Fields are documented below.
CaptureContentTypeHeader []CaptureContentTypeHeaderObservation `json:"captureContentTypeHeader,omitempty" tf:"capture_content_type_header,omitempty"`
// Specifies what data to capture. Fields are documented below.
CaptureOptions []CaptureOptionsObservation `json:"captureOptions,omitempty" tf:"capture_options,omitempty"`
// The URL for S3 location where the captured data is stored.
DestinationS3URI *string `json:"destinationS3Uri,omitempty" tf:"destination_s3_uri,omitempty"`
// Flag to enable data capture. Defaults to false.
EnableCapture *bool `json:"enableCapture,omitempty" tf:"enable_capture,omitempty"`
// Portion of data to capture. Should be between 0 and 100.
InitialSamplingPercentage *float64 `json:"initialSamplingPercentage,omitempty" tf:"initial_sampling_percentage,omitempty"`
// Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type DataCaptureConfigParameters struct {
// The content type headers to capture. Fields are documented below.
// +kubebuilder:validation:Optional
CaptureContentTypeHeader []CaptureContentTypeHeaderParameters `json:"captureContentTypeHeader,omitempty" tf:"capture_content_type_header,omitempty"`
// Specifies what data to capture. Fields are documented below.
// +kubebuilder:validation:Optional
CaptureOptions []CaptureOptionsParameters `json:"captureOptions" tf:"capture_options,omitempty"`
// The URL for S3 location where the captured data is stored.
// +kubebuilder:validation:Optional
DestinationS3URI *string `json:"destinationS3Uri" tf:"destination_s3_uri,omitempty"`
// Flag to enable data capture. Defaults to false.
// +kubebuilder:validation:Optional
EnableCapture *bool `json:"enableCapture,omitempty" tf:"enable_capture,omitempty"`
// Portion of data to capture. Should be between 0 and 100.
// +kubebuilder:validation:Optional
InitialSamplingPercentage *float64 `json:"initialSamplingPercentage" tf:"initial_sampling_percentage,omitempty"`
// Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt the captured data on Amazon S3.
// +kubebuilder:validation:Optional
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type EndpointConfigurationInitParameters struct {
// Specifies configuration for how an endpoint performs asynchronous inference.
AsyncInferenceConfig []AsyncInferenceConfigInitParameters `json:"asyncInferenceConfig,omitempty" tf:"async_inference_config,omitempty"`
// Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.
DataCaptureConfig []DataCaptureConfigInitParameters `json:"dataCaptureConfig,omitempty" tf:"data_capture_config,omitempty"`
// Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
// +crossplane:generate:reference:type=github.com/upbound/provider-aws/apis/kms/v1beta1.Key
KMSKeyArn *string `json:"kmsKeyArn,omitempty" tf:"kms_key_arn,omitempty"`
// Reference to a Key in kms to populate kmsKeyArn.
// +kubebuilder:validation:Optional
KMSKeyArnRef *v1.Reference `json:"kmsKeyArnRef,omitempty" tf:"-"`
// Selector for a Key in kms to populate kmsKeyArn.
// +kubebuilder:validation:Optional
KMSKeyArnSelector *v1.Selector `json:"kmsKeyArnSelector,omitempty" tf:"-"`
// An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.
ProductionVariants []ProductionVariantsInitParameters `json:"productionVariants,omitempty" tf:"production_variants,omitempty"`
// Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.
ShadowProductionVariants []ShadowProductionVariantsInitParameters `json:"shadowProductionVariants,omitempty" tf:"shadow_production_variants,omitempty"`
// Key-value map of resource tags.
// +mapType=granular
Tags map[string]*string `json:"tags,omitempty" tf:"tags,omitempty"`
}
type EndpointConfigurationObservation struct {
// The Amazon Resource Name (ARN) assigned by AWS to this endpoint configuration.
Arn *string `json:"arn,omitempty" tf:"arn,omitempty"`
// Specifies configuration for how an endpoint performs asynchronous inference.
AsyncInferenceConfig []AsyncInferenceConfigObservation `json:"asyncInferenceConfig,omitempty" tf:"async_inference_config,omitempty"`
// Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.
DataCaptureConfig []DataCaptureConfigObservation `json:"dataCaptureConfig,omitempty" tf:"data_capture_config,omitempty"`
ID *string `json:"id,omitempty" tf:"id,omitempty"`
// Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
KMSKeyArn *string `json:"kmsKeyArn,omitempty" tf:"kms_key_arn,omitempty"`
// An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.
ProductionVariants []ProductionVariantsObservation `json:"productionVariants,omitempty" tf:"production_variants,omitempty"`
// Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.
ShadowProductionVariants []ShadowProductionVariantsObservation `json:"shadowProductionVariants,omitempty" tf:"shadow_production_variants,omitempty"`
// Key-value map of resource tags.
// +mapType=granular
Tags map[string]*string `json:"tags,omitempty" tf:"tags,omitempty"`
// A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.
// +mapType=granular
TagsAll map[string]*string `json:"tagsAll,omitempty" tf:"tags_all,omitempty"`
}
type EndpointConfigurationParameters struct {
// Specifies configuration for how an endpoint performs asynchronous inference.
// +kubebuilder:validation:Optional
AsyncInferenceConfig []AsyncInferenceConfigParameters `json:"asyncInferenceConfig,omitempty" tf:"async_inference_config,omitempty"`
// Specifies the parameters to capture input/output of SageMaker models endpoints. Fields are documented below.
// +kubebuilder:validation:Optional
DataCaptureConfig []DataCaptureConfigParameters `json:"dataCaptureConfig,omitempty" tf:"data_capture_config,omitempty"`
// Amazon Resource Name (ARN) of a AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
// +crossplane:generate:reference:type=github.com/upbound/provider-aws/apis/kms/v1beta1.Key
// +kubebuilder:validation:Optional
KMSKeyArn *string `json:"kmsKeyArn,omitempty" tf:"kms_key_arn,omitempty"`
// Reference to a Key in kms to populate kmsKeyArn.
// +kubebuilder:validation:Optional
KMSKeyArnRef *v1.Reference `json:"kmsKeyArnRef,omitempty" tf:"-"`
// Selector for a Key in kms to populate kmsKeyArn.
// +kubebuilder:validation:Optional
KMSKeyArnSelector *v1.Selector `json:"kmsKeyArnSelector,omitempty" tf:"-"`
// An list of ProductionVariant objects, one for each model that you want to host at this endpoint. Fields are documented below.
// +kubebuilder:validation:Optional
ProductionVariants []ProductionVariantsParameters `json:"productionVariants,omitempty" tf:"production_variants,omitempty"`
// Region is the region you'd like your resource to be created in.
// +upjet:crd:field:TFTag=-
// +kubebuilder:validation:Required
Region *string `json:"region" tf:"-"`
// Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants. Fields are documented below.
// +kubebuilder:validation:Optional
ShadowProductionVariants []ShadowProductionVariantsParameters `json:"shadowProductionVariants,omitempty" tf:"shadow_production_variants,omitempty"`
// Key-value map of resource tags.
// +kubebuilder:validation:Optional
// +mapType=granular
Tags map[string]*string `json:"tags,omitempty" tf:"tags,omitempty"`
}
type NotificationConfigInitParameters struct {
// Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.
ErrorTopic *string `json:"errorTopic,omitempty" tf:"error_topic,omitempty"`
// The Amazon SNS topics where you want the inference response to be included. Valid values are SUCCESS_NOTIFICATION_TOPIC and ERROR_NOTIFICATION_TOPIC.
// +listType=set
IncludeInferenceResponseIn []*string `json:"includeInferenceResponseIn,omitempty" tf:"include_inference_response_in,omitempty"`
// Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.
SuccessTopic *string `json:"successTopic,omitempty" tf:"success_topic,omitempty"`
}
type NotificationConfigObservation struct {
// Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.
ErrorTopic *string `json:"errorTopic,omitempty" tf:"error_topic,omitempty"`
// The Amazon SNS topics where you want the inference response to be included. Valid values are SUCCESS_NOTIFICATION_TOPIC and ERROR_NOTIFICATION_TOPIC.
// +listType=set
IncludeInferenceResponseIn []*string `json:"includeInferenceResponseIn,omitempty" tf:"include_inference_response_in,omitempty"`
// Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.
SuccessTopic *string `json:"successTopic,omitempty" tf:"success_topic,omitempty"`
}
type NotificationConfigParameters struct {
// Amazon SNS topic to post a notification to when inference fails. If no topic is provided, no notification is sent on failure.
// +kubebuilder:validation:Optional
ErrorTopic *string `json:"errorTopic,omitempty" tf:"error_topic,omitempty"`
// The Amazon SNS topics where you want the inference response to be included. Valid values are SUCCESS_NOTIFICATION_TOPIC and ERROR_NOTIFICATION_TOPIC.
// +kubebuilder:validation:Optional
// +listType=set
IncludeInferenceResponseIn []*string `json:"includeInferenceResponseIn,omitempty" tf:"include_inference_response_in,omitempty"`
// Amazon SNS topic to post a notification to when inference completes successfully. If no topic is provided, no notification is sent on success.
// +kubebuilder:validation:Optional
SuccessTopic *string `json:"successTopic,omitempty" tf:"success_topic,omitempty"`
}
type ProductionVariantsInitParameters struct {
// The size of the Elastic Inference (EI) instance to use for the production variant.
AcceleratorType *string `json:"acceleratorType,omitempty" tf:"accelerator_type,omitempty"`
// The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.
ContainerStartupHealthCheckTimeoutInSeconds *float64 `json:"containerStartupHealthCheckTimeoutInSeconds,omitempty" tf:"container_startup_health_check_timeout_in_seconds,omitempty"`
// Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.
CoreDumpConfig []CoreDumpConfigInitParameters `json:"coreDumpConfig,omitempty" tf:"core_dump_config,omitempty"`
// You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoints.
EnableSsmAccess *bool `json:"enableSsmAccess,omitempty" tf:"enable_ssm_access,omitempty"`
// Initial number of instances used for auto-scaling.
InitialInstanceCount *float64 `json:"initialInstanceCount,omitempty" tf:"initial_instance_count,omitempty"`
// Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
InitialVariantWeight *float64 `json:"initialVariantWeight,omitempty" tf:"initial_variant_weight,omitempty"`
// The type of instance to start.
InstanceType *string `json:"instanceType,omitempty" tf:"instance_type,omitempty"`
// The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.
ModelDataDownloadTimeoutInSeconds *float64 `json:"modelDataDownloadTimeoutInSeconds,omitempty" tf:"model_data_download_timeout_in_seconds,omitempty"`
// The name of the model to use.
// +crossplane:generate:reference:type=github.com/upbound/provider-aws/apis/sagemaker/v1beta1.Model
ModelName *string `json:"modelName,omitempty" tf:"model_name,omitempty"`
// Reference to a Model in sagemaker to populate modelName.
// +kubebuilder:validation:Optional
ModelNameRef *v1.Reference `json:"modelNameRef,omitempty" tf:"-"`
// Selector for a Model in sagemaker to populate modelName.
// +kubebuilder:validation:Optional
ModelNameSelector *v1.Selector `json:"modelNameSelector,omitempty" tf:"-"`
// Sets how the endpoint routes incoming traffic. See routing_config below.
RoutingConfig []RoutingConfigInitParameters `json:"routingConfig,omitempty" tf:"routing_config,omitempty"`
// Specifies configuration for how an endpoint performs asynchronous inference.
ServerlessConfig []ServerlessConfigInitParameters `json:"serverlessConfig,omitempty" tf:"serverless_config,omitempty"`
// The name of the variant.
VariantName *string `json:"variantName,omitempty" tf:"variant_name,omitempty"`
// The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.
VolumeSizeInGb *float64 `json:"volumeSizeInGb,omitempty" tf:"volume_size_in_gb,omitempty"`
}
type ProductionVariantsObservation struct {
// The size of the Elastic Inference (EI) instance to use for the production variant.
AcceleratorType *string `json:"acceleratorType,omitempty" tf:"accelerator_type,omitempty"`
// The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.
ContainerStartupHealthCheckTimeoutInSeconds *float64 `json:"containerStartupHealthCheckTimeoutInSeconds,omitempty" tf:"container_startup_health_check_timeout_in_seconds,omitempty"`
// Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.
CoreDumpConfig []CoreDumpConfigObservation `json:"coreDumpConfig,omitempty" tf:"core_dump_config,omitempty"`
// You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoints.
EnableSsmAccess *bool `json:"enableSsmAccess,omitempty" tf:"enable_ssm_access,omitempty"`
// Initial number of instances used for auto-scaling.
InitialInstanceCount *float64 `json:"initialInstanceCount,omitempty" tf:"initial_instance_count,omitempty"`
// Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
InitialVariantWeight *float64 `json:"initialVariantWeight,omitempty" tf:"initial_variant_weight,omitempty"`
// The type of instance to start.
InstanceType *string `json:"instanceType,omitempty" tf:"instance_type,omitempty"`
// The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.
ModelDataDownloadTimeoutInSeconds *float64 `json:"modelDataDownloadTimeoutInSeconds,omitempty" tf:"model_data_download_timeout_in_seconds,omitempty"`
// The name of the model to use.
ModelName *string `json:"modelName,omitempty" tf:"model_name,omitempty"`
// Sets how the endpoint routes incoming traffic. See routing_config below.
RoutingConfig []RoutingConfigObservation `json:"routingConfig,omitempty" tf:"routing_config,omitempty"`
// Specifies configuration for how an endpoint performs asynchronous inference.
ServerlessConfig []ServerlessConfigObservation `json:"serverlessConfig,omitempty" tf:"serverless_config,omitempty"`
// The name of the variant.
VariantName *string `json:"variantName,omitempty" tf:"variant_name,omitempty"`
// The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.
VolumeSizeInGb *float64 `json:"volumeSizeInGb,omitempty" tf:"volume_size_in_gb,omitempty"`
}
type ProductionVariantsParameters struct {
// The size of the Elastic Inference (EI) instance to use for the production variant.
// +kubebuilder:validation:Optional
AcceleratorType *string `json:"acceleratorType,omitempty" tf:"accelerator_type,omitempty"`
// The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.
// +kubebuilder:validation:Optional
ContainerStartupHealthCheckTimeoutInSeconds *float64 `json:"containerStartupHealthCheckTimeoutInSeconds,omitempty" tf:"container_startup_health_check_timeout_in_seconds,omitempty"`
// Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.
// +kubebuilder:validation:Optional
CoreDumpConfig []CoreDumpConfigParameters `json:"coreDumpConfig,omitempty" tf:"core_dump_config,omitempty"`
// You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoints.
// +kubebuilder:validation:Optional
EnableSsmAccess *bool `json:"enableSsmAccess,omitempty" tf:"enable_ssm_access,omitempty"`
// Initial number of instances used for auto-scaling.
// +kubebuilder:validation:Optional
InitialInstanceCount *float64 `json:"initialInstanceCount,omitempty" tf:"initial_instance_count,omitempty"`
// Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
// +kubebuilder:validation:Optional
InitialVariantWeight *float64 `json:"initialVariantWeight,omitempty" tf:"initial_variant_weight,omitempty"`
// The type of instance to start.
// +kubebuilder:validation:Optional
InstanceType *string `json:"instanceType,omitempty" tf:"instance_type,omitempty"`
// The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.
// +kubebuilder:validation:Optional
ModelDataDownloadTimeoutInSeconds *float64 `json:"modelDataDownloadTimeoutInSeconds,omitempty" tf:"model_data_download_timeout_in_seconds,omitempty"`
// The name of the model to use.
// +crossplane:generate:reference:type=github.com/upbound/provider-aws/apis/sagemaker/v1beta1.Model
// +kubebuilder:validation:Optional
ModelName *string `json:"modelName,omitempty" tf:"model_name,omitempty"`
// Reference to a Model in sagemaker to populate modelName.
// +kubebuilder:validation:Optional
ModelNameRef *v1.Reference `json:"modelNameRef,omitempty" tf:"-"`
// Selector for a Model in sagemaker to populate modelName.
// +kubebuilder:validation:Optional
ModelNameSelector *v1.Selector `json:"modelNameSelector,omitempty" tf:"-"`
// Sets how the endpoint routes incoming traffic. See routing_config below.
// +kubebuilder:validation:Optional
RoutingConfig []RoutingConfigParameters `json:"routingConfig,omitempty" tf:"routing_config,omitempty"`
// Specifies configuration for how an endpoint performs asynchronous inference.
// +kubebuilder:validation:Optional
ServerlessConfig []ServerlessConfigParameters `json:"serverlessConfig,omitempty" tf:"serverless_config,omitempty"`
// The name of the variant.
// +kubebuilder:validation:Optional
VariantName *string `json:"variantName,omitempty" tf:"variant_name,omitempty"`
// The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.
// +kubebuilder:validation:Optional
VolumeSizeInGb *float64 `json:"volumeSizeInGb,omitempty" tf:"volume_size_in_gb,omitempty"`
}
type RoutingConfigInitParameters struct {
// Sets how the endpoint routes incoming traffic. Valid values are LEAST_OUTSTANDING_REQUESTS and RANDOM. LEAST_OUTSTANDING_REQUESTS routes requests to the specific instances that have more capacity to process them. RANDOM routes each request to a randomly chosen instance.
RoutingStrategy *string `json:"routingStrategy,omitempty" tf:"routing_strategy,omitempty"`
}
type RoutingConfigObservation struct {
// Sets how the endpoint routes incoming traffic. Valid values are LEAST_OUTSTANDING_REQUESTS and RANDOM. LEAST_OUTSTANDING_REQUESTS routes requests to the specific instances that have more capacity to process them. RANDOM routes each request to a randomly chosen instance.
RoutingStrategy *string `json:"routingStrategy,omitempty" tf:"routing_strategy,omitempty"`
}
type RoutingConfigParameters struct {
// Sets how the endpoint routes incoming traffic. Valid values are LEAST_OUTSTANDING_REQUESTS and RANDOM. LEAST_OUTSTANDING_REQUESTS routes requests to the specific instances that have more capacity to process them. RANDOM routes each request to a randomly chosen instance.
// +kubebuilder:validation:Optional
RoutingStrategy *string `json:"routingStrategy" tf:"routing_strategy,omitempty"`
}
type ServerlessConfigInitParameters struct {
// The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.
MaxConcurrency *float64 `json:"maxConcurrency,omitempty" tf:"max_concurrency,omitempty"`
// The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
MemorySizeInMb *float64 `json:"memorySizeInMb,omitempty" tf:"memory_size_in_mb,omitempty"`
// The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to max_concurrency. Valid values are between 1 and 200.
ProvisionedConcurrency *float64 `json:"provisionedConcurrency,omitempty" tf:"provisioned_concurrency,omitempty"`
}
type ServerlessConfigObservation struct {
// The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.
MaxConcurrency *float64 `json:"maxConcurrency,omitempty" tf:"max_concurrency,omitempty"`
// The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
MemorySizeInMb *float64 `json:"memorySizeInMb,omitempty" tf:"memory_size_in_mb,omitempty"`
// The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to max_concurrency. Valid values are between 1 and 200.
ProvisionedConcurrency *float64 `json:"provisionedConcurrency,omitempty" tf:"provisioned_concurrency,omitempty"`
}
type ServerlessConfigParameters struct {
// The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.
// +kubebuilder:validation:Optional
MaxConcurrency *float64 `json:"maxConcurrency" tf:"max_concurrency,omitempty"`
// The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
// +kubebuilder:validation:Optional
MemorySizeInMb *float64 `json:"memorySizeInMb" tf:"memory_size_in_mb,omitempty"`
// The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to max_concurrency. Valid values are between 1 and 200.
// +kubebuilder:validation:Optional
ProvisionedConcurrency *float64 `json:"provisionedConcurrency,omitempty" tf:"provisioned_concurrency,omitempty"`
}
type ShadowProductionVariantsCoreDumpConfigInitParameters struct {
// The Amazon S3 bucket to send the core dump to.
DestinationS3URI *string `json:"destinationS3Uri,omitempty" tf:"destination_s3_uri,omitempty"`
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type ShadowProductionVariantsCoreDumpConfigObservation struct {
// The Amazon S3 bucket to send the core dump to.
DestinationS3URI *string `json:"destinationS3Uri,omitempty" tf:"destination_s3_uri,omitempty"`
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.
KMSKeyID *string `json:"kmsKeyId,omitempty" tf:"kms_key_id,omitempty"`
}
type ShadowProductionVariantsCoreDumpConfigParameters struct {
// The Amazon S3 bucket to send the core dump to.
// +kubebuilder:validation:Optional
DestinationS3URI *string `json:"destinationS3Uri" tf:"destination_s3_uri,omitempty"`
// The Amazon Web Services Key Management Service (Amazon Web Services KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption.
// +kubebuilder:validation:Optional
KMSKeyID *string `json:"kmsKeyId" tf:"kms_key_id,omitempty"`
}
type ShadowProductionVariantsInitParameters struct {
// The size of the Elastic Inference (EI) instance to use for the production variant.
AcceleratorType *string `json:"acceleratorType,omitempty" tf:"accelerator_type,omitempty"`
// The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.
ContainerStartupHealthCheckTimeoutInSeconds *float64 `json:"containerStartupHealthCheckTimeoutInSeconds,omitempty" tf:"container_startup_health_check_timeout_in_seconds,omitempty"`
// Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.
CoreDumpConfig []ShadowProductionVariantsCoreDumpConfigInitParameters `json:"coreDumpConfig,omitempty" tf:"core_dump_config,omitempty"`
// You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoints.
EnableSsmAccess *bool `json:"enableSsmAccess,omitempty" tf:"enable_ssm_access,omitempty"`
// Initial number of instances used for auto-scaling.
InitialInstanceCount *float64 `json:"initialInstanceCount,omitempty" tf:"initial_instance_count,omitempty"`
// Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
InitialVariantWeight *float64 `json:"initialVariantWeight,omitempty" tf:"initial_variant_weight,omitempty"`
// The type of instance to start.
InstanceType *string `json:"instanceType,omitempty" tf:"instance_type,omitempty"`
// The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.
ModelDataDownloadTimeoutInSeconds *float64 `json:"modelDataDownloadTimeoutInSeconds,omitempty" tf:"model_data_download_timeout_in_seconds,omitempty"`
// The name of the model to use.
ModelName *string `json:"modelName,omitempty" tf:"model_name,omitempty"`
// Sets how the endpoint routes incoming traffic. See routing_config below.
RoutingConfig []ShadowProductionVariantsRoutingConfigInitParameters `json:"routingConfig,omitempty" tf:"routing_config,omitempty"`
// Specifies configuration for how an endpoint performs asynchronous inference.
ServerlessConfig []ShadowProductionVariantsServerlessConfigInitParameters `json:"serverlessConfig,omitempty" tf:"serverless_config,omitempty"`
// The name of the variant.
VariantName *string `json:"variantName,omitempty" tf:"variant_name,omitempty"`
// The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.
VolumeSizeInGb *float64 `json:"volumeSizeInGb,omitempty" tf:"volume_size_in_gb,omitempty"`
}
type ShadowProductionVariantsObservation struct {
// The size of the Elastic Inference (EI) instance to use for the production variant.
AcceleratorType *string `json:"acceleratorType,omitempty" tf:"accelerator_type,omitempty"`
// The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.
ContainerStartupHealthCheckTimeoutInSeconds *float64 `json:"containerStartupHealthCheckTimeoutInSeconds,omitempty" tf:"container_startup_health_check_timeout_in_seconds,omitempty"`
// Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.
CoreDumpConfig []ShadowProductionVariantsCoreDumpConfigObservation `json:"coreDumpConfig,omitempty" tf:"core_dump_config,omitempty"`
// You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoints.
EnableSsmAccess *bool `json:"enableSsmAccess,omitempty" tf:"enable_ssm_access,omitempty"`
// Initial number of instances used for auto-scaling.
InitialInstanceCount *float64 `json:"initialInstanceCount,omitempty" tf:"initial_instance_count,omitempty"`
// Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
InitialVariantWeight *float64 `json:"initialVariantWeight,omitempty" tf:"initial_variant_weight,omitempty"`
// The type of instance to start.
InstanceType *string `json:"instanceType,omitempty" tf:"instance_type,omitempty"`
// The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.
ModelDataDownloadTimeoutInSeconds *float64 `json:"modelDataDownloadTimeoutInSeconds,omitempty" tf:"model_data_download_timeout_in_seconds,omitempty"`
// The name of the model to use.
ModelName *string `json:"modelName,omitempty" tf:"model_name,omitempty"`
// Sets how the endpoint routes incoming traffic. See routing_config below.
RoutingConfig []ShadowProductionVariantsRoutingConfigObservation `json:"routingConfig,omitempty" tf:"routing_config,omitempty"`
// Specifies configuration for how an endpoint performs asynchronous inference.
ServerlessConfig []ShadowProductionVariantsServerlessConfigObservation `json:"serverlessConfig,omitempty" tf:"serverless_config,omitempty"`
// The name of the variant.
VariantName *string `json:"variantName,omitempty" tf:"variant_name,omitempty"`
// The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.
VolumeSizeInGb *float64 `json:"volumeSizeInGb,omitempty" tf:"volume_size_in_gb,omitempty"`
}
type ShadowProductionVariantsParameters struct {
// The size of the Elastic Inference (EI) instance to use for the production variant.
// +kubebuilder:validation:Optional
AcceleratorType *string `json:"acceleratorType,omitempty" tf:"accelerator_type,omitempty"`
// The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting. For more information about health check, see How Your Container Should Respond to Health Check (Ping) Requests. Valid values between 60 and 3600.
// +kubebuilder:validation:Optional
ContainerStartupHealthCheckTimeoutInSeconds *float64 `json:"containerStartupHealthCheckTimeoutInSeconds,omitempty" tf:"container_startup_health_check_timeout_in_seconds,omitempty"`
// Specifies configuration for a core dump from the model container when the process crashes. Fields are documented below.
// +kubebuilder:validation:Optional
CoreDumpConfig []ShadowProductionVariantsCoreDumpConfigParameters `json:"coreDumpConfig,omitempty" tf:"core_dump_config,omitempty"`
// You can use this parameter to turn on native Amazon Web Services Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoints.
// +kubebuilder:validation:Optional
EnableSsmAccess *bool `json:"enableSsmAccess,omitempty" tf:"enable_ssm_access,omitempty"`
// Initial number of instances used for auto-scaling.
// +kubebuilder:validation:Optional
InitialInstanceCount *float64 `json:"initialInstanceCount,omitempty" tf:"initial_instance_count,omitempty"`
// Determines initial traffic distribution among all of the models that you specify in the endpoint configuration. If unspecified, it defaults to 1.0.
// +kubebuilder:validation:Optional
InitialVariantWeight *float64 `json:"initialVariantWeight,omitempty" tf:"initial_variant_weight,omitempty"`
// The type of instance to start.
// +kubebuilder:validation:Optional
InstanceType *string `json:"instanceType,omitempty" tf:"instance_type,omitempty"`
// The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant. Valid values between 60 and 3600.
// +kubebuilder:validation:Optional
ModelDataDownloadTimeoutInSeconds *float64 `json:"modelDataDownloadTimeoutInSeconds,omitempty" tf:"model_data_download_timeout_in_seconds,omitempty"`
// The name of the model to use.
// +kubebuilder:validation:Optional
ModelName *string `json:"modelName" tf:"model_name,omitempty"`
// Sets how the endpoint routes incoming traffic. See routing_config below.
// +kubebuilder:validation:Optional
RoutingConfig []ShadowProductionVariantsRoutingConfigParameters `json:"routingConfig,omitempty" tf:"routing_config,omitempty"`
// Specifies configuration for how an endpoint performs asynchronous inference.
// +kubebuilder:validation:Optional
ServerlessConfig []ShadowProductionVariantsServerlessConfigParameters `json:"serverlessConfig,omitempty" tf:"serverless_config,omitempty"`
// The name of the variant.
// +kubebuilder:validation:Optional
VariantName *string `json:"variantName,omitempty" tf:"variant_name,omitempty"`
// The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Valid values between 1 and 512.
// +kubebuilder:validation:Optional
VolumeSizeInGb *float64 `json:"volumeSizeInGb,omitempty" tf:"volume_size_in_gb,omitempty"`
}
type ShadowProductionVariantsRoutingConfigInitParameters struct {
// Sets how the endpoint routes incoming traffic. Valid values are LEAST_OUTSTANDING_REQUESTS and RANDOM. LEAST_OUTSTANDING_REQUESTS routes requests to the specific instances that have more capacity to process them. RANDOM routes each request to a randomly chosen instance.
RoutingStrategy *string `json:"routingStrategy,omitempty" tf:"routing_strategy,omitempty"`
}
type ShadowProductionVariantsRoutingConfigObservation struct {
// Sets how the endpoint routes incoming traffic. Valid values are LEAST_OUTSTANDING_REQUESTS and RANDOM. LEAST_OUTSTANDING_REQUESTS routes requests to the specific instances that have more capacity to process them. RANDOM routes each request to a randomly chosen instance.
RoutingStrategy *string `json:"routingStrategy,omitempty" tf:"routing_strategy,omitempty"`
}
type ShadowProductionVariantsRoutingConfigParameters struct {
// Sets how the endpoint routes incoming traffic. Valid values are LEAST_OUTSTANDING_REQUESTS and RANDOM. LEAST_OUTSTANDING_REQUESTS routes requests to the specific instances that have more capacity to process them. RANDOM routes each request to a randomly chosen instance.
// +kubebuilder:validation:Optional
RoutingStrategy *string `json:"routingStrategy" tf:"routing_strategy,omitempty"`
}
type ShadowProductionVariantsServerlessConfigInitParameters struct {
// The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.
MaxConcurrency *float64 `json:"maxConcurrency,omitempty" tf:"max_concurrency,omitempty"`
// The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
MemorySizeInMb *float64 `json:"memorySizeInMb,omitempty" tf:"memory_size_in_mb,omitempty"`
// The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to max_concurrency. Valid values are between 1 and 200.
ProvisionedConcurrency *float64 `json:"provisionedConcurrency,omitempty" tf:"provisioned_concurrency,omitempty"`
}
type ShadowProductionVariantsServerlessConfigObservation struct {
// The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.
MaxConcurrency *float64 `json:"maxConcurrency,omitempty" tf:"max_concurrency,omitempty"`
// The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
MemorySizeInMb *float64 `json:"memorySizeInMb,omitempty" tf:"memory_size_in_mb,omitempty"`
// The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to max_concurrency. Valid values are between 1 and 200.
ProvisionedConcurrency *float64 `json:"provisionedConcurrency,omitempty" tf:"provisioned_concurrency,omitempty"`
}
type ShadowProductionVariantsServerlessConfigParameters struct {
// The maximum number of concurrent invocations your serverless endpoint can process. Valid values are between 1 and 200.
// +kubebuilder:validation:Optional
MaxConcurrency *float64 `json:"maxConcurrency" tf:"max_concurrency,omitempty"`
// The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
// +kubebuilder:validation:Optional
MemorySizeInMb *float64 `json:"memorySizeInMb" tf:"memory_size_in_mb,omitempty"`
// The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to max_concurrency. Valid values are between 1 and 200.
// +kubebuilder:validation:Optional
ProvisionedConcurrency *float64 `json:"provisionedConcurrency,omitempty" tf:"provisioned_concurrency,omitempty"`
}
// EndpointConfigurationSpec defines the desired state of EndpointConfiguration
type EndpointConfigurationSpec struct {
v1.ResourceSpec `json:",inline"`
ForProvider EndpointConfigurationParameters `json:"forProvider"`
// THIS IS A BETA FIELD. It will be honored
// unless the Management Policies feature flag is disabled.
// InitProvider holds the same fields as ForProvider, with the exception
// of Identifier and other resource reference fields. The fields that are
// in InitProvider are merged into ForProvider when the resource is created.
// The same fields are also added to the terraform ignore_changes hook, to
// avoid updating them after creation. This is useful for fields that are
// required on creation, but we do not desire to update them after creation,
// for example because of an external controller is managing them, like an
// autoscaler.
InitProvider EndpointConfigurationInitParameters `json:"initProvider,omitempty"`
}
// EndpointConfigurationStatus defines the observed state of EndpointConfiguration.
type EndpointConfigurationStatus struct {
v1.ResourceStatus `json:",inline"`
AtProvider EndpointConfigurationObservation `json:"atProvider,omitempty"`
}
// +kubebuilder:object:root=true
// +kubebuilder:subresource:status
// +kubebuilder:storageversion
// EndpointConfiguration is the Schema for the EndpointConfigurations API. Provides a SageMaker Endpoint Configuration resource.
// +kubebuilder:printcolumn:name="SYNCED",type="string",JSONPath=".status.conditions[?(@.type=='Synced')].status"
// +kubebuilder:printcolumn:name="READY",type="string",JSONPath=".status.conditions[?(@.type=='Ready')].status"
// +kubebuilder:printcolumn:name="EXTERNAL-NAME",type="string",JSONPath=".metadata.annotations.crossplane\\.io/external-name"
// +kubebuilder:printcolumn:name="AGE",type="date",JSONPath=".metadata.creationTimestamp"
// +kubebuilder:resource:scope=Cluster,categories={crossplane,managed,aws}
type EndpointConfiguration struct {
metav1.TypeMeta `json:",inline"`
metav1.ObjectMeta `json:"metadata,omitempty"`
// +kubebuilder:validation:XValidation:rule="!('*' in self.managementPolicies || 'Create' in self.managementPolicies || 'Update' in self.managementPolicies) || has(self.forProvider.productionVariants) || (has(self.initProvider) && has(self.initProvider.productionVariants))",message="spec.forProvider.productionVariants is a required parameter"
Spec EndpointConfigurationSpec `json:"spec"`
Status EndpointConfigurationStatus `json:"status,omitempty"`
}
// +kubebuilder:object:root=true
// EndpointConfigurationList contains a list of EndpointConfigurations
type EndpointConfigurationList struct {
metav1.TypeMeta `json:",inline"`
metav1.ListMeta `json:"metadata,omitempty"`
Items []EndpointConfiguration `json:"items"`
}
// Repository type metadata.
var (
EndpointConfiguration_Kind = "EndpointConfiguration"
EndpointConfiguration_GroupKind = schema.GroupKind{Group: CRDGroup, Kind: EndpointConfiguration_Kind}.String()
EndpointConfiguration_KindAPIVersion = EndpointConfiguration_Kind + "." + CRDGroupVersion.String()
EndpointConfiguration_GroupVersionKind = CRDGroupVersion.WithKind(EndpointConfiguration_Kind)
)
func init() {
SchemeBuilder.Register(&EndpointConfiguration{}, &EndpointConfigurationList{})
}