aws-sdk-sagemakerinferencerouterruntime 1.0.0
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 +7 -0
- data/CHANGELOG.md +8 -0
- data/LICENSE.txt +202 -0
- data/VERSION +1 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/client.rb +768 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/client_api.rb +189 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/customizations.rb +0 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/endpoint_parameters.rb +69 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/endpoint_provider.rb +56 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/endpoints.rb +20 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/errors.rb +217 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/plugins/endpoints.rb +77 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/resource.rb +26 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime/types.rb +400 -0
- data/lib/aws-sdk-sagemakerinferencerouterruntime.rb +61 -0
- data/sig/client.rbs +128 -0
- data/sig/errors.rbs +46 -0
- data/sig/resource.rbs +86 -0
- data/sig/types.rbs +103 -0
- metadata +95 -0
|
@@ -0,0 +1,400 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
# WARNING ABOUT GENERATED CODE
|
|
4
|
+
#
|
|
5
|
+
# This file is generated. See the contributing guide for more information:
|
|
6
|
+
# https://github.com/aws/aws-sdk-ruby/blob/version-3/CONTRIBUTING.md
|
|
7
|
+
#
|
|
8
|
+
# WARNING ABOUT GENERATED CODE
|
|
9
|
+
|
|
10
|
+
module Aws::SageMakerInferenceRouterRuntime
|
|
11
|
+
module Types
|
|
12
|
+
|
|
13
|
+
# You don't have permission to perform this action. Check that the
|
|
14
|
+
# caller is allowed to invoke the inference router and every destination
|
|
15
|
+
# of the routing target.
|
|
16
|
+
#
|
|
17
|
+
# @!attribute [rw] message
|
|
18
|
+
# A message that describes the error.
|
|
19
|
+
# @return [String]
|
|
20
|
+
#
|
|
21
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/AccessDeniedException AWS API Documentation
|
|
22
|
+
#
|
|
23
|
+
class AccessDeniedException < Struct.new(
|
|
24
|
+
:message)
|
|
25
|
+
SENSITIVE = []
|
|
26
|
+
include Aws::Structure
|
|
27
|
+
end
|
|
28
|
+
|
|
29
|
+
# The request failed because of an error in an internal dependency.
|
|
30
|
+
# Retry the request with exponential backoff.
|
|
31
|
+
#
|
|
32
|
+
# @!attribute [rw] message
|
|
33
|
+
# A message that describes the error.
|
|
34
|
+
# @return [String]
|
|
35
|
+
#
|
|
36
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InternalDependencyException AWS API Documentation
|
|
37
|
+
#
|
|
38
|
+
class InternalDependencyException < Struct.new(
|
|
39
|
+
:message)
|
|
40
|
+
SENSITIVE = []
|
|
41
|
+
include Aws::Structure
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
# An internal error occurred. Retry the request with exponential
|
|
45
|
+
# backoff. The Amazon Web Services SDKs and the Amazon Web Services CLI
|
|
46
|
+
# do this by default.
|
|
47
|
+
#
|
|
48
|
+
# @!attribute [rw] message
|
|
49
|
+
# A message that describes the error.
|
|
50
|
+
# @return [String]
|
|
51
|
+
#
|
|
52
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InternalFailure AWS API Documentation
|
|
53
|
+
#
|
|
54
|
+
class InternalFailure < Struct.new(
|
|
55
|
+
:message)
|
|
56
|
+
SENSITIVE = []
|
|
57
|
+
include Aws::Structure
|
|
58
|
+
end
|
|
59
|
+
|
|
60
|
+
# @!attribute [rw] inference_router_name
|
|
61
|
+
# The name of the inference router to invoke.
|
|
62
|
+
# @return [String]
|
|
63
|
+
#
|
|
64
|
+
# @!attribute [rw] routing_target_name
|
|
65
|
+
# The name of the routing target in the inference router. The routing
|
|
66
|
+
# target must be configured for asynchronous inference.
|
|
67
|
+
# @return [String]
|
|
68
|
+
#
|
|
69
|
+
# @!attribute [rw] content_type
|
|
70
|
+
# The MIME type of the input data in Amazon S3. The router passes it
|
|
71
|
+
# to the destination.
|
|
72
|
+
# @return [String]
|
|
73
|
+
#
|
|
74
|
+
# @!attribute [rw] accept
|
|
75
|
+
# The MIME type that you want for the inference response. The router
|
|
76
|
+
# passes it to the destination.
|
|
77
|
+
# @return [String]
|
|
78
|
+
#
|
|
79
|
+
# @!attribute [rw] custom_attributes
|
|
80
|
+
# Provides additional information about the inference request. The
|
|
81
|
+
# value is an opaque string that the router passes, unchanged, to the
|
|
82
|
+
# model container of the destination that serves the request. The
|
|
83
|
+
# value can contain up to 1,024 visible US-ASCII characters.
|
|
84
|
+
# @return [String]
|
|
85
|
+
#
|
|
86
|
+
# @!attribute [rw] inference_id
|
|
87
|
+
# An identifier for the inference request. If you don't provide one,
|
|
88
|
+
# SageMaker AI generates one and returns it in the response.
|
|
89
|
+
# @return [String]
|
|
90
|
+
#
|
|
91
|
+
# @!attribute [rw] input_location
|
|
92
|
+
# The Amazon S3 URI of the object that contains the input data for the
|
|
93
|
+
# inference. The bucket must be in the inference router's Amazon Web
|
|
94
|
+
# Services Region and owned by the router's account. The destination
|
|
95
|
+
# endpoint's execution role reads the object, and the destination's
|
|
96
|
+
# asynchronous inference limits apply to it.
|
|
97
|
+
# @return [String]
|
|
98
|
+
#
|
|
99
|
+
# @!attribute [rw] s3_output_path_extension
|
|
100
|
+
# The path extension that is appended to the routing target's Amazon
|
|
101
|
+
# S3 output path where the inference response is stored.
|
|
102
|
+
# @return [String]
|
|
103
|
+
#
|
|
104
|
+
# @!attribute [rw] filename
|
|
105
|
+
# The file name of the inference response stored in Amazon S3. If you
|
|
106
|
+
# don't provide one, SageMaker AI generates one.
|
|
107
|
+
# @return [String]
|
|
108
|
+
#
|
|
109
|
+
# @!attribute [rw] request_ttl_seconds
|
|
110
|
+
# The time to live of the request, in seconds, measured from when the
|
|
111
|
+
# router accepts it. If no destination starts the request in this
|
|
112
|
+
# time, the request fails. The default is 21,600 seconds (6 hours).
|
|
113
|
+
# @return [Integer]
|
|
114
|
+
#
|
|
115
|
+
# @!attribute [rw] invocation_timeout_seconds
|
|
116
|
+
# The maximum time, in seconds, that a destination can spend
|
|
117
|
+
# processing the request before the request is marked as expired. The
|
|
118
|
+
# default is 900 seconds (15 minutes).
|
|
119
|
+
# @return [Integer]
|
|
120
|
+
#
|
|
121
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InvokeInferenceRouterAsyncInput AWS API Documentation
|
|
122
|
+
#
|
|
123
|
+
class InvokeInferenceRouterAsyncInput < Struct.new(
|
|
124
|
+
:inference_router_name,
|
|
125
|
+
:routing_target_name,
|
|
126
|
+
:content_type,
|
|
127
|
+
:accept,
|
|
128
|
+
:custom_attributes,
|
|
129
|
+
:inference_id,
|
|
130
|
+
:input_location,
|
|
131
|
+
:s3_output_path_extension,
|
|
132
|
+
:filename,
|
|
133
|
+
:request_ttl_seconds,
|
|
134
|
+
:invocation_timeout_seconds)
|
|
135
|
+
SENSITIVE = [:custom_attributes]
|
|
136
|
+
include Aws::Structure
|
|
137
|
+
end
|
|
138
|
+
|
|
139
|
+
# @!attribute [rw] inference_id
|
|
140
|
+
# The identifier for the inference request. This is the `InferenceId`
|
|
141
|
+
# that you provided, or the one that SageMaker AI generated.
|
|
142
|
+
# @return [String]
|
|
143
|
+
#
|
|
144
|
+
# @!attribute [rw] output_location
|
|
145
|
+
# The Amazon S3 URI where the inference response is written. The
|
|
146
|
+
# location doesn't change if the router moves the request to another
|
|
147
|
+
# destination.
|
|
148
|
+
# @return [String]
|
|
149
|
+
#
|
|
150
|
+
# @!attribute [rw] failure_location
|
|
151
|
+
# The Amazon S3 URI where the failure details are written if the
|
|
152
|
+
# inference fails.
|
|
153
|
+
# @return [String]
|
|
154
|
+
#
|
|
155
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InvokeInferenceRouterAsyncOutput AWS API Documentation
|
|
156
|
+
#
|
|
157
|
+
class InvokeInferenceRouterAsyncOutput < Struct.new(
|
|
158
|
+
:inference_id,
|
|
159
|
+
:output_location,
|
|
160
|
+
:failure_location)
|
|
161
|
+
SENSITIVE = []
|
|
162
|
+
include Aws::Structure
|
|
163
|
+
end
|
|
164
|
+
|
|
165
|
+
# @!attribute [rw] inference_router_name
|
|
166
|
+
# The name of the inference router to invoke.
|
|
167
|
+
# @return [String]
|
|
168
|
+
#
|
|
169
|
+
# @!attribute [rw] routing_target_name
|
|
170
|
+
# The name of the routing target in the inference router. The routing
|
|
171
|
+
# target lists the destinations that can serve the request.
|
|
172
|
+
# @return [String]
|
|
173
|
+
#
|
|
174
|
+
# @!attribute [rw] content_type
|
|
175
|
+
# The MIME type of the input data in the request body. The router
|
|
176
|
+
# passes it to the destination.
|
|
177
|
+
# @return [String]
|
|
178
|
+
#
|
|
179
|
+
# @!attribute [rw] accept
|
|
180
|
+
# The MIME type that you want for the inference response. The router
|
|
181
|
+
# passes it to the destination.
|
|
182
|
+
# @return [String]
|
|
183
|
+
#
|
|
184
|
+
# @!attribute [rw] inference_id
|
|
185
|
+
# An identifier for the inference request. The router passes it to the
|
|
186
|
+
# destination.
|
|
187
|
+
# @return [String]
|
|
188
|
+
#
|
|
189
|
+
# @!attribute [rw] prefix_aware_id
|
|
190
|
+
# An optional, stable identifier that serves as a routing hint for
|
|
191
|
+
# prefix-aware routing. The router passes it to the destination that
|
|
192
|
+
# serves the request. Within that destination, requests with the same
|
|
193
|
+
# prefix and the same identifier go to the same instance. If requests
|
|
194
|
+
# from different applications might have the same prompt prefix, set a
|
|
195
|
+
# different identifier for each application to differentiate their
|
|
196
|
+
# routing decisions.
|
|
197
|
+
#
|
|
198
|
+
# Applies only to destination endpoints configured with a
|
|
199
|
+
# `RoutingStrategy` of `PREFIX_AWARE`.
|
|
200
|
+
# @return [String]
|
|
201
|
+
#
|
|
202
|
+
# @!attribute [rw] custom_attributes
|
|
203
|
+
# Provides additional information about the inference request. The
|
|
204
|
+
# value is an opaque string that the router passes, unchanged, to the
|
|
205
|
+
# model container of the destination that serves the request. The
|
|
206
|
+
# value can contain up to 1,024 visible US-ASCII characters.
|
|
207
|
+
# @return [String]
|
|
208
|
+
#
|
|
209
|
+
# @!attribute [rw] body
|
|
210
|
+
# The input data for the inference, in the format that your model
|
|
211
|
+
# expects. The body can't be empty.
|
|
212
|
+
# @return [String]
|
|
213
|
+
#
|
|
214
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InvokeInferenceRouterInput AWS API Documentation
|
|
215
|
+
#
|
|
216
|
+
class InvokeInferenceRouterInput < Struct.new(
|
|
217
|
+
:inference_router_name,
|
|
218
|
+
:routing_target_name,
|
|
219
|
+
:content_type,
|
|
220
|
+
:accept,
|
|
221
|
+
:inference_id,
|
|
222
|
+
:prefix_aware_id,
|
|
223
|
+
:custom_attributes,
|
|
224
|
+
:body)
|
|
225
|
+
SENSITIVE = [:custom_attributes, :body]
|
|
226
|
+
include Aws::Structure
|
|
227
|
+
end
|
|
228
|
+
|
|
229
|
+
# @!attribute [rw] body
|
|
230
|
+
# The inference that the model returned.
|
|
231
|
+
# @return [String]
|
|
232
|
+
#
|
|
233
|
+
# @!attribute [rw] content_type
|
|
234
|
+
# The MIME type of the inference returned in the response body.
|
|
235
|
+
# @return [String]
|
|
236
|
+
#
|
|
237
|
+
# @!attribute [rw] invoked_routed_resource_arn
|
|
238
|
+
# The Amazon Resource Name (ARN) of the endpoint or inference
|
|
239
|
+
# component that served the request.
|
|
240
|
+
# @return [String]
|
|
241
|
+
#
|
|
242
|
+
# @!attribute [rw] routing_reason
|
|
243
|
+
# The reason that the router chose the destination that served the
|
|
244
|
+
# request. Possible values:
|
|
245
|
+
#
|
|
246
|
+
# * `local-preferred` – The destination is a healthy destination in
|
|
247
|
+
# the router's Region.
|
|
248
|
+
#
|
|
249
|
+
# * `capacity-available` – No destination in the router's Region
|
|
250
|
+
# could take the request, and two or more destinations in other
|
|
251
|
+
# Regions could.
|
|
252
|
+
#
|
|
253
|
+
# * `only-healthy` – No destination in the router's Region could take
|
|
254
|
+
# the request, and exactly one destination in another Region could.
|
|
255
|
+
#
|
|
256
|
+
# * `failover` – The router moved the request away from destinations
|
|
257
|
+
# in its Region because they were overloaded or returning errors.
|
|
258
|
+
# You also see this value when the router can't assess destination
|
|
259
|
+
# health, and when no destination is healthy and the router tries
|
|
260
|
+
# one anyway.
|
|
261
|
+
# @return [String]
|
|
262
|
+
#
|
|
263
|
+
# @!attribute [rw] invoked_production_variant
|
|
264
|
+
# The production variant of the destination endpoint that served the
|
|
265
|
+
# request.
|
|
266
|
+
# @return [String]
|
|
267
|
+
#
|
|
268
|
+
# @!attribute [rw] custom_attributes
|
|
269
|
+
# Provides additional information in the response about the inference.
|
|
270
|
+
# This is the value that the model container of the destination
|
|
271
|
+
# returned, unchanged.
|
|
272
|
+
# @return [String]
|
|
273
|
+
#
|
|
274
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InvokeInferenceRouterOutput AWS API Documentation
|
|
275
|
+
#
|
|
276
|
+
class InvokeInferenceRouterOutput < Struct.new(
|
|
277
|
+
:body,
|
|
278
|
+
:content_type,
|
|
279
|
+
:invoked_routed_resource_arn,
|
|
280
|
+
:routing_reason,
|
|
281
|
+
:invoked_production_variant,
|
|
282
|
+
:custom_attributes)
|
|
283
|
+
SENSITIVE = [:body, :custom_attributes]
|
|
284
|
+
include Aws::Structure
|
|
285
|
+
end
|
|
286
|
+
|
|
287
|
+
# The model in the destination that served the request returned an
|
|
288
|
+
# error. Check `OriginalStatusCode`, `OriginalMessage`, and the
|
|
289
|
+
# destination's logs in Amazon CloudWatch.
|
|
290
|
+
#
|
|
291
|
+
# @!attribute [rw] message
|
|
292
|
+
# A message that describes the error.
|
|
293
|
+
# @return [String]
|
|
294
|
+
#
|
|
295
|
+
# @!attribute [rw] original_status_code
|
|
296
|
+
# The HTTP status code that the model container returned.
|
|
297
|
+
# @return [Integer]
|
|
298
|
+
#
|
|
299
|
+
# @!attribute [rw] original_message
|
|
300
|
+
# The error message that the model container returned.
|
|
301
|
+
# @return [String]
|
|
302
|
+
#
|
|
303
|
+
# @!attribute [rw] log_stream_arn
|
|
304
|
+
# The Amazon Resource Name (ARN) of the Amazon CloudWatch log stream
|
|
305
|
+
# for the destination that served the request.
|
|
306
|
+
# @return [String]
|
|
307
|
+
#
|
|
308
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/ModelError AWS API Documentation
|
|
309
|
+
#
|
|
310
|
+
class ModelError < Struct.new(
|
|
311
|
+
:message,
|
|
312
|
+
:original_status_code,
|
|
313
|
+
:original_message,
|
|
314
|
+
:log_stream_arn)
|
|
315
|
+
SENSITIVE = []
|
|
316
|
+
include Aws::Structure
|
|
317
|
+
end
|
|
318
|
+
|
|
319
|
+
# The destination isn't ready to serve the model, for example because
|
|
320
|
+
# an inference component has no copies. Retry the request later.
|
|
321
|
+
#
|
|
322
|
+
# @!attribute [rw] message
|
|
323
|
+
# A message that describes the error.
|
|
324
|
+
# @return [String]
|
|
325
|
+
#
|
|
326
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/ModelNotReadyException AWS API Documentation
|
|
327
|
+
#
|
|
328
|
+
class ModelNotReadyException < Struct.new(
|
|
329
|
+
:message)
|
|
330
|
+
SENSITIVE = []
|
|
331
|
+
include Aws::Structure
|
|
332
|
+
end
|
|
333
|
+
|
|
334
|
+
# The inference router didn't receive the complete request within 300
|
|
335
|
+
# seconds of accepting it, for example because of a very slow upload.
|
|
336
|
+
# Retry the request.
|
|
337
|
+
#
|
|
338
|
+
# @!attribute [rw] message
|
|
339
|
+
# A message that describes the error.
|
|
340
|
+
# @return [String]
|
|
341
|
+
#
|
|
342
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/RequestTimeoutException AWS API Documentation
|
|
343
|
+
#
|
|
344
|
+
class RequestTimeoutException < Struct.new(
|
|
345
|
+
:message)
|
|
346
|
+
SENSITIVE = []
|
|
347
|
+
include Aws::Structure
|
|
348
|
+
end
|
|
349
|
+
|
|
350
|
+
# The service is temporarily unavailable. For example, no destination of
|
|
351
|
+
# the routing target could serve the request, or a destination didn't
|
|
352
|
+
# respond. Retry the request with exponential backoff. The Amazon Web
|
|
353
|
+
# Services SDKs and the Amazon Web Services CLI do this by default.
|
|
354
|
+
#
|
|
355
|
+
# @!attribute [rw] message
|
|
356
|
+
# A message that describes the error.
|
|
357
|
+
# @return [String]
|
|
358
|
+
#
|
|
359
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/ServiceUnavailableException AWS API Documentation
|
|
360
|
+
#
|
|
361
|
+
class ServiceUnavailableException < Struct.new(
|
|
362
|
+
:message)
|
|
363
|
+
SENSITIVE = []
|
|
364
|
+
include Aws::Structure
|
|
365
|
+
end
|
|
366
|
+
|
|
367
|
+
# The request was denied because you exceeded the request rate for the
|
|
368
|
+
# inference router, or because a destination throttled the request.
|
|
369
|
+
# Retry the request with exponential backoff.
|
|
370
|
+
#
|
|
371
|
+
# @!attribute [rw] message
|
|
372
|
+
# A message that describes the error.
|
|
373
|
+
# @return [String]
|
|
374
|
+
#
|
|
375
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/ThrottlingException AWS API Documentation
|
|
376
|
+
#
|
|
377
|
+
class ThrottlingException < Struct.new(
|
|
378
|
+
:message)
|
|
379
|
+
SENSITIVE = []
|
|
380
|
+
include Aws::Structure
|
|
381
|
+
end
|
|
382
|
+
|
|
383
|
+
# The request isn't valid. Check the inference router name, the routing
|
|
384
|
+
# target name, and the request parameters, and then try again.
|
|
385
|
+
#
|
|
386
|
+
# @!attribute [rw] message
|
|
387
|
+
# A message that describes the error.
|
|
388
|
+
# @return [String]
|
|
389
|
+
#
|
|
390
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/ValidationException AWS API Documentation
|
|
391
|
+
#
|
|
392
|
+
class ValidationException < Struct.new(
|
|
393
|
+
:message)
|
|
394
|
+
SENSITIVE = []
|
|
395
|
+
include Aws::Structure
|
|
396
|
+
end
|
|
397
|
+
|
|
398
|
+
end
|
|
399
|
+
end
|
|
400
|
+
|
|
@@ -0,0 +1,61 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
# WARNING ABOUT GENERATED CODE
|
|
4
|
+
#
|
|
5
|
+
# This file is generated. See the contributing guide for more information:
|
|
6
|
+
# https://github.com/aws/aws-sdk-ruby/blob/version-3/CONTRIBUTING.md
|
|
7
|
+
#
|
|
8
|
+
# WARNING ABOUT GENERATED CODE
|
|
9
|
+
|
|
10
|
+
|
|
11
|
+
require 'aws-sdk-core'
|
|
12
|
+
require 'aws-sigv4'
|
|
13
|
+
|
|
14
|
+
Aws::Plugins::GlobalConfiguration.add_identifier(:sagemakerinferencerouterruntime)
|
|
15
|
+
|
|
16
|
+
# This module provides support for Amazon SageMaker Inference Router Runtime. This module is available in the
|
|
17
|
+
# `aws-sdk-sagemakerinferencerouterruntime` gem.
|
|
18
|
+
#
|
|
19
|
+
# # Client
|
|
20
|
+
#
|
|
21
|
+
# The {Client} class provides one method for each API operation. Operation
|
|
22
|
+
# methods each accept a hash of request parameters and return a response
|
|
23
|
+
# structure.
|
|
24
|
+
#
|
|
25
|
+
# sage_maker_inference_router_runtime = Aws::SageMakerInferenceRouterRuntime::Client.new
|
|
26
|
+
# resp = sage_maker_inference_router_runtime.invoke_inference_router(params)
|
|
27
|
+
#
|
|
28
|
+
# See {Client} for more information.
|
|
29
|
+
#
|
|
30
|
+
# # Errors
|
|
31
|
+
#
|
|
32
|
+
# Errors returned from Amazon SageMaker Inference Router Runtime are defined in the
|
|
33
|
+
# {Errors} module and all extend {Errors::ServiceError}.
|
|
34
|
+
#
|
|
35
|
+
# begin
|
|
36
|
+
# # do stuff
|
|
37
|
+
# rescue Aws::SageMakerInferenceRouterRuntime::Errors::ServiceError
|
|
38
|
+
# # rescues all Amazon SageMaker Inference Router Runtime API errors
|
|
39
|
+
# end
|
|
40
|
+
#
|
|
41
|
+
# See {Errors} for more information.
|
|
42
|
+
#
|
|
43
|
+
# @!group service
|
|
44
|
+
module Aws::SageMakerInferenceRouterRuntime
|
|
45
|
+
autoload :Types, 'aws-sdk-sagemakerinferencerouterruntime/types'
|
|
46
|
+
autoload :ClientApi, 'aws-sdk-sagemakerinferencerouterruntime/client_api'
|
|
47
|
+
module Plugins
|
|
48
|
+
autoload :Endpoints, 'aws-sdk-sagemakerinferencerouterruntime/plugins/endpoints.rb'
|
|
49
|
+
end
|
|
50
|
+
autoload :Client, 'aws-sdk-sagemakerinferencerouterruntime/client'
|
|
51
|
+
autoload :Errors, 'aws-sdk-sagemakerinferencerouterruntime/errors'
|
|
52
|
+
autoload :Resource, 'aws-sdk-sagemakerinferencerouterruntime/resource'
|
|
53
|
+
autoload :EndpointParameters, 'aws-sdk-sagemakerinferencerouterruntime/endpoint_parameters'
|
|
54
|
+
autoload :EndpointProvider, 'aws-sdk-sagemakerinferencerouterruntime/endpoint_provider'
|
|
55
|
+
autoload :Endpoints, 'aws-sdk-sagemakerinferencerouterruntime/endpoints'
|
|
56
|
+
|
|
57
|
+
GEM_VERSION = '1.0.0'
|
|
58
|
+
|
|
59
|
+
end
|
|
60
|
+
|
|
61
|
+
require_relative 'aws-sdk-sagemakerinferencerouterruntime/customizations'
|
data/sig/client.rbs
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
1
|
+
# WARNING ABOUT GENERATED CODE
|
|
2
|
+
#
|
|
3
|
+
# This file is generated. See the contributing guide for more information:
|
|
4
|
+
# https://github.com/aws/aws-sdk-ruby/blob/version-3/CONTRIBUTING.md
|
|
5
|
+
#
|
|
6
|
+
# WARNING ABOUT GENERATED CODE
|
|
7
|
+
|
|
8
|
+
module Aws
|
|
9
|
+
module SageMakerInferenceRouterRuntime
|
|
10
|
+
class Client < ::Seahorse::Client::Base
|
|
11
|
+
include ::Aws::ClientStubs
|
|
12
|
+
|
|
13
|
+
# https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMakerInferenceRouterRuntime/Client.html#initialize-instance_method
|
|
14
|
+
def self.new: (
|
|
15
|
+
?credentials: untyped,
|
|
16
|
+
?region: String,
|
|
17
|
+
?access_key_id: String,
|
|
18
|
+
?account_id: String,
|
|
19
|
+
?active_endpoint_cache: bool,
|
|
20
|
+
?adaptive_retry_wait_to_fill: bool,
|
|
21
|
+
?auth_scheme_preference: Array[String],
|
|
22
|
+
?client_side_monitoring: bool,
|
|
23
|
+
?client_side_monitoring_client_id: String,
|
|
24
|
+
?client_side_monitoring_host: String,
|
|
25
|
+
?client_side_monitoring_port: Integer,
|
|
26
|
+
?client_side_monitoring_publisher: untyped,
|
|
27
|
+
?convert_params: bool,
|
|
28
|
+
?correct_clock_skew: bool,
|
|
29
|
+
?defaults_mode: String,
|
|
30
|
+
?disable_clock_skew_correction: bool,
|
|
31
|
+
?disable_host_prefix_injection: bool,
|
|
32
|
+
?disable_request_compression: bool,
|
|
33
|
+
?endpoint: String,
|
|
34
|
+
?endpoint_cache_max_entries: Integer,
|
|
35
|
+
?endpoint_cache_max_threads: Integer,
|
|
36
|
+
?endpoint_cache_poll_interval: Integer,
|
|
37
|
+
?endpoint_discovery: bool,
|
|
38
|
+
?ignore_configured_endpoint_urls: bool,
|
|
39
|
+
?log_formatter: untyped,
|
|
40
|
+
?log_level: Symbol,
|
|
41
|
+
?logger: untyped,
|
|
42
|
+
?max_attempts: Integer,
|
|
43
|
+
?profile: String,
|
|
44
|
+
?request_checksum_calculation: String,
|
|
45
|
+
?request_min_compression_size_bytes: Integer,
|
|
46
|
+
?response_checksum_validation: String,
|
|
47
|
+
?retry_backoff: Proc,
|
|
48
|
+
?retry_base_delay: Float,
|
|
49
|
+
?retry_jitter: (:none | :equal | :full | ^(Integer) -> Integer),
|
|
50
|
+
?retry_limit: Integer,
|
|
51
|
+
?retry_max_delay: Integer,
|
|
52
|
+
?retry_mode: ("legacy" | "standard" | "adaptive"),
|
|
53
|
+
?sdk_ua_app_id: String,
|
|
54
|
+
?secret_access_key: String,
|
|
55
|
+
?session_token: String,
|
|
56
|
+
?sigv4a_signing_region_set: Array[String],
|
|
57
|
+
?stub_responses: untyped,
|
|
58
|
+
?telemetry_provider: Aws::Telemetry::TelemetryProviderBase,
|
|
59
|
+
?token_provider: untyped,
|
|
60
|
+
?use_dualstack_endpoint: bool,
|
|
61
|
+
?use_fips_endpoint: bool,
|
|
62
|
+
?validate_params: bool,
|
|
63
|
+
?endpoint_provider: untyped,
|
|
64
|
+
?http_proxy: String,
|
|
65
|
+
?http_open_timeout: (Float | Integer),
|
|
66
|
+
?http_read_timeout: (Float | Integer),
|
|
67
|
+
?http_idle_timeout: (Float | Integer),
|
|
68
|
+
?http_continue_timeout: (Float | Integer),
|
|
69
|
+
?ssl_timeout: (Float | Integer | nil),
|
|
70
|
+
?http_wire_trace: bool,
|
|
71
|
+
?ssl_verify_peer: bool,
|
|
72
|
+
?ssl_ca_bundle: String,
|
|
73
|
+
?ssl_ca_directory: String,
|
|
74
|
+
?ssl_ca_store: String,
|
|
75
|
+
?on_chunk_received: Proc,
|
|
76
|
+
?on_chunk_sent: Proc,
|
|
77
|
+
?raise_response_errors: bool
|
|
78
|
+
) -> instance
|
|
79
|
+
| (?Hash[Symbol, untyped]) -> instance
|
|
80
|
+
|
|
81
|
+
|
|
82
|
+
interface _InvokeInferenceRouterResponseSuccess
|
|
83
|
+
include ::Seahorse::Client::_ResponseSuccess[Types::InvokeInferenceRouterOutput]
|
|
84
|
+
def body: () -> ::String
|
|
85
|
+
def content_type: () -> ::String
|
|
86
|
+
def invoked_routed_resource_arn: () -> ::String
|
|
87
|
+
def routing_reason: () -> ::String
|
|
88
|
+
def invoked_production_variant: () -> ::String
|
|
89
|
+
def custom_attributes: () -> ::String
|
|
90
|
+
end
|
|
91
|
+
# https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMakerInferenceRouterRuntime/Client.html#invoke_inference_router-instance_method
|
|
92
|
+
def invoke_inference_router: (
|
|
93
|
+
inference_router_name: ::String,
|
|
94
|
+
routing_target_name: ::String,
|
|
95
|
+
?content_type: ::String,
|
|
96
|
+
?accept: ::String,
|
|
97
|
+
?inference_id: ::String,
|
|
98
|
+
?prefix_aware_id: ::String,
|
|
99
|
+
?custom_attributes: ::String,
|
|
100
|
+
body: ::String
|
|
101
|
+
) -> _InvokeInferenceRouterResponseSuccess
|
|
102
|
+
| (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _InvokeInferenceRouterResponseSuccess
|
|
103
|
+
|
|
104
|
+
interface _InvokeInferenceRouterAsyncResponseSuccess
|
|
105
|
+
include ::Seahorse::Client::_ResponseSuccess[Types::InvokeInferenceRouterAsyncOutput]
|
|
106
|
+
def inference_id: () -> ::String
|
|
107
|
+
def output_location: () -> ::String
|
|
108
|
+
def failure_location: () -> ::String
|
|
109
|
+
end
|
|
110
|
+
# https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMakerInferenceRouterRuntime/Client.html#invoke_inference_router_async-instance_method
|
|
111
|
+
def invoke_inference_router_async: (
|
|
112
|
+
inference_router_name: ::String,
|
|
113
|
+
routing_target_name: ::String,
|
|
114
|
+
?content_type: ::String,
|
|
115
|
+
?accept: ::String,
|
|
116
|
+
?custom_attributes: ::String,
|
|
117
|
+
?inference_id: ::String,
|
|
118
|
+
input_location: ::String,
|
|
119
|
+
?s3_output_path_extension: ::String,
|
|
120
|
+
?filename: ::String,
|
|
121
|
+
?request_ttl_seconds: ::Integer,
|
|
122
|
+
?invocation_timeout_seconds: ::Integer
|
|
123
|
+
) -> _InvokeInferenceRouterAsyncResponseSuccess
|
|
124
|
+
| (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _InvokeInferenceRouterAsyncResponseSuccess
|
|
125
|
+
end
|
|
126
|
+
end
|
|
127
|
+
end
|
|
128
|
+
|
data/sig/errors.rbs
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
# WARNING ABOUT GENERATED CODE
|
|
2
|
+
#
|
|
3
|
+
# This file is generated. See the contributing guide for more information:
|
|
4
|
+
# https://github.com/aws/aws-sdk-ruby/blob/version-3/CONTRIBUTING.md
|
|
5
|
+
#
|
|
6
|
+
# WARNING ABOUT GENERATED CODE
|
|
7
|
+
|
|
8
|
+
module Aws
|
|
9
|
+
module SageMakerInferenceRouterRuntime
|
|
10
|
+
module Errors
|
|
11
|
+
class ServiceError < ::Aws::Errors::ServiceError
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
class AccessDeniedException < ServiceError
|
|
15
|
+
def message: () -> ::String
|
|
16
|
+
end
|
|
17
|
+
class InternalDependencyException < ServiceError
|
|
18
|
+
def message: () -> ::String
|
|
19
|
+
end
|
|
20
|
+
class InternalFailure < ServiceError
|
|
21
|
+
def message: () -> ::String
|
|
22
|
+
end
|
|
23
|
+
class ModelError < ServiceError
|
|
24
|
+
def message: () -> ::String
|
|
25
|
+
def original_status_code: () -> ::String
|
|
26
|
+
def original_message: () -> ::String
|
|
27
|
+
def log_stream_arn: () -> ::String
|
|
28
|
+
end
|
|
29
|
+
class ModelNotReadyException < ServiceError
|
|
30
|
+
def message: () -> ::String
|
|
31
|
+
end
|
|
32
|
+
class RequestTimeoutException < ServiceError
|
|
33
|
+
def message: () -> ::String
|
|
34
|
+
end
|
|
35
|
+
class ServiceUnavailableException < ServiceError
|
|
36
|
+
def message: () -> ::String
|
|
37
|
+
end
|
|
38
|
+
class ThrottlingException < ServiceError
|
|
39
|
+
def message: () -> ::String
|
|
40
|
+
end
|
|
41
|
+
class ValidationException < ServiceError
|
|
42
|
+
def message: () -> ::String
|
|
43
|
+
end
|
|
44
|
+
end
|
|
45
|
+
end
|
|
46
|
+
end
|