aws-sdk-sagemakergatewayruntime 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-sagemakergatewayruntime/client.rb +903 -0
- data/lib/aws-sdk-sagemakergatewayruntime/client_api.rb +166 -0
- data/lib/aws-sdk-sagemakergatewayruntime/customizations.rb +0 -0
- data/lib/aws-sdk-sagemakergatewayruntime/endpoint_parameters.rb +69 -0
- data/lib/aws-sdk-sagemakergatewayruntime/endpoint_provider.rb +50 -0
- data/lib/aws-sdk-sagemakergatewayruntime/endpoints.rb +20 -0
- data/lib/aws-sdk-sagemakergatewayruntime/errors.rb +229 -0
- data/lib/aws-sdk-sagemakergatewayruntime/event_streams.rb +59 -0
- data/lib/aws-sdk-sagemakergatewayruntime/plugins/endpoints.rb +77 -0
- data/lib/aws-sdk-sagemakergatewayruntime/resource.rb +26 -0
- data/lib/aws-sdk-sagemakergatewayruntime/types.rb +440 -0
- data/lib/aws-sdk-sagemakergatewayruntime.rb +62 -0
- data/sig/client.rbs +115 -0
- data/sig/errors.rbs +49 -0
- data/sig/resource.rbs +89 -0
- data/sig/types.rbs +104 -0
- metadata +96 -0
|
@@ -0,0 +1,26 @@
|
|
|
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::SageMakerGatewayRuntime
|
|
11
|
+
|
|
12
|
+
class Resource
|
|
13
|
+
|
|
14
|
+
# @param options ({})
|
|
15
|
+
# @option options [Client] :client
|
|
16
|
+
def initialize(options = {})
|
|
17
|
+
@client = options[:client] || Client.new(options)
|
|
18
|
+
end
|
|
19
|
+
|
|
20
|
+
# @return [Client]
|
|
21
|
+
def client
|
|
22
|
+
@client
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
end
|
|
26
|
+
end
|
|
@@ -0,0 +1,440 @@
|
|
|
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::SageMakerGatewayRuntime
|
|
11
|
+
module Types
|
|
12
|
+
|
|
13
|
+
# The caller is not authorized to invoke this gateway. Invoking requires
|
|
14
|
+
# the `sagemaker:InvokeGlobalInferenceGateway` permission, or
|
|
15
|
+
# `sagemaker:InvokeGlobalInferenceGatewayWithResponseStream` for the
|
|
16
|
+
# streaming operation, on the gateway ARN. A message starting `inference
|
|
17
|
+
# gateway` means the inference gateway serving the model refused the
|
|
18
|
+
# request with a 401 or 403, for example for its customer identity
|
|
19
|
+
# token. Its status code is in the message (the response status is 403),
|
|
20
|
+
# and up to 256 bytes of its error message are quoted.
|
|
21
|
+
#
|
|
22
|
+
# @!attribute [rw] message
|
|
23
|
+
# A description of the error. It starts with a prefix such as `Global
|
|
24
|
+
# Inference Gateway:` or `inference gateway:` that says where the
|
|
25
|
+
# error came from.
|
|
26
|
+
# @return [String]
|
|
27
|
+
#
|
|
28
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/AccessDeniedException AWS API Documentation
|
|
29
|
+
#
|
|
30
|
+
class AccessDeniedException < Struct.new(
|
|
31
|
+
:message)
|
|
32
|
+
SENSITIVE = []
|
|
33
|
+
include Aws::Structure
|
|
34
|
+
end
|
|
35
|
+
|
|
36
|
+
# 502 -- The gateway could not get a usable response from the inference
|
|
37
|
+
# gateway. The `Message` prefix says why:
|
|
38
|
+
#
|
|
39
|
+
# * `Global Inference Gateway: could not reach the inference gateway:
|
|
40
|
+
# <reason>` -- the request could not be sent, or the connection closed
|
|
41
|
+
# before a response arrived (for example, the connection failed, or
|
|
42
|
+
# the inference gateway closed it after reading the request).
|
|
43
|
+
# * `Global Inference Gateway: timed out waiting for the inference
|
|
44
|
+
# gateway` -- on the buffered operation, the inference gateway stopped
|
|
45
|
+
# sending partway through the response body and the gateway's read
|
|
46
|
+
# timeout expired. (The same text on a GatewayTimeoutException means
|
|
47
|
+
# no response arrived.)
|
|
48
|
+
# * Any other `Global Inference Gateway:` message -- the gateway ended a
|
|
49
|
+
# response before it was complete, for example because it exceeded the
|
|
50
|
+
# 10 MiB limit of the buffered operation, the request exceeded its
|
|
51
|
+
# maximum duration, or the inference gateway was taken out of service.
|
|
52
|
+
# * `inference gateway: <status> <message>` -- the inference gateway
|
|
53
|
+
# serving the model returned a 502, 500, 503 or another 5xx error. Its
|
|
54
|
+
# status code is in the message (the response status is 502), and up
|
|
55
|
+
# to 256 bytes of its error message are quoted.
|
|
56
|
+
# * `inference gateway: response ended unexpectedly` -- the inference
|
|
57
|
+
# gateway's connection failed while it was sending the response.
|
|
58
|
+
#
|
|
59
|
+
# The inference gateway names a component in the prefix when it reports
|
|
60
|
+
# one: `inference gateway (<component>):`, where the component is
|
|
61
|
+
# `config` (the inference gateway's configuration and proxy layer),
|
|
62
|
+
# `scheduler` (its request scheduler), `model selector` (its model
|
|
63
|
+
# selector) or `model server` (the model server).
|
|
64
|
+
#
|
|
65
|
+
# Not modeled as retryable: a 502 can mean the inference already ran,
|
|
66
|
+
# and the gateway may already have tried another inference gateway.
|
|
67
|
+
# Standard SDK retry modes may still retry a 5xx status, which would run
|
|
68
|
+
# (and bill) the inference again; set max attempts to 1 if a repeated
|
|
69
|
+
# inference is unacceptable.
|
|
70
|
+
#
|
|
71
|
+
# @!attribute [rw] message
|
|
72
|
+
# A description of the error. It starts with a prefix such as `Global
|
|
73
|
+
# Inference Gateway:` or `inference gateway:` that says where the
|
|
74
|
+
# error came from.
|
|
75
|
+
# @return [String]
|
|
76
|
+
#
|
|
77
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/BadGatewayException AWS API Documentation
|
|
78
|
+
#
|
|
79
|
+
class BadGatewayException < Struct.new(
|
|
80
|
+
:message)
|
|
81
|
+
SENSITIVE = []
|
|
82
|
+
include Aws::Structure
|
|
83
|
+
end
|
|
84
|
+
|
|
85
|
+
# 504 -- The inference gateway did not respond in time. The `Message`
|
|
86
|
+
# prefix says whose time limit expired:
|
|
87
|
+
#
|
|
88
|
+
# * `Global Inference Gateway: timed out waiting for the inference
|
|
89
|
+
# gateway` -- the gateway's limit on the wait for the first part of
|
|
90
|
+
# the response.
|
|
91
|
+
# * `inference gateway: <status> <message>` -- the inference gateway
|
|
92
|
+
# serving the model returned a 504, or a 408 because it timed out
|
|
93
|
+
# waiting for the request to arrive. Its status code is in the message
|
|
94
|
+
# (the response status is 504), and up to 256 bytes of its error
|
|
95
|
+
# message are quoted.
|
|
96
|
+
#
|
|
97
|
+
# The inference gateway names a component in the prefix when it reports
|
|
98
|
+
# one: `inference gateway (<component>):`, where the component is
|
|
99
|
+
# `config` (the inference gateway's configuration and proxy layer),
|
|
100
|
+
# `scheduler` (its request scheduler), `model selector` (its model
|
|
101
|
+
# selector) or `model server` (the model server).
|
|
102
|
+
#
|
|
103
|
+
# Not modeled as retryable: a timeout does not prove the inference did
|
|
104
|
+
# not run, and the gateway may already have tried another inference
|
|
105
|
+
# gateway. Standard SDK retry modes may still retry a 5xx status, which
|
|
106
|
+
# could run (and bill) the inference again; set max attempts to 1 if a
|
|
107
|
+
# repeated inference is unacceptable.
|
|
108
|
+
#
|
|
109
|
+
# @!attribute [rw] message
|
|
110
|
+
# A description of the error. It starts with a prefix such as `Global
|
|
111
|
+
# Inference Gateway:` or `inference gateway:` that says where the
|
|
112
|
+
# error came from.
|
|
113
|
+
# @return [String]
|
|
114
|
+
#
|
|
115
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/GatewayTimeoutException AWS API Documentation
|
|
116
|
+
#
|
|
117
|
+
class GatewayTimeoutException < Struct.new(
|
|
118
|
+
:message)
|
|
119
|
+
SENSITIVE = []
|
|
120
|
+
include Aws::Structure
|
|
121
|
+
end
|
|
122
|
+
|
|
123
|
+
# An unexpected internal failure occurred.
|
|
124
|
+
#
|
|
125
|
+
# @!attribute [rw] message
|
|
126
|
+
# A description of the error. It starts with `Global Inference
|
|
127
|
+
# Gateway:`, because the Global Inference Gateway returns this error
|
|
128
|
+
# itself.
|
|
129
|
+
# @return [String]
|
|
130
|
+
#
|
|
131
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/InternalServerException AWS API Documentation
|
|
132
|
+
#
|
|
133
|
+
class InternalServerException < Struct.new(
|
|
134
|
+
:message)
|
|
135
|
+
SENSITIVE = []
|
|
136
|
+
include Aws::Structure
|
|
137
|
+
end
|
|
138
|
+
|
|
139
|
+
# A failure after the stream started. The `Message` says where it came
|
|
140
|
+
# from: `Global Inference Gateway:` when a gateway time limit expired or
|
|
141
|
+
# the inference gateway was taken out of service, or `inference gateway:
|
|
142
|
+
# response ended unexpectedly` when the inference gateway's connection
|
|
143
|
+
# failed while it was sending the response. The stream ends after this
|
|
144
|
+
# event.
|
|
145
|
+
#
|
|
146
|
+
# @!attribute [rw] message
|
|
147
|
+
# A description of the failure. It starts with `Global Inference
|
|
148
|
+
# Gateway:` or `inference gateway:`, which says where the failure came
|
|
149
|
+
# from.
|
|
150
|
+
# @return [String]
|
|
151
|
+
#
|
|
152
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/InternalStreamFailure AWS API Documentation
|
|
153
|
+
#
|
|
154
|
+
class InternalStreamFailure < Struct.new(
|
|
155
|
+
:message,
|
|
156
|
+
:event_type)
|
|
157
|
+
SENSITIVE = []
|
|
158
|
+
include Aws::Structure
|
|
159
|
+
end
|
|
160
|
+
|
|
161
|
+
# The request for InvokeGlobalInferenceGateway.
|
|
162
|
+
#
|
|
163
|
+
# @!attribute [rw] gateway_id
|
|
164
|
+
# The ID of the Global Inference Gateway to invoke. IAM policies refer
|
|
165
|
+
# to the gateway by its ARN,
|
|
166
|
+
# `arn:<partition>:sagemaker:<region>:<account>:global-inference-gateway/<id>`.
|
|
167
|
+
# @return [String]
|
|
168
|
+
#
|
|
169
|
+
# @!attribute [rw] accept
|
|
170
|
+
# The MIME type you want for the response. It is passed to the model
|
|
171
|
+
# server.
|
|
172
|
+
# @return [String]
|
|
173
|
+
#
|
|
174
|
+
# @!attribute [rw] content_type
|
|
175
|
+
# The MIME type of the request body. Pass `application/json`
|
|
176
|
+
# (parameters such as `charset=utf-8` are allowed): the body is one
|
|
177
|
+
# OpenAI JSON object. The Global Inference Gateway rejects other
|
|
178
|
+
# content types with a 415 error.
|
|
179
|
+
# @return [String]
|
|
180
|
+
#
|
|
181
|
+
# @!attribute [rw] customer_identity_token
|
|
182
|
+
# Per-caller customer identity token (a JWT), forwarded unchanged to
|
|
183
|
+
# the inference gateway, which validates it. The gateway does not use
|
|
184
|
+
# it to authorize the request. Include it in the SigV4 signed headers
|
|
185
|
+
# so it cannot be altered in transit. Redacted from logs, metrics and
|
|
186
|
+
# traces.
|
|
187
|
+
# @return [String]
|
|
188
|
+
#
|
|
189
|
+
# @!attribute [rw] body
|
|
190
|
+
# The inference request body: one OpenAI JSON object, at most 10 MiB.
|
|
191
|
+
# Its content is passed to the model server unchanged, except that the
|
|
192
|
+
# request is always sent with `"stream": false`: this operation
|
|
193
|
+
# returns one JSON document, so a `"stream": true` in the body is
|
|
194
|
+
# overridden (use InvokeGlobalInferenceGatewayWithResponseStream to
|
|
195
|
+
# stream). A body that is not one JSON object, or that repeats the
|
|
196
|
+
# top-level `model` key with different values, is rejected with a 400
|
|
197
|
+
# validation error. A body larger than 10 MiB is rejected with
|
|
198
|
+
# PayloadTooLargeException (413). The gateway reads only `model` and
|
|
199
|
+
# `stream`, and does not store the body.
|
|
200
|
+
# @return [String]
|
|
201
|
+
#
|
|
202
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/InvokeGlobalInferenceGatewayInput AWS API Documentation
|
|
203
|
+
#
|
|
204
|
+
class InvokeGlobalInferenceGatewayInput < Struct.new(
|
|
205
|
+
:gateway_id,
|
|
206
|
+
:accept,
|
|
207
|
+
:content_type,
|
|
208
|
+
:customer_identity_token,
|
|
209
|
+
:body)
|
|
210
|
+
SENSITIVE = [:customer_identity_token, :body]
|
|
211
|
+
include Aws::Structure
|
|
212
|
+
end
|
|
213
|
+
|
|
214
|
+
# The response from InvokeGlobalInferenceGateway.
|
|
215
|
+
#
|
|
216
|
+
# @!attribute [rw] body
|
|
217
|
+
# The model server's OpenAI completion JSON, returned unchanged. A
|
|
218
|
+
# response larger than 10 MiB fails with BadGatewayException (502).
|
|
219
|
+
# @return [String]
|
|
220
|
+
#
|
|
221
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/InvokeGlobalInferenceGatewayOutput AWS API Documentation
|
|
222
|
+
#
|
|
223
|
+
class InvokeGlobalInferenceGatewayOutput < Struct.new(
|
|
224
|
+
:body)
|
|
225
|
+
SENSITIVE = [:body]
|
|
226
|
+
include Aws::Structure
|
|
227
|
+
end
|
|
228
|
+
|
|
229
|
+
# The request for InvokeGlobalInferenceGatewayWithResponseStream. It has
|
|
230
|
+
# the same members as the InvokeGlobalInferenceGateway request.
|
|
231
|
+
#
|
|
232
|
+
# @!attribute [rw] gateway_id
|
|
233
|
+
# The ID of the Global Inference Gateway to invoke, as for
|
|
234
|
+
# InvokeGlobalInferenceGateway.
|
|
235
|
+
# @return [String]
|
|
236
|
+
#
|
|
237
|
+
# @!attribute [rw] accept
|
|
238
|
+
# The MIME type you want for the response. It is passed to the model
|
|
239
|
+
# server.
|
|
240
|
+
# @return [String]
|
|
241
|
+
#
|
|
242
|
+
# @!attribute [rw] content_type
|
|
243
|
+
# The MIME type of the request body, as for
|
|
244
|
+
# InvokeGlobalInferenceGateway. Pass `application/json`.
|
|
245
|
+
# @return [String]
|
|
246
|
+
#
|
|
247
|
+
# @!attribute [rw] customer_identity_token
|
|
248
|
+
# The customer identity token (a JWT), as for
|
|
249
|
+
# InvokeGlobalInferenceGateway. It is passed unchanged to the
|
|
250
|
+
# inference gateway, which validates it.
|
|
251
|
+
# @return [String]
|
|
252
|
+
#
|
|
253
|
+
# @!attribute [rw] body
|
|
254
|
+
# The inference request body, as for InvokeGlobalInferenceGateway,
|
|
255
|
+
# except that the request is always sent with `"stream": true`: this
|
|
256
|
+
# operation returns an event stream, so a `"stream": false` in the
|
|
257
|
+
# body (or no `stream` key) is overridden. A body larger than 10 MiB
|
|
258
|
+
# is rejected with PayloadTooLargeException (413).
|
|
259
|
+
# @return [String]
|
|
260
|
+
#
|
|
261
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/InvokeGlobalInferenceGatewayWithResponseStreamInput AWS API Documentation
|
|
262
|
+
#
|
|
263
|
+
class InvokeGlobalInferenceGatewayWithResponseStreamInput < Struct.new(
|
|
264
|
+
:gateway_id,
|
|
265
|
+
:accept,
|
|
266
|
+
:content_type,
|
|
267
|
+
:customer_identity_token,
|
|
268
|
+
:body)
|
|
269
|
+
SENSITIVE = [:customer_identity_token, :body]
|
|
270
|
+
include Aws::Structure
|
|
271
|
+
end
|
|
272
|
+
|
|
273
|
+
# The response from InvokeGlobalInferenceGatewayWithResponseStream.
|
|
274
|
+
#
|
|
275
|
+
# @!attribute [rw] body
|
|
276
|
+
# The response as an AWS event stream
|
|
277
|
+
# (application/vnd.amazon.eventstream).
|
|
278
|
+
# @return [Types::ResponseStream]
|
|
279
|
+
#
|
|
280
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/InvokeGlobalInferenceGatewayWithResponseStreamOutput AWS API Documentation
|
|
281
|
+
#
|
|
282
|
+
class InvokeGlobalInferenceGatewayWithResponseStreamOutput < Struct.new(
|
|
283
|
+
:body)
|
|
284
|
+
SENSITIVE = []
|
|
285
|
+
include Aws::Structure
|
|
286
|
+
end
|
|
287
|
+
|
|
288
|
+
# Reserved for a model error during the stream. Not currently sent; a
|
|
289
|
+
# failure after the stream starts is reported as InternalStreamFailure.
|
|
290
|
+
#
|
|
291
|
+
# @!attribute [rw] message
|
|
292
|
+
# A description of the error.
|
|
293
|
+
# @return [String]
|
|
294
|
+
#
|
|
295
|
+
# @!attribute [rw] error_code
|
|
296
|
+
# The error code: `StreamBroken` if the model server's stream broke
|
|
297
|
+
# before it completed, or `ModelInvocationTimeExceeded` if the model
|
|
298
|
+
# exceeded its allowed invocation time.
|
|
299
|
+
# @return [String]
|
|
300
|
+
#
|
|
301
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/ModelStreamError AWS API Documentation
|
|
302
|
+
#
|
|
303
|
+
class ModelStreamError < Struct.new(
|
|
304
|
+
:message,
|
|
305
|
+
:error_code,
|
|
306
|
+
:event_type)
|
|
307
|
+
SENSITIVE = []
|
|
308
|
+
include Aws::Structure
|
|
309
|
+
end
|
|
310
|
+
|
|
311
|
+
# A part of the streamed response.
|
|
312
|
+
#
|
|
313
|
+
# @!attribute [rw] bytes
|
|
314
|
+
# The bytes of this part: a chunk of the model server's server-sent
|
|
315
|
+
# event (SSE) stream.
|
|
316
|
+
# @return [String]
|
|
317
|
+
#
|
|
318
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/PayloadPart AWS API Documentation
|
|
319
|
+
#
|
|
320
|
+
class PayloadPart < Struct.new(
|
|
321
|
+
:bytes,
|
|
322
|
+
:event_type)
|
|
323
|
+
SENSITIVE = [:bytes]
|
|
324
|
+
include Aws::Structure
|
|
325
|
+
end
|
|
326
|
+
|
|
327
|
+
# The request body exceeds the 10 MiB limit. Reduce the size of the
|
|
328
|
+
# payload and send the request again.
|
|
329
|
+
#
|
|
330
|
+
# @!attribute [rw] message
|
|
331
|
+
# A description of the error. It starts with `Global Inference
|
|
332
|
+
# Gateway:`, because the Global Inference Gateway returns this error
|
|
333
|
+
# itself.
|
|
334
|
+
# @return [String]
|
|
335
|
+
#
|
|
336
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/PayloadTooLargeException AWS API Documentation
|
|
337
|
+
#
|
|
338
|
+
class PayloadTooLargeException < Struct.new(
|
|
339
|
+
:message)
|
|
340
|
+
SENSITIVE = []
|
|
341
|
+
include Aws::Structure
|
|
342
|
+
end
|
|
343
|
+
|
|
344
|
+
# No gateway with this ID exists in this account and Region, or no
|
|
345
|
+
# target of the gateway serves the model named in the request body. A
|
|
346
|
+
# model that is served but has no available target right now returns
|
|
347
|
+
# ServiceUnavailableException instead. A message starting `inference
|
|
348
|
+
# gateway` means the inference gateway serving the model returned a 404;
|
|
349
|
+
# up to 256 bytes of its error message are quoted.
|
|
350
|
+
#
|
|
351
|
+
# @!attribute [rw] message
|
|
352
|
+
# A description of the error. It starts with a prefix such as `Global
|
|
353
|
+
# Inference Gateway:` or `inference gateway:` that says where the
|
|
354
|
+
# error came from.
|
|
355
|
+
# @return [String]
|
|
356
|
+
#
|
|
357
|
+
# @!attribute [rw] resource_id
|
|
358
|
+
# The ID of the resource that was not found: the gateway ID, or the
|
|
359
|
+
# model name.
|
|
360
|
+
# @return [String]
|
|
361
|
+
#
|
|
362
|
+
# @!attribute [rw] resource_type
|
|
363
|
+
# The kind of resource that was not found: the gateway, or the model.
|
|
364
|
+
# @return [String]
|
|
365
|
+
#
|
|
366
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/ResourceNotFoundException AWS API Documentation
|
|
367
|
+
#
|
|
368
|
+
class ResourceNotFoundException < Struct.new(
|
|
369
|
+
:message,
|
|
370
|
+
:resource_id,
|
|
371
|
+
:resource_type)
|
|
372
|
+
SENSITIVE = []
|
|
373
|
+
include Aws::Structure
|
|
374
|
+
end
|
|
375
|
+
|
|
376
|
+
# The service is temporarily unable to serve the request, for example
|
|
377
|
+
# because no capacity is available for the requested model. The request
|
|
378
|
+
# was not dispatched for inference. A 503 returned by the inference
|
|
379
|
+
# gateway serving the model after dispatch is reported as
|
|
380
|
+
# BadGatewayException, with the 503 in its `Message`, not as this error.
|
|
381
|
+
#
|
|
382
|
+
# @!attribute [rw] message
|
|
383
|
+
# A description of the error. It starts with `Global Inference
|
|
384
|
+
# Gateway:`, because the Global Inference Gateway returns this error
|
|
385
|
+
# itself.
|
|
386
|
+
# @return [String]
|
|
387
|
+
#
|
|
388
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/ServiceUnavailableException AWS API Documentation
|
|
389
|
+
#
|
|
390
|
+
class ServiceUnavailableException < Struct.new(
|
|
391
|
+
:message)
|
|
392
|
+
SENSITIVE = []
|
|
393
|
+
include Aws::Structure
|
|
394
|
+
end
|
|
395
|
+
|
|
396
|
+
# The request was throttled before it was dispatched for inference.
|
|
397
|
+
# Retry the request with backoff, after the `Retry-After` seconds when
|
|
398
|
+
# the response carries one. A message starting `inference gateway` means
|
|
399
|
+
# the last inference gateway tried for the model returned a 429. The
|
|
400
|
+
# gateway may have tried others first, and they may have failed for
|
|
401
|
+
# other reasons. Up to 256 bytes of its error message are quoted.
|
|
402
|
+
#
|
|
403
|
+
# @!attribute [rw] message
|
|
404
|
+
# A description of the error. It starts with a prefix such as `Global
|
|
405
|
+
# Inference Gateway:` or `inference gateway:` that says where the
|
|
406
|
+
# error came from.
|
|
407
|
+
# @return [String]
|
|
408
|
+
#
|
|
409
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/ThrottlingException AWS API Documentation
|
|
410
|
+
#
|
|
411
|
+
class ThrottlingException < Struct.new(
|
|
412
|
+
:message)
|
|
413
|
+
SENSITIVE = []
|
|
414
|
+
include Aws::Structure
|
|
415
|
+
end
|
|
416
|
+
|
|
417
|
+
# The events in the response stream. The response arrives as PayloadPart
|
|
418
|
+
# events. A failure after the stream starts arrives as one
|
|
419
|
+
# InternalStreamFailure event, and then the stream ends.
|
|
420
|
+
#
|
|
421
|
+
# EventStream is an Enumerator of Events.
|
|
422
|
+
# #event_types #=> Array, returns all modeled event types in the stream
|
|
423
|
+
#
|
|
424
|
+
# @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-gateway-runtime-2026-10-01/ResponseStream AWS API Documentation
|
|
425
|
+
#
|
|
426
|
+
class ResponseStream < Enumerator
|
|
427
|
+
|
|
428
|
+
def event_types
|
|
429
|
+
[
|
|
430
|
+
:payload_part,
|
|
431
|
+
:model_stream_error,
|
|
432
|
+
:internal_stream_failure
|
|
433
|
+
]
|
|
434
|
+
end
|
|
435
|
+
|
|
436
|
+
end
|
|
437
|
+
|
|
438
|
+
end
|
|
439
|
+
end
|
|
440
|
+
|
|
@@ -0,0 +1,62 @@
|
|
|
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(:sagemakergatewayruntime)
|
|
15
|
+
|
|
16
|
+
# This module provides support for Amazon SageMaker Gateway Runtime. This module is available in the
|
|
17
|
+
# `aws-sdk-sagemakergatewayruntime` 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_gateway_runtime = Aws::SageMakerGatewayRuntime::Client.new
|
|
26
|
+
# resp = sage_maker_gateway_runtime.invoke_global_inference_gateway(params)
|
|
27
|
+
#
|
|
28
|
+
# See {Client} for more information.
|
|
29
|
+
#
|
|
30
|
+
# # Errors
|
|
31
|
+
#
|
|
32
|
+
# Errors returned from Amazon SageMaker Gateway Runtime are defined in the
|
|
33
|
+
# {Errors} module and all extend {Errors::ServiceError}.
|
|
34
|
+
#
|
|
35
|
+
# begin
|
|
36
|
+
# # do stuff
|
|
37
|
+
# rescue Aws::SageMakerGatewayRuntime::Errors::ServiceError
|
|
38
|
+
# # rescues all Amazon SageMaker Gateway Runtime API errors
|
|
39
|
+
# end
|
|
40
|
+
#
|
|
41
|
+
# See {Errors} for more information.
|
|
42
|
+
#
|
|
43
|
+
# @!group service
|
|
44
|
+
module Aws::SageMakerGatewayRuntime
|
|
45
|
+
autoload :Types, 'aws-sdk-sagemakergatewayruntime/types'
|
|
46
|
+
autoload :ClientApi, 'aws-sdk-sagemakergatewayruntime/client_api'
|
|
47
|
+
module Plugins
|
|
48
|
+
autoload :Endpoints, 'aws-sdk-sagemakergatewayruntime/plugins/endpoints.rb'
|
|
49
|
+
end
|
|
50
|
+
autoload :Client, 'aws-sdk-sagemakergatewayruntime/client'
|
|
51
|
+
autoload :Errors, 'aws-sdk-sagemakergatewayruntime/errors'
|
|
52
|
+
autoload :Resource, 'aws-sdk-sagemakergatewayruntime/resource'
|
|
53
|
+
autoload :EndpointParameters, 'aws-sdk-sagemakergatewayruntime/endpoint_parameters'
|
|
54
|
+
autoload :EndpointProvider, 'aws-sdk-sagemakergatewayruntime/endpoint_provider'
|
|
55
|
+
autoload :Endpoints, 'aws-sdk-sagemakergatewayruntime/endpoints'
|
|
56
|
+
autoload :EventStreams, 'aws-sdk-sagemakergatewayruntime/event_streams'
|
|
57
|
+
|
|
58
|
+
GEM_VERSION = '1.0.0'
|
|
59
|
+
|
|
60
|
+
end
|
|
61
|
+
|
|
62
|
+
require_relative 'aws-sdk-sagemakergatewayruntime/customizations'
|
data/sig/client.rbs
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
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 SageMakerGatewayRuntime
|
|
10
|
+
class Client < ::Seahorse::Client::Base
|
|
11
|
+
include ::Aws::ClientStubs
|
|
12
|
+
|
|
13
|
+
# https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMakerGatewayRuntime/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
|
+
?event_stream_handler: Proc,
|
|
39
|
+
?ignore_configured_endpoint_urls: bool,
|
|
40
|
+
?input_event_stream_handler: Proc,
|
|
41
|
+
?log_formatter: untyped,
|
|
42
|
+
?log_level: Symbol,
|
|
43
|
+
?logger: untyped,
|
|
44
|
+
?max_attempts: Integer,
|
|
45
|
+
?output_event_stream_handler: Proc,
|
|
46
|
+
?profile: String,
|
|
47
|
+
?request_checksum_calculation: String,
|
|
48
|
+
?request_min_compression_size_bytes: Integer,
|
|
49
|
+
?response_checksum_validation: String,
|
|
50
|
+
?retry_backoff: Proc,
|
|
51
|
+
?retry_base_delay: Float,
|
|
52
|
+
?retry_jitter: (:none | :equal | :full | ^(Integer) -> Integer),
|
|
53
|
+
?retry_limit: Integer,
|
|
54
|
+
?retry_max_delay: Integer,
|
|
55
|
+
?retry_mode: ("legacy" | "standard" | "adaptive"),
|
|
56
|
+
?sdk_ua_app_id: String,
|
|
57
|
+
?secret_access_key: String,
|
|
58
|
+
?session_token: String,
|
|
59
|
+
?sigv4a_signing_region_set: Array[String],
|
|
60
|
+
?stub_responses: untyped,
|
|
61
|
+
?telemetry_provider: Aws::Telemetry::TelemetryProviderBase,
|
|
62
|
+
?token_provider: untyped,
|
|
63
|
+
?use_dualstack_endpoint: bool,
|
|
64
|
+
?use_fips_endpoint: bool,
|
|
65
|
+
?validate_params: bool,
|
|
66
|
+
?endpoint_provider: untyped,
|
|
67
|
+
?http_proxy: String,
|
|
68
|
+
?http_open_timeout: (Float | Integer),
|
|
69
|
+
?http_read_timeout: (Float | Integer),
|
|
70
|
+
?http_idle_timeout: (Float | Integer),
|
|
71
|
+
?http_continue_timeout: (Float | Integer),
|
|
72
|
+
?ssl_timeout: (Float | Integer | nil),
|
|
73
|
+
?http_wire_trace: bool,
|
|
74
|
+
?ssl_verify_peer: bool,
|
|
75
|
+
?ssl_ca_bundle: String,
|
|
76
|
+
?ssl_ca_directory: String,
|
|
77
|
+
?ssl_ca_store: String,
|
|
78
|
+
?on_chunk_received: Proc,
|
|
79
|
+
?on_chunk_sent: Proc,
|
|
80
|
+
?raise_response_errors: bool
|
|
81
|
+
) -> instance
|
|
82
|
+
| (?Hash[Symbol, untyped]) -> instance
|
|
83
|
+
|
|
84
|
+
|
|
85
|
+
interface _InvokeGlobalInferenceGatewayResponseSuccess
|
|
86
|
+
include ::Seahorse::Client::_ResponseSuccess[Types::InvokeGlobalInferenceGatewayOutput]
|
|
87
|
+
def body: () -> ::String
|
|
88
|
+
end
|
|
89
|
+
# https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMakerGatewayRuntime/Client.html#invoke_global_inference_gateway-instance_method
|
|
90
|
+
def invoke_global_inference_gateway: (
|
|
91
|
+
gateway_id: ::String,
|
|
92
|
+
?accept: ::String,
|
|
93
|
+
content_type: ::String,
|
|
94
|
+
?customer_identity_token: ::String,
|
|
95
|
+
body: ::String
|
|
96
|
+
) -> _InvokeGlobalInferenceGatewayResponseSuccess
|
|
97
|
+
| (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) -> _InvokeGlobalInferenceGatewayResponseSuccess
|
|
98
|
+
|
|
99
|
+
interface _InvokeGlobalInferenceGatewayWithResponseStreamResponseSuccess
|
|
100
|
+
include ::Seahorse::Client::_ResponseSuccess[Types::InvokeGlobalInferenceGatewayWithResponseStreamOutput]
|
|
101
|
+
def body: () -> Types::ResponseStream
|
|
102
|
+
end
|
|
103
|
+
# https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/SageMakerGatewayRuntime/Client.html#invoke_global_inference_gateway_with_response_stream-instance_method
|
|
104
|
+
def invoke_global_inference_gateway_with_response_stream: (
|
|
105
|
+
gateway_id: ::String,
|
|
106
|
+
?accept: ::String,
|
|
107
|
+
content_type: ::String,
|
|
108
|
+
?customer_identity_token: ::String,
|
|
109
|
+
body: ::String
|
|
110
|
+
) ?{ (*untyped) -> void } -> _InvokeGlobalInferenceGatewayWithResponseStreamResponseSuccess
|
|
111
|
+
| (Hash[Symbol, untyped] params, ?Hash[Symbol, untyped] options) ?{ (*untyped) -> void } -> _InvokeGlobalInferenceGatewayWithResponseStreamResponseSuccess
|
|
112
|
+
end
|
|
113
|
+
end
|
|
114
|
+
end
|
|
115
|
+
|
data/sig/errors.rbs
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
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 SageMakerGatewayRuntime
|
|
10
|
+
module Errors
|
|
11
|
+
class ServiceError < ::Aws::Errors::ServiceError
|
|
12
|
+
end
|
|
13
|
+
|
|
14
|
+
class AccessDeniedException < ServiceError
|
|
15
|
+
def message: () -> ::String
|
|
16
|
+
end
|
|
17
|
+
class BadGatewayException < ServiceError
|
|
18
|
+
def message: () -> ::String
|
|
19
|
+
end
|
|
20
|
+
class GatewayTimeoutException < ServiceError
|
|
21
|
+
def message: () -> ::String
|
|
22
|
+
end
|
|
23
|
+
class InternalServerException < ServiceError
|
|
24
|
+
def message: () -> ::String
|
|
25
|
+
end
|
|
26
|
+
class InternalStreamFailure < ServiceError
|
|
27
|
+
def message: () -> ::String
|
|
28
|
+
end
|
|
29
|
+
class ModelStreamError < ServiceError
|
|
30
|
+
def message: () -> ::String
|
|
31
|
+
def error_code: () -> ::String
|
|
32
|
+
end
|
|
33
|
+
class PayloadTooLargeException < ServiceError
|
|
34
|
+
def message: () -> ::String
|
|
35
|
+
end
|
|
36
|
+
class ResourceNotFoundException < ServiceError
|
|
37
|
+
def message: () -> ::String
|
|
38
|
+
def resource_id: () -> ::String
|
|
39
|
+
def resource_type: () -> ::String
|
|
40
|
+
end
|
|
41
|
+
class ServiceUnavailableException < ServiceError
|
|
42
|
+
def message: () -> ::String
|
|
43
|
+
end
|
|
44
|
+
class ThrottlingException < ServiceError
|
|
45
|
+
def message: () -> ::String
|
|
46
|
+
end
|
|
47
|
+
end
|
|
48
|
+
end
|
|
49
|
+
end
|