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.
@@ -0,0 +1,768 @@
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
+ require 'seahorse/client/plugins/content_length'
11
+ require 'aws-sdk-core/plugins/credentials_configuration'
12
+ require 'aws-sdk-core/plugins/logging'
13
+ require 'aws-sdk-core/plugins/param_converter'
14
+ require 'aws-sdk-core/plugins/param_validator'
15
+ require 'aws-sdk-core/plugins/user_agent'
16
+ require 'aws-sdk-core/plugins/helpful_socket_errors'
17
+ require 'aws-sdk-core/plugins/retry_errors'
18
+ require 'aws-sdk-core/plugins/global_configuration'
19
+ require 'aws-sdk-core/plugins/regional_endpoint'
20
+ require 'aws-sdk-core/plugins/endpoint_discovery'
21
+ require 'aws-sdk-core/plugins/endpoint_pattern'
22
+ require 'aws-sdk-core/plugins/response_paging'
23
+ require 'aws-sdk-core/plugins/stub_responses'
24
+ require 'aws-sdk-core/plugins/idempotency_token'
25
+ require 'aws-sdk-core/plugins/invocation_id'
26
+ require 'aws-sdk-core/plugins/jsonvalue_converter'
27
+ require 'aws-sdk-core/plugins/client_metrics_plugin'
28
+ require 'aws-sdk-core/plugins/client_metrics_send_plugin'
29
+ require 'aws-sdk-core/plugins/transfer_encoding'
30
+ require 'aws-sdk-core/plugins/http_checksum'
31
+ require 'aws-sdk-core/plugins/checksum_algorithm'
32
+ require 'aws-sdk-core/plugins/request_compression'
33
+ require 'aws-sdk-core/plugins/defaults_mode'
34
+ require 'aws-sdk-core/plugins/recursion_detection'
35
+ require 'aws-sdk-core/plugins/telemetry'
36
+ require 'aws-sdk-core/plugins/sign'
37
+ require 'aws-sdk-core/plugins/protocols/rest_json'
38
+
39
+ module Aws::SageMakerInferenceRouterRuntime
40
+ # An API client for SageMakerInferenceRouterRuntime. To construct a client, you need to configure a `:region` and `:credentials`.
41
+ #
42
+ # client = Aws::SageMakerInferenceRouterRuntime::Client.new(
43
+ # region: region_name,
44
+ # credentials: credentials,
45
+ # # ...
46
+ # )
47
+ #
48
+ # For details on configuring region and credentials see
49
+ # the [developer guide](/sdk-for-ruby/v3/developer-guide/setup-config.html).
50
+ #
51
+ # See {#initialize} for a full list of supported configuration options.
52
+ class Client < Seahorse::Client::Base
53
+
54
+ include Aws::ClientStubs
55
+
56
+ @identifier = :sagemakerinferencerouterruntime
57
+
58
+ set_api(ClientApi::API)
59
+
60
+ add_plugin(Seahorse::Client::Plugins::ContentLength)
61
+ add_plugin(Aws::Plugins::CredentialsConfiguration)
62
+ add_plugin(Aws::Plugins::Logging)
63
+ add_plugin(Aws::Plugins::ParamConverter)
64
+ add_plugin(Aws::Plugins::ParamValidator)
65
+ add_plugin(Aws::Plugins::UserAgent)
66
+ add_plugin(Aws::Plugins::HelpfulSocketErrors)
67
+ add_plugin(Aws::Plugins::RetryErrors)
68
+ add_plugin(Aws::Plugins::GlobalConfiguration)
69
+ add_plugin(Aws::Plugins::RegionalEndpoint)
70
+ add_plugin(Aws::Plugins::EndpointDiscovery)
71
+ add_plugin(Aws::Plugins::EndpointPattern)
72
+ add_plugin(Aws::Plugins::ResponsePaging)
73
+ add_plugin(Aws::Plugins::StubResponses)
74
+ add_plugin(Aws::Plugins::IdempotencyToken)
75
+ add_plugin(Aws::Plugins::InvocationId)
76
+ add_plugin(Aws::Plugins::JsonvalueConverter)
77
+ add_plugin(Aws::Plugins::ClientMetricsPlugin)
78
+ add_plugin(Aws::Plugins::ClientMetricsSendPlugin)
79
+ add_plugin(Aws::Plugins::TransferEncoding)
80
+ add_plugin(Aws::Plugins::HttpChecksum)
81
+ add_plugin(Aws::Plugins::ChecksumAlgorithm)
82
+ add_plugin(Aws::Plugins::RequestCompression)
83
+ add_plugin(Aws::Plugins::DefaultsMode)
84
+ add_plugin(Aws::Plugins::RecursionDetection)
85
+ add_plugin(Aws::Plugins::Telemetry)
86
+ add_plugin(Aws::Plugins::Sign)
87
+ add_plugin(Aws::Plugins::Protocols::RestJson)
88
+ add_plugin(Aws::SageMakerInferenceRouterRuntime::Plugins::Endpoints)
89
+
90
+ # @overload initialize(options)
91
+ # @param [Hash] options
92
+ #
93
+ # @option options [Array<Seahorse::Client::Plugin>] :plugins ([]])
94
+ # A list of plugins to apply to the client. Each plugin is either a
95
+ # class name or an instance of a plugin class.
96
+ #
97
+ # @option options [required, Aws::CredentialProvider] :credentials
98
+ # Your AWS credentials used for authentication. This can be any class that includes and implements
99
+ # `Aws::CredentialProvider`, or instance of any one of the following classes:
100
+ #
101
+ # * `Aws::Credentials` - Used for configuring static, non-refreshing
102
+ # credentials.
103
+ #
104
+ # * `Aws::SharedCredentials` - Used for loading static credentials from a
105
+ # shared file, such as `~/.aws/config`.
106
+ #
107
+ # * `Aws::AssumeRoleCredentials` - Used when you need to assume a role.
108
+ #
109
+ # * `Aws::AssumeRoleWebIdentityCredentials` - Used when you need to
110
+ # assume a role after providing credentials via the web.
111
+ #
112
+ # * `Aws::SSOCredentials` - Used for loading credentials from AWS SSO using an
113
+ # access token generated from `aws login`.
114
+ #
115
+ # * `Aws::ProcessCredentials` - Used for loading credentials from a
116
+ # process that outputs to stdout.
117
+ #
118
+ # * `Aws::InstanceProfileCredentials` - Used for loading credentials
119
+ # from an EC2 IMDS on an EC2 instance.
120
+ #
121
+ # * `Aws::ECSCredentials` - Used for loading credentials from
122
+ # instances running in ECS.
123
+ #
124
+ # * `Aws::CognitoIdentityCredentials` - Used for loading credentials
125
+ # from the Cognito Identity service.
126
+ #
127
+ # When `:credentials` are not configured directly, the following locations will be searched for credentials:
128
+ #
129
+ # * `Aws.config[:credentials]`
130
+ #
131
+ # * The `:access_key_id`, `:secret_access_key`, `:session_token`, and
132
+ # `:account_id` options.
133
+ #
134
+ # * `ENV['AWS_ACCESS_KEY_ID']`, `ENV['AWS_SECRET_ACCESS_KEY']`,
135
+ # `ENV['AWS_SESSION_TOKEN']`, and `ENV['AWS_ACCOUNT_ID']`.
136
+ #
137
+ # * `~/.aws/credentials`
138
+ #
139
+ # * `~/.aws/config`
140
+ #
141
+ # * EC2/ECS IMDS instance profile - When used by default, the timeouts are very aggressive.
142
+ # Construct and pass an instance of `Aws::InstanceProfileCredentials` or `Aws::ECSCredentials` to
143
+ # enable retries and extended timeouts. Instance profile credential fetching can be disabled by
144
+ # setting `ENV['AWS_EC2_METADATA_DISABLED']` to `true`.
145
+ #
146
+ # @option options [required, String] :region
147
+ # The AWS region to connect to. The configured `:region` is
148
+ # used to determine the service `:endpoint`. When not passed,
149
+ # a default `:region` is searched for in the following locations:
150
+ #
151
+ # * `Aws.config[:region]`
152
+ # * `ENV['AWS_REGION']`
153
+ # * `ENV['AMAZON_REGION']`
154
+ # * `ENV['AWS_DEFAULT_REGION']`
155
+ # * `~/.aws/credentials`
156
+ # * `~/.aws/config`
157
+ #
158
+ # @option options [String] :access_key_id
159
+ #
160
+ # @option options [String] :account_id
161
+ #
162
+ # @option options [Boolean] :active_endpoint_cache (false)
163
+ # When set to `true`, a thread polling for endpoints will be running in
164
+ # the background every 60 secs (default). Defaults to `false`.
165
+ #
166
+ # @option options [Boolean] :adaptive_retry_wait_to_fill (true)
167
+ # Used only in `adaptive` retry mode. When true, the request will sleep
168
+ # until there is sufficent client side capacity to retry the request.
169
+ # When false, the request will raise a `RetryCapacityNotAvailableError` and will
170
+ # not retry instead of sleeping.
171
+ #
172
+ # @option options [Array<String>] :auth_scheme_preference
173
+ # A list of preferred authentication schemes to use when making a request. Supported values are:
174
+ # `sigv4`, `sigv4a`, `httpBearerAuth`, and `noAuth`. When set using `ENV['AWS_AUTH_SCHEME_PREFERENCE']` or in
175
+ # shared config as `auth_scheme_preference`, the value should be a comma-separated list.
176
+ #
177
+ # @option options [Boolean] :client_side_monitoring (false)
178
+ # When `true`, client-side metrics will be collected for all API requests from
179
+ # this client.
180
+ #
181
+ # @option options [String] :client_side_monitoring_client_id ("")
182
+ # Allows you to provide an identifier for this client which will be attached to
183
+ # all generated client side metrics. Defaults to an empty string.
184
+ #
185
+ # @option options [String] :client_side_monitoring_host ("127.0.0.1")
186
+ # Allows you to specify the DNS hostname or IPv4 or IPv6 address that the client
187
+ # side monitoring agent is running on, where client metrics will be published via UDP.
188
+ #
189
+ # @option options [Integer] :client_side_monitoring_port (31000)
190
+ # Required for publishing client metrics. The port that the client side monitoring
191
+ # agent is running on, where client metrics will be published via UDP.
192
+ #
193
+ # @option options [Aws::ClientSideMonitoring::Publisher] :client_side_monitoring_publisher (Aws::ClientSideMonitoring::Publisher)
194
+ # Allows you to provide a custom client-side monitoring publisher class. By default,
195
+ # will use the Client Side Monitoring Agent Publisher.
196
+ #
197
+ # @option options [Boolean] :convert_params (true)
198
+ # When `true`, an attempt is made to coerce request parameters into
199
+ # the required types.
200
+ #
201
+ # @option options [Boolean] :correct_clock_skew (true)
202
+ # Used only in `standard` and `adaptive` retry modes. Specifies whether
203
+ # to apply a clock skew correction and retry requests with skewed client
204
+ # clocks. Takes effect only when `disable_clock_skew_correction` is not set.
205
+ #
206
+ # @option options [String] :defaults_mode ("legacy")
207
+ # See {Aws::DefaultsModeConfiguration} for a list of the
208
+ # accepted modes and the configuration defaults that are included.
209
+ #
210
+ # @option options [Boolean] :disable_clock_skew_correction
211
+ # Used only in `standard` and `adaptive` retry modes. When `true`, the
212
+ # SDK does not apply a clock skew correction, does not update its stored
213
+ # skew from responses, and does not retry clock skew errors. Clock skew
214
+ # correction is enabled by default.
215
+ #
216
+ # @option options [Boolean] :disable_host_prefix_injection (false)
217
+ # When `true`, the SDK will not prepend the modeled host prefix to the endpoint.
218
+ #
219
+ # @option options [Boolean] :disable_request_compression (false)
220
+ # When set to 'true' the request body will not be compressed
221
+ # for supported operations.
222
+ #
223
+ # @option options [String, URI::HTTPS, URI::HTTP] :endpoint
224
+ # Normally you should not configure the `:endpoint` option
225
+ # directly. This is normally constructed from the `:region`
226
+ # option. Configuring `:endpoint` is normally reserved for
227
+ # connecting to test or custom endpoints. The endpoint should
228
+ # be a URI formatted like:
229
+ #
230
+ # 'http://example.com'
231
+ # 'https://example.com'
232
+ # 'http://example.com:123'
233
+ #
234
+ # @option options [Integer] :endpoint_cache_max_entries (1000)
235
+ # Used for the maximum size limit of the LRU cache storing endpoints data
236
+ # for endpoint discovery enabled operations. Defaults to 1000.
237
+ #
238
+ # @option options [Integer] :endpoint_cache_max_threads (10)
239
+ # Used for the maximum threads in use for polling endpoints to be cached, defaults to 10.
240
+ #
241
+ # @option options [Integer] :endpoint_cache_poll_interval (60)
242
+ # When :endpoint_discovery and :active_endpoint_cache is enabled,
243
+ # Use this option to config the time interval in seconds for making
244
+ # requests fetching endpoints information. Defaults to 60 sec.
245
+ #
246
+ # @option options [Boolean] :endpoint_discovery (false)
247
+ # When set to `true`, endpoint discovery will be enabled for operations when available.
248
+ #
249
+ # @option options [Boolean] :ignore_configured_endpoint_urls
250
+ # Setting to true disables use of endpoint URLs provided via environment
251
+ # variables and the shared configuration file.
252
+ #
253
+ # @option options [Aws::Log::Formatter] :log_formatter (Aws::Log::Formatter.default)
254
+ # The log formatter.
255
+ #
256
+ # @option options [Symbol] :log_level (:info)
257
+ # The log level to send messages to the `:logger` at.
258
+ #
259
+ # @option options [Logger] :logger
260
+ # The Logger instance to send log messages to. If this option
261
+ # is not set, logging will be disabled.
262
+ #
263
+ # @option options [Integer] :max_attempts (3)
264
+ # An integer representing the maximum number attempts that will be made for
265
+ # a single request, including the initial attempt. For example,
266
+ # setting this value to 5 will result in a request being retried up to
267
+ # 4 times. Used in `standard` and `adaptive` retry modes. Defaults to 3,
268
+ # except for DynamoDB and DynamoDB Streams, which default to 4.
269
+ #
270
+ # @option options [String] :profile ("default")
271
+ # Used when loading credentials from the shared credentials file at `HOME/.aws/credentials`.
272
+ # When not specified, 'default' is used.
273
+ #
274
+ # @option options [String] :request_checksum_calculation ("when_supported")
275
+ # Determines when a checksum will be calculated for request payloads. Values are:
276
+ #
277
+ # * `when_supported` - (default) When set, a checksum will be
278
+ # calculated for all request payloads of operations modeled with the
279
+ # `httpChecksum` trait where `requestChecksumRequired` is `true` and/or a
280
+ # `requestAlgorithmMember` is modeled.
281
+ # * `when_required` - When set, a checksum will only be calculated for
282
+ # request payloads of operations modeled with the `httpChecksum` trait where
283
+ # `requestChecksumRequired` is `true` or where a `requestAlgorithmMember`
284
+ # is modeled and supplied.
285
+ #
286
+ # @option options [Integer] :request_min_compression_size_bytes (10240)
287
+ # The minimum size in bytes that triggers compression for request
288
+ # bodies. The value must be non-negative integer value between 0
289
+ # and 10485780 bytes inclusive.
290
+ #
291
+ # @option options [String] :response_checksum_validation ("when_supported")
292
+ # Determines when checksum validation will be performed on response payloads. Values are:
293
+ #
294
+ # * `when_supported` - (default) When set, checksum validation is performed on all
295
+ # response payloads of operations modeled with the `httpChecksum` trait where
296
+ # `responseAlgorithms` is modeled, except when no modeled checksum algorithms
297
+ # are supported.
298
+ # * `when_required` - When set, checksum validation is not performed on
299
+ # response payloads of operations unless the checksum algorithm is supported and
300
+ # the `requestValidationModeMember` member is set to `ENABLED`.
301
+ #
302
+ # @option options [Proc] :retry_backoff
303
+ # A proc or lambda used for backoff. Defaults to 2**retries * retry_base_delay.
304
+ # This option is only used in the `legacy` retry mode.
305
+ #
306
+ # @option options [Float] :retry_base_delay (0.3)
307
+ # The base delay in seconds used by the default backoff function. This option
308
+ # is only used in the `legacy` retry mode.
309
+ #
310
+ # @option options [Symbol] :retry_jitter (:none)
311
+ # A delay randomiser function used by the default backoff function.
312
+ # Some predefined functions can be referenced by name - :none, :equal, :full,
313
+ # otherwise a Proc that takes and returns a number. This option is only used
314
+ # in the `legacy` retry mode.
315
+ #
316
+ # @see https://www.awsarchitectureblog.com/2015/03/backoff.html
317
+ #
318
+ # @option options [Integer] :retry_limit (3)
319
+ # The maximum number of times to retry failed requests. Only
320
+ # ~ 500 level server errors and certain ~ 400 level client errors
321
+ # are retried. Generally, these are throttling errors, data
322
+ # checksum errors, networking errors, timeout errors, auth errors,
323
+ # endpoint discovery, and errors from expired credentials.
324
+ # This option is only used in the `legacy` retry mode.
325
+ #
326
+ # @option options [Integer] :retry_max_delay (0)
327
+ # The maximum number of seconds to delay between retries (0 for no limit)
328
+ # used by the default backoff function. This option is only used in the
329
+ # `legacy` retry mode.
330
+ #
331
+ # @option options [String] :retry_mode ("standard")
332
+ # Specifies which retry algorithm to use. Values are:
333
+ #
334
+ # * `legacy` - The pre-existing retry behavior.
335
+ #
336
+ # * `standard` - A standardized set of retry rules across the AWS SDKs.
337
+ # This includes support for retry quotas, which limit the number of
338
+ # unsuccessful retries a client can make. This is the default value
339
+ # if no retry mode is provided.
340
+ #
341
+ # * `adaptive` - A retry mode that includes all the functionality of
342
+ # `standard` mode along with automatic client side throttling.
343
+ #
344
+ # @option options [String] :sdk_ua_app_id
345
+ # A unique and opaque application ID that is appended to the
346
+ # User-Agent header as app/sdk_ua_app_id. It should have a
347
+ # maximum length of 50. This variable is sourced from environment
348
+ # variable AWS_SDK_UA_APP_ID or the shared config profile attribute sdk_ua_app_id.
349
+ #
350
+ # @option options [String] :secret_access_key
351
+ #
352
+ # @option options [String] :session_token
353
+ #
354
+ # @option options [Array] :sigv4a_signing_region_set
355
+ # A list of regions that should be signed with SigV4a signing. When
356
+ # not passed, a default `:sigv4a_signing_region_set` is searched for
357
+ # in the following locations:
358
+ #
359
+ # * `Aws.config[:sigv4a_signing_region_set]`
360
+ # * `ENV['AWS_SIGV4A_SIGNING_REGION_SET']`
361
+ # * `~/.aws/config`
362
+ #
363
+ # @option options [Boolean] :stub_responses (false)
364
+ # Causes the client to return stubbed responses. By default
365
+ # fake responses are generated and returned. You can specify
366
+ # the response data to return or errors to raise by calling
367
+ # {ClientStubs#stub_responses}. See {ClientStubs} for more information.
368
+ #
369
+ # ** Please note ** When response stubbing is enabled, no HTTP
370
+ # requests are made, and retries are disabled.
371
+ #
372
+ # @option options [Aws::Telemetry::TelemetryProviderBase] :telemetry_provider (Aws::Telemetry::NoOpTelemetryProvider)
373
+ # Allows you to provide a telemetry provider, which is used to
374
+ # emit telemetry data. By default, uses `NoOpTelemetryProvider` which
375
+ # will not record or emit any telemetry data. The SDK supports the
376
+ # following telemetry providers:
377
+ #
378
+ # * OpenTelemetry (OTel) - To use the OTel provider, install and require the
379
+ # `opentelemetry-sdk` gem and then, pass in an instance of a
380
+ # `Aws::Telemetry::OTelProvider` for telemetry provider.
381
+ #
382
+ # @option options [Aws::TokenProvider] :token_provider
383
+ # Your Bearer token used for authentication. This can be any class that includes and implements
384
+ # `Aws::TokenProvider`, or instance of any one of the following classes:
385
+ #
386
+ # * `Aws::StaticTokenProvider` - Used for configuring static, non-refreshing
387
+ # tokens.
388
+ #
389
+ # * `Aws::SSOTokenProvider` - Used for loading tokens from AWS SSO using an
390
+ # access token generated from `aws login`.
391
+ #
392
+ # When `:token_provider` is not configured directly, the `Aws::TokenProviderChain`
393
+ # will be used to search for tokens configured for your profile in shared configuration files.
394
+ #
395
+ # @option options [Boolean] :use_dualstack_endpoint
396
+ # When set to `true`, dualstack enabled endpoints (with `.aws` TLD)
397
+ # will be used if available.
398
+ #
399
+ # @option options [Boolean] :use_fips_endpoint
400
+ # When set to `true`, fips compatible endpoints will be used if available.
401
+ # When a `fips` region is used, the region is normalized and this config
402
+ # is set to `true`.
403
+ #
404
+ # @option options [Boolean] :validate_params (true)
405
+ # When `true`, request parameters are validated before
406
+ # sending the request.
407
+ #
408
+ # @option options [Aws::SageMakerInferenceRouterRuntime::EndpointProvider] :endpoint_provider
409
+ # The endpoint provider used to resolve endpoints. Any object that responds to
410
+ # `#resolve_endpoint(parameters)` where `parameters` is a Struct similar to
411
+ # `Aws::SageMakerInferenceRouterRuntime::EndpointParameters`.
412
+ #
413
+ # @option options [Float] :http_continue_timeout (1)
414
+ # The number of seconds to wait for a 100-continue response before sending the
415
+ # request body. This option has no effect unless the request has "Expect"
416
+ # header set to "100-continue". Defaults to `nil` which disables this
417
+ # behaviour. This value can safely be set per request on the session.
418
+ #
419
+ # @option options [Float] :http_idle_timeout (5)
420
+ # The number of seconds a connection is allowed to sit idle before it
421
+ # is considered stale. Stale connections are closed and removed from the
422
+ # pool before making a request.
423
+ #
424
+ # @option options [Float] :http_open_timeout (15)
425
+ # The default number of seconds to wait for response data.
426
+ # This value can safely be set per-request on the session.
427
+ #
428
+ # @option options [URI::HTTP,String] :http_proxy
429
+ # A proxy to send requests through. Formatted like 'http://proxy.com:123'.
430
+ #
431
+ # @option options [Float] :http_read_timeout (60)
432
+ # The default number of seconds to wait for response data.
433
+ # This value can safely be set per-request on the session.
434
+ #
435
+ # @option options [Boolean] :http_wire_trace (false)
436
+ # When `true`, HTTP debug output will be sent to the `:logger`.
437
+ #
438
+ # @option options [Proc] :on_chunk_received
439
+ # When a Proc object is provided, it will be used as callback when each chunk
440
+ # of the response body is received. It provides three arguments: the chunk,
441
+ # the number of bytes received, and the total number of
442
+ # bytes in the response (or nil if the server did not send a `content-length`).
443
+ #
444
+ # @option options [Proc] :on_chunk_sent
445
+ # When a Proc object is provided, it will be used as callback when each chunk
446
+ # of the request body is sent. It provides three arguments: the chunk,
447
+ # the number of bytes read from the body, and the total number of
448
+ # bytes in the body.
449
+ #
450
+ # @option options [Boolean] :raise_response_errors (true)
451
+ # When `true`, response errors are raised.
452
+ #
453
+ # @option options [String] :ssl_ca_bundle
454
+ # Full path to the SSL certificate authority bundle file that should be used when
455
+ # verifying peer certificates. If you do not pass `:ssl_ca_bundle` or
456
+ # `:ssl_ca_directory` the the system default will be used if available.
457
+ #
458
+ # @option options [String] :ssl_ca_directory
459
+ # Full path of the directory that contains the unbundled SSL certificate
460
+ # authority files for verifying peer certificates. If you do
461
+ # not pass `:ssl_ca_bundle` or `:ssl_ca_directory` the the system
462
+ # default will be used if available.
463
+ #
464
+ # @option options [String] :ssl_ca_store
465
+ # Sets the X509::Store to verify peer certificate.
466
+ #
467
+ # @option options [OpenSSL::X509::Certificate] :ssl_cert
468
+ # Sets a client certificate when creating http connections.
469
+ #
470
+ # @option options [OpenSSL::PKey] :ssl_key
471
+ # Sets a client key when creating http connections.
472
+ #
473
+ # @option options [Float] :ssl_timeout
474
+ # Sets the SSL timeout in seconds
475
+ #
476
+ # @option options [Boolean] :ssl_verify_peer (true)
477
+ # When `true`, SSL peer certificates are verified when establishing a connection.
478
+ #
479
+ def initialize(*args)
480
+ super
481
+ end
482
+
483
+ # @!group API Operations
484
+
485
+ # Sends a real-time inference request to an inference router. In the
486
+ # request, you name the routing target, and the router sends the request
487
+ # to one of the routing target's destinations. The response includes
488
+ # the destination that served the request and the reason that the router
489
+ # chose it.
490
+ #
491
+ # The following limits apply:
492
+ #
493
+ # * The maximum request payload is 6 MB. A request with a larger body
494
+ # fails with HTTP status code 413.
495
+ #
496
+ # * Your model has up to 60 seconds for each attempt, the same limit as
497
+ # `InvokeEndpoint`. If your account has a higher model execution
498
+ # timeout for `InvokeEndpoint`, it doesn't apply through an inference
499
+ # router. For models that take longer, use
500
+ # `InvokeInferenceRouterAsync`.
501
+ #
502
+ # If a destination returns an error that the router can retry, such as a
503
+ # throttling error, before your model produces a response, the router
504
+ # retries the request once on another destination. A request that times
505
+ # out on a destination isn't retried. Because a request can make two
506
+ # attempts, set your client read timeout to at least 170 seconds.
507
+ #
508
+ # The caller needs permission to invoke the inference router and every
509
+ # destination of the routing target. For information about permissions,
510
+ # see [Route requests across Regions with inference routers][1].
511
+ #
512
+ #
513
+ #
514
+ # [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/inference-router.html
515
+ #
516
+ # @option params [required, String] :inference_router_name
517
+ # The name of the inference router to invoke.
518
+ #
519
+ # @option params [required, String] :routing_target_name
520
+ # The name of the routing target in the inference router. The routing
521
+ # target lists the destinations that can serve the request.
522
+ #
523
+ # @option params [String] :content_type
524
+ # The MIME type of the input data in the request body. The router passes
525
+ # it to the destination.
526
+ #
527
+ # @option params [String] :accept
528
+ # The MIME type that you want for the inference response. The router
529
+ # passes it to the destination.
530
+ #
531
+ # @option params [String] :inference_id
532
+ # An identifier for the inference request. The router passes it to the
533
+ # destination.
534
+ #
535
+ # @option params [String] :prefix_aware_id
536
+ # An optional, stable identifier that serves as a routing hint for
537
+ # prefix-aware routing. The router passes it to the destination that
538
+ # serves the request. Within that destination, requests with the same
539
+ # prefix and the same identifier go to the same instance. If requests
540
+ # from different applications might have the same prompt prefix, set a
541
+ # different identifier for each application to differentiate their
542
+ # routing decisions.
543
+ #
544
+ # Applies only to destination endpoints configured with a
545
+ # `RoutingStrategy` of `PREFIX_AWARE`.
546
+ #
547
+ # @option params [String] :custom_attributes
548
+ # Provides additional information about the inference request. The value
549
+ # is an opaque string that the router passes, unchanged, to the model
550
+ # container of the destination that serves the request. The value can
551
+ # contain up to 1,024 visible US-ASCII characters.
552
+ #
553
+ # @option params [required, String, StringIO, File] :body
554
+ # The input data for the inference, in the format that your model
555
+ # expects. The body can't be empty.
556
+ #
557
+ # @return [Types::InvokeInferenceRouterOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
558
+ #
559
+ # * {Types::InvokeInferenceRouterOutput#body #body} => String
560
+ # * {Types::InvokeInferenceRouterOutput#content_type #content_type} => String
561
+ # * {Types::InvokeInferenceRouterOutput#invoked_routed_resource_arn #invoked_routed_resource_arn} => String
562
+ # * {Types::InvokeInferenceRouterOutput#routing_reason #routing_reason} => String
563
+ # * {Types::InvokeInferenceRouterOutput#invoked_production_variant #invoked_production_variant} => String
564
+ # * {Types::InvokeInferenceRouterOutput#custom_attributes #custom_attributes} => String
565
+ #
566
+ #
567
+ # @example Example: Invoke an inference router
568
+ #
569
+ # # The following example sends a JSON request to the my-target routing target of the my-router inference router. The
570
+ # # response shows that a destination in the router's Region served the request.
571
+ #
572
+ # resp = client.invoke_inference_router({
573
+ # body: "{\"instances\": [[1.0, 2.0, 5.0]]}",
574
+ # content_type: "application/json",
575
+ # inference_router_name: "my-router",
576
+ # routing_target_name: "my-target",
577
+ # })
578
+ #
579
+ # resp.to_h outputs the following:
580
+ # {
581
+ # content_type: "application/json",
582
+ # routing_reason: "local-preferred",
583
+ # }
584
+ #
585
+ # @example Request syntax with placeholder values
586
+ #
587
+ # resp = client.invoke_inference_router({
588
+ # inference_router_name: "InvokeInferenceRouterInputInferenceRouterNameString", # required
589
+ # routing_target_name: "InvokeInferenceRouterInputRoutingTargetNameString", # required
590
+ # content_type: "InvokeInferenceRouterInputContentTypeString",
591
+ # accept: "InvokeInferenceRouterInputAcceptString",
592
+ # inference_id: "InvokeInferenceRouterInputInferenceIdString",
593
+ # prefix_aware_id: "InvokeInferenceRouterInputPrefixAwareIdString",
594
+ # custom_attributes: "CustomAttributesHeader",
595
+ # body: "data", # required
596
+ # })
597
+ #
598
+ # @example Response structure
599
+ #
600
+ # resp.body #=> String
601
+ # resp.content_type #=> String
602
+ # resp.invoked_routed_resource_arn #=> String
603
+ # resp.routing_reason #=> String
604
+ # resp.invoked_production_variant #=> String
605
+ # resp.custom_attributes #=> String
606
+ #
607
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InvokeInferenceRouter AWS API Documentation
608
+ #
609
+ # @overload invoke_inference_router(params = {})
610
+ # @param [Hash] params ({})
611
+ def invoke_inference_router(params = {}, options = {})
612
+ req = build_request(:invoke_inference_router, params)
613
+ req.send_request(options)
614
+ end
615
+
616
+ # Submits an asynchronous inference request to an inference router.
617
+ # Before you call this operation, upload the input data to Amazon S3 in
618
+ # the router's Amazon Web Services Region. The router returns as soon
619
+ # as it accepts the request, and sends the request to one of the
620
+ # destinations of the routing target. The destination reads the input
621
+ # from Amazon S3, and the inference response is written to the Amazon S3
622
+ # output path that the routing target specifies.
623
+ #
624
+ # If a destination doesn't start the request within the routing
625
+ # target's `MaxTimeInBacklogSeconds`, the router moves the request to
626
+ # another destination. After your model starts processing the request,
627
+ # the request doesn't move. If no destination can take the request
628
+ # before `RequestTTLSeconds` runs out, or every destination has been
629
+ # tried, the router writes a failure object to the `FailureLocation` and
630
+ # publishes a notification to the routing target's error topic, if one
631
+ # is configured.
632
+ #
633
+ # For information about the permissions that the caller and each
634
+ # destination need, see [Send asynchronous requests through an inference
635
+ # router][1].
636
+ #
637
+ #
638
+ #
639
+ # [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/inference-router-async.html
640
+ #
641
+ # @option params [required, String] :inference_router_name
642
+ # The name of the inference router to invoke.
643
+ #
644
+ # @option params [required, String] :routing_target_name
645
+ # The name of the routing target in the inference router. The routing
646
+ # target must be configured for asynchronous inference.
647
+ #
648
+ # @option params [String] :content_type
649
+ # The MIME type of the input data in Amazon S3. The router passes it to
650
+ # the destination.
651
+ #
652
+ # @option params [String] :accept
653
+ # The MIME type that you want for the inference response. The router
654
+ # passes it to the destination.
655
+ #
656
+ # @option params [String] :custom_attributes
657
+ # Provides additional information about the inference request. The value
658
+ # is an opaque string that the router passes, unchanged, to the model
659
+ # container of the destination that serves the request. The value can
660
+ # contain up to 1,024 visible US-ASCII characters.
661
+ #
662
+ # @option params [String] :inference_id
663
+ # An identifier for the inference request. If you don't provide one,
664
+ # SageMaker AI generates one and returns it in the response.
665
+ #
666
+ # @option params [required, String] :input_location
667
+ # The Amazon S3 URI of the object that contains the input data for the
668
+ # inference. The bucket must be in the inference router's Amazon Web
669
+ # Services Region and owned by the router's account. The destination
670
+ # endpoint's execution role reads the object, and the destination's
671
+ # asynchronous inference limits apply to it.
672
+ #
673
+ # @option params [String] :s3_output_path_extension
674
+ # The path extension that is appended to the routing target's Amazon S3
675
+ # output path where the inference response is stored.
676
+ #
677
+ # @option params [String] :filename
678
+ # The file name of the inference response stored in Amazon S3. If you
679
+ # don't provide one, SageMaker AI generates one.
680
+ #
681
+ # @option params [Integer] :request_ttl_seconds
682
+ # The time to live of the request, in seconds, measured from when the
683
+ # router accepts it. If no destination starts the request in this time,
684
+ # the request fails. The default is 21,600 seconds (6 hours).
685
+ #
686
+ # @option params [Integer] :invocation_timeout_seconds
687
+ # The maximum time, in seconds, that a destination can spend processing
688
+ # the request before the request is marked as expired. The default is
689
+ # 900 seconds (15 minutes).
690
+ #
691
+ # @return [Types::InvokeInferenceRouterAsyncOutput] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
692
+ #
693
+ # * {Types::InvokeInferenceRouterAsyncOutput#inference_id #inference_id} => String
694
+ # * {Types::InvokeInferenceRouterAsyncOutput#output_location #output_location} => String
695
+ # * {Types::InvokeInferenceRouterAsyncOutput#failure_location #failure_location} => String
696
+ #
697
+ # @example Request syntax with placeholder values
698
+ #
699
+ # resp = client.invoke_inference_router_async({
700
+ # inference_router_name: "InvokeInferenceRouterAsyncInputInferenceRouterNameString", # required
701
+ # routing_target_name: "InvokeInferenceRouterAsyncInputRoutingTargetNameString", # required
702
+ # content_type: "InvokeInferenceRouterAsyncInputContentTypeString",
703
+ # accept: "InvokeInferenceRouterAsyncInputAcceptString",
704
+ # custom_attributes: "CustomAttributesHeader",
705
+ # inference_id: "InvokeInferenceRouterAsyncInputInferenceIdString",
706
+ # input_location: "InvokeInferenceRouterAsyncInputInputLocationString", # required
707
+ # s3_output_path_extension: "InvokeInferenceRouterAsyncInputS3OutputPathExtensionString",
708
+ # filename: "InvokeInferenceRouterAsyncInputFilenameString",
709
+ # request_ttl_seconds: 1,
710
+ # invocation_timeout_seconds: 1,
711
+ # })
712
+ #
713
+ # @example Response structure
714
+ #
715
+ # resp.inference_id #=> String
716
+ # resp.output_location #=> String
717
+ # resp.failure_location #=> String
718
+ #
719
+ # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-inference-router-runtime-2026-01-01/InvokeInferenceRouterAsync AWS API Documentation
720
+ #
721
+ # @overload invoke_inference_router_async(params = {})
722
+ # @param [Hash] params ({})
723
+ def invoke_inference_router_async(params = {}, options = {})
724
+ req = build_request(:invoke_inference_router_async, params)
725
+ req.send_request(options)
726
+ end
727
+
728
+ # @!endgroup
729
+
730
+ # @param params ({})
731
+ # @api private
732
+ def build_request(operation_name, params = {})
733
+ handlers = @handlers.for(operation_name)
734
+ tracer = config.telemetry_provider.tracer_provider.tracer(
735
+ Aws::Telemetry.module_to_tracer_name('Aws::SageMakerInferenceRouterRuntime')
736
+ )
737
+ context = Seahorse::Client::RequestContext.new(
738
+ operation_name: operation_name,
739
+ operation: config.api.operation(operation_name),
740
+ client: self,
741
+ params: params,
742
+ config: config,
743
+ tracer: tracer
744
+ )
745
+ context[:gem_name] = 'aws-sdk-sagemakerinferencerouterruntime'
746
+ context[:gem_version] = '1.0.0'
747
+ Seahorse::Client::Request.new(handlers, context)
748
+ end
749
+
750
+ # @api private
751
+ # @deprecated
752
+ def waiter_names
753
+ []
754
+ end
755
+
756
+ class << self
757
+
758
+ # @api private
759
+ attr_reader :identifier
760
+
761
+ # @api private
762
+ def errors_module
763
+ Errors
764
+ end
765
+
766
+ end
767
+ end
768
+ end