File: api_op_CreateEndpointConfig.go

package info (click to toggle)
golang-github-aws-aws-sdk-go-v2 1.24.1-2~bpo12%2B1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm-backports
  • size: 554,032 kB
  • sloc: java: 15,941; makefile: 419; sh: 175
file content (241 lines) | stat: -rw-r--r-- 10,683 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
// Code generated by smithy-go-codegen DO NOT EDIT.

package sagemaker

import (
	"context"
	"fmt"
	awsmiddleware "github.com/aws/aws-sdk-go-v2/aws/middleware"
	"github.com/aws/aws-sdk-go-v2/aws/signer/v4"
	"github.com/aws/aws-sdk-go-v2/service/sagemaker/types"
	"github.com/aws/smithy-go/middleware"
	smithyhttp "github.com/aws/smithy-go/transport/http"
)

// Creates an endpoint configuration that SageMaker hosting services uses to
// deploy models. In the configuration, you identify one or more models, created
// using the CreateModel API, to deploy and the resources that you want SageMaker
// to provision. Then you call the CreateEndpoint (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html)
// API. Use this API if you want to use SageMaker hosting services to deploy models
// into production. In the request, you define a ProductionVariant , for each model
// that you want to deploy. Each ProductionVariant parameter also describes the
// resources that you want SageMaker to provision. This includes the number and
// type of ML compute instances to deploy. If you are hosting multiple models, you
// also assign a VariantWeight to specify how much traffic you want to allocate to
// each model. For example, suppose that you want to host two models, A and B, and
// you assign traffic weight 2 for model A and 1 for model B. SageMaker distributes
// two-thirds of the traffic to Model A, and one-third to model B. When you call
// CreateEndpoint (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html)
// , a load call is made to DynamoDB to verify that your endpoint configuration
// exists. When you read data from a DynamoDB table supporting Eventually
// Consistent Reads (https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/HowItWorks.ReadConsistency.html)
// , the response might not reflect the results of a recently completed write
// operation. The response might include some stale data. If the dependent entities
// are not yet in DynamoDB, this causes a validation error. If you repeat your read
// request after a short time, the response should return the latest data. So retry
// logic is recommended to handle these possible issues. We also recommend that
// customers call DescribeEndpointConfig (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_DescribeEndpointConfig.html)
// before calling CreateEndpoint (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html)
// to minimize the potential impact of a DynamoDB eventually consistent read.
func (c *Client) CreateEndpointConfig(ctx context.Context, params *CreateEndpointConfigInput, optFns ...func(*Options)) (*CreateEndpointConfigOutput, error) {
	if params == nil {
		params = &CreateEndpointConfigInput{}
	}

	result, metadata, err := c.invokeOperation(ctx, "CreateEndpointConfig", params, optFns, c.addOperationCreateEndpointConfigMiddlewares)
	if err != nil {
		return nil, err
	}

	out := result.(*CreateEndpointConfigOutput)
	out.ResultMetadata = metadata
	return out, nil
}

type CreateEndpointConfigInput struct {

	// The name of the endpoint configuration. You specify this name in a
	// CreateEndpoint (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateEndpoint.html)
	// request.
	//
	// This member is required.
	EndpointConfigName *string

	// An array of ProductionVariant objects, one for each model that you want to host
	// at this endpoint.
	//
	// This member is required.
	ProductionVariants []types.ProductionVariant

	// Specifies configuration for how an endpoint performs asynchronous inference.
	// This is a required field in order for your Endpoint to be invoked using
	// InvokeEndpointAsync (https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_runtime_InvokeEndpointAsync.html)
	// .
	AsyncInferenceConfig *types.AsyncInferenceConfig

	// Configuration to control how SageMaker captures inference data.
	DataCaptureConfig *types.DataCaptureConfig

	// Sets whether all model containers deployed to the endpoint are isolated. If
	// they are, no inbound or outbound network calls can be made to or from the model
	// containers.
	EnableNetworkIsolation *bool

	// The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker can assume
	// to perform actions on your behalf. For more information, see SageMaker Roles (https://docs.aws.amazon.com/sagemaker/latest/dg/sagemaker-roles.html)
	// . To be able to pass this role to Amazon SageMaker, the caller of this action
	// must have the iam:PassRole permission.
	ExecutionRoleArn *string

	// A member of CreateEndpointConfig that enables explainers.
	ExplainerConfig *types.ExplainerConfig

	// The Amazon Resource Name (ARN) of a Amazon Web Services Key Management Service
	// key that SageMaker uses to encrypt data on the storage volume attached to the ML
	// compute instance that hosts the endpoint. The KmsKeyId can be any of the
	// following formats:
	//   - Key ID: 1234abcd-12ab-34cd-56ef-1234567890ab
	//   - Key ARN:
	//   arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab
	//   - Alias name: alias/ExampleAlias
	//   - Alias name ARN: arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias
	// The KMS key policy must grant permission to the IAM role that you specify in
	// your CreateEndpoint , UpdateEndpoint requests. For more information, refer to
	// the Amazon Web Services Key Management Service section Using Key Policies in
	// Amazon Web Services KMS  (https://docs.aws.amazon.com/kms/latest/developerguide/key-policies.html)
	// Certain Nitro-based instances include local storage, dependent on the instance
	// type. Local storage volumes are encrypted using a hardware module on the
	// instance. You can't request a KmsKeyId when using an instance type with local
	// storage. If any of the models that you specify in the ProductionVariants
	// parameter use nitro-based instances with local storage, do not specify a value
	// for the KmsKeyId parameter. If you specify a value for KmsKeyId when using any
	// nitro-based instances with local storage, the call to CreateEndpointConfig
	// fails. For a list of instance types that support local instance storage, see
	// Instance Store Volumes (https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html#instance-store-volumes)
	// . For more information about local instance storage encryption, see SSD
	// Instance Store Volumes (https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ssd-instance-store.html)
	// .
	KmsKeyId *string

	// An array of ProductionVariant objects, one for each model that you want to host
	// at this endpoint in shadow mode with production traffic replicated from the
	// model specified on ProductionVariants . If you use this field, you can only
	// specify one variant for ProductionVariants and one variant for
	// ShadowProductionVariants .
	ShadowProductionVariants []types.ProductionVariant

	// An array of key-value pairs. You can use tags to categorize your Amazon Web
	// Services resources in different ways, for example, by purpose, owner, or
	// environment. For more information, see Tagging Amazon Web Services Resources (https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html)
	// .
	Tags []types.Tag

	// Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs,
	// hosted models, and compute resources have access to. You can control access to
	// and from your resources by configuring a VPC. For more information, see Give
	// SageMaker Access to Resources in your Amazon VPC (https://docs.aws.amazon.com/sagemaker/latest/dg/infrastructure-give-access.html)
	// .
	VpcConfig *types.VpcConfig

	noSmithyDocumentSerde
}

type CreateEndpointConfigOutput struct {

	// The Amazon Resource Name (ARN) of the endpoint configuration.
	//
	// This member is required.
	EndpointConfigArn *string

	// Metadata pertaining to the operation's result.
	ResultMetadata middleware.Metadata

	noSmithyDocumentSerde
}

func (c *Client) addOperationCreateEndpointConfigMiddlewares(stack *middleware.Stack, options Options) (err error) {
	if err := stack.Serialize.Add(&setOperationInputMiddleware{}, middleware.After); err != nil {
		return err
	}
	err = stack.Serialize.Add(&awsAwsjson11_serializeOpCreateEndpointConfig{}, middleware.After)
	if err != nil {
		return err
	}
	err = stack.Deserialize.Add(&awsAwsjson11_deserializeOpCreateEndpointConfig{}, middleware.After)
	if err != nil {
		return err
	}
	if err := addProtocolFinalizerMiddlewares(stack, options, "CreateEndpointConfig"); err != nil {
		return fmt.Errorf("add protocol finalizers: %v", err)
	}

	if err = addlegacyEndpointContextSetter(stack, options); err != nil {
		return err
	}
	if err = addSetLoggerMiddleware(stack, options); err != nil {
		return err
	}
	if err = awsmiddleware.AddClientRequestIDMiddleware(stack); err != nil {
		return err
	}
	if err = smithyhttp.AddComputeContentLengthMiddleware(stack); err != nil {
		return err
	}
	if err = addResolveEndpointMiddleware(stack, options); err != nil {
		return err
	}
	if err = v4.AddComputePayloadSHA256Middleware(stack); err != nil {
		return err
	}
	if err = addRetryMiddlewares(stack, options); err != nil {
		return err
	}
	if err = awsmiddleware.AddRawResponseToMetadata(stack); err != nil {
		return err
	}
	if err = awsmiddleware.AddRecordResponseTiming(stack); err != nil {
		return err
	}
	if err = addClientUserAgent(stack, options); err != nil {
		return err
	}
	if err = smithyhttp.AddErrorCloseResponseBodyMiddleware(stack); err != nil {
		return err
	}
	if err = smithyhttp.AddCloseResponseBodyMiddleware(stack); err != nil {
		return err
	}
	if err = addSetLegacyContextSigningOptionsMiddleware(stack); err != nil {
		return err
	}
	if err = addOpCreateEndpointConfigValidationMiddleware(stack); err != nil {
		return err
	}
	if err = stack.Initialize.Add(newServiceMetadataMiddleware_opCreateEndpointConfig(options.Region), middleware.Before); err != nil {
		return err
	}
	if err = awsmiddleware.AddRecursionDetection(stack); err != nil {
		return err
	}
	if err = addRequestIDRetrieverMiddleware(stack); err != nil {
		return err
	}
	if err = addResponseErrorMiddleware(stack); err != nil {
		return err
	}
	if err = addRequestResponseLogging(stack, options); err != nil {
		return err
	}
	if err = addDisableHTTPSMiddleware(stack, options); err != nil {
		return err
	}
	return nil
}

func newServiceMetadataMiddleware_opCreateEndpointConfig(region string) *awsmiddleware.RegisterServiceMetadata {
	return &awsmiddleware.RegisterServiceMetadata{
		Region:        region,
		ServiceID:     ServiceID,
		OperationName: "CreateEndpointConfig",
	}
}