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
|
// 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 inference component, which is a SageMaker hosting object that you
// can use to deploy a model to an endpoint. In the inference component settings,
// you specify the model, the endpoint, and how the model utilizes the resources
// that the endpoint hosts. You can optimize resource utilization by tailoring how
// the required CPU cores, accelerators, and memory are allocated. You can deploy
// multiple inference components to an endpoint, where each inference component
// contains one model and the resource utilization needs for that individual model.
// After you deploy an inference component, you can directly invoke the associated
// model when you use the InvokeEndpoint API action.
func (c *Client) CreateInferenceComponent(ctx context.Context, params *CreateInferenceComponentInput, optFns ...func(*Options)) (*CreateInferenceComponentOutput, error) {
if params == nil {
params = &CreateInferenceComponentInput{}
}
result, metadata, err := c.invokeOperation(ctx, "CreateInferenceComponent", params, optFns, c.addOperationCreateInferenceComponentMiddlewares)
if err != nil {
return nil, err
}
out := result.(*CreateInferenceComponentOutput)
out.ResultMetadata = metadata
return out, nil
}
type CreateInferenceComponentInput struct {
// The name of an existing endpoint where you host the inference component.
//
// This member is required.
EndpointName *string
// A unique name to assign to the inference component.
//
// This member is required.
InferenceComponentName *string
// Runtime settings for a model that is deployed with an inference component.
//
// This member is required.
RuntimeConfig *types.InferenceComponentRuntimeConfig
// Details about the resources to deploy with this inference component, including
// the model, container, and compute resources.
//
// This member is required.
Specification *types.InferenceComponentSpecification
// The name of an existing production variant where you host the inference
// component.
//
// This member is required.
VariantName *string
// A list of key-value pairs associated with the model. For more information, see
// Tagging Amazon Web Services resources (https://docs.aws.amazon.com/general/latest/gr/aws_tagging.html)
// in the Amazon Web Services General Reference.
Tags []types.Tag
noSmithyDocumentSerde
}
type CreateInferenceComponentOutput struct {
// The Amazon Resource Name (ARN) of the inference component.
//
// This member is required.
InferenceComponentArn *string
// Metadata pertaining to the operation's result.
ResultMetadata middleware.Metadata
noSmithyDocumentSerde
}
func (c *Client) addOperationCreateInferenceComponentMiddlewares(stack *middleware.Stack, options Options) (err error) {
if err := stack.Serialize.Add(&setOperationInputMiddleware{}, middleware.After); err != nil {
return err
}
err = stack.Serialize.Add(&awsAwsjson11_serializeOpCreateInferenceComponent{}, middleware.After)
if err != nil {
return err
}
err = stack.Deserialize.Add(&awsAwsjson11_deserializeOpCreateInferenceComponent{}, middleware.After)
if err != nil {
return err
}
if err := addProtocolFinalizerMiddlewares(stack, options, "CreateInferenceComponent"); 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 = addOpCreateInferenceComponentValidationMiddleware(stack); err != nil {
return err
}
if err = stack.Initialize.Add(newServiceMetadataMiddleware_opCreateInferenceComponent(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_opCreateInferenceComponent(region string) *awsmiddleware.RegisterServiceMetadata {
return &awsmiddleware.RegisterServiceMetadata{
Region: region,
ServiceID: ServiceID,
OperationName: "CreateInferenceComponent",
}
}
|
