DataCaptureConfig
Configuration to control how SageMaker captures inference data.
Contents
- CaptureContentTypeHeader
-
Configuration specifying how to treat different headers. If no headers are specified SageMaker will by default base64 encode when capturing the data.
Type: CaptureContentTypeHeader object
Required: No
- CaptureOptions
-
Specifies data Model Monitor will capture. You can configure whether to collect only input, only output, or both
Type: Array of CaptureOption objects
Array Members: Minimum number of 1 item. Maximum number of 2 items.
Required: Yes
- DestinationS3Uri
-
The Amazon S3 location used to capture the data.
Type: String
Length Constraints: Maximum length of 512.
Pattern:
^(https|s3)://([^/])/?(.*)$
Required: Yes
- EnableCapture
-
Whether data capture should be enabled or disabled (defaults to enabled).
Type: Boolean
Required: No
- InitialSamplingPercentage
-
The percentage of requests SageMaker will capture. A lower value is recommended for Endpoints with high traffic.
Type: Integer
Valid Range: Minimum value of 0. Maximum value of 100.
Required: Yes
- KmsKeyId
-
The Amazon Resource Name (ARN) of a Amazon 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
Type: String
Length Constraints: Maximum length of 2048.
Pattern:
.*
Required: No
-
See Also
For more information about using this API in one of the language-specific Amazon SDKs, see the following: