| Class | Description |
|---|---|
| AutomatedEvaluationConfig |
Use to specify a automatic model evaluation job.
|
| CloudWatchConfig |
CloudWatch logging configuration.
|
| CreateEvaluationJobRequest | |
| CreateEvaluationJobResult | |
| CreateGuardrailRequest | |
| CreateGuardrailResult | |
| CreateGuardrailVersionRequest | |
| CreateGuardrailVersionResult | |
| CreateModelCustomizationJobRequest | |
| CreateModelCustomizationJobResult | |
| CreateProvisionedModelThroughputRequest | |
| CreateProvisionedModelThroughputResult | |
| CustomModelSummary |
Summary information for a custom model.
|
| DeleteCustomModelRequest | |
| DeleteCustomModelResult | |
| DeleteGuardrailRequest | |
| DeleteGuardrailResult | |
| DeleteModelInvocationLoggingConfigurationRequest | |
| DeleteModelInvocationLoggingConfigurationResult | |
| DeleteProvisionedModelThroughputRequest | |
| DeleteProvisionedModelThroughputResult | |
| EvaluationBedrockModel |
Contains the ARN of the Amazon Bedrock models specified in your model evaluation job.
|
| EvaluationConfig |
Used to specify either a
AutomatedEvaluationConfig or HumanEvaluationConfig object. |
| EvaluationDataset |
Used to specify the name of a built-in prompt dataset and optionally, the Amazon S3 bucket where a custom prompt
dataset is saved.
|
| EvaluationDatasetLocation |
The location in Amazon S3 where your prompt dataset is stored.
|
| EvaluationDatasetMetricConfig |
Defines the built-in prompt datasets, built-in metric names and custom metric names, and the task type.
|
| EvaluationInferenceConfig |
Used to define the models you want used in your model evaluation job.
|
| EvaluationModelConfig |
Defines the models used in the model evaluation job.
|
| EvaluationOutputDataConfig |
The Amazon S3 location where the results of your model evaluation job are saved.
|
| EvaluationSummary |
A summary of the model evaluation job.
|
| FoundationModelDetails |
Information about a foundation model.
|
| FoundationModelLifecycle |
Details about whether a model version is available or deprecated.
|
| FoundationModelSummary |
Summary information for a foundation model.
|
| GetCustomModelRequest | |
| GetCustomModelResult | |
| GetEvaluationJobRequest | |
| GetEvaluationJobResult | |
| GetFoundationModelRequest | |
| GetFoundationModelResult | |
| GetGuardrailRequest | |
| GetGuardrailResult | |
| GetModelCustomizationJobRequest | |
| GetModelCustomizationJobResult | |
| GetModelInvocationLoggingConfigurationRequest | |
| GetModelInvocationLoggingConfigurationResult | |
| GetProvisionedModelThroughputRequest | |
| GetProvisionedModelThroughputResult | |
| GuardrailContentFilter |
Contains filter strengths for harmful content.
|
| GuardrailContentFilterConfig |
Contains filter strengths for harmful content.
|
| GuardrailContentPolicy |
Contains details about how to handle harmful content.
|
| GuardrailContentPolicyConfig |
Contains details about how to handle harmful content.
|
| GuardrailContextualGroundingFilter |
The details for the guardrails contextual grounding filter.
|
| GuardrailContextualGroundingFilterConfig |
The filter configuration details for the guardrails contextual grounding filter.
|
| GuardrailContextualGroundingPolicy |
The details for the guardrails contextual grounding policy.
|
| GuardrailContextualGroundingPolicyConfig |
The policy configuration details for the guardrails contextual grounding policy.
|
| GuardrailManagedWords |
The managed word list that was configured for the guardrail.
|
| GuardrailManagedWordsConfig |
The managed word list to configure for the guardrail.
|
| GuardrailPiiEntity |
The PII entity configured for the guardrail.
|
| GuardrailPiiEntityConfig |
The PII entity to configure for the guardrail.
|
| GuardrailRegex |
The regular expression configured for the guardrail.
|
| GuardrailRegexConfig |
The regular expression to configure for the guardrail.
|
| GuardrailSensitiveInformationPolicy |
Contains details about PII entities and regular expressions configured for the guardrail.
|
| GuardrailSensitiveInformationPolicyConfig |
Contains details about PII entities and regular expressions to configure for the guardrail.
|
| GuardrailSummary |
Contains details about a guardrail.
|
| GuardrailTopic |
Details about topics for the guardrail to identify and deny.
|
| GuardrailTopicConfig |
Details about topics for the guardrail to identify and deny.
|
| GuardrailTopicPolicy |
Contains details about topics that the guardrail should identify and deny.
|
| GuardrailTopicPolicyConfig |
Contains details about topics that the guardrail should identify and deny.
|
| GuardrailWord |
A word configured for the guardrail.
|
| GuardrailWordConfig |
A word to configure for the guardrail.
|
| GuardrailWordPolicy |
Contains details about the word policy configured for the guardrail.
|
| GuardrailWordPolicyConfig |
Contains details about the word policy to configured for the guardrail.
|
| HumanEvaluationConfig |
Specifies the custom metrics, how tasks will be rated, the flow definition ARN, and your custom prompt datasets.
|
| HumanEvaluationCustomMetric |
In a model evaluation job that uses human workers you must define the name of the metric, and how you want that
metric rated
ratingMethod, and an optional description of the metric. |
| HumanWorkflowConfig |
Contains
SageMakerFlowDefinition object. |
| ListCustomModelsRequest | |
| ListCustomModelsResult | |
| ListEvaluationJobsRequest | |
| ListEvaluationJobsResult | |
| ListFoundationModelsRequest | |
| ListFoundationModelsResult | |
| ListGuardrailsRequest | |
| ListGuardrailsResult | |
| ListModelCustomizationJobsRequest | |
| ListModelCustomizationJobsResult | |
| ListProvisionedModelThroughputsRequest | |
| ListProvisionedModelThroughputsResult | |
| ListTagsForResourceRequest | |
| ListTagsForResourceResult | |
| LoggingConfig |
Configuration fields for invocation logging.
|
| ModelCustomizationJobSummary |
Information about one customization job
|
| OutputDataConfig |
S3 Location of the output data.
|
| ProvisionedModelSummary |
A summary of information about a Provisioned Throughput.
|
| PutModelInvocationLoggingConfigurationRequest | |
| PutModelInvocationLoggingConfigurationResult | |
| S3Config |
S3 configuration for storing log data.
|
| StopEvaluationJobRequest | |
| StopEvaluationJobResult | |
| StopModelCustomizationJobRequest | |
| StopModelCustomizationJobResult | |
| Tag |
Definition of the key/value pair for a tag.
|
| TagResourceRequest | |
| TagResourceResult | |
| TrainingDataConfig |
S3 Location of the training data.
|
| TrainingMetrics |
Metrics associated with the custom job.
|
| UntagResourceRequest | |
| UntagResourceResult | |
| UpdateGuardrailRequest | |
| UpdateGuardrailResult | |
| UpdateProvisionedModelThroughputRequest | |
| UpdateProvisionedModelThroughputResult | |
| ValidationDataConfig |
Array of up to 10 validators.
|
| Validator |
Information about a validator.
|
| ValidatorMetric |
The metric for the validator.
|
| VpcConfig |
VPC configuration.
|
| Exception | Description |
|---|---|
| AccessDeniedException |
The request is denied because of missing access permissions.
|
| AmazonBedrockException |
Base exception for all service exceptions thrown by Amazon Bedrock
|
| ConflictException |
Error occurred because of a conflict while performing an operation.
|
| InternalServerException |
An internal server error occurred.
|
| ResourceNotFoundException |
The specified resource Amazon Resource Name (ARN) was not found.
|
| ServiceQuotaExceededException |
The number of requests exceeds the service quota.
|
| ThrottlingException |
The number of requests exceeds the limit.
|
| TooManyTagsException |
The request contains more tags than can be associated with a resource (50 tags per resource).
|
| ValidationException |
Input validation failed.
|