Module aws_sdk_bedrock::types

Data structures used by operation inputs/outputs.

Modules

• builders
  Builders
• error
  Error types that Amazon Bedrock can respond with.

Structs

• AutomatedEvaluationConfig

  Use to specify a automatic model evaluation job. The EvaluationDatasetMetricConfig object is used to specify the prompt datasets, task type, and metric names.

• CloudWatchConfig

  CloudWatch logging configuration.

• CustomModelSummary

  Summary information for a custom model.

• EvaluationBedrockModel

  Contains the ARN of the Amazon Bedrock models specified in your model evaluation job. Each Amazon Bedrock model supports different inferenceParams. To learn more about supported inference parameters for Amazon Bedrock models, see Inference parameters for foundation models.

• 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.

• EvaluationDatasetMetricConfig

  Defines the built-in prompt datasets, built-in metric names and custom metric names, and the task type.

• 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.

• GuardrailContentFilter

  Contains filter strengths for harmful content. Guardrails support the following content filters to detect and filter harmful user inputs and FM-generated outputs.

• GuardrailContentFilterConfig

  Contains filter strengths for harmful content. Guardrails support the following content filters to detect and filter harmful user inputs and FM-generated outputs.

• GuardrailContentPolicy

  Contains details about how to handle harmful content.

• GuardrailContentPolicyConfig

  Contains details about how to handle harmful content.

• GuardrailManagedWords

  The managed word list that was configured for the guardrail. (This is a list of words that are pre-defined and managed by Guardrails only.)

• 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. Model evaluation jobs use human workers only support the use of custom prompt datasets. To learn more about custom prompt datasets and the required format, see 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. The object is used to specify the prompt dataset, task type, rating method and metric names.

• 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.

• S3Config

  S3 configuration for storing log data.

• Tag

  Definition of the key/value pair for a tag.

• TrainingDataConfig

  S3 Location of the training data.

• TrainingMetrics

  Metrics associated with the custom job.

• ValidationDataConfig

  Array of up to 10 validators.

• Validator

  Information about a validator.

• ValidatorMetric

  The metric for the validator.

• VpcConfig

  VPC configuration.

Enums

• CommitmentDuration
  When writing a match expression against CommitmentDuration, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• CustomizationType
  When writing a match expression against CustomizationType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• EvaluationConfig

  Used to specify either a AutomatedEvaluationConfig or HumanEvaluationConfig object.

• EvaluationDatasetLocation

  The location in Amazon S3 where your prompt dataset is stored.

• EvaluationInferenceConfig

  Used to define the models you want used in your model evaluation job. Automated model evaluation jobs support only a single model. In a human-based model evaluation job, your annotator can compare the responses for up to two different models.

• EvaluationJobStatus
  When writing a match expression against EvaluationJobStatus, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• EvaluationJobType
  When writing a match expression against EvaluationJobType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• EvaluationModelConfig

  Defines the models used in the model evaluation job.

• EvaluationTaskType
  When writing a match expression against EvaluationTaskType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• FineTuningJobStatus
  When writing a match expression against FineTuningJobStatus, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• FoundationModelLifecycleStatus
  When writing a match expression against FoundationModelLifecycleStatus, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• GuardrailContentFilterType
  When writing a match expression against GuardrailContentFilterType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• GuardrailFilterStrength
  When writing a match expression against GuardrailFilterStrength, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• GuardrailManagedWordsType
  When writing a match expression against GuardrailManagedWordsType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• GuardrailPiiEntityType
  When writing a match expression against GuardrailPiiEntityType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• GuardrailSensitiveInformationAction
  When writing a match expression against GuardrailSensitiveInformationAction, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• GuardrailStatus
  When writing a match expression against GuardrailStatus, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• GuardrailTopicType
  When writing a match expression against GuardrailTopicType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• InferenceType
  When writing a match expression against InferenceType, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• ModelCustomization
  When writing a match expression against ModelCustomization, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• ModelCustomizationJobStatus
  When writing a match expression against ModelCustomizationJobStatus, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• ModelModality
  When writing a match expression against ModelModality, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• ProvisionedModelStatus
  When writing a match expression against ProvisionedModelStatus, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• SortByProvisionedModels
  When writing a match expression against SortByProvisionedModels, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• SortJobsBy
  When writing a match expression against SortJobsBy, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• SortModelsBy
  When writing a match expression against SortModelsBy, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.
• SortOrder
  When writing a match expression against SortOrder, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.