types

package
v1.47.2 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Sep 26, 2025 License: Apache-2.0 Imports: 5 Imported by: 10

Documentation

Index

Examples

Constants

This section is empty.

Variables

This section is empty.

Functions

This section is empty.

Types

type AccessDeniedException 

type AccessDeniedException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

The request is denied because of missing access permissions.

func (*AccessDeniedException) Error 

func (e *AccessDeniedException) Error() string

func (*AccessDeniedException) ErrorCode 

func (e *AccessDeniedException) ErrorCode() string

func (*AccessDeniedException) ErrorFault 

func (e *AccessDeniedException) ErrorFault() smithy.ErrorFault

func (*AccessDeniedException) ErrorMessage 

func (e *AccessDeniedException) ErrorMessage() string

type AgreementAvailability added in v1.37.0 

type AgreementAvailability struct {

	// Status of the agreement.
	//
	// This member is required.
	Status AgreementStatus

	// Error message.
	ErrorMessage *string
	// contains filtered or unexported fields
}

Information about the agreement availability

type AgreementStatus added in v1.37.0 

type AgreementStatus string
const (
	AgreementStatusAvailable    AgreementStatus = "AVAILABLE"
	AgreementStatusPending      AgreementStatus = "PENDING"
	AgreementStatusNotAvailable AgreementStatus = "NOT_AVAILABLE"
	AgreementStatusError        AgreementStatus = "ERROR"
)

Enum values for AgreementStatus

func (AgreementStatus) Values added in v1.37.0 

func (AgreementStatus) Values() []AgreementStatus

Values returns all known values for AgreementStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ApplicationType added in v1.23.0 

type ApplicationType string
const (
	ApplicationTypeModelEvaluation ApplicationType = "ModelEvaluation"
	ApplicationTypeRagEvaluation   ApplicationType = "RagEvaluation"
)

Enum values for ApplicationType

func (ApplicationType) Values added in v1.23.0 

func (ApplicationType) Values() []ApplicationType

Values returns all known values for ApplicationType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AttributeType added in v1.38.0 

type AttributeType string
const (
	AttributeTypeString     AttributeType = "STRING"
	AttributeTypeNumber     AttributeType = "NUMBER"
	AttributeTypeBoolean    AttributeType = "BOOLEAN"
	AttributeTypeStringList AttributeType = "STRING_LIST"
)

Enum values for AttributeType

func (AttributeType) Values added in v1.38.0 

func (AttributeType) Values() []AttributeType

Values returns all known values for AttributeType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AuthorizationStatus added in v1.37.0 

type AuthorizationStatus string
const (
	AuthorizationStatusAuthorized    AuthorizationStatus = "AUTHORIZED"
	AuthorizationStatusNotAuthorized AuthorizationStatus = "NOT_AUTHORIZED"
)

Enum values for AuthorizationStatus

func (AuthorizationStatus) Values added in v1.37.0 

func (AuthorizationStatus) Values() []AuthorizationStatus

Values returns all known values for AuthorizationStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedEvaluationConfig added in v1.8.0 

type AutomatedEvaluationConfig struct {

	// Configuration details of the prompt datasets and metrics you want to use for
	// your evaluation job.
	//
	// This member is required.
	DatasetMetricConfigs []EvaluationDatasetMetricConfig

	// Defines the configuration of custom metrics to be used in an evaluation job.
	CustomMetricConfig *AutomatedEvaluationCustomMetricConfig

	// Contains the evaluator model configuration details. EvaluatorModelConfig is
	// required for evaluation jobs that use a knowledge base or in model evaluation
	// job that use a model as judge. This model computes all evaluation related
	// metrics.
	EvaluatorModelConfig EvaluatorModelConfig
	// contains filtered or unexported fields
}

The configuration details of an automated evaluation job. The EvaluationDatasetMetricConfig object is used to specify the prompt datasets, task type, and metric names.

type AutomatedEvaluationCustomMetricConfig added in v1.32.0 

type AutomatedEvaluationCustomMetricConfig struct {

	// Defines a list of custom metrics to be used in an Amazon Bedrock evaluation job.
	//
	// This member is required.
	CustomMetrics []AutomatedEvaluationCustomMetricSource

	// Configuration of the evaluator model you want to use to evaluate custom metrics
	// in an Amazon Bedrock evaluation job.
	//
	// This member is required.
	EvaluatorModelConfig *CustomMetricEvaluatorModelConfig
	// contains filtered or unexported fields
}

Defines the configuration of custom metrics to be used in an evaluation job. To learn more about using custom metrics in Amazon Bedrock evaluation jobs, see Create a prompt for a custom metrics (LLM-as-a-judge model evaluations) and Create a prompt for a custom metrics (RAG evaluations).

type AutomatedEvaluationCustomMetricSource added in v1.32.0 

type AutomatedEvaluationCustomMetricSource interface {
	// contains filtered or unexported methods
}

An array item definining a single custom metric for use in an Amazon Bedrock evaluation job.

The following types satisfy this interface: 

AutomatedEvaluationCustomMetricSourceMemberCustomMetricDefinition
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedEvaluationCustomMetricSource
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedEvaluationCustomMetricSourceMemberCustomMetricDefinition:
		_ = v.Value // Value is types.CustomMetricDefinition

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedEvaluationCustomMetricSourceMemberCustomMetricDefinition added in v1.32.0 

type AutomatedEvaluationCustomMetricSourceMemberCustomMetricDefinition struct {
	Value CustomMetricDefinition
	// contains filtered or unexported fields
}

The definition of a custom metric for use in an Amazon Bedrock evaluation job.

type AutomatedReasoningCheckFinding added in v1.42.0 

type AutomatedReasoningCheckFinding interface {
	// contains filtered or unexported methods
}

Represents the result of an Automated Reasoning validation check, indicating whether the content is logically valid, invalid, or falls into other categories based on the policy rules.

The following types satisfy this interface: 

AutomatedReasoningCheckFindingMemberImpossible
AutomatedReasoningCheckFindingMemberInvalid
AutomatedReasoningCheckFindingMemberNoTranslations
AutomatedReasoningCheckFindingMemberSatisfiable
AutomatedReasoningCheckFindingMemberTooComplex
AutomatedReasoningCheckFindingMemberTranslationAmbiguous
AutomatedReasoningCheckFindingMemberValid
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningCheckFinding
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningCheckFindingMemberImpossible:
		_ = v.Value // Value is types.AutomatedReasoningCheckImpossibleFinding

	case *types.AutomatedReasoningCheckFindingMemberInvalid:
		_ = v.Value // Value is types.AutomatedReasoningCheckInvalidFinding

	case *types.AutomatedReasoningCheckFindingMemberNoTranslations:
		_ = v.Value // Value is types.AutomatedReasoningCheckNoTranslationsFinding

	case *types.AutomatedReasoningCheckFindingMemberSatisfiable:
		_ = v.Value // Value is types.AutomatedReasoningCheckSatisfiableFinding

	case *types.AutomatedReasoningCheckFindingMemberTooComplex:
		_ = v.Value // Value is types.AutomatedReasoningCheckTooComplexFinding

	case *types.AutomatedReasoningCheckFindingMemberTranslationAmbiguous:
		_ = v.Value // Value is types.AutomatedReasoningCheckTranslationAmbiguousFinding

	case *types.AutomatedReasoningCheckFindingMemberValid:
		_ = v.Value // Value is types.AutomatedReasoningCheckValidFinding

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningCheckFindingMemberImpossible added in v1.42.0 

type AutomatedReasoningCheckFindingMemberImpossible struct {
	Value AutomatedReasoningCheckImpossibleFinding
	// contains filtered or unexported fields
}

Indicates that Automated Reasoning cannot make a statement about the claims. This can happen if the premises are logically incorrect, or if there is a conflict within the Automated Reasoning policy itself.

type AutomatedReasoningCheckFindingMemberInvalid added in v1.42.0 

type AutomatedReasoningCheckFindingMemberInvalid struct {
	Value AutomatedReasoningCheckInvalidFinding
	// contains filtered or unexported fields
}

Indicates that the claims are false. The claims are not implied by the premises and Automated Reasoning policy. Furthermore, there exist different claims that are consistent with the premises and Automated Reasoning policy.

type AutomatedReasoningCheckFindingMemberNoTranslations added in v1.42.0 

type AutomatedReasoningCheckFindingMemberNoTranslations struct {
	Value AutomatedReasoningCheckNoTranslationsFinding
	// contains filtered or unexported fields
}

Identifies that some or all of the input prompt wasn't translated into logic. This can happen if the input isn't relevant to the Automated Reasoning policy, or if the policy doesn't have variables to model relevant input.

type AutomatedReasoningCheckFindingMemberSatisfiable added in v1.42.0 

type AutomatedReasoningCheckFindingMemberSatisfiable struct {
	Value AutomatedReasoningCheckSatisfiableFinding
	// contains filtered or unexported fields
}

Indicates that the claims can be true or false. It depends on what assumptions are made for the claim to be implied from the premises and Automated Reasoning policy rules. In this situation, different assumptions can make input claims false and alternative claims true.

type AutomatedReasoningCheckFindingMemberTooComplex added in v1.42.0 

type AutomatedReasoningCheckFindingMemberTooComplex struct {
	Value AutomatedReasoningCheckTooComplexFinding
	// contains filtered or unexported fields
}

Indicates that the input contains too much information for Automated Reasoning to process within its latency limits.

type AutomatedReasoningCheckFindingMemberTranslationAmbiguous added in v1.42.0 

type AutomatedReasoningCheckFindingMemberTranslationAmbiguous struct {
	Value AutomatedReasoningCheckTranslationAmbiguousFinding
	// contains filtered or unexported fields
}

Indicates that an ambiguity was detected in the translation, making it unsound to continue with validity checking. Additional context or follow-up questions might be needed to get translation to succeed.

type AutomatedReasoningCheckFindingMemberValid added in v1.42.0 

type AutomatedReasoningCheckFindingMemberValid struct {
	Value AutomatedReasoningCheckValidFinding
	// contains filtered or unexported fields
}

Indicates that the claims are true. The claims are implied by the premises and the Automated Reasoning policy. Given the Automated Reasoning policy and premises, it is not possible for these claims to be false.

type AutomatedReasoningCheckImpossibleFinding added in v1.42.0 

type AutomatedReasoningCheckImpossibleFinding struct {

	// The automated reasoning policy rules that contradict the claims and/or premises
	// in the input.
	ContradictingRules []AutomatedReasoningCheckRule

	// Indication of a logic issue with the translation without needing to consider
	// the automated reasoning policy rules.
	LogicWarning *AutomatedReasoningCheckLogicWarning

	// The logical translation of the input that this finding evaluates.
	Translation *AutomatedReasoningCheckTranslation
	// contains filtered or unexported fields
}

Indicates that no valid claims can be made due to logical contradictions in the premises or rules.

type AutomatedReasoningCheckInputTextReference added in v1.42.0 

type AutomatedReasoningCheckInputTextReference struct {

	// The specific text from the original input that this reference points to.
	Text *string
	// contains filtered or unexported fields
}

References a portion of the original input text that corresponds to logical elements.

type AutomatedReasoningCheckInvalidFinding added in v1.42.0 

type AutomatedReasoningCheckInvalidFinding struct {

	// The automated reasoning policy rules that contradict the claims in the input.
	ContradictingRules []AutomatedReasoningCheckRule

	// Indication of a logic issue with the translation without needing to consider
	// the automated reasoning policy rules.
	LogicWarning *AutomatedReasoningCheckLogicWarning

	// The logical translation of the input that this finding invalidates.
	Translation *AutomatedReasoningCheckTranslation
	// contains filtered or unexported fields
}

Indicates that the claims are logically false and contradictory to the established rules or premises.

type AutomatedReasoningCheckLogicWarning added in v1.42.0 

type AutomatedReasoningCheckLogicWarning struct {

	// The logical statements that are validated while assuming the policy and
	// premises.
	Claims []AutomatedReasoningLogicStatement

	// The logical statements that serve as premises under which the claims are
	// validated.
	Premises []AutomatedReasoningLogicStatement

	// The category of the detected logical issue, such as statements that are always
	// true or always false.
	Type AutomatedReasoningCheckLogicWarningType
	// contains filtered or unexported fields
}

Identifies logical issues in the translated statements that exist independent of any policy rules, such as statements that are always true or always false.

type AutomatedReasoningCheckLogicWarningType added in v1.42.0 

type AutomatedReasoningCheckLogicWarningType string
const (
	AutomatedReasoningCheckLogicWarningTypeAlwaysTrue  AutomatedReasoningCheckLogicWarningType = "ALWAYS_TRUE"
	AutomatedReasoningCheckLogicWarningTypeAlwaysFalse AutomatedReasoningCheckLogicWarningType = "ALWAYS_FALSE"
)

Enum values for AutomatedReasoningCheckLogicWarningType

func (AutomatedReasoningCheckLogicWarningType) Values added in v1.42.0 

func (AutomatedReasoningCheckLogicWarningType) Values() []AutomatedReasoningCheckLogicWarningType

Values returns all known values for AutomatedReasoningCheckLogicWarningType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningCheckNoTranslationsFinding added in v1.42.0 

type AutomatedReasoningCheckNoTranslationsFinding struct {
	// contains filtered or unexported fields
}

Indicates that no relevant logical information could be extracted from the input for validation.

type AutomatedReasoningCheckResult added in v1.42.0 

type AutomatedReasoningCheckResult string
const (
	AutomatedReasoningCheckResultValid                AutomatedReasoningCheckResult = "VALID"
	AutomatedReasoningCheckResultInvalid              AutomatedReasoningCheckResult = "INVALID"
	AutomatedReasoningCheckResultSatisfiable          AutomatedReasoningCheckResult = "SATISFIABLE"
	AutomatedReasoningCheckResultImpossible           AutomatedReasoningCheckResult = "IMPOSSIBLE"
	AutomatedReasoningCheckResultTranslationAmbiguous AutomatedReasoningCheckResult = "TRANSLATION_AMBIGUOUS"
	AutomatedReasoningCheckResultTooComplex           AutomatedReasoningCheckResult = "TOO_COMPLEX"
	AutomatedReasoningCheckResultNoTranslation        AutomatedReasoningCheckResult = "NO_TRANSLATION"
)

Enum values for AutomatedReasoningCheckResult

func (AutomatedReasoningCheckResult) Values added in v1.42.0 

func (AutomatedReasoningCheckResult) Values() []AutomatedReasoningCheckResult

Values returns all known values for AutomatedReasoningCheckResult. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningCheckRule added in v1.42.0 

type AutomatedReasoningCheckRule struct {

	// The unique identifier of the automated reasoning rule.
	Id *string

	// The ARN of the automated reasoning policy version that contains this rule.
	PolicyVersionArn *string
	// contains filtered or unexported fields
}

References a specific automated reasoning policy rule that was applied during evaluation.

type AutomatedReasoningCheckSatisfiableFinding added in v1.42.0 

type AutomatedReasoningCheckSatisfiableFinding struct {

	// An example scenario demonstrating how the claims could be logically false.
	ClaimsFalseScenario *AutomatedReasoningCheckScenario

	// An example scenario demonstrating how the claims could be logically true.
	ClaimsTrueScenario *AutomatedReasoningCheckScenario

	// Indication of a logic issue with the translation without needing to consider
	// the automated reasoning policy rules.
	LogicWarning *AutomatedReasoningCheckLogicWarning

	// The logical translation of the input that this finding evaluates.
	Translation *AutomatedReasoningCheckTranslation
	// contains filtered or unexported fields
}

Indicates that the claims could be either true or false depending on additional assumptions not provided in the input.

type AutomatedReasoningCheckScenario added in v1.42.0 

type AutomatedReasoningCheckScenario struct {

	// List of logical assignments and statements that define this scenario.
	Statements []AutomatedReasoningLogicStatement
	// contains filtered or unexported fields
}

Represents a logical scenario where claims can be evaluated as true or false, containing specific logical assignments.

type AutomatedReasoningCheckTooComplexFinding added in v1.42.0 

type AutomatedReasoningCheckTooComplexFinding struct {
	// contains filtered or unexported fields
}

Indicates that the input exceeds the processing capacity due to the volume or complexity of the logical information.

type AutomatedReasoningCheckTranslation added in v1.42.0 

type AutomatedReasoningCheckTranslation struct {

	// The logical statements that are being validated against the premises and policy
	// rules.
	//
	// This member is required.
	Claims []AutomatedReasoningLogicStatement

	// A confidence score between 0 and 1 indicating how certain the system is about
	// the logical translation.
	//
	// This member is required.
	Confidence *float64

	// The logical statements that serve as the foundation or assumptions for the
	// claims.
	Premises []AutomatedReasoningLogicStatement

	// References to portions of the original input text that correspond to the claims
	// but could not be fully translated.
	UntranslatedClaims []AutomatedReasoningCheckInputTextReference

	// References to portions of the original input text that correspond to the
	// premises but could not be fully translated.
	UntranslatedPremises []AutomatedReasoningCheckInputTextReference
	// contains filtered or unexported fields
}

Contains the logical translation of natural language input into formal logical statements, including premises, claims, and confidence scores.

type AutomatedReasoningCheckTranslationAmbiguousFinding added in v1.42.0 

type AutomatedReasoningCheckTranslationAmbiguousFinding struct {

	// Scenarios showing how the different translation options differ in meaning.
	DifferenceScenarios []AutomatedReasoningCheckScenario

	// Different logical interpretations that were detected during translation of the
	// input.
	Options []AutomatedReasoningCheckTranslationOption
	// contains filtered or unexported fields
}

Indicates that the input has multiple valid logical interpretations, requiring additional context or clarification.

type AutomatedReasoningCheckTranslationOption added in v1.42.0 

type AutomatedReasoningCheckTranslationOption struct {

	// Different logical interpretations that were detected during translation of the
	// input.
	Translations []AutomatedReasoningCheckTranslation
	// contains filtered or unexported fields
}

Represents one possible logical interpretation of ambiguous input content.

type AutomatedReasoningCheckValidFinding added in v1.42.0 

type AutomatedReasoningCheckValidFinding struct {

	// An example scenario demonstrating how the claims are logically true.
	ClaimsTrueScenario *AutomatedReasoningCheckScenario

	// Indication of a logic issue with the translation without needing to consider
	// the automated reasoning policy rules.
	LogicWarning *AutomatedReasoningCheckLogicWarning

	// The automated reasoning policy rules that support why this result is considered
	// valid.
	SupportingRules []AutomatedReasoningCheckRule

	// The logical translation of the input that this finding validates.
	Translation *AutomatedReasoningCheckTranslation
	// contains filtered or unexported fields
}

Indicates that the claims are definitively true and logically implied by the premises, with no possible alternative interpretations.

type AutomatedReasoningLogicStatement added in v1.42.0 

type AutomatedReasoningLogicStatement struct {

	// The formal logic representation of the statement using mathematical notation
	// and logical operators.
	//
	// This member is required.
	Logic *string

	// The natural language representation of the logical statement, providing a
	// human-readable interpretation of the formal logic.
	NaturalLanguage *string
	// contains filtered or unexported fields
}

Represents a logical statement that can be expressed both in formal logic notation and natural language, providing dual representations for better understanding and validation.

type AutomatedReasoningPolicyAddRuleAnnotation added in v1.42.0 

type AutomatedReasoningPolicyAddRuleAnnotation struct {

	// The formal logical expression that defines the rule, using mathematical
	// notation and referencing policy variables and types.
	//
	// This member is required.
	Expression *string
	// contains filtered or unexported fields
}

An annotation for adding a new rule to an Automated Reasoning policy using a formal logical expression.

type AutomatedReasoningPolicyAddRuleFromNaturalLanguageAnnotation added in v1.42.0 

type AutomatedReasoningPolicyAddRuleFromNaturalLanguageAnnotation struct {

	// The natural language description of the rule that should be converted into a
	// formal logical expression.
	//
	// This member is required.
	NaturalLanguage *string
	// contains filtered or unexported fields
}

An annotation for adding a new rule to the policy by converting a natural language description into a formal logical expression.

type AutomatedReasoningPolicyAddRuleMutation added in v1.42.0 

type AutomatedReasoningPolicyAddRuleMutation struct {

	// The rule definition that specifies the formal logical expression and metadata
	// for the new rule being added to the policy.
	//
	// This member is required.
	Rule *AutomatedReasoningPolicyDefinitionRule
	// contains filtered or unexported fields
}

A mutation operation that adds a new rule to the policy definition during the build process.

type AutomatedReasoningPolicyAddTypeAnnotation added in v1.42.0 

type AutomatedReasoningPolicyAddTypeAnnotation struct {

	// A description of what the custom type represents and how it should be used in
	// the policy.
	//
	// This member is required.
	Description *string

	// The name of the new custom type. This name will be used to reference the type
	// in variable definitions and rules.
	//
	// This member is required.
	Name *string

	// The list of possible values that variables of this type can take, each with its
	// own description and identifier.
	//
	// This member is required.
	Values []AutomatedReasoningPolicyDefinitionTypeValue
	// contains filtered or unexported fields
}

An annotation for adding a new custom type to an Automated Reasoning policy, defining a set of possible values for variables.

type AutomatedReasoningPolicyAddTypeMutation added in v1.42.0 

type AutomatedReasoningPolicyAddTypeMutation struct {

	// The type definition that specifies the name, description, and possible values
	// for the new custom type being added to the policy.
	//
	// This member is required.
	Type *AutomatedReasoningPolicyDefinitionType
	// contains filtered or unexported fields
}

A mutation operation that adds a new custom type to the policy definition during the build process.

type AutomatedReasoningPolicyAddTypeValue added in v1.42.0 

type AutomatedReasoningPolicyAddTypeValue struct {

	// The identifier or name of the new value to add to the type.
	//
	// This member is required.
	Value *string

	// A description of what this new type value represents and when it should be used.
	Description *string
	// contains filtered or unexported fields
}

Represents a single value that can be added to an existing custom type in the policy.

type AutomatedReasoningPolicyAddVariableAnnotation added in v1.42.0 

type AutomatedReasoningPolicyAddVariableAnnotation struct {

	// A description of what the variable represents and how it should be used in
	// rules.
	//
	// This member is required.
	Description *string

	// The name of the new variable. This name will be used to reference the variable
	// in rule expressions.
	//
	// This member is required.
	Name *string

	// The type of the variable, which can be a built-in type (like string or number)
	// or a custom type defined in the policy.
	//
	// This member is required.
	Type *string
	// contains filtered or unexported fields
}

An annotation for adding a new variable to an Automated Reasoning policy, which can be used in rule expressions.

type AutomatedReasoningPolicyAddVariableMutation added in v1.42.0 

type AutomatedReasoningPolicyAddVariableMutation struct {

	// The variable definition that specifies the name, type, and description for the
	// new variable being added to the policy.
	//
	// This member is required.
	Variable *AutomatedReasoningPolicyDefinitionVariable
	// contains filtered or unexported fields
}

A mutation operation that adds a new variable to the policy definition during the build process.

type AutomatedReasoningPolicyAnnotation added in v1.42.0 

type AutomatedReasoningPolicyAnnotation interface {
	// contains filtered or unexported methods
}

Contains the various operations that can be performed on an Automated Reasoning policy, including adding, updating, and deleting rules, variables, and types.

The following types satisfy this interface: 

AutomatedReasoningPolicyAnnotationMemberAddRule
AutomatedReasoningPolicyAnnotationMemberAddRuleFromNaturalLanguage
AutomatedReasoningPolicyAnnotationMemberAddType
AutomatedReasoningPolicyAnnotationMemberAddVariable
AutomatedReasoningPolicyAnnotationMemberDeleteRule
AutomatedReasoningPolicyAnnotationMemberDeleteType
AutomatedReasoningPolicyAnnotationMemberDeleteVariable
AutomatedReasoningPolicyAnnotationMemberIngestContent
AutomatedReasoningPolicyAnnotationMemberUpdateFromRulesFeedback
AutomatedReasoningPolicyAnnotationMemberUpdateFromScenarioFeedback
AutomatedReasoningPolicyAnnotationMemberUpdateRule
AutomatedReasoningPolicyAnnotationMemberUpdateType
AutomatedReasoningPolicyAnnotationMemberUpdateVariable
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningPolicyAnnotation
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningPolicyAnnotationMemberAddRule:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddRuleAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberAddRuleFromNaturalLanguage:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddRuleFromNaturalLanguageAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberAddType:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddTypeAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberAddVariable:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddVariableAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberDeleteRule:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDeleteRuleAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberDeleteType:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDeleteTypeAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberDeleteVariable:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDeleteVariableAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberIngestContent:
		_ = v.Value // Value is types.AutomatedReasoningPolicyIngestContentAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberUpdateFromRulesFeedback:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateFromRuleFeedbackAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberUpdateFromScenarioFeedback:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberUpdateRule:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateRuleAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberUpdateType:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateTypeAnnotation

	case *types.AutomatedReasoningPolicyAnnotationMemberUpdateVariable:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateVariableAnnotation

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningPolicyAnnotationMemberAddRule added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberAddRule struct {
	Value AutomatedReasoningPolicyAddRuleAnnotation
	// contains filtered or unexported fields
}

An operation to add a new logical rule to the policy using formal mathematical expressions.

type AutomatedReasoningPolicyAnnotationMemberAddRuleFromNaturalLanguage added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberAddRuleFromNaturalLanguage struct {
	Value AutomatedReasoningPolicyAddRuleFromNaturalLanguageAnnotation
	// contains filtered or unexported fields
}

An operation to add a new rule by converting natural language descriptions into formal logical expressions.

type AutomatedReasoningPolicyAnnotationMemberAddType added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberAddType struct {
	Value AutomatedReasoningPolicyAddTypeAnnotation
	// contains filtered or unexported fields
}

An operation to add a new custom type to the policy, defining a set of possible values for policy variables.

type AutomatedReasoningPolicyAnnotationMemberAddVariable added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberAddVariable struct {
	Value AutomatedReasoningPolicyAddVariableAnnotation
	// contains filtered or unexported fields
}

An operation to add a new variable to the policy, which can be used in rule expressions to represent dynamic values.

type AutomatedReasoningPolicyAnnotationMemberDeleteRule added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberDeleteRule struct {
	Value AutomatedReasoningPolicyDeleteRuleAnnotation
	// contains filtered or unexported fields
}

An operation to remove a rule from the policy.

type AutomatedReasoningPolicyAnnotationMemberDeleteType added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberDeleteType struct {
	Value AutomatedReasoningPolicyDeleteTypeAnnotation
	// contains filtered or unexported fields
}

An operation to remove a custom type from the policy. The type must not be referenced by any variables or rules.

type AutomatedReasoningPolicyAnnotationMemberDeleteVariable added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberDeleteVariable struct {
	Value AutomatedReasoningPolicyDeleteVariableAnnotation
	// contains filtered or unexported fields
}

An operation to remove a variable from the policy. The variable must not be referenced by any rules.

type AutomatedReasoningPolicyAnnotationMemberIngestContent added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberIngestContent struct {
	Value AutomatedReasoningPolicyIngestContentAnnotation
	// contains filtered or unexported fields
}

An operation to process and incorporate new content into the policy, extracting additional rules and concepts.

type AutomatedReasoningPolicyAnnotationMemberUpdateFromRulesFeedback added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberUpdateFromRulesFeedback struct {
	Value AutomatedReasoningPolicyUpdateFromRuleFeedbackAnnotation
	// contains filtered or unexported fields
}

An operation to update the policy based on feedback about how specific rules performed during testing or validation.

type AutomatedReasoningPolicyAnnotationMemberUpdateFromScenarioFeedback added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberUpdateFromScenarioFeedback struct {
	Value AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation
	// contains filtered or unexported fields
}

An operation to update the policy based on feedback about how it performed on specific test scenarios.

type AutomatedReasoningPolicyAnnotationMemberUpdateRule added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberUpdateRule struct {
	Value AutomatedReasoningPolicyUpdateRuleAnnotation
	// contains filtered or unexported fields
}

An operation to modify an existing rule in the policy, such as changing its logical expression or conditions.

type AutomatedReasoningPolicyAnnotationMemberUpdateType added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberUpdateType struct {
	Value AutomatedReasoningPolicyUpdateTypeAnnotation
	// contains filtered or unexported fields
}

An operation to modify an existing custom type in the policy, such as changing its name, description, or allowed values.

type AutomatedReasoningPolicyAnnotationMemberUpdateVariable added in v1.42.0 

type AutomatedReasoningPolicyAnnotationMemberUpdateVariable struct {
	Value AutomatedReasoningPolicyUpdateVariableAnnotation
	// contains filtered or unexported fields
}

An operation to modify an existing variable in the policy, such as changing its name, type, or description.

type AutomatedReasoningPolicyAnnotationStatus added in v1.42.0 

type AutomatedReasoningPolicyAnnotationStatus string
const (
	AutomatedReasoningPolicyAnnotationStatusApplied AutomatedReasoningPolicyAnnotationStatus = "APPLIED"
	AutomatedReasoningPolicyAnnotationStatusFailed  AutomatedReasoningPolicyAnnotationStatus = "FAILED"
)

Enum values for AutomatedReasoningPolicyAnnotationStatus

func (AutomatedReasoningPolicyAnnotationStatus) Values added in v1.42.0 

func (AutomatedReasoningPolicyAnnotationStatus) Values() []AutomatedReasoningPolicyAnnotationStatus

Values returns all known values for AutomatedReasoningPolicyAnnotationStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyBuildDocumentContentType added in v1.42.0 

type AutomatedReasoningPolicyBuildDocumentContentType string
const (
	AutomatedReasoningPolicyBuildDocumentContentTypePdf  AutomatedReasoningPolicyBuildDocumentContentType = "pdf"
	AutomatedReasoningPolicyBuildDocumentContentTypeText AutomatedReasoningPolicyBuildDocumentContentType = "txt"
)

Enum values for AutomatedReasoningPolicyBuildDocumentContentType

func (AutomatedReasoningPolicyBuildDocumentContentType) Values added in v1.42.0 

func (AutomatedReasoningPolicyBuildDocumentContentType) Values() []AutomatedReasoningPolicyBuildDocumentContentType

Values returns all known values for AutomatedReasoningPolicyBuildDocumentContentType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyBuildLog added in v1.42.0 

type AutomatedReasoningPolicyBuildLog struct {

	// A list of log entries documenting each step in the policy build process,
	// including timestamps, status, and detailed messages.
	//
	// This member is required.
	Entries []AutomatedReasoningPolicyBuildLogEntry
	// contains filtered or unexported fields
}

Contains detailed logging information about the policy build process, including steps taken, decisions made, and any issues encountered.

type AutomatedReasoningPolicyBuildLogEntry added in v1.42.0 

type AutomatedReasoningPolicyBuildLogEntry struct {

	// The annotation or operation that was being processed when this log entry was
	// created.
	//
	// This member is required.
	Annotation AutomatedReasoningPolicyAnnotation

	// Detailed information about the specific build steps that were executed,
	// including any sub-operations or transformations.
	//
	// This member is required.
	BuildSteps []AutomatedReasoningPolicyBuildStep

	// The status of the build step (e.g., SUCCESS, FAILED, IN_PROGRESS).
	//
	// This member is required.
	Status AutomatedReasoningPolicyAnnotationStatus
	// contains filtered or unexported fields
}

Represents a single entry in the policy build log, containing information about a specific step or event in the build process.

type AutomatedReasoningPolicyBuildMessageType added in v1.42.0 

type AutomatedReasoningPolicyBuildMessageType string
const (
	AutomatedReasoningPolicyBuildMessageTypeInfo    AutomatedReasoningPolicyBuildMessageType = "INFO"
	AutomatedReasoningPolicyBuildMessageTypeWarning AutomatedReasoningPolicyBuildMessageType = "WARNING"
	AutomatedReasoningPolicyBuildMessageTypeError   AutomatedReasoningPolicyBuildMessageType = "ERROR"
)

Enum values for AutomatedReasoningPolicyBuildMessageType

func (AutomatedReasoningPolicyBuildMessageType) Values added in v1.42.0 

func (AutomatedReasoningPolicyBuildMessageType) Values() []AutomatedReasoningPolicyBuildMessageType

Values returns all known values for AutomatedReasoningPolicyBuildMessageType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyBuildResultAssetType added in v1.42.0 

type AutomatedReasoningPolicyBuildResultAssetType string
const (
	AutomatedReasoningPolicyBuildResultAssetTypeBuildLog         AutomatedReasoningPolicyBuildResultAssetType = "BUILD_LOG"
	AutomatedReasoningPolicyBuildResultAssetTypeQualityReport    AutomatedReasoningPolicyBuildResultAssetType = "QUALITY_REPORT"
	AutomatedReasoningPolicyBuildResultAssetTypePolicyDefinition AutomatedReasoningPolicyBuildResultAssetType = "POLICY_DEFINITION"
)

Enum values for AutomatedReasoningPolicyBuildResultAssetType

func (AutomatedReasoningPolicyBuildResultAssetType) Values added in v1.42.0 

func (AutomatedReasoningPolicyBuildResultAssetType) Values() []AutomatedReasoningPolicyBuildResultAssetType

Values returns all known values for AutomatedReasoningPolicyBuildResultAssetType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyBuildResultAssets added in v1.42.0 

type AutomatedReasoningPolicyBuildResultAssets interface {
	// contains filtered or unexported methods
}

Contains the various assets generated during a policy build workflow, including logs, quality reports, and the final policy definition.

The following types satisfy this interface: 

AutomatedReasoningPolicyBuildResultAssetsMemberBuildLog
AutomatedReasoningPolicyBuildResultAssetsMemberPolicyDefinition
AutomatedReasoningPolicyBuildResultAssetsMemberQualityReport
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningPolicyBuildResultAssets
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningPolicyBuildResultAssetsMemberBuildLog:
		_ = v.Value // Value is types.AutomatedReasoningPolicyBuildLog

	case *types.AutomatedReasoningPolicyBuildResultAssetsMemberPolicyDefinition:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDefinition

	case *types.AutomatedReasoningPolicyBuildResultAssetsMemberQualityReport:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDefinitionQualityReport

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningPolicyBuildResultAssetsMemberBuildLog added in v1.42.0 

type AutomatedReasoningPolicyBuildResultAssetsMemberBuildLog struct {
	Value AutomatedReasoningPolicyBuildLog
	// contains filtered or unexported fields
}

The complete build log containing detailed information about each step in the policy generation process.

type AutomatedReasoningPolicyBuildResultAssetsMemberPolicyDefinition added in v1.42.0 

type AutomatedReasoningPolicyBuildResultAssetsMemberPolicyDefinition struct {
	Value AutomatedReasoningPolicyDefinition
	// contains filtered or unexported fields
}

The complete policy definition generated by the build workflow, containing all rules, variables, and custom types extracted from the source documents.

type AutomatedReasoningPolicyBuildResultAssetsMemberQualityReport added in v1.42.0 

type AutomatedReasoningPolicyBuildResultAssetsMemberQualityReport struct {
	Value AutomatedReasoningPolicyDefinitionQualityReport
	// contains filtered or unexported fields
}

A comprehensive report analyzing the quality of the generated policy, including metrics about rule coverage, potential conflicts, and unused elements.

type AutomatedReasoningPolicyBuildStep added in v1.42.0 

type AutomatedReasoningPolicyBuildStep struct {

	// Contextual information about what was being processed during this build step,
	// such as the type of operation or the source material being analyzed.
	//
	// This member is required.
	Context AutomatedReasoningPolicyBuildStepContext

	// A list of messages generated during this build step, including informational
	// messages, warnings, and error details.
	//
	// This member is required.
	Messages []AutomatedReasoningPolicyBuildStepMessage

	// Reference to the previous element or step in the build process, helping to
	// trace the sequence of operations.
	PriorElement AutomatedReasoningPolicyDefinitionElement
	// contains filtered or unexported fields
}

Represents a single step in the policy build process, containing context about what was being processed and any messages or results.

type AutomatedReasoningPolicyBuildStepContext added in v1.42.0 

type AutomatedReasoningPolicyBuildStepContext interface {
	// contains filtered or unexported methods
}

Provides context about what type of operation was being performed during a build step.

The following types satisfy this interface: 

AutomatedReasoningPolicyBuildStepContextMemberMutation
AutomatedReasoningPolicyBuildStepContextMemberPlanning
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningPolicyBuildStepContext
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningPolicyBuildStepContextMemberMutation:
		_ = v.Value // Value is types.AutomatedReasoningPolicyMutation

	case *types.AutomatedReasoningPolicyBuildStepContextMemberPlanning:
		_ = v.Value // Value is types.AutomatedReasoningPolicyPlanning

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningPolicyBuildStepContextMemberMutation added in v1.42.0 

type AutomatedReasoningPolicyBuildStepContextMemberMutation struct {
	Value AutomatedReasoningPolicyMutation
	// contains filtered or unexported fields
}

Indicates that this build step involved modifying the policy structure, such as adding or updating rules, variables, or types.

type AutomatedReasoningPolicyBuildStepContextMemberPlanning added in v1.42.0 

type AutomatedReasoningPolicyBuildStepContextMemberPlanning struct {
	Value AutomatedReasoningPolicyPlanning
	// contains filtered or unexported fields
}

Indicates that this build step was part of the planning phase, where the system determines what operations to perform.

type AutomatedReasoningPolicyBuildStepMessage added in v1.42.0 

type AutomatedReasoningPolicyBuildStepMessage struct {

	// The content of the message, describing what occurred during the build step.
	//
	// This member is required.
	Message *string

	// The type of message (e.g., INFO, WARNING, ERROR) indicating its severity and
	// purpose.
	//
	// This member is required.
	MessageType AutomatedReasoningPolicyBuildMessageType
	// contains filtered or unexported fields
}

Represents a message generated during a build step, providing information about what happened or any issues encountered.

type AutomatedReasoningPolicyBuildWorkflowDocument added in v1.42.0 

type AutomatedReasoningPolicyBuildWorkflowDocument struct {

	// The actual content of the source document that will be analyzed to extract
	// policy rules and concepts.
	//
	// This member is required.
	Document []byte

	// The MIME type of the document content (e.g., text/plain, application/pdf,
	// text/markdown).
	//
	// This member is required.
	DocumentContentType AutomatedReasoningPolicyBuildDocumentContentType

	// A descriptive name for the document that helps identify its purpose and content.
	//
	// This member is required.
	DocumentName *string

	// A detailed description of the document's content and how it should be used in
	// the policy generation process.
	DocumentDescription *string
	// contains filtered or unexported fields
}

Represents a source document used in the policy build workflow, containing the content and metadata needed for policy generation.

type AutomatedReasoningPolicyBuildWorkflowRepairContent added in v1.42.0 

type AutomatedReasoningPolicyBuildWorkflowRepairContent struct {

	// Specific annotations or modifications to apply during the policy repair
	// process, such as rule corrections or variable updates.
	//
	// This member is required.
	Annotations []AutomatedReasoningPolicyAnnotation
	// contains filtered or unexported fields
}

Contains content and instructions for repairing or improving an existing Automated Reasoning policy.

type AutomatedReasoningPolicyBuildWorkflowSource added in v1.42.0 

type AutomatedReasoningPolicyBuildWorkflowSource struct {

	// An existing policy definition that serves as the starting point for the build
	// workflow, typically used in policy repair or update scenarios.
	PolicyDefinition *AutomatedReasoningPolicyDefinition

	// The actual content to be processed in the build workflow, such as documents to
	// analyze or repair instructions to apply.
	WorkflowContent AutomatedReasoningPolicyWorkflowTypeContent
	// contains filtered or unexported fields
}

Defines the source content for a policy build workflow, which can include documents, repair instructions, or other input materials.

type AutomatedReasoningPolicyBuildWorkflowStatus added in v1.42.0 

type AutomatedReasoningPolicyBuildWorkflowStatus string
const (
	AutomatedReasoningPolicyBuildWorkflowStatusScheduled       AutomatedReasoningPolicyBuildWorkflowStatus = "SCHEDULED"
	AutomatedReasoningPolicyBuildWorkflowStatusCancelRequested AutomatedReasoningPolicyBuildWorkflowStatus = "CANCEL_REQUESTED"
	AutomatedReasoningPolicyBuildWorkflowStatusPreprocessing   AutomatedReasoningPolicyBuildWorkflowStatus = "PREPROCESSING"
	AutomatedReasoningPolicyBuildWorkflowStatusBuilding        AutomatedReasoningPolicyBuildWorkflowStatus = "BUILDING"
	AutomatedReasoningPolicyBuildWorkflowStatusTesting         AutomatedReasoningPolicyBuildWorkflowStatus = "TESTING"
	AutomatedReasoningPolicyBuildWorkflowStatusCompleted       AutomatedReasoningPolicyBuildWorkflowStatus = "COMPLETED"
	AutomatedReasoningPolicyBuildWorkflowStatusFailed          AutomatedReasoningPolicyBuildWorkflowStatus = "FAILED"
	AutomatedReasoningPolicyBuildWorkflowStatusCancelled       AutomatedReasoningPolicyBuildWorkflowStatus = "CANCELLED"
)

Enum values for AutomatedReasoningPolicyBuildWorkflowStatus

func (AutomatedReasoningPolicyBuildWorkflowStatus) Values added in v1.42.0 

func (AutomatedReasoningPolicyBuildWorkflowStatus) Values() []AutomatedReasoningPolicyBuildWorkflowStatus

Values returns all known values for AutomatedReasoningPolicyBuildWorkflowStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyBuildWorkflowSummary added in v1.42.0 

type AutomatedReasoningPolicyBuildWorkflowSummary struct {

	// The unique identifier of the build workflow.
	//
	// This member is required.
	BuildWorkflowId *string

	// The type of build workflow (e.g., DOCUMENT_INGESTION, POLICY_REPAIR).
	//
	// This member is required.
	BuildWorkflowType AutomatedReasoningPolicyBuildWorkflowType

	// The timestamp when the build workflow was created.
	//
	// This member is required.
	CreatedAt *time.Time

	// The Amazon Resource Name (ARN) of the Automated Reasoning policy associated
	// with this build workflow.
	//
	// This member is required.
	PolicyArn *string

	// The current status of the build workflow (e.g., RUNNING, COMPLETED, FAILED,
	// CANCELLED).
	//
	// This member is required.
	Status AutomatedReasoningPolicyBuildWorkflowStatus

	// The timestamp when the build workflow was last updated.
	//
	// This member is required.
	UpdatedAt *time.Time
	// contains filtered or unexported fields
}

Provides a summary of a policy build workflow, including its current status, timing information, and key identifiers.

type AutomatedReasoningPolicyBuildWorkflowType added in v1.42.0 

type AutomatedReasoningPolicyBuildWorkflowType string
const (
	AutomatedReasoningPolicyBuildWorkflowTypeIngestContent AutomatedReasoningPolicyBuildWorkflowType = "INGEST_CONTENT"
	AutomatedReasoningPolicyBuildWorkflowTypeRefinePolicy  AutomatedReasoningPolicyBuildWorkflowType = "REFINE_POLICY"
	AutomatedReasoningPolicyBuildWorkflowTypeImportPolicy  AutomatedReasoningPolicyBuildWorkflowType = "IMPORT_POLICY"
)

Enum values for AutomatedReasoningPolicyBuildWorkflowType

func (AutomatedReasoningPolicyBuildWorkflowType) Values added in v1.42.0 

func (AutomatedReasoningPolicyBuildWorkflowType) Values() []AutomatedReasoningPolicyBuildWorkflowType

Values returns all known values for AutomatedReasoningPolicyBuildWorkflowType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyDefinition added in v1.42.0 

type AutomatedReasoningPolicyDefinition struct {

	// The formal logic rules extracted from the source document. Rules define the
	// logical constraints that determine whether model responses are valid, invalid,
	// or satisfiable.
	Rules []AutomatedReasoningPolicyDefinitionRule

	// The custom user-defined vairable types used in the policy. Types are enum-based
	// variable types that provide additional context beyond the predefined variable
	// types.
	Types []AutomatedReasoningPolicyDefinitionType

	// The variables that represent concepts in the policy. Variables can have values
	// assigned when translating natural language into formal logic. Their descriptions
	// are crucial for accurate translation.
	Variables []AutomatedReasoningPolicyDefinitionVariable

	// The version of the policy definition format.
	Version *string
	// contains filtered or unexported fields
}

Contains the formal logic rules, variables, and custom variable types that define an Automated Reasoning policy. The policy definition specifies the constraints used to validate foundation model responses for accuracy and logical consistency.

type AutomatedReasoningPolicyDefinitionElement added in v1.42.0 

type AutomatedReasoningPolicyDefinitionElement interface {
	// contains filtered or unexported methods
}

Represents a single element in an Automated Reasoning policy definition, such as a rule, variable, or type definition.

The following types satisfy this interface: 

AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionRule
AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionType
AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionVariable
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningPolicyDefinitionElement
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionRule:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDefinitionRule

	case *types.AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionType:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDefinitionType

	case *types.AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionVariable:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDefinitionVariable

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionRule added in v1.42.0 

type AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionRule struct {
	Value AutomatedReasoningPolicyDefinitionRule
	// contains filtered or unexported fields
}

A rule element within the policy definition that contains a formal logical expression used for validation.

type AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionType added in v1.42.0 

type AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionType struct {
	Value AutomatedReasoningPolicyDefinitionType
	// contains filtered or unexported fields
}

A custom type element within the policy definition that defines a set of possible values for variables.

type AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionVariable added in v1.42.0 

type AutomatedReasoningPolicyDefinitionElementMemberPolicyDefinitionVariable struct {
	Value AutomatedReasoningPolicyDefinitionVariable
	// contains filtered or unexported fields
}

A variable element within the policy definition that represents a concept used in logical expressions and rules.

type AutomatedReasoningPolicyDefinitionQualityReport added in v1.42.0 

type AutomatedReasoningPolicyDefinitionQualityReport struct {

	// A list of rules that may conflict with each other, potentially leading to
	// inconsistent policy behavior.
	//
	// This member is required.
	ConflictingRules []string

	// Groups of rules that operate on completely separate sets of variables,
	// indicating the policy may be addressing multiple unrelated concerns.
	//
	// This member is required.
	DisjointRuleSets []AutomatedReasoningPolicyDisjointRuleSet

	// The total number of rules defined in the policy.
	//
	// This member is required.
	RuleCount *int32

	// The total number of custom types defined in the policy.
	//
	// This member is required.
	TypeCount *int32

	// A list of type values that are defined but never used in any rules, indicating
	// potential cleanup opportunities.
	//
	// This member is required.
	UnusedTypeValues []AutomatedReasoningPolicyDefinitionTypeValuePair

	// A list of custom types that are defined but not referenced by any variables or
	// rules, suggesting they may be unnecessary.
	//
	// This member is required.
	UnusedTypes []string

	// A list of variables that are defined but not referenced by any rules,
	// suggesting they may be unnecessary.
	//
	// This member is required.
	UnusedVariables []string

	// The total number of variables defined in the policy.
	//
	// This member is required.
	VariableCount *int32
	// contains filtered or unexported fields
}

Provides a comprehensive analysis of the quality and completeness of an Automated Reasoning policy definition, highlighting potential issues and optimization opportunities.

type AutomatedReasoningPolicyDefinitionRule added in v1.42.0 

type AutomatedReasoningPolicyDefinitionRule struct {

	// The formal logic expression of the rule.
	//
	// This member is required.
	Expression *string

	// The unique identifier of the rule within the policy.
	//
	// This member is required.
	Id *string

	// The human-readable form of the rule expression, often in natural language or
	// simplified notation.
	AlternateExpression *string
	// contains filtered or unexported fields
}

Represents a formal logic rule in an Automated Reasoning policy. For example, rules can be expressed as if-then statements that define logical constraints.

type AutomatedReasoningPolicyDefinitionType added in v1.42.0 

type AutomatedReasoningPolicyDefinitionType struct {

	// The name of the custom type.
	//
	// This member is required.
	Name *string

	// The possible values for this enum-based type, each with its own description.
	//
	// This member is required.
	Values []AutomatedReasoningPolicyDefinitionTypeValue

	// The description of what the custom type represents.
	Description *string
	// contains filtered or unexported fields
}

Represents a custom user-defined viarble type in an Automated Reasoning policy. Types are enum-based and provide additional context beyond predefined variable types.

type AutomatedReasoningPolicyDefinitionTypeValue added in v1.42.0 

type AutomatedReasoningPolicyDefinitionTypeValue struct {

	// The actual value or identifier for this type value.
	//
	// This member is required.
	Value *string

	// A human-readable description explaining what this type value represents and
	// when it should be used.
	Description *string
	// contains filtered or unexported fields
}

Represents a single value within a custom type definition, including its identifier and description.

type AutomatedReasoningPolicyDefinitionTypeValuePair added in v1.42.0 

type AutomatedReasoningPolicyDefinitionTypeValuePair struct {

	// The name of the custom type that contains the referenced value.
	//
	// This member is required.
	TypeName *string

	// The name of the specific value within the type.
	//
	// This member is required.
	ValueName *string
	// contains filtered or unexported fields
}

Associates a type name with a specific value name, used for referencing type values in rules and other policy elements.

type AutomatedReasoningPolicyDefinitionVariable added in v1.42.0 

type AutomatedReasoningPolicyDefinitionVariable struct {

	// The description of the variable that explains what it represents and how users
	// might refer to it. Clear and comprehensive descriptions are essential for
	// accurate natural language translation.
	//
	// This member is required.
	Description *string

	// The name of the variable. Use descriptive names that clearly indicate the
	// concept being represented.
	//
	// This member is required.
	Name *string

	// The data type of the variable. Valid types include bool, int, real, enum, and
	// custom types that you can provide.
	//
	// This member is required.
	Type *string
	// contains filtered or unexported fields
}

Represents a variable in an Automated Reasoning policy. Variables represent concepts that can have values assigned during natural language translation.

type AutomatedReasoningPolicyDeleteRuleAnnotation added in v1.42.0 

type AutomatedReasoningPolicyDeleteRuleAnnotation struct {

	// The unique identifier of the rule to delete from the policy.
	//
	// This member is required.
	RuleId *string
	// contains filtered or unexported fields
}

An annotation for removing a rule from an Automated Reasoning policy.

type AutomatedReasoningPolicyDeleteRuleMutation added in v1.42.0 

type AutomatedReasoningPolicyDeleteRuleMutation struct {

	// The unique identifier of the rule to delete.
	//
	// This member is required.
	Id *string
	// contains filtered or unexported fields
}

A mutation operation that removes a rule from the policy definition during the build process.

type AutomatedReasoningPolicyDeleteTypeAnnotation added in v1.42.0 

type AutomatedReasoningPolicyDeleteTypeAnnotation struct {

	// The name of the custom type to delete from the policy. The type must not be
	// referenced by any variables or rules.
	//
	// This member is required.
	Name *string
	// contains filtered or unexported fields
}

An annotation for removing a custom type from an Automated Reasoning policy.

type AutomatedReasoningPolicyDeleteTypeMutation added in v1.42.0 

type AutomatedReasoningPolicyDeleteTypeMutation struct {

	// The name of the custom type to delete.
	//
	// This member is required.
	Name *string
	// contains filtered or unexported fields
}

A mutation operation that removes a custom type from the policy definition during the build process.

type AutomatedReasoningPolicyDeleteTypeValue added in v1.42.0 

type AutomatedReasoningPolicyDeleteTypeValue struct {

	// The identifier or name of the value to remove from the type.
	//
	// This member is required.
	Value *string
	// contains filtered or unexported fields
}

Represents a value to be removed from an existing custom type in the policy.

type AutomatedReasoningPolicyDeleteVariableAnnotation added in v1.42.0 

type AutomatedReasoningPolicyDeleteVariableAnnotation struct {

	// The name of the variable to delete from the policy. The variable must not be
	// referenced by any rules.
	//
	// This member is required.
	Name *string
	// contains filtered or unexported fields
}

An annotation for removing a variable from an Automated Reasoning policy.

type AutomatedReasoningPolicyDeleteVariableMutation added in v1.42.0 

type AutomatedReasoningPolicyDeleteVariableMutation struct {

	// The name of the variable to delete.
	//
	// This member is required.
	Name *string
	// contains filtered or unexported fields
}

A mutation operation that removes a variable from the policy definition during the build process.

type AutomatedReasoningPolicyDisjointRuleSet added in v1.42.0 

type AutomatedReasoningPolicyDisjointRuleSet struct {

	// The list of rules that form this disjoint set, all operating on the same set of
	// variables.
	//
	// This member is required.
	Rules []string

	// The set of variables that are used by the rules in this disjoint set.
	//
	// This member is required.
	Variables []string
	// contains filtered or unexported fields
}

Represents a set of rules that operate on completely separate variables, indicating they address different concerns or domains within the policy.

type AutomatedReasoningPolicyIngestContentAnnotation added in v1.42.0 

type AutomatedReasoningPolicyIngestContentAnnotation struct {

	// The new content to be analyzed and incorporated into the policy, such as
	// additional documents or rule descriptions.
	//
	// This member is required.
	Content *string
	// contains filtered or unexported fields
}

An annotation for processing and incorporating new content into an Automated Reasoning policy.

type AutomatedReasoningPolicyMutation added in v1.42.0 

type AutomatedReasoningPolicyMutation interface {
	// contains filtered or unexported methods
}

A container for various mutation operations that can be applied to an Automated Reasoning policy, including adding, updating, and deleting policy elements.

The following types satisfy this interface: 

AutomatedReasoningPolicyMutationMemberAddRule
AutomatedReasoningPolicyMutationMemberAddType
AutomatedReasoningPolicyMutationMemberAddVariable
AutomatedReasoningPolicyMutationMemberDeleteRule
AutomatedReasoningPolicyMutationMemberDeleteType
AutomatedReasoningPolicyMutationMemberDeleteVariable
AutomatedReasoningPolicyMutationMemberUpdateRule
AutomatedReasoningPolicyMutationMemberUpdateType
AutomatedReasoningPolicyMutationMemberUpdateVariable
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningPolicyMutation
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningPolicyMutationMemberAddRule:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddRuleMutation

	case *types.AutomatedReasoningPolicyMutationMemberAddType:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddTypeMutation

	case *types.AutomatedReasoningPolicyMutationMemberAddVariable:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddVariableMutation

	case *types.AutomatedReasoningPolicyMutationMemberDeleteRule:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDeleteRuleMutation

	case *types.AutomatedReasoningPolicyMutationMemberDeleteType:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDeleteTypeMutation

	case *types.AutomatedReasoningPolicyMutationMemberDeleteVariable:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDeleteVariableMutation

	case *types.AutomatedReasoningPolicyMutationMemberUpdateRule:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateRuleMutation

	case *types.AutomatedReasoningPolicyMutationMemberUpdateType:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateTypeMutation

	case *types.AutomatedReasoningPolicyMutationMemberUpdateVariable:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateVariableMutation

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningPolicyMutationMemberAddRule added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberAddRule struct {
	Value AutomatedReasoningPolicyAddRuleMutation
	// contains filtered or unexported fields
}

A mutation to add a new rule to the policy.

type AutomatedReasoningPolicyMutationMemberAddType added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberAddType struct {
	Value AutomatedReasoningPolicyAddTypeMutation
	// contains filtered or unexported fields
}

A mutation to add a new custom type to the policy.

type AutomatedReasoningPolicyMutationMemberAddVariable added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberAddVariable struct {
	Value AutomatedReasoningPolicyAddVariableMutation
	// contains filtered or unexported fields
}

A mutation to add a new variable to the policy.

type AutomatedReasoningPolicyMutationMemberDeleteRule added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberDeleteRule struct {
	Value AutomatedReasoningPolicyDeleteRuleMutation
	// contains filtered or unexported fields
}

A mutation to remove a rule from the policy.

type AutomatedReasoningPolicyMutationMemberDeleteType added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberDeleteType struct {
	Value AutomatedReasoningPolicyDeleteTypeMutation
	// contains filtered or unexported fields
}

A mutation to remove a custom type from the policy.

type AutomatedReasoningPolicyMutationMemberDeleteVariable added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberDeleteVariable struct {
	Value AutomatedReasoningPolicyDeleteVariableMutation
	// contains filtered or unexported fields
}

A mutation to remove a variable from the policy.

type AutomatedReasoningPolicyMutationMemberUpdateRule added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberUpdateRule struct {
	Value AutomatedReasoningPolicyUpdateRuleMutation
	// contains filtered or unexported fields
}

A mutation to modify an existing rule in the policy.

type AutomatedReasoningPolicyMutationMemberUpdateType added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberUpdateType struct {
	Value AutomatedReasoningPolicyUpdateTypeMutation
	// contains filtered or unexported fields
}

A mutation to modify an existing custom type in the policy.

type AutomatedReasoningPolicyMutationMemberUpdateVariable added in v1.42.0 

type AutomatedReasoningPolicyMutationMemberUpdateVariable struct {
	Value AutomatedReasoningPolicyUpdateVariableMutation
	// contains filtered or unexported fields
}

A mutation to modify an existing variable in the policy.

type AutomatedReasoningPolicyPlanning added in v1.42.0 

type AutomatedReasoningPolicyPlanning struct {
	// contains filtered or unexported fields
}

Represents the planning phase of policy build workflow, where the system analyzes source content and determines what operations to perform.

type AutomatedReasoningPolicyScenario added in v1.42.0 

type AutomatedReasoningPolicyScenario struct {

	// An alternative way to express the same test scenario, used for validation and
	// comparison purposes.
	//
	// This member is required.
	AlternateExpression *string

	// The expected outcome when this scenario is evaluated against the policy (e.g.,
	// PASS, FAIL, VIOLATION).
	//
	// This member is required.
	ExpectedResult AutomatedReasoningCheckResult

	// The logical expression or condition that defines this test scenario.
	//
	// This member is required.
	Expression *string

	// The list of rule identifiers that are expected to be triggered or evaluated by
	// this test scenario.
	//
	// This member is required.
	RuleIds []string
	// contains filtered or unexported fields
}

Represents a test scenario used to validate an Automated Reasoning policy, including the test conditions and expected outcomes.

type AutomatedReasoningPolicySummary added in v1.42.0 

type AutomatedReasoningPolicySummary struct {

	// The timestamp when the policy was created.
	//
	// This member is required.
	CreatedAt *time.Time

	// The name of the policy.
	//
	// This member is required.
	Name *string

	// The Amazon Resource Name (ARN) of the policy.
	//
	// This member is required.
	PolicyArn *string

	// The unique identifier of the policy.
	//
	// This member is required.
	PolicyId *string

	// The timestamp when the policy was last updated.
	//
	// This member is required.
	UpdatedAt *time.Time

	// The version of the policy.
	//
	// This member is required.
	Version *string

	// The description of the policy.
	Description *string
	// contains filtered or unexported fields
}

Contains summary information about an Automated Reasoning policy, including metadata and timestamps.

type AutomatedReasoningPolicyTestCase added in v1.42.0 

type AutomatedReasoningPolicyTestCase struct {

	// The timestamp when the test was created.
	//
	// This member is required.
	CreatedAt *time.Time

	// The output content to be validated by the policy, typically representing a
	// foundation model response.
	//
	// This member is required.
	GuardContent *string

	// The unique identifier of the test.
	//
	// This member is required.
	TestCaseId *string

	// The timestamp when the test was last updated.
	//
	// This member is required.
	UpdatedAt *time.Time

	// The minimum confidence level for logic validation. Content meeting this
	// threshold is considered high-confidence and can be validated.
	ConfidenceThreshold *float64

	// The expected result of the Automated Reasoning check for this test.
	ExpectedAggregatedFindingsResult AutomatedReasoningCheckResult

	// The input query or prompt that generated the content. This provides context for
	// the validation.
	QueryContent *string
	// contains filtered or unexported fields
}

Represents a test for validating an Automated Reasoning policy. tests contain sample inputs and expected outcomes to verify policy behavior.

type AutomatedReasoningPolicyTestResult added in v1.42.0 

type AutomatedReasoningPolicyTestResult struct {

	// The Amazon Resource Name (ARN) of the Automated Reasoning policy that was
	// tested.
	//
	// This member is required.
	PolicyArn *string

	// The test case that was executed, including the input content, expected results,
	// and configuration parameters used during validation.
	//
	// This member is required.
	TestCase *AutomatedReasoningPolicyTestCase

	// The overall status of the test run (e.g., COMPLETED, FAILED, IN_PROGRESS).
	//
	// This member is required.
	TestRunStatus AutomatedReasoningPolicyTestRunStatus

	// The timestamp when the test results were last updated.
	//
	// This member is required.
	UpdatedAt *time.Time

	// A summary of all test findings, aggregated to provide an overall assessment of
	// policy quality and correctness.
	AggregatedTestFindingsResult AutomatedReasoningCheckResult

	// Detailed findings from the test run, including any issues, violations, or
	// unexpected behaviors discovered.
	TestFindings []AutomatedReasoningCheckFinding

	// The overall result of the test run, indicating whether the policy passed or
	// failed validation.
	TestRunResult AutomatedReasoningPolicyTestRunResult
	// contains filtered or unexported fields
}

Contains the results of testing an Automated Reasoning policy against various scenarios and validation checks.

type AutomatedReasoningPolicyTestRunResult added in v1.42.0 

type AutomatedReasoningPolicyTestRunResult string
const (
	AutomatedReasoningPolicyTestRunResultPassed AutomatedReasoningPolicyTestRunResult = "PASSED"
	AutomatedReasoningPolicyTestRunResultFailed AutomatedReasoningPolicyTestRunResult = "FAILED"
)

Enum values for AutomatedReasoningPolicyTestRunResult

func (AutomatedReasoningPolicyTestRunResult) Values added in v1.42.0 

func (AutomatedReasoningPolicyTestRunResult) Values() []AutomatedReasoningPolicyTestRunResult

Values returns all known values for AutomatedReasoningPolicyTestRunResult. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyTestRunStatus added in v1.42.0 

type AutomatedReasoningPolicyTestRunStatus string
const (
	AutomatedReasoningPolicyTestRunStatusNotStarted AutomatedReasoningPolicyTestRunStatus = "NOT_STARTED"
	AutomatedReasoningPolicyTestRunStatusScheduled  AutomatedReasoningPolicyTestRunStatus = "SCHEDULED"
	AutomatedReasoningPolicyTestRunStatusInProgress AutomatedReasoningPolicyTestRunStatus = "IN_PROGRESS"
	AutomatedReasoningPolicyTestRunStatusCompleted  AutomatedReasoningPolicyTestRunStatus = "COMPLETED"
	AutomatedReasoningPolicyTestRunStatusFailed     AutomatedReasoningPolicyTestRunStatus = "FAILED"
)

Enum values for AutomatedReasoningPolicyTestRunStatus

func (AutomatedReasoningPolicyTestRunStatus) Values added in v1.42.0 

func (AutomatedReasoningPolicyTestRunStatus) Values() []AutomatedReasoningPolicyTestRunStatus

Values returns all known values for AutomatedReasoningPolicyTestRunStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type AutomatedReasoningPolicyTypeValueAnnotation added in v1.42.0 

type AutomatedReasoningPolicyTypeValueAnnotation interface {
	// contains filtered or unexported methods
}

An annotation for managing values within custom types, including adding, updating, or removing specific type values.

The following types satisfy this interface: 

AutomatedReasoningPolicyTypeValueAnnotationMemberAddTypeValue
AutomatedReasoningPolicyTypeValueAnnotationMemberDeleteTypeValue
AutomatedReasoningPolicyTypeValueAnnotationMemberUpdateTypeValue
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningPolicyTypeValueAnnotation
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningPolicyTypeValueAnnotationMemberAddTypeValue:
		_ = v.Value // Value is types.AutomatedReasoningPolicyAddTypeValue

	case *types.AutomatedReasoningPolicyTypeValueAnnotationMemberDeleteTypeValue:
		_ = v.Value // Value is types.AutomatedReasoningPolicyDeleteTypeValue

	case *types.AutomatedReasoningPolicyTypeValueAnnotationMemberUpdateTypeValue:
		_ = v.Value // Value is types.AutomatedReasoningPolicyUpdateTypeValue

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningPolicyTypeValueAnnotationMemberAddTypeValue added in v1.42.0 

type AutomatedReasoningPolicyTypeValueAnnotationMemberAddTypeValue struct {
	Value AutomatedReasoningPolicyAddTypeValue
	// contains filtered or unexported fields
}

An operation to add a new value to an existing custom type.

type AutomatedReasoningPolicyTypeValueAnnotationMemberDeleteTypeValue added in v1.42.0 

type AutomatedReasoningPolicyTypeValueAnnotationMemberDeleteTypeValue struct {
	Value AutomatedReasoningPolicyDeleteTypeValue
	// contains filtered or unexported fields
}

An operation to remove a value from an existing custom type.

type AutomatedReasoningPolicyTypeValueAnnotationMemberUpdateTypeValue added in v1.42.0 

type AutomatedReasoningPolicyTypeValueAnnotationMemberUpdateTypeValue struct {
	Value AutomatedReasoningPolicyUpdateTypeValue
	// contains filtered or unexported fields
}

An operation to modify an existing value within a custom type.

type AutomatedReasoningPolicyUpdateFromRuleFeedbackAnnotation added in v1.42.0 

type AutomatedReasoningPolicyUpdateFromRuleFeedbackAnnotation struct {

	// The feedback information about rule performance, including suggestions for
	// improvements or corrections.
	//
	// This member is required.
	Feedback *string

	// The list of rule identifiers that the feedback applies to.
	RuleIds []string
	// contains filtered or unexported fields
}

An annotation for updating the policy based on feedback about how specific rules performed during testing or real-world usage.

type AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation added in v1.42.0 

type AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation struct {

	// The logical expression that defines the test scenario that generated this
	// feedback.
	//
	// This member is required.
	ScenarioExpression *string

	// The feedback information about scenario performance, including any issues or
	// improvements identified.
	Feedback *string

	// The list of rule identifiers that were involved in the scenario being evaluated.
	RuleIds []string
	// contains filtered or unexported fields
}

An annotation for updating the policy based on feedback about how it performed on specific test scenarios.

type AutomatedReasoningPolicyUpdateRuleAnnotation added in v1.42.0 

type AutomatedReasoningPolicyUpdateRuleAnnotation struct {

	// The new formal logical expression for the rule, replacing the previous
	// expression.
	//
	// This member is required.
	Expression *string

	// The unique identifier of the rule to update.
	//
	// This member is required.
	RuleId *string
	// contains filtered or unexported fields
}

An annotation for modifying an existing rule in an Automated Reasoning policy.

type AutomatedReasoningPolicyUpdateRuleMutation added in v1.42.0 

type AutomatedReasoningPolicyUpdateRuleMutation struct {

	// The updated rule definition containing the modified formal logical expression
	// and any changed metadata for the existing rule.
	//
	// This member is required.
	Rule *AutomatedReasoningPolicyDefinitionRule
	// contains filtered or unexported fields
}

A mutation operation that modifies an existing rule in the policy definition during the build process.

type AutomatedReasoningPolicyUpdateTypeAnnotation added in v1.42.0 

type AutomatedReasoningPolicyUpdateTypeAnnotation struct {

	// The current name of the custom type to update.
	//
	// This member is required.
	Name *string

	// The updated list of values for the custom type, which can include additions,
	// modifications, or removals.
	//
	// This member is required.
	Values []AutomatedReasoningPolicyTypeValueAnnotation

	// The new description for the custom type, replacing the previous description.
	Description *string

	// The new name for the custom type, if you want to rename it. If not provided,
	// the name remains unchanged.
	NewName *string
	// contains filtered or unexported fields
}

An annotation for modifying an existing custom type in an Automated Reasoning policy.

type AutomatedReasoningPolicyUpdateTypeMutation added in v1.42.0 

type AutomatedReasoningPolicyUpdateTypeMutation struct {

	// The updated type definition containing the modified name, description, or
	// values for the existing custom type.
	//
	// This member is required.
	Type *AutomatedReasoningPolicyDefinitionType
	// contains filtered or unexported fields
}

A mutation operation that modifies an existing custom type in the policy definition during the build process.

type AutomatedReasoningPolicyUpdateTypeValue added in v1.42.0 

type AutomatedReasoningPolicyUpdateTypeValue struct {

	// The current identifier or name of the type value to update.
	//
	// This member is required.
	Value *string

	// The new description for the type value, replacing the previous description.
	Description *string

	// The new identifier or name for the type value, if you want to rename it.
	NewValue *string
	// contains filtered or unexported fields
}

Represents a modification to a value within an existing custom type.

type AutomatedReasoningPolicyUpdateVariableAnnotation added in v1.42.0 

type AutomatedReasoningPolicyUpdateVariableAnnotation struct {

	// The current name of the variable to update.
	//
	// This member is required.
	Name *string

	// The new description for the variable, replacing the previous description.
	Description *string

	// The new name for the variable, if you want to rename it. If not provided, the
	// name remains unchanged.
	NewName *string
	// contains filtered or unexported fields
}

An annotation for modifying an existing variable in an Automated Reasoning policy.

type AutomatedReasoningPolicyUpdateVariableMutation added in v1.42.0 

type AutomatedReasoningPolicyUpdateVariableMutation struct {

	// The updated variable definition containing the modified name, type, or
	// description for the existing variable.
	//
	// This member is required.
	Variable *AutomatedReasoningPolicyDefinitionVariable
	// contains filtered or unexported fields
}

A mutation operation that modifies an existing variable in the policy definition during the build process.

type AutomatedReasoningPolicyWorkflowTypeContent added in v1.42.0 

type AutomatedReasoningPolicyWorkflowTypeContent interface {
	// contains filtered or unexported methods
}

Defines the content and configuration for different types of policy build workflows.

The following types satisfy this interface: 

AutomatedReasoningPolicyWorkflowTypeContentMemberDocuments
AutomatedReasoningPolicyWorkflowTypeContentMemberPolicyRepairAssets
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.AutomatedReasoningPolicyWorkflowTypeContent
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.AutomatedReasoningPolicyWorkflowTypeContentMemberDocuments:
		_ = v.Value // Value is []types.AutomatedReasoningPolicyBuildWorkflowDocument

	case *types.AutomatedReasoningPolicyWorkflowTypeContentMemberPolicyRepairAssets:
		_ = v.Value // Value is types.AutomatedReasoningPolicyBuildWorkflowRepairContent

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type AutomatedReasoningPolicyWorkflowTypeContentMemberDocuments added in v1.42.0 

type AutomatedReasoningPolicyWorkflowTypeContentMemberDocuments struct {
	Value []AutomatedReasoningPolicyBuildWorkflowDocument
	// contains filtered or unexported fields
}

The list of documents to be processed in a document ingestion workflow.

type AutomatedReasoningPolicyWorkflowTypeContentMemberPolicyRepairAssets added in v1.42.0 

type AutomatedReasoningPolicyWorkflowTypeContentMemberPolicyRepairAssets struct {
	Value AutomatedReasoningPolicyBuildWorkflowRepairContent
	// contains filtered or unexported fields
}

The assets and instructions needed for a policy repair workflow, including repair annotations and guidance.

type BatchDeleteEvaluationJobError added in v1.15.0 

type BatchDeleteEvaluationJobError struct {

	// A HTTP status code of the evaluation job being deleted.
	//
	// This member is required.
	Code *string

	// The ARN of the evaluation job being deleted.
	//
	// This member is required.
	JobIdentifier *string

	// A status message about the evaluation job deletion.
	Message *string
	// contains filtered or unexported fields
}

A JSON array that provides the status of the evaluation jobs being deleted.

type BatchDeleteEvaluationJobItem added in v1.15.0 

type BatchDeleteEvaluationJobItem struct {

	// The Amazon Resource Name (ARN) of the evaluation job for deletion.
	//
	// This member is required.
	JobIdentifier *string

	// The status of the evaluation job for deletion.
	//
	// This member is required.
	JobStatus EvaluationJobStatus
	// contains filtered or unexported fields
}

An evaluation job for deletion, and it’s current status.

type BedrockEvaluatorModel added in v1.23.0 

type BedrockEvaluatorModel struct {

	// The Amazon Resource Name (ARN) of the evaluator model used used in knowledge
	// base evaluation job or in model evaluation job that use a model as judge.
	//
	// This member is required.
	ModelIdentifier *string
	// contains filtered or unexported fields
}

The evaluator model used in knowledge base evaluation job or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.

type ByteContentDoc added in v1.23.0 

type ByteContentDoc struct {

	// The MIME type of the document contained in the wrapper object.
	//
	// This member is required.
	ContentType *string

	// The byte value of the file to upload, encoded as a Base-64 string.
	//
	// This member is required.
	Data []byte

	// The file name of the document contained in the wrapper object.
	//
	// This member is required.
	Identifier *string
	// contains filtered or unexported fields
}

Contains the document contained in the wrapper object, along with its attributes/fields.

type CloudWatchConfig 

type CloudWatchConfig struct {

	// The log group name.
	//
	// This member is required.
	LogGroupName *string

	// The role Amazon Resource Name (ARN).
	//
	// This member is required.
	RoleArn *string

	// S3 configuration for delivering a large amount of data.
	LargeDataDeliveryS3Config *S3Config
	// contains filtered or unexported fields
}

CloudWatch logging configuration.

type CommitmentDuration added in v1.1.0 

type CommitmentDuration string
const (
	CommitmentDurationOneMonth  CommitmentDuration = "OneMonth"
	CommitmentDurationSixMonths CommitmentDuration = "SixMonths"
)

Enum values for CommitmentDuration

func (CommitmentDuration) Values added in v1.1.0 

func (CommitmentDuration) Values() []CommitmentDuration

Values returns all known values for CommitmentDuration. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ConflictException 

type ConflictException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

Error occurred because of a conflict while performing an operation.

func (*ConflictException) Error 

func (e *ConflictException) Error() string

func (*ConflictException) ErrorCode 

func (e *ConflictException) ErrorCode() string

func (*ConflictException) ErrorFault 

func (e *ConflictException) ErrorFault() smithy.ErrorFault

func (*ConflictException) ErrorMessage 

func (e *ConflictException) ErrorMessage() string

type CustomMetricBedrockEvaluatorModel added in v1.32.0 

type CustomMetricBedrockEvaluatorModel struct {

	// The Amazon Resource Name (ARN) of the evaluator model for custom metrics. For a
	// list of supported evaluator models, see [Evaluate model performance using another LLM as a judge]and [Evaluate the performance of RAG sources using Amazon Bedrock evaluations].
	//
	// [Evaluate the performance of RAG sources using Amazon Bedrock evaluations]: https://docs.aws.amazon.com/bedrock/latest/userguide/evaluation-kb.html
	// [Evaluate model performance using another LLM as a judge]: https://docs.aws.amazon.com/bedrock/latest/userguide/evaluation-judge.html
	//
	// This member is required.
	ModelIdentifier *string
	// contains filtered or unexported fields
}

Defines the model you want to evaluate custom metrics in an Amazon Bedrock evaluation job.

type CustomMetricDefinition added in v1.32.0 

type CustomMetricDefinition struct {

	// The prompt for a custom metric that instructs the evaluator model how to rate
	// the model or RAG source under evaluation.
	//
	// This member is required.
	Instructions *string

	// The name for a custom metric. Names must be unique in your Amazon Web Services
	// region.
	//
	// This member is required.
	Name *string

	// Defines the rating scale to be used for a custom metric. We recommend that you
	// always define a ratings scale when creating a custom metric. If you don't define
	// a scale, Amazon Bedrock won't be able to visually display the results of the
	// evaluation in the console or calculate average values of numerical scores. For
	// more information on specifying a rating scale, see [Specifying an output schema (rating scale)].
	//
	// [Specifying an output schema (rating scale)]: https://docs.aws.amazon.com/bedrock/latest/userguide/model-evaluation-custom-metrics-prompt-formats.html#model-evaluation-custom-metrics-prompt-formats-schema
	RatingScale []RatingScaleItem
	// contains filtered or unexported fields
}

The definition of a custom metric for use in an Amazon Bedrock evaluation job. A custom metric definition includes a metric name, prompt (instructions) and optionally, a rating scale. Your prompt must include a task description and input variables. The required input variables are different for model-as-a-judge and RAG evaluations.

For more information about how to define a custom metric in Amazon Bedrock, see Create a prompt for a custom metrics (LLM-as-a-judge model evaluations) and Create a prompt for a custom metrics (RAG evaluations).

type CustomMetricEvaluatorModelConfig added in v1.32.0 

type CustomMetricEvaluatorModelConfig struct {

	// Defines the model you want to evaluate custom metrics in an Amazon Bedrock
	// evaluation job.
	//
	// This member is required.
	BedrockEvaluatorModels []CustomMetricBedrockEvaluatorModel
	// contains filtered or unexported fields
}

Configuration of the evaluator model you want to use to evaluate custom metrics in an Amazon Bedrock evaluation job.

type CustomModelDeploymentStatus added in v1.39.0 

type CustomModelDeploymentStatus string
const (
	CustomModelDeploymentStatusCreating CustomModelDeploymentStatus = "Creating"
	CustomModelDeploymentStatusActive   CustomModelDeploymentStatus = "Active"
	CustomModelDeploymentStatusFailed   CustomModelDeploymentStatus = "Failed"
)

Enum values for CustomModelDeploymentStatus

func (CustomModelDeploymentStatus) Values added in v1.39.0 

func (CustomModelDeploymentStatus) Values() []CustomModelDeploymentStatus

Values returns all known values for CustomModelDeploymentStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type CustomModelDeploymentSummary added in v1.39.0 

type CustomModelDeploymentSummary struct {

	// The date and time when the custom model deployment was created.
	//
	// This member is required.
	CreatedAt *time.Time

	// The Amazon Resource Name (ARN) of the custom model deployment.
	//
	// This member is required.
	CustomModelDeploymentArn *string

	// The name of the custom model deployment.
	//
	// This member is required.
	CustomModelDeploymentName *string

	// The Amazon Resource Name (ARN) of the custom model associated with this
	// deployment.
	//
	// This member is required.
	ModelArn *string

	// The status of the custom model deployment. Possible values are CREATING , ACTIVE
	// , and FAILED .
	//
	// This member is required.
	Status CustomModelDeploymentStatus

	// If the deployment status is FAILED , this field contains a message describing
	// the failure reason.
	FailureMessage *string

	// The date and time when the custom model deployment was last modified.
	LastUpdatedAt *time.Time
	// contains filtered or unexported fields
}

Contains summary information about a custom model deployment, including its ARN, name, status, and associated custom model.

type CustomModelSummary 

type CustomModelSummary struct {

	// The base model Amazon Resource Name (ARN).
	//
	// This member is required.
	BaseModelArn *string

	// The base model name.
	//
	// This member is required.
	BaseModelName *string

	// Creation time of the model.
	//
	// This member is required.
	CreationTime *time.Time

	// The Amazon Resource Name (ARN) of the custom model.
	//
	// This member is required.
	ModelArn *string

	// The name of the custom model.
	//
	// This member is required.
	ModelName *string

	// Specifies whether to carry out continued pre-training of a model or whether to
	// fine-tune it. For more information, see [Custom models].
	//
	// [Custom models]: https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html
	CustomizationType CustomizationType

	// The current status of the custom model. Possible values include:
	//
	//   - Creating - The model is being created and validated.
	//
	//   - Active - The model has been successfully created and is ready for use.
	//
	//   - Failed - The model creation process failed.
	ModelStatus ModelStatus

	// The unique identifier of the account that owns the model.
	OwnerAccountId *string
	// contains filtered or unexported fields
}

Summary information for a custom model.

type CustomModelUnits added in v1.30.0 

type CustomModelUnits struct {

	// The number of custom model units used to host a model copy.
	CustomModelUnitsPerModelCopy *int32

	// The version of the custom model unit. Use to determine the billing rate for the
	// custom model unit.
	CustomModelUnitsVersion *string
	// contains filtered or unexported fields
}

A CustomModelUnit (CMU) is an abstract view of the hardware utilization that Amazon Bedrock needs to host a single copy of your custom model. A model copy represents a single instance of your imported model that is ready to serve inference requests. Amazon Bedrock determines the number of custom model units that a model copy needs when you import the custom model.

You can use CustomModelUnits to estimate the cost of running your custom model. For more information, see Calculate the cost of running a custom model in the Amazon Bedrock user guide.

type CustomizationConfig added in v1.24.0 

type CustomizationConfig interface {
	// contains filtered or unexported methods
}

A model customization configuration

The following types satisfy this interface: 

CustomizationConfigMemberDistillationConfig
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.CustomizationConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.CustomizationConfigMemberDistillationConfig:
		_ = v.Value // Value is types.DistillationConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type CustomizationConfigMemberDistillationConfig added in v1.24.0 

type CustomizationConfigMemberDistillationConfig struct {
	Value DistillationConfig
	// contains filtered or unexported fields
}

The Distillation configuration for the custom model.

type CustomizationType added in v1.4.0 

type CustomizationType string
const (
	CustomizationTypeFineTuning           CustomizationType = "FINE_TUNING"
	CustomizationTypeContinuedPreTraining CustomizationType = "CONTINUED_PRE_TRAINING"
	CustomizationTypeDistillation         CustomizationType = "DISTILLATION"
	CustomizationTypeImported             CustomizationType = "IMPORTED"
)

Enum values for CustomizationType

func (CustomizationType) Values added in v1.4.0 

func (CustomizationType) Values() []CustomizationType

Values returns all known values for CustomizationType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type DataProcessingDetails added in v1.33.0 

type DataProcessingDetails struct {

	// The start time of the data processing sub-task of the job.
	CreationTime *time.Time

	// The latest update to the data processing sub-task of the job.
	LastModifiedTime *time.Time

	// The status of the data processing sub-task of the job.
	Status JobStatusDetails
	// contains filtered or unexported fields
}

For a Distillation job, the status details for the data processing sub-task of the job.

type DimensionalPriceRate added in v1.37.0 

type DimensionalPriceRate struct {

	// Description of the price rate.
	Description *string

	// Dimension for the price rate.
	Dimension *string

	// Single-dimensional rate information.
	Price *string

	// Unit associated with the price.
	Unit *string
	// contains filtered or unexported fields
}

Dimensional price rate.

type DistillationConfig added in v1.24.0 

type DistillationConfig struct {

	// The teacher model configuration.
	//
	// This member is required.
	TeacherModelConfig *TeacherModelConfig
	// contains filtered or unexported fields
}

Settings for distilling a foundation model into a smaller and more efficient model.

type EndpointConfig added in v1.25.0 

type EndpointConfig interface {
	// contains filtered or unexported methods
}

Specifies the configuration for the endpoint.

The following types satisfy this interface: 

EndpointConfigMemberSageMaker
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.EndpointConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.EndpointConfigMemberSageMaker:
		_ = v.Value // Value is types.SageMakerEndpoint

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type EndpointConfigMemberSageMaker added in v1.25.0 

type EndpointConfigMemberSageMaker struct {
	Value SageMakerEndpoint
	// contains filtered or unexported fields
}

The configuration specific to Amazon SageMaker for the endpoint.

type EntitlementAvailability added in v1.37.0 

type EntitlementAvailability string
const (
	EntitlementAvailabilityAvailable    EntitlementAvailability = "AVAILABLE"
	EntitlementAvailabilityNotAvailable EntitlementAvailability = "NOT_AVAILABLE"
)

Enum values for EntitlementAvailability

func (EntitlementAvailability) Values added in v1.37.0 

func (EntitlementAvailability) Values() []EntitlementAvailability

Values returns all known values for EntitlementAvailability. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type EvaluationBedrockModel added in v1.8.0 

type EvaluationBedrockModel struct {

	// The ARN of the Amazon Bedrock model or inference profile specified.
	//
	// This member is required.
	ModelIdentifier *string

	// Each Amazon Bedrock support different inference parameters that change how the
	// model behaves during inference.
	InferenceParams *string

	// Specifies performance settings for the model or inference profile.
	PerformanceConfig *PerformanceConfiguration
	// contains filtered or unexported fields
}

Contains the ARN of the Amazon Bedrock model or inference profile specified in your 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.

The inferenceParams are specified using JSON. To successfully insert JSON as string make sure that all quotations are properly escaped. For example, "temperature":"0.25" key value pair would need to be formatted as \"temperature\":\"0.25\" to successfully accepted in the request.

type EvaluationConfig added in v1.8.0 

type EvaluationConfig interface {
	// contains filtered or unexported methods
}

The configuration details of either an automated or human-based evaluation job.

The following types satisfy this interface: 

EvaluationConfigMemberAutomated
EvaluationConfigMemberHuman
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.EvaluationConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.EvaluationConfigMemberAutomated:
		_ = v.Value // Value is types.AutomatedEvaluationConfig

	case *types.EvaluationConfigMemberHuman:
		_ = v.Value // Value is types.HumanEvaluationConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type EvaluationConfigMemberAutomated added in v1.8.0 

type EvaluationConfigMemberAutomated struct {
	Value AutomatedEvaluationConfig
	// contains filtered or unexported fields
}

Contains the configuration details of an automated evaluation job that computes metrics.

type EvaluationConfigMemberHuman added in v1.8.0 

type EvaluationConfigMemberHuman struct {
	Value HumanEvaluationConfig
	// contains filtered or unexported fields
}

Contains the configuration details of an evaluation job that uses human workers.

type EvaluationDataset added in v1.8.0 

type EvaluationDataset struct {

	// Used to specify supported built-in prompt datasets. Valid values are
	// Builtin.Bold , Builtin.BoolQ , Builtin.NaturalQuestions , Builtin.Gigaword ,
	// Builtin.RealToxicityPrompts , Builtin.TriviaQA , Builtin.T-Rex ,
	// Builtin.WomensEcommerceClothingReviews and Builtin.Wikitext2 .
	//
	// This member is required.
	Name *string

	// For custom prompt datasets, you must specify the location in Amazon S3 where
	// the prompt dataset is saved.
	DatasetLocation EvaluationDatasetLocation
	// contains filtered or unexported fields
}

Used to specify the name of a built-in prompt dataset and optionally, the Amazon S3 bucket where a custom prompt dataset is saved.

type EvaluationDatasetLocation added in v1.8.0 

type EvaluationDatasetLocation interface {
	// contains filtered or unexported methods
}

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

The following types satisfy this interface: 

EvaluationDatasetLocationMemberS3Uri
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.EvaluationDatasetLocation
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.EvaluationDatasetLocationMemberS3Uri:
		_ = v.Value // Value is string

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type EvaluationDatasetLocationMemberS3Uri added in v1.8.0 

type EvaluationDatasetLocationMemberS3Uri struct {
	Value string
	// contains filtered or unexported fields
}

The S3 URI of the S3 bucket specified in the job.

type EvaluationDatasetMetricConfig added in v1.8.0 

type EvaluationDatasetMetricConfig struct {

	// Specifies the prompt dataset.
	//
	// This member is required.
	Dataset *EvaluationDataset

	// The names of the metrics you want to use for your evaluation job.
	//
	// For knowledge base evaluation jobs that evaluate retrieval only, valid values
	// are " Builtin.ContextRelevance ", " Builtin.ContextCoverage ".
	//
	// For knowledge base evaluation jobs that evaluate retrieval with response
	// generation, valid values are " Builtin.Correctness ", " Builtin.Completeness ", "
	// Builtin.Helpfulness ", " Builtin.LogicalCoherence ", " Builtin.Faithfulness ", "
	// Builtin.Harmfulness ", " Builtin.Stereotyping ", " Builtin.Refusal ".
	//
	// For automated model evaluation jobs, valid values are " Builtin.Accuracy ", "
	// Builtin.Robustness ", and " Builtin.Toxicity ". In model evaluation jobs that
	// use a LLM as judge you can specify " Builtin.Correctness ", "
	// Builtin.Completeness" , " Builtin.Faithfulness" , " Builtin.Helpfulness ", "
	// Builtin.Coherence ", " Builtin.Relevance ", " Builtin.FollowingInstructions ", "
	// Builtin.ProfessionalStyleAndTone ", You can also specify the following
	// responsible AI related metrics only for model evaluation job that use a LLM as
	// judge " Builtin.Harmfulness ", " Builtin.Stereotyping ", and " Builtin.Refusal ".
	//
	// For human-based model evaluation jobs, the list of strings must match the name
	// parameter specified in HumanEvaluationCustomMetric .
	//
	// This member is required.
	MetricNames []string

	// The the type of task you want to evaluate for your evaluation job. This applies
	// only to model evaluation jobs and is ignored for knowledge base evaluation jobs.
	//
	// This member is required.
	TaskType EvaluationTaskType
	// contains filtered or unexported fields
}

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

type EvaluationInferenceConfig added in v1.8.0 

type EvaluationInferenceConfig interface {
	// contains filtered or unexported methods
}

The configuration details of the inference model for an evaluation job.

For automated model evaluation jobs, only a single model is supported.

For human-based model evaluation jobs, your annotator can compare the responses for up to two different models.

The following types satisfy this interface: 

EvaluationInferenceConfigMemberModels
EvaluationInferenceConfigMemberRagConfigs
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.EvaluationInferenceConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.EvaluationInferenceConfigMemberModels:
		_ = v.Value // Value is []types.EvaluationModelConfig

	case *types.EvaluationInferenceConfigMemberRagConfigs:
		_ = v.Value // Value is []types.RAGConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type EvaluationInferenceConfigMemberModels added in v1.8.0 

type EvaluationInferenceConfigMemberModels struct {
	Value []EvaluationModelConfig
	// contains filtered or unexported fields
}

Specifies the inference models.

type EvaluationInferenceConfigMemberRagConfigs added in v1.23.0 

type EvaluationInferenceConfigMemberRagConfigs struct {
	Value []RAGConfig
	// contains filtered or unexported fields
}

Contains the configuration details of the inference for a knowledge base evaluation job, including either the retrieval only configuration or the retrieval with response generation configuration.

type EvaluationInferenceConfigSummary added in v1.29.0 

type EvaluationInferenceConfigSummary struct {

	// A summary of the models used in an Amazon Bedrock model evaluation job. These
	// resources can be models in Amazon Bedrock or models outside of Amazon Bedrock
	// that you use to generate your own inference response data.
	ModelConfigSummary *EvaluationModelConfigSummary

	// A summary of the RAG resources used in an Amazon Bedrock Knowledge Base
	// evaluation job. These resources can be Knowledge Bases in Amazon Bedrock or RAG
	// sources outside of Amazon Bedrock that you use to generate your own inference
	// response data.
	RagConfigSummary *EvaluationRagConfigSummary
	// contains filtered or unexported fields
}

Identifies the models, Knowledge Bases, or other RAG sources evaluated in a model or Knowledge Base evaluation job.

type EvaluationJobStatus added in v1.8.0 

type EvaluationJobStatus string
const (
	EvaluationJobStatusInProgress EvaluationJobStatus = "InProgress"
	EvaluationJobStatusCompleted  EvaluationJobStatus = "Completed"
	EvaluationJobStatusFailed     EvaluationJobStatus = "Failed"
	EvaluationJobStatusStopping   EvaluationJobStatus = "Stopping"
	EvaluationJobStatusStopped    EvaluationJobStatus = "Stopped"
	EvaluationJobStatusDeleting   EvaluationJobStatus = "Deleting"
)

Enum values for EvaluationJobStatus

func (EvaluationJobStatus) Values added in v1.8.0 

func (EvaluationJobStatus) Values() []EvaluationJobStatus

Values returns all known values for EvaluationJobStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type EvaluationJobType added in v1.8.0 

type EvaluationJobType string
const (
	EvaluationJobTypeHuman     EvaluationJobType = "Human"
	EvaluationJobTypeAutomated EvaluationJobType = "Automated"
)

Enum values for EvaluationJobType

func (EvaluationJobType) Values added in v1.8.0 

func (EvaluationJobType) Values() []EvaluationJobType

Values returns all known values for EvaluationJobType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type EvaluationModelConfig added in v1.8.0 

type EvaluationModelConfig interface {
	// contains filtered or unexported methods
}

Defines the models used in the model evaluation job.

The following types satisfy this interface: 

EvaluationModelConfigMemberBedrockModel
EvaluationModelConfigMemberPrecomputedInferenceSource
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.EvaluationModelConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.EvaluationModelConfigMemberBedrockModel:
		_ = v.Value // Value is types.EvaluationBedrockModel

	case *types.EvaluationModelConfigMemberPrecomputedInferenceSource:
		_ = v.Value // Value is types.EvaluationPrecomputedInferenceSource

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type EvaluationModelConfigMemberBedrockModel added in v1.8.0 

type EvaluationModelConfigMemberBedrockModel struct {
	Value EvaluationBedrockModel
	// contains filtered or unexported fields
}

Defines the Amazon Bedrock model or inference profile and inference parameters you want used.

type EvaluationModelConfigMemberPrecomputedInferenceSource added in v1.29.0 

type EvaluationModelConfigMemberPrecomputedInferenceSource struct {
	Value EvaluationPrecomputedInferenceSource
	// contains filtered or unexported fields
}

Defines the model used to generate inference response data for a model evaluation job where you provide your own inference response data.

type EvaluationModelConfigSummary added in v1.29.0 

type EvaluationModelConfigSummary struct {

	// The Amazon Resource Names (ARNs) of the models used for the evaluation job.
	BedrockModelIdentifiers []string

	// A label that identifies the models used for a model evaluation job where you
	// provide your own inference response data.
	PrecomputedInferenceSourceIdentifiers []string
	// contains filtered or unexported fields
}

A summary of the models used in an Amazon Bedrock model evaluation job. These resources can be models in Amazon Bedrock or models outside of Amazon Bedrock that you use to generate your own inference response data.

type EvaluationOutputDataConfig added in v1.8.0 

type EvaluationOutputDataConfig struct {

	// The Amazon S3 URI where the results of the evaluation job are saved.
	//
	// This member is required.
	S3Uri *string
	// contains filtered or unexported fields
}

The Amazon S3 location where the results of your evaluation job are saved.

type EvaluationPrecomputedInferenceSource added in v1.29.0 

type EvaluationPrecomputedInferenceSource struct {

	// A label that identifies a model used in a model evaluation job where you
	// provide your own inference response data.
	//
	// This member is required.
	InferenceSourceIdentifier *string
	// contains filtered or unexported fields
}

A summary of a model used for a model evaluation job where you provide your own inference response data.

type EvaluationPrecomputedRagSourceConfig added in v1.29.0 

type EvaluationPrecomputedRagSourceConfig interface {
	// contains filtered or unexported methods
}

A summary of a RAG source used for a Knowledge Base evaluation job where you provide your own inference response data.

The following types satisfy this interface: 

EvaluationPrecomputedRagSourceConfigMemberRetrieveAndGenerateSourceConfig
EvaluationPrecomputedRagSourceConfigMemberRetrieveSourceConfig
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.EvaluationPrecomputedRagSourceConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.EvaluationPrecomputedRagSourceConfigMemberRetrieveAndGenerateSourceConfig:
		_ = v.Value // Value is types.EvaluationPrecomputedRetrieveAndGenerateSourceConfig

	case *types.EvaluationPrecomputedRagSourceConfigMemberRetrieveSourceConfig:
		_ = v.Value // Value is types.EvaluationPrecomputedRetrieveSourceConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type EvaluationPrecomputedRagSourceConfigMemberRetrieveAndGenerateSourceConfig added in v1.29.0 

type EvaluationPrecomputedRagSourceConfigMemberRetrieveAndGenerateSourceConfig struct {
	Value EvaluationPrecomputedRetrieveAndGenerateSourceConfig
	// contains filtered or unexported fields
}

A summary of a RAG source used for a retrieve-and-generate Knowledge Base evaluation job where you provide your own inference response data.

type EvaluationPrecomputedRagSourceConfigMemberRetrieveSourceConfig added in v1.29.0 

type EvaluationPrecomputedRagSourceConfigMemberRetrieveSourceConfig struct {
	Value EvaluationPrecomputedRetrieveSourceConfig
	// contains filtered or unexported fields
}

A summary of a RAG source used for a retrieve-only Knowledge Base evaluation job where you provide your own inference response data.

type EvaluationPrecomputedRetrieveAndGenerateSourceConfig added in v1.29.0 

type EvaluationPrecomputedRetrieveAndGenerateSourceConfig struct {

	// A label that identifies the RAG source used for a retrieve-and-generate
	// Knowledge Base evaluation job where you provide your own inference response
	// data.
	//
	// This member is required.
	RagSourceIdentifier *string
	// contains filtered or unexported fields
}

A summary of a RAG source used for a retrieve-and-generate Knowledge Base evaluation job where you provide your own inference response data.

type EvaluationPrecomputedRetrieveSourceConfig added in v1.29.0 

type EvaluationPrecomputedRetrieveSourceConfig struct {

	// A label that identifies the RAG source used for a retrieve-only Knowledge Base
	// evaluation job where you provide your own inference response data.
	//
	// This member is required.
	RagSourceIdentifier *string
	// contains filtered or unexported fields
}

A summary of a RAG source used for a retrieve-only Knowledge Base evaluation job where you provide your own inference response data.

type EvaluationRagConfigSummary added in v1.29.0 

type EvaluationRagConfigSummary struct {

	// The Amazon Resource Names (ARNs) of the Knowledge Base resources used for a
	// Knowledge Base evaluation job where Amazon Bedrock invokes the Knowledge Base
	// for you.
	BedrockKnowledgeBaseIdentifiers []string

	// A label that identifies the RAG sources used for a Knowledge Base evaluation
	// job where you provide your own inference response data.
	PrecomputedRagSourceIdentifiers []string
	// contains filtered or unexported fields
}

A summary of the RAG resources used in an Amazon Bedrock Knowledge Base evaluation job. These resources can be Knowledge Bases in Amazon Bedrock or RAG sources outside of Amazon Bedrock that you use to generate your own inference response data.

type EvaluationSummary added in v1.8.0 

type EvaluationSummary struct {

	// The time the evaluation job was created.
	//
	// This member is required.
	CreationTime *time.Time

	// The type of task for model evaluation.
	//
	// This member is required.
	EvaluationTaskTypes []EvaluationTaskType

	// The Amazon Resource Name (ARN) of the evaluation job.
	//
	// This member is required.
	JobArn *string

	// The name for the evaluation job.
	//
	// This member is required.
	JobName *string

	// Specifies whether the evaluation job is automated or human-based.
	//
	// This member is required.
	JobType EvaluationJobType

	// The current status of the evaluation job.
	//
	// This member is required.
	Status EvaluationJobStatus

	// Specifies whether the evaluation job is for evaluating a model or evaluating a
	// knowledge base (retrieval and response generation).
	ApplicationType ApplicationType

	// The Amazon Resource Names (ARNs) of the models used to compute custom metrics
	// in an Amazon Bedrock evaluation job.
	CustomMetricsEvaluatorModelIdentifiers []string

	// The Amazon Resource Names (ARNs) of the models used to compute the metrics for
	// a knowledge base evaluation job.
	EvaluatorModelIdentifiers []string

	// Identifies the models, Knowledge Bases, or other RAG sources evaluated in a
	// model or Knowledge Base evaluation job.
	InferenceConfigSummary *EvaluationInferenceConfigSummary

	// The Amazon Resource Names (ARNs) of the model(s) used for the evaluation job.
	//
	// Deprecated: Inference identifiers should be retrieved from the
	// inferenceConfigSummary
	ModelIdentifiers []string

	// The Amazon Resource Names (ARNs) of the knowledge base resources used for a
	// knowledge base evaluation job.
	//
	// Deprecated: Inference identifiers should be retrieved from the
	// inferenceConfigSummary
	RagIdentifiers []string
	// contains filtered or unexported fields
}

Summary information of an evaluation job.

type EvaluationTaskType added in v1.8.0 

type EvaluationTaskType string
const (
	EvaluationTaskTypeSummarization     EvaluationTaskType = "Summarization"
	EvaluationTaskTypeClassification    EvaluationTaskType = "Classification"
	EvaluationTaskTypeQuestionAndAnswer EvaluationTaskType = "QuestionAndAnswer"
	EvaluationTaskTypeGeneration        EvaluationTaskType = "Generation"
	EvaluationTaskTypeCustom            EvaluationTaskType = "Custom"
)

Enum values for EvaluationTaskType

func (EvaluationTaskType) Values added in v1.8.0 

func (EvaluationTaskType) Values() []EvaluationTaskType

Values returns all known values for EvaluationTaskType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type EvaluatorModelConfig added in v1.23.0 

type EvaluatorModelConfig interface {
	// contains filtered or unexported methods
}

Specifies the model configuration for the evaluator model. EvaluatorModelConfig is required for evaluation jobs that use a knowledge base or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.

The following types satisfy this interface: 

EvaluatorModelConfigMemberBedrockEvaluatorModels
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.EvaluatorModelConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.EvaluatorModelConfigMemberBedrockEvaluatorModels:
		_ = v.Value // Value is []types.BedrockEvaluatorModel

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type EvaluatorModelConfigMemberBedrockEvaluatorModels added in v1.23.0 

type EvaluatorModelConfigMemberBedrockEvaluatorModels struct {
	Value []BedrockEvaluatorModel
	// contains filtered or unexported fields
}

The evaluator model used in knowledge base evaluation job or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.

type ExternalSource added in v1.23.0 

type ExternalSource struct {

	// The source type of the external source wrapper object.
	//
	// This member is required.
	SourceType ExternalSourceType

	// The identifier, content type, and data of the external source wrapper object.
	ByteContent *ByteContentDoc

	// The S3 location of the external source wrapper object.
	S3Location *S3ObjectDoc
	// contains filtered or unexported fields
}

The unique external source of the content contained in the wrapper object.

type ExternalSourceType added in v1.23.0 

type ExternalSourceType string
const (
	ExternalSourceTypeS3          ExternalSourceType = "S3"
	ExternalSourceTypeByteContent ExternalSourceType = "BYTE_CONTENT"
)

Enum values for ExternalSourceType

func (ExternalSourceType) Values added in v1.23.0 

func (ExternalSourceType) Values() []ExternalSourceType

Values returns all known values for ExternalSourceType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ExternalSourcesGenerationConfiguration added in v1.23.0 

type ExternalSourcesGenerationConfiguration struct {

	// Additional model parameters and their corresponding values not included in the
	// text inference configuration for an external source. Takes in custom model
	// parameters specific to the language model being used.
	AdditionalModelRequestFields map[string]document.Interface

	// Configuration details for the guardrail.
	GuardrailConfiguration *GuardrailConfiguration

	// Configuration details for inference when using RetrieveAndGenerate to generate
	// responses while using an external source.
	KbInferenceConfig *KbInferenceConfig

	// Contains the template for the prompt for the external source wrapper object.
	PromptTemplate *PromptTemplate
	// contains filtered or unexported fields
}

The response generation configuration of the external source wrapper object.

type ExternalSourcesRetrieveAndGenerateConfiguration added in v1.23.0 

type ExternalSourcesRetrieveAndGenerateConfiguration struct {

	// The Amazon Resource Name (ARN) of the foundation model or [inference profile] used to generate
	// responses.
	//
	// [inference profile]: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html
	//
	// This member is required.
	ModelArn *string

	// The document for the external source wrapper object in the retrieveAndGenerate
	// function.
	//
	// This member is required.
	Sources []ExternalSource

	// Contains configurations details for response generation based on retrieved text
	// chunks.
	GenerationConfiguration *ExternalSourcesGenerationConfiguration
	// contains filtered or unexported fields
}

The configuration of the external source wrapper object in the retrieveAndGenerate function.

type FieldForReranking added in v1.38.0 

type FieldForReranking struct {

	// The name of the metadata field to be used during the reranking process.
	//
	// This member is required.
	FieldName *string
	// contains filtered or unexported fields
}

Specifies a field to be used during the reranking process in a Knowledge Base vector search. This structure identifies metadata fields that should be considered when reordering search results to improve relevance.

type FilterAttribute added in v1.23.0 

type FilterAttribute struct {

	// The name of metadata attribute/field, which must match the name in your data
	// source/document metadata.
	//
	// This member is required.
	Key *string

	// The value of the metadata attribute/field.
	//
	// This member is required.
	Value document.Interface
	// contains filtered or unexported fields
}

Specifies the name of the metadata attribute/field to apply filters. You must match the name of the attribute/field in your data source/document metadata.

type FineTuningJobStatus 

type FineTuningJobStatus string
const (
	FineTuningJobStatusInProgress FineTuningJobStatus = "InProgress"
	FineTuningJobStatusCompleted  FineTuningJobStatus = "Completed"
	FineTuningJobStatusFailed     FineTuningJobStatus = "Failed"
	FineTuningJobStatusStopping   FineTuningJobStatus = "Stopping"
	FineTuningJobStatusStopped    FineTuningJobStatus = "Stopped"
)

Enum values for FineTuningJobStatus

func (FineTuningJobStatus) Values 

func (FineTuningJobStatus) Values() []FineTuningJobStatus

Values returns all known values for FineTuningJobStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type FoundationModelDetails 

type FoundationModelDetails struct {

	// The model Amazon Resource Name (ARN).
	//
	// This member is required.
	ModelArn *string

	// The model identifier.
	//
	// This member is required.
	ModelId *string

	// The customization that the model supports.
	CustomizationsSupported []ModelCustomization

	// The inference types that the model supports.
	InferenceTypesSupported []InferenceType

	// The input modalities that the model supports.
	InputModalities []ModelModality

	// Contains details about whether a model version is available or deprecated
	ModelLifecycle *FoundationModelLifecycle

	// The model name.
	ModelName *string

	// The output modalities that the model supports.
	OutputModalities []ModelModality

	// The model's provider name.
	ProviderName *string

	// Indicates whether the model supports streaming.
	ResponseStreamingSupported *bool
	// contains filtered or unexported fields
}

Information about a foundation model.

type FoundationModelLifecycle added in v1.4.0 

type FoundationModelLifecycle struct {

	// Specifies whether a model version is available ( ACTIVE ) or deprecated ( LEGACY
	// .
	//
	// This member is required.
	Status FoundationModelLifecycleStatus
	// contains filtered or unexported fields
}

Details about whether a model version is available or deprecated.

type FoundationModelLifecycleStatus added in v1.4.0 

type FoundationModelLifecycleStatus string
const (
	FoundationModelLifecycleStatusActive FoundationModelLifecycleStatus = "ACTIVE"
	FoundationModelLifecycleStatusLegacy FoundationModelLifecycleStatus = "LEGACY"
)

Enum values for FoundationModelLifecycleStatus

func (FoundationModelLifecycleStatus) Values added in v1.4.0 

func (FoundationModelLifecycleStatus) Values() []FoundationModelLifecycleStatus

Values returns all known values for FoundationModelLifecycleStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type FoundationModelSummary 

type FoundationModelSummary struct {

	// The Amazon Resource Name (ARN) of the foundation model.
	//
	// This member is required.
	ModelArn *string

	// The model ID of the foundation model.
	//
	// This member is required.
	ModelId *string

	// Whether the model supports fine-tuning or continual pre-training.
	CustomizationsSupported []ModelCustomization

	// The inference types that the model supports.
	InferenceTypesSupported []InferenceType

	// The input modalities that the model supports.
	InputModalities []ModelModality

	// Contains details about whether a model version is available or deprecated.
	ModelLifecycle *FoundationModelLifecycle

	// The name of the model.
	ModelName *string

	// The output modalities that the model supports.
	OutputModalities []ModelModality

	// The model's provider name.
	ProviderName *string

	// Indicates whether the model supports streaming.
	ResponseStreamingSupported *bool
	// contains filtered or unexported fields
}

Summary information for a foundation model.

type GenerationConfiguration added in v1.23.0 

type GenerationConfiguration struct {

	// Additional model parameters and corresponding values not included in the
	// textInferenceConfig structure for a knowledge base. This allows you to provide
	// custom model parameters specific to the language model being used.
	AdditionalModelRequestFields map[string]document.Interface

	// Contains configuration details for the guardrail.
	GuardrailConfiguration *GuardrailConfiguration

	// Contains configuration details for inference for knowledge base retrieval and
	// response generation.
	KbInferenceConfig *KbInferenceConfig

	// Contains the template for the prompt that's sent to the model for response
	// generation.
	PromptTemplate *PromptTemplate
	// contains filtered or unexported fields
}

The configuration details for response generation based on retrieved text chunks.

type GuardrailAutomatedReasoningPolicy added in v1.42.0 

type GuardrailAutomatedReasoningPolicy struct {

	// The list of Automated Reasoning policy ARNs that should be applied as part of
	// this guardrail configuration.
	//
	// This member is required.
	Policies []string

	// The minimum confidence level required for Automated Reasoning policy violations
	// to trigger guardrail actions. Values range from 0.0 to 1.0.
	ConfidenceThreshold *float64
	// contains filtered or unexported fields
}

Represents the configuration of Automated Reasoning policies within a Amazon Bedrock Guardrail, including the policies to apply and confidence thresholds.

type GuardrailAutomatedReasoningPolicyConfig added in v1.42.0 

type GuardrailAutomatedReasoningPolicyConfig struct {

	// The list of Automated Reasoning policy ARNs to include in the guardrail
	// configuration.
	//
	// This member is required.
	Policies []string

	// The confidence threshold for triggering guardrail actions based on Automated
	// Reasoning policy violations.
	ConfidenceThreshold *float64
	// contains filtered or unexported fields
}

Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.

type GuardrailConfiguration added in v1.23.0 

type GuardrailConfiguration struct {

	// The unique identifier for the guardrail.
	//
	// This member is required.
	GuardrailId *string

	// The version of the guardrail.
	//
	// This member is required.
	GuardrailVersion *string
	// contains filtered or unexported fields
}

The configuration details for the guardrail.

type GuardrailContentFilter added in v1.8.0 

type GuardrailContentFilter struct {

	// The strength of the content filter to apply to prompts. As you increase the
	// filter strength, the likelihood of filtering harmful content increases and the
	// probability of seeing harmful content in your application reduces.
	//
	// This member is required.
	InputStrength GuardrailFilterStrength

	// The strength of the content filter to apply to model responses. As you increase
	// the filter strength, the likelihood of filtering harmful content increases and
	// the probability of seeing harmful content in your application reduces.
	//
	// This member is required.
	OutputStrength GuardrailFilterStrength

	// The harmful category that the content filter is applied to.
	//
	// This member is required.
	Type GuardrailContentFilterType

	// The action to take when harmful content is detected in the input. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailContentFilterAction

	// Indicates whether guardrail evaluation is enabled on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// The input modalities selected for the guardrail content filter.
	InputModalities []GuardrailModality

	// The action to take when harmful content is detected in the output. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailContentFilterAction

	// Indicates whether guardrail evaluation is enabled on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool

	// The output modalities selected for the guardrail content filter.
	OutputModalities []GuardrailModality
	// contains filtered or unexported fields
}

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

  • Hate – Describes language or a statement that discriminates, criticizes, insults, denounces, or dehumanizes a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).

  • Insults – Describes language or a statement that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.

  • Sexual – Describes language or a statement that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.

  • Violence – Describes language or a statement that includes glorification of or threats to inflict physical pain, hurt, or injury toward a person, group or thing.

Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.

For more information, see Guardrails content filters.

This data type is used in the following API operations:

GetGuardrail response body

type GuardrailContentFilterAction added in v1.31.0 

type GuardrailContentFilterAction string
const (
	GuardrailContentFilterActionBlock GuardrailContentFilterAction = "BLOCK"
	GuardrailContentFilterActionNone  GuardrailContentFilterAction = "NONE"
)

Enum values for GuardrailContentFilterAction

func (GuardrailContentFilterAction) Values added in v1.31.0 

func (GuardrailContentFilterAction) Values() []GuardrailContentFilterAction

Values returns all known values for GuardrailContentFilterAction. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailContentFilterConfig added in v1.8.0 

type GuardrailContentFilterConfig struct {

	// The strength of the content filter to apply to prompts. As you increase the
	// filter strength, the likelihood of filtering harmful content increases and the
	// probability of seeing harmful content in your application reduces.
	//
	// This member is required.
	InputStrength GuardrailFilterStrength

	// The strength of the content filter to apply to model responses. As you increase
	// the filter strength, the likelihood of filtering harmful content increases and
	// the probability of seeing harmful content in your application reduces.
	//
	// This member is required.
	OutputStrength GuardrailFilterStrength

	// The harmful category that the content filter is applied to.
	//
	// This member is required.
	Type GuardrailContentFilterType

	// Specifies the action to take when harmful content is detected. Supported values
	// include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailContentFilterAction

	// Specifies whether to enable guardrail evaluation on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// The input modalities selected for the guardrail content filter configuration.
	InputModalities []GuardrailModality

	// Specifies the action to take when harmful content is detected in the output.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailContentFilterAction

	// Specifies whether to enable guardrail evaluation on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool

	// The output modalities selected for the guardrail content filter configuration.
	OutputModalities []GuardrailModality
	// contains filtered or unexported fields
}

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

  • Hate – Describes language or a statement that discriminates, criticizes, insults, denounces, or dehumanizes a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).

  • Insults – Describes language or a statement that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.

  • Sexual – Describes language or a statement that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.

  • Violence – Describes language or a statement that includes glorification of or threats to inflict physical pain, hurt, or injury toward a person, group or thing.

Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.

For more information, see Guardrails content filters.

type GuardrailContentFilterType added in v1.8.0 

type GuardrailContentFilterType string
const (
	GuardrailContentFilterTypeSexual       GuardrailContentFilterType = "SEXUAL"
	GuardrailContentFilterTypeViolence     GuardrailContentFilterType = "VIOLENCE"
	GuardrailContentFilterTypeHate         GuardrailContentFilterType = "HATE"
	GuardrailContentFilterTypeInsults      GuardrailContentFilterType = "INSULTS"
	GuardrailContentFilterTypeMisconduct   GuardrailContentFilterType = "MISCONDUCT"
	GuardrailContentFilterTypePromptAttack GuardrailContentFilterType = "PROMPT_ATTACK"
)

Enum values for GuardrailContentFilterType

func (GuardrailContentFilterType) Values added in v1.8.0 

func (GuardrailContentFilterType) Values() []GuardrailContentFilterType

Values returns all known values for GuardrailContentFilterType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailContentFiltersTier added in v1.36.0 

type GuardrailContentFiltersTier struct {

	// The tier that your guardrail uses for content filters. Valid values include:
	//
	//   - CLASSIC tier – Provides established guardrails functionality supporting
	//   English, French, and Spanish languages.
	//
	//   - STANDARD tier – Provides a more robust solution than the CLASSIC tier and
	//   has more comprehensive language support. This tier requires that your guardrail
	//   use [cross-Region inference].
	//
	// [cross-Region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region.html
	//
	// This member is required.
	TierName GuardrailContentFiltersTierName
	// contains filtered or unexported fields
}

The tier that your guardrail uses for content filters.

type GuardrailContentFiltersTierConfig added in v1.36.0 

type GuardrailContentFiltersTierConfig struct {

	// The tier that your guardrail uses for content filters. Valid values include:
	//
	//   - CLASSIC tier – Provides established guardrails functionality supporting
	//   English, French, and Spanish languages.
	//
	//   - STANDARD tier – Provides a more robust solution than the CLASSIC tier and
	//   has more comprehensive language support. This tier requires that your guardrail
	//   use [cross-Region inference].
	//
	// [cross-Region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region.html
	//
	// This member is required.
	TierName GuardrailContentFiltersTierName
	// contains filtered or unexported fields
}

The tier that your guardrail uses for content filters. Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.

type GuardrailContentFiltersTierName added in v1.36.0 

type GuardrailContentFiltersTierName string
const (
	GuardrailContentFiltersTierNameClassic  GuardrailContentFiltersTierName = "CLASSIC"
	GuardrailContentFiltersTierNameStandard GuardrailContentFiltersTierName = "STANDARD"
)

Enum values for GuardrailContentFiltersTierName

func (GuardrailContentFiltersTierName) Values added in v1.36.0 

func (GuardrailContentFiltersTierName) Values() []GuardrailContentFiltersTierName

Values returns all known values for GuardrailContentFiltersTierName. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailContentPolicy added in v1.8.0 

type GuardrailContentPolicy struct {

	// Contains the type of the content filter and how strongly it should apply to
	// prompts and model responses.
	Filters []GuardrailContentFilter

	// The tier that your guardrail uses for content filters.
	Tier *GuardrailContentFiltersTier
	// contains filtered or unexported fields
}

Contains details about how to handle harmful content.

This data type is used in the following API operations:

GetGuardrail response body

type GuardrailContentPolicyConfig added in v1.8.0 

type GuardrailContentPolicyConfig struct {

	// Contains the type of the content filter and how strongly it should apply to
	// prompts and model responses.
	//
	// This member is required.
	FiltersConfig []GuardrailContentFilterConfig

	// The tier that your guardrail uses for content filters.
	TierConfig *GuardrailContentFiltersTierConfig
	// contains filtered or unexported fields
}

Contains details about how to handle harmful content.

type GuardrailContextualGroundingAction added in v1.31.0 

type GuardrailContextualGroundingAction string
const (
	GuardrailContextualGroundingActionBlock GuardrailContextualGroundingAction = "BLOCK"
	GuardrailContextualGroundingActionNone  GuardrailContextualGroundingAction = "NONE"
)

Enum values for GuardrailContextualGroundingAction

func (GuardrailContextualGroundingAction) Values added in v1.31.0 

func (GuardrailContextualGroundingAction) Values() []GuardrailContextualGroundingAction

Values returns all known values for GuardrailContextualGroundingAction. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailContextualGroundingFilter added in v1.11.0 

type GuardrailContextualGroundingFilter struct {

	// The threshold details for the guardrails contextual grounding filter.
	//
	// This member is required.
	Threshold *float64

	// The filter type details for the guardrails contextual grounding filter.
	//
	// This member is required.
	Type GuardrailContextualGroundingFilterType

	// The action to take when content fails the contextual grounding evaluation.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	Action GuardrailContextualGroundingAction

	// Indicates whether contextual grounding is enabled for evaluation. When
	// disabled, you aren't charged for the evaluation. The evaluation doesn't appear
	// in the response.
	Enabled *bool
	// contains filtered or unexported fields
}

The details for the guardrails contextual grounding filter.

type GuardrailContextualGroundingFilterConfig added in v1.11.0 

type GuardrailContextualGroundingFilterConfig struct {

	// The threshold details for the guardrails contextual grounding filter.
	//
	// This member is required.
	Threshold *float64

	// The filter details for the guardrails contextual grounding filter.
	//
	// This member is required.
	Type GuardrailContextualGroundingFilterType

	// Specifies the action to take when content fails the contextual grounding
	// evaluation. Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	Action GuardrailContextualGroundingAction

	// Specifies whether to enable contextual grounding evaluation. When disabled, you
	// aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	Enabled *bool
	// contains filtered or unexported fields
}

The filter configuration details for the guardrails contextual grounding filter.

type GuardrailContextualGroundingFilterType added in v1.11.0 

type GuardrailContextualGroundingFilterType string
const (
	GuardrailContextualGroundingFilterTypeGrounding GuardrailContextualGroundingFilterType = "GROUNDING"
	GuardrailContextualGroundingFilterTypeRelevance GuardrailContextualGroundingFilterType = "RELEVANCE"
)

Enum values for GuardrailContextualGroundingFilterType

func (GuardrailContextualGroundingFilterType) Values added in v1.11.0 

func (GuardrailContextualGroundingFilterType) Values() []GuardrailContextualGroundingFilterType

Values returns all known values for GuardrailContextualGroundingFilterType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailContextualGroundingPolicy added in v1.11.0 

type GuardrailContextualGroundingPolicy struct {

	// The filter details for the guardrails contextual grounding policy.
	//
	// This member is required.
	Filters []GuardrailContextualGroundingFilter
	// contains filtered or unexported fields
}

The details for the guardrails contextual grounding policy.

type GuardrailContextualGroundingPolicyConfig added in v1.11.0 

type GuardrailContextualGroundingPolicyConfig struct {

	// The filter configuration details for the guardrails contextual grounding policy.
	//
	// This member is required.
	FiltersConfig []GuardrailContextualGroundingFilterConfig
	// contains filtered or unexported fields
}

The policy configuration details for the guardrails contextual grounding policy.

type GuardrailCrossRegionConfig added in v1.34.0 

type GuardrailCrossRegionConfig struct {

	// The ID or Amazon Resource Name (ARN) of the guardrail profile that your
	// guardrail is using. Guardrail profile availability depends on your current
	// Amazon Web Services Region. For more information, see the [Amazon Bedrock User Guide].
	//
	// [Amazon Bedrock User Guide]: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region-support.html
	//
	// This member is required.
	GuardrailProfileIdentifier *string
	// contains filtered or unexported fields
}

The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.

For more information, see the Amazon Bedrock User Guide.

type GuardrailCrossRegionDetails added in v1.34.0 

type GuardrailCrossRegionDetails struct {

	// The Amazon Resource Name (ARN) of the guardrail profile that you're using with
	// your guardrail.
	GuardrailProfileArn *string

	// The ID of the guardrail profile that your guardrail is using. Profile
	// availability depends on your current Amazon Web Services Region. For more
	// information, see the [Amazon Bedrock User Guide].
	//
	// [Amazon Bedrock User Guide]: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region-support.html
	GuardrailProfileId *string
	// contains filtered or unexported fields
}

Contains details about the system-defined guardrail profile that you're using with your guardrail for cross-Region inference.

For more information, see the Amazon Bedrock User Guide.

type GuardrailFilterStrength added in v1.8.0 

type GuardrailFilterStrength string
const (
	GuardrailFilterStrengthNone   GuardrailFilterStrength = "NONE"
	GuardrailFilterStrengthLow    GuardrailFilterStrength = "LOW"
	GuardrailFilterStrengthMedium GuardrailFilterStrength = "MEDIUM"
	GuardrailFilterStrengthHigh   GuardrailFilterStrength = "HIGH"
)

Enum values for GuardrailFilterStrength

func (GuardrailFilterStrength) Values added in v1.8.0 

func (GuardrailFilterStrength) Values() []GuardrailFilterStrength

Values returns all known values for GuardrailFilterStrength. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailManagedWords added in v1.8.0 

type GuardrailManagedWords struct {

	// ManagedWords$type The managed word type that was configured for the guardrail.
	// (For now, we only offer profanity word list)
	//
	// This member is required.
	Type GuardrailManagedWordsType

	// The action to take when harmful content is detected in the input. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailWordAction

	// Indicates whether guardrail evaluation is enabled on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// The action to take when harmful content is detected in the output. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailWordAction

	// Indicates whether guardrail evaluation is enabled on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

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.)

type GuardrailManagedWordsConfig added in v1.8.0 

type GuardrailManagedWordsConfig struct {

	// The managed word type to configure for the guardrail.
	//
	// This member is required.
	Type GuardrailManagedWordsType

	// Specifies the action to take when harmful content is detected in the input.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailWordAction

	// Specifies whether to enable guardrail evaluation on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// Specifies the action to take when harmful content is detected in the output.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailWordAction

	// Specifies whether to enable guardrail evaluation on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

The managed word list to configure for the guardrail.

type GuardrailManagedWordsType added in v1.8.0 

type GuardrailManagedWordsType string
const (
	GuardrailManagedWordsTypeProfanity GuardrailManagedWordsType = "PROFANITY"
)

Enum values for GuardrailManagedWordsType

func (GuardrailManagedWordsType) Values added in v1.8.0 

func (GuardrailManagedWordsType) Values() []GuardrailManagedWordsType

Values returns all known values for GuardrailManagedWordsType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailModality added in v1.25.0 

type GuardrailModality string
const (
	GuardrailModalityText  GuardrailModality = "TEXT"
	GuardrailModalityImage GuardrailModality = "IMAGE"
)

Enum values for GuardrailModality

func (GuardrailModality) Values added in v1.25.0 

func (GuardrailModality) Values() []GuardrailModality

Values returns all known values for GuardrailModality. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailPiiEntity added in v1.8.0 

type GuardrailPiiEntity struct {

	// The configured guardrail action when PII entity is detected.
	//
	// This member is required.
	Action GuardrailSensitiveInformationAction

	// The type of PII entity. For example, Social Security Number.
	//
	// This member is required.
	Type GuardrailPiiEntityType

	// The action to take when harmful content is detected in the input. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - ANONYMIZE – Mask the content and replace it with identifier tags.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailSensitiveInformationAction

	// Indicates whether guardrail evaluation is enabled on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// The action to take when harmful content is detected in the output. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - ANONYMIZE – Mask the content and replace it with identifier tags.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailSensitiveInformationAction

	// Indicates whether guardrail evaluation is enabled on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

The PII entity configured for the guardrail.

type GuardrailPiiEntityConfig added in v1.8.0 

type GuardrailPiiEntityConfig struct {

	// Configure guardrail action when the PII entity is detected.
	//
	// This member is required.
	Action GuardrailSensitiveInformationAction

	// Configure guardrail type when the PII entity is detected.
	//
	// The following PIIs are used to block or mask sensitive information:
	//
	//   - General
	//
	//   - ADDRESS
	//
	// A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12,
	//   Building 123". An address can include information such as the street, building,
	//   location, city, state, country, county, zip code, precinct, and neighborhood.
	//
	//   - AGE
	//
	// An individual's age, including the quantity and unit of time. For example, in
	//   the phrase "I am 40 years old," Guardrails recognizes "40 years" as an age.
	//
	//   - NAME
	//
	// An individual's name. This entity type does not include titles, such as Dr.,
	//   Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are
	//   part of organizations or addresses. For example, guardrails recognizes the "John
	//   Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an
	//   address.
	//
	//   - EMAIL
	//
	// An email address, such as marymajor@email.com.
	//
	//   - PHONE
	//
	// A phone number. This entity type also includes fax and pager numbers.
	//
	//   - USERNAME
	//
	// A user name that identifies an account, such as a login name, screen name, nick
	//   name, or handle.
	//
	//   - PASSWORD
	//
	// An alphanumeric string that is used as a password, such as
	//   "*very20special#pass*".
	//
	//   - DRIVER_ID
	//
	// The number assigned to a driver's license, which is an official document
	//   permitting an individual to operate one or more motorized vehicles on a public
	//   road. A driver's license number consists of alphanumeric characters.
	//
	//   - LICENSE_PLATE
	//
	// A license plate for a vehicle is issued by the state or country where the
	//   vehicle is registered. The format for passenger vehicles is typically five to
	//   eight digits, consisting of upper-case letters and numbers. The format varies
	//   depending on the location of the issuing state or country.
	//
	//   - VEHICLE_IDENTIFICATION_NUMBER
	//
	// A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN
	//   content and format are defined in the ISO 3779 specification. Each country has
	//   specific codes and formats for VINs.
	//
	//   - Finance
	//
	//   - CREDIT_DEBIT_CARD_CVV
	//
	// A three-digit card verification code (CVV) that is present on VISA, MasterCard,
	//   and Discover credit and debit cards. For American Express credit or debit cards,
	//   the CVV is a four-digit numeric code.
	//
	//   - CREDIT_DEBIT_CARD_EXPIRY
	//
	// The expiration date for a credit or debit card. This number is usually four
	//   digits long and is often formatted as month/year or MM/YY. Guardrails recognizes
	//   expiration dates such as 01/21, 01/2021, and Jan 2021.
	//
	//   - CREDIT_DEBIT_CARD_NUMBER
	//
	// The number for a credit or debit card. These numbers can vary from 13 to 16
	//   digits in length. However, Amazon Comprehend also recognizes credit or debit
	//   card numbers when only the last four digits are present.
	//
	//   - PIN
	//
	// A four-digit personal identification number (PIN) with which you can access
	//   your bank account.
	//
	//   - INTERNATIONAL_BANK_ACCOUNT_NUMBER
	//
	// An International Bank Account Number has specific formats in each country. For
	//   more information, see [www.iban.com/structure].
	//
	//   - SWIFT_CODE
	//
	// A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify
	//   a particular bank or branch. Banks use these codes for money transfers such as
	//   international wire transfers.
	//
	// SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to
	//   specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX')
	//   refer to the head or primary office.
	//
	//   - IT
	//
	//   - IP_ADDRESS
	//
	// An IPv4 address, such as 198.51.100.0.
	//
	//   - MAC_ADDRESS
	//
	// A media access control (MAC) address is a unique identifier assigned to a
	//   network interface controller (NIC).
	//
	//   - URL
	//
	// A web address, such as www.example.com.
	//
	//   - AWS_ACCESS_KEY
	//
	// A unique identifier that's associated with a secret access key; you use the
	//   access key ID and secret access key to sign programmatic Amazon Web Services
	//   requests cryptographically.
	//
	//   - AWS_SECRET_KEY
	//
	// A unique identifier that's associated with an access key. You use the access
	//   key ID and secret access key to sign programmatic Amazon Web Services requests
	//   cryptographically.
	//
	//   - USA specific
	//
	//   - US_BANK_ACCOUNT_NUMBER
	//
	// A US bank account number, which is typically 10 to 12 digits long.
	//
	//   - US_BANK_ROUTING_NUMBER
	//
	// A US bank account routing number. These are typically nine digits long,
	//
	//   - US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
	//
	// A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number
	//   that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can
	//   be formatted with a space or a dash after the third and forth digits.
	//
	//   - US_PASSPORT_NUMBER
	//
	// A US passport number. Passport numbers range from six to nine alphanumeric
	//   characters.
	//
	//   - US_SOCIAL_SECURITY_NUMBER
	//
	// A US Social Security Number (SSN) is a nine-digit number that is issued to US
	//   citizens, permanent residents, and temporary working residents.
	//
	//   - Canada specific
	//
	//   - CA_HEALTH_NUMBER
	//
	// A Canadian Health Service Number is a 10-digit unique identifier, required for
	//   individuals to access healthcare benefits.
	//
	//   - CA_SOCIAL_INSURANCE_NUMBER
	//
	// A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier,
	//   required for individuals to access government programs and benefits.
	//
	// The SIN is formatted as three groups of three digits, such as 123-456-789. A
	//   SIN can be validated through a simple check-digit process called the [Luhn algorithm].
	//
	//   - UK Specific
	//
	//   - UK_NATIONAL_HEALTH_SERVICE_NUMBER
	//
	// A UK National Health Service Number is a 10-17 digit number, such as 485 777
	//   3456. The current system formats the 10-digit number with spaces after the third
	//   and sixth digits. The final digit is an error-detecting checksum.
	//
	//   - UK_NATIONAL_INSURANCE_NUMBER
	//
	// A UK National Insurance Number (NINO) provides individuals with access to
	//   National Insurance (social security) benefits. It is also used for some purposes
	//   in the UK tax system.
	//
	// The number is nine digits long and starts with two letters, followed by six
	//   numbers and one letter. A NINO can be formatted with a space or a dash after the
	//   two letters and after the second, forth, and sixth digits.
	//
	//   - UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
	//
	// A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a
	//   taxpayer or a business.
	//
	//   - Custom
	//
	//   - Regex filter - You can use a regular expressions to define patterns for a
	//   guardrail to recognize and act upon such as serial number, booking ID etc..
	//
	// [Luhn algorithm]: https://www.wikipedia.org/wiki/Luhn_algorithm
	// [www.iban.com/structure]: https://www.iban.com/structure
	//
	// This member is required.
	Type GuardrailPiiEntityType

	// Specifies the action to take when harmful content is detected in the input.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - ANONYMIZE – Mask the content and replace it with identifier tags.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailSensitiveInformationAction

	// Specifies whether to enable guardrail evaluation on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// Specifies the action to take when harmful content is detected in the output.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - ANONYMIZE – Mask the content and replace it with identifier tags.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailSensitiveInformationAction

	// Specifies whether to enable guardrail evaluation on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

The PII entity to configure for the guardrail.

type GuardrailPiiEntityType added in v1.8.0 

type GuardrailPiiEntityType string
const (
	GuardrailPiiEntityTypeAddress                             GuardrailPiiEntityType = "ADDRESS"
	GuardrailPiiEntityTypeAge                                 GuardrailPiiEntityType = "AGE"
	GuardrailPiiEntityTypeAwsAccessKey                        GuardrailPiiEntityType = "AWS_ACCESS_KEY"
	GuardrailPiiEntityTypeAwsSecretKey                        GuardrailPiiEntityType = "AWS_SECRET_KEY"
	GuardrailPiiEntityTypeCaHealthNumber                      GuardrailPiiEntityType = "CA_HEALTH_NUMBER"
	GuardrailPiiEntityTypeCaSocialInsuranceNumber             GuardrailPiiEntityType = "CA_SOCIAL_INSURANCE_NUMBER"
	GuardrailPiiEntityTypeCreditDebitCardCvv                  GuardrailPiiEntityType = "CREDIT_DEBIT_CARD_CVV"
	GuardrailPiiEntityTypeCreditDebitCardExpiry               GuardrailPiiEntityType = "CREDIT_DEBIT_CARD_EXPIRY"
	GuardrailPiiEntityTypeCreditDebitCardNumber               GuardrailPiiEntityType = "CREDIT_DEBIT_CARD_NUMBER"
	GuardrailPiiEntityTypeDriverId                            GuardrailPiiEntityType = "DRIVER_ID"
	GuardrailPiiEntityTypeEmail                               GuardrailPiiEntityType = "EMAIL"
	GuardrailPiiEntityTypeInternationalBankAccountNumber      GuardrailPiiEntityType = "INTERNATIONAL_BANK_ACCOUNT_NUMBER"
	GuardrailPiiEntityTypeIpAddress                           GuardrailPiiEntityType = "IP_ADDRESS"
	GuardrailPiiEntityTypeLicensePlate                        GuardrailPiiEntityType = "LICENSE_PLATE"
	GuardrailPiiEntityTypeMacAddress                          GuardrailPiiEntityType = "MAC_ADDRESS"
	GuardrailPiiEntityTypeName                                GuardrailPiiEntityType = "NAME"
	GuardrailPiiEntityTypePassword                            GuardrailPiiEntityType = "PASSWORD"
	GuardrailPiiEntityTypePhone                               GuardrailPiiEntityType = "PHONE"
	GuardrailPiiEntityTypePin                                 GuardrailPiiEntityType = "PIN"
	GuardrailPiiEntityTypeSwiftCode                           GuardrailPiiEntityType = "SWIFT_CODE"
	GuardrailPiiEntityTypeUkNationalHealthServiceNumber       GuardrailPiiEntityType = "UK_NATIONAL_HEALTH_SERVICE_NUMBER"
	GuardrailPiiEntityTypeUkNationalInsuranceNumber           GuardrailPiiEntityType = "UK_NATIONAL_INSURANCE_NUMBER"
	GuardrailPiiEntityTypeUkUniqueTaxpayerReferenceNumber     GuardrailPiiEntityType = "UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER"
	GuardrailPiiEntityTypeUrl                                 GuardrailPiiEntityType = "URL"
	GuardrailPiiEntityTypeUsername                            GuardrailPiiEntityType = "USERNAME"
	GuardrailPiiEntityTypeUsBankAccountNumber                 GuardrailPiiEntityType = "US_BANK_ACCOUNT_NUMBER"
	GuardrailPiiEntityTypeUsBankRoutingNumber                 GuardrailPiiEntityType = "US_BANK_ROUTING_NUMBER"
	GuardrailPiiEntityTypeUsIndividualTaxIdentificationNumber GuardrailPiiEntityType = "US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER"
	GuardrailPiiEntityTypeUsPassportNumber                    GuardrailPiiEntityType = "US_PASSPORT_NUMBER"
	GuardrailPiiEntityTypeUsSocialSecurityNumber              GuardrailPiiEntityType = "US_SOCIAL_SECURITY_NUMBER"
	GuardrailPiiEntityTypeVehicleIdentificationNumber         GuardrailPiiEntityType = "VEHICLE_IDENTIFICATION_NUMBER"
)

Enum values for GuardrailPiiEntityType

func (GuardrailPiiEntityType) Values added in v1.8.0 

func (GuardrailPiiEntityType) Values() []GuardrailPiiEntityType

Values returns all known values for GuardrailPiiEntityType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailRegex added in v1.8.0 

type GuardrailRegex struct {

	// The action taken when a match to the regular expression is detected.
	//
	// This member is required.
	Action GuardrailSensitiveInformationAction

	// The name of the regular expression for the guardrail.
	//
	// This member is required.
	Name *string

	// The pattern of the regular expression configured for the guardrail.
	//
	// This member is required.
	Pattern *string

	// The description of the regular expression for the guardrail.
	Description *string

	// The action to take when harmful content is detected in the input. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailSensitiveInformationAction

	// Indicates whether guardrail evaluation is enabled on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// The action to take when harmful content is detected in the output. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailSensitiveInformationAction

	// Indicates whether guardrail evaluation is enabled on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

The regular expression configured for the guardrail.

type GuardrailRegexConfig added in v1.8.0 

type GuardrailRegexConfig struct {

	// The guardrail action to configure when matching regular expression is detected.
	//
	// This member is required.
	Action GuardrailSensitiveInformationAction

	// The name of the regular expression to configure for the guardrail.
	//
	// This member is required.
	Name *string

	// The regular expression pattern to configure for the guardrail.
	//
	// This member is required.
	Pattern *string

	// The description of the regular expression to configure for the guardrail.
	Description *string

	// Specifies the action to take when harmful content is detected in the input.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailSensitiveInformationAction

	// Specifies whether to enable guardrail evaluation on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// Specifies the action to take when harmful content is detected in the output.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailSensitiveInformationAction

	// Specifies whether to enable guardrail evaluation on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

The regular expression to configure for the guardrail.

type GuardrailSensitiveInformationAction added in v1.8.0 

type GuardrailSensitiveInformationAction string
const (
	GuardrailSensitiveInformationActionBlock     GuardrailSensitiveInformationAction = "BLOCK"
	GuardrailSensitiveInformationActionAnonymize GuardrailSensitiveInformationAction = "ANONYMIZE"
	GuardrailSensitiveInformationActionNone      GuardrailSensitiveInformationAction = "NONE"
)

Enum values for GuardrailSensitiveInformationAction

func (GuardrailSensitiveInformationAction) Values added in v1.8.0 

func (GuardrailSensitiveInformationAction) Values() []GuardrailSensitiveInformationAction

Values returns all known values for GuardrailSensitiveInformationAction. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailSensitiveInformationPolicy added in v1.8.0 

type GuardrailSensitiveInformationPolicy struct {

	// The list of PII entities configured for the guardrail.
	PiiEntities []GuardrailPiiEntity

	// The list of regular expressions configured for the guardrail.
	Regexes []GuardrailRegex
	// contains filtered or unexported fields
}

Contains details about PII entities and regular expressions configured for the guardrail.

type GuardrailSensitiveInformationPolicyConfig added in v1.8.0 

type GuardrailSensitiveInformationPolicyConfig struct {

	// A list of PII entities to configure to the guardrail.
	PiiEntitiesConfig []GuardrailPiiEntityConfig

	// A list of regular expressions to configure to the guardrail.
	RegexesConfig []GuardrailRegexConfig
	// contains filtered or unexported fields
}

Contains details about PII entities and regular expressions to configure for the guardrail.

type GuardrailStatus added in v1.8.0 

type GuardrailStatus string
const (
	GuardrailStatusCreating   GuardrailStatus = "CREATING"
	GuardrailStatusUpdating   GuardrailStatus = "UPDATING"
	GuardrailStatusVersioning GuardrailStatus = "VERSIONING"
	GuardrailStatusReady      GuardrailStatus = "READY"
	GuardrailStatusFailed     GuardrailStatus = "FAILED"
	GuardrailStatusDeleting   GuardrailStatus = "DELETING"
)

Enum values for GuardrailStatus

func (GuardrailStatus) Values added in v1.8.0 

func (GuardrailStatus) Values() []GuardrailStatus

Values returns all known values for GuardrailStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailSummary added in v1.8.0 

type GuardrailSummary struct {

	// The ARN of the guardrail.
	//
	// This member is required.
	Arn *string

	// The date and time at which the guardrail was created.
	//
	// This member is required.
	CreatedAt *time.Time

	// The unique identifier of the guardrail.
	//
	// This member is required.
	Id *string

	// The name of the guardrail.
	//
	// This member is required.
	Name *string

	// The status of the guardrail.
	//
	// This member is required.
	Status GuardrailStatus

	// The date and time at which the guardrail was last updated.
	//
	// This member is required.
	UpdatedAt *time.Time

	// The version of the guardrail.
	//
	// This member is required.
	Version *string

	// Details about the system-defined guardrail profile that you're using with your
	// guardrail, including the guardrail profile ID and Amazon Resource Name (ARN).
	CrossRegionDetails *GuardrailCrossRegionDetails

	// A description of the guardrail.
	Description *string
	// contains filtered or unexported fields
}

Contains details about a guardrail.

This data type is used in the following API operations:

ListGuardrails response body

type GuardrailTopic added in v1.8.0 

type GuardrailTopic struct {

	// A definition of the topic to deny.
	//
	// This member is required.
	Definition *string

	// The name of the topic to deny.
	//
	// This member is required.
	Name *string

	// A list of prompts, each of which is an example of a prompt that can be
	// categorized as belonging to the topic.
	Examples []string

	// The action to take when harmful content is detected in the input. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailTopicAction

	// Indicates whether guardrail evaluation is enabled on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// The action to take when harmful content is detected in the output. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailTopicAction

	// Indicates whether guardrail evaluation is enabled on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool

	// Specifies to deny the topic.
	Type GuardrailTopicType
	// contains filtered or unexported fields
}

Details about topics for the guardrail to identify and deny.

This data type is used in the following API operations:

GetGuardrail response body

type GuardrailTopicAction added in v1.31.0 

type GuardrailTopicAction string
const (
	GuardrailTopicActionBlock GuardrailTopicAction = "BLOCK"
	GuardrailTopicActionNone  GuardrailTopicAction = "NONE"
)

Enum values for GuardrailTopicAction

func (GuardrailTopicAction) Values added in v1.31.0 

func (GuardrailTopicAction) Values() []GuardrailTopicAction

Values returns all known values for GuardrailTopicAction. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailTopicConfig added in v1.8.0 

type GuardrailTopicConfig struct {

	// A definition of the topic to deny.
	//
	// This member is required.
	Definition *string

	// The name of the topic to deny.
	//
	// This member is required.
	Name *string

	// Specifies to deny the topic.
	//
	// This member is required.
	Type GuardrailTopicType

	// A list of prompts, each of which is an example of a prompt that can be
	// categorized as belonging to the topic.
	Examples []string

	// Specifies the action to take when harmful content is detected in the input.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailTopicAction

	// Specifies whether to enable guardrail evaluation on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// Specifies the action to take when harmful content is detected in the output.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailTopicAction

	// Specifies whether to enable guardrail evaluation on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

Details about topics for the guardrail to identify and deny.

type GuardrailTopicPolicy added in v1.8.0 

type GuardrailTopicPolicy struct {

	// A list of policies related to topics that the guardrail should deny.
	//
	// This member is required.
	Topics []GuardrailTopic

	// The tier that your guardrail uses for denied topic filters.
	Tier *GuardrailTopicsTier
	// contains filtered or unexported fields
}

Contains details about topics that the guardrail should identify and deny.

This data type is used in the following API operations:

GetGuardrail response body

type GuardrailTopicPolicyConfig added in v1.8.0 

type GuardrailTopicPolicyConfig struct {

	// A list of policies related to topics that the guardrail should deny.
	//
	// This member is required.
	TopicsConfig []GuardrailTopicConfig

	// The tier that your guardrail uses for denied topic filters.
	TierConfig *GuardrailTopicsTierConfig
	// contains filtered or unexported fields
}

Contains details about topics that the guardrail should identify and deny.

type GuardrailTopicType added in v1.8.0 

type GuardrailTopicType string
const (
	GuardrailTopicTypeDeny GuardrailTopicType = "DENY"
)

Enum values for GuardrailTopicType

func (GuardrailTopicType) Values added in v1.8.0 

func (GuardrailTopicType) Values() []GuardrailTopicType

Values returns all known values for GuardrailTopicType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailTopicsTier added in v1.36.0 

type GuardrailTopicsTier struct {

	// The tier that your guardrail uses for denied topic filters. Valid values
	// include:
	//
	//   - CLASSIC tier – Provides established guardrails functionality supporting
	//   English, French, and Spanish languages.
	//
	//   - STANDARD tier – Provides a more robust solution than the CLASSIC tier and
	//   has more comprehensive language support. This tier requires that your guardrail
	//   use [cross-Region inference].
	//
	// [cross-Region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region.html
	//
	// This member is required.
	TierName GuardrailTopicsTierName
	// contains filtered or unexported fields
}

The tier that your guardrail uses for denied topic filters.

type GuardrailTopicsTierConfig added in v1.36.0 

type GuardrailTopicsTierConfig struct {

	// The tier that your guardrail uses for denied topic filters. Valid values
	// include:
	//
	//   - CLASSIC tier – Provides established guardrails functionality supporting
	//   English, French, and Spanish languages.
	//
	//   - STANDARD tier – Provides a more robust solution than the CLASSIC tier and
	//   has more comprehensive language support. This tier requires that your guardrail
	//   use [cross-Region inference].
	//
	// [cross-Region inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region.html
	//
	// This member is required.
	TierName GuardrailTopicsTierName
	// contains filtered or unexported fields
}

The tier that your guardrail uses for denied topic filters. Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.

type GuardrailTopicsTierName added in v1.36.0 

type GuardrailTopicsTierName string
const (
	GuardrailTopicsTierNameClassic  GuardrailTopicsTierName = "CLASSIC"
	GuardrailTopicsTierNameStandard GuardrailTopicsTierName = "STANDARD"
)

Enum values for GuardrailTopicsTierName

func (GuardrailTopicsTierName) Values added in v1.36.0 

func (GuardrailTopicsTierName) Values() []GuardrailTopicsTierName

Values returns all known values for GuardrailTopicsTierName. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailWord added in v1.8.0 

type GuardrailWord struct {

	// Text of the word configured for the guardrail to block.
	//
	// This member is required.
	Text *string

	// The action to take when harmful content is detected in the input. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailWordAction

	// Indicates whether guardrail evaluation is enabled on the input. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// The action to take when harmful content is detected in the output. Supported
	// values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailWordAction

	// Indicates whether guardrail evaluation is enabled on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

A word configured for the guardrail.

type GuardrailWordAction added in v1.31.0 

type GuardrailWordAction string
const (
	GuardrailWordActionBlock GuardrailWordAction = "BLOCK"
	GuardrailWordActionNone  GuardrailWordAction = "NONE"
)

Enum values for GuardrailWordAction

func (GuardrailWordAction) Values added in v1.31.0 

func (GuardrailWordAction) Values() []GuardrailWordAction

Values returns all known values for GuardrailWordAction. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type GuardrailWordConfig added in v1.8.0 

type GuardrailWordConfig struct {

	// Text of the word configured for the guardrail to block.
	//
	// This member is required.
	Text *string

	// Specifies the action to take when harmful content is detected in the input.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	InputAction GuardrailWordAction

	// Specifies whether to enable guardrail evaluation on the intput. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	InputEnabled *bool

	// Specifies the action to take when harmful content is detected in the output.
	// Supported values include:
	//
	//   - BLOCK – Block the content and replace it with blocked messaging.
	//
	//   - NONE – Take no action but return detection information in the trace response.
	OutputAction GuardrailWordAction

	// Specifies whether to enable guardrail evaluation on the output. When disabled,
	// you aren't charged for the evaluation. The evaluation doesn't appear in the
	// response.
	OutputEnabled *bool
	// contains filtered or unexported fields
}

A word to configure for the guardrail.

type GuardrailWordPolicy added in v1.8.0 

type GuardrailWordPolicy struct {

	// A list of managed words configured for the guardrail.
	ManagedWordLists []GuardrailManagedWords

	// A list of words configured for the guardrail.
	Words []GuardrailWord
	// contains filtered or unexported fields
}

Contains details about the word policy configured for the guardrail.

type GuardrailWordPolicyConfig added in v1.8.0 

type GuardrailWordPolicyConfig struct {

	// A list of managed words to configure for the guardrail.
	ManagedWordListsConfig []GuardrailManagedWordsConfig

	// A list of words to configure for the guardrail.
	WordsConfig []GuardrailWordConfig
	// contains filtered or unexported fields
}

Contains details about the word policy to configured for the guardrail.

type HumanEvaluationConfig added in v1.8.0 

type HumanEvaluationConfig struct {

	// Use to specify the metrics, task, and prompt dataset to be used in your model
	// evaluation job.
	//
	// This member is required.
	DatasetMetricConfigs []EvaluationDatasetMetricConfig

	// A HumanEvaluationCustomMetric object. It contains the names the metrics, how
	// the metrics are to be evaluated, an optional description.
	CustomMetrics []HumanEvaluationCustomMetric

	// The parameters of the human workflow.
	HumanWorkflowConfig *HumanWorkflowConfig
	// contains filtered or unexported fields
}

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.

When you create custom metrics in HumanEvaluationCustomMetric you must specify the metric's name . The list of names specified in the HumanEvaluationCustomMetric array, must match the metricNames array of strings specified in EvaluationDatasetMetricConfig . For example, if in the HumanEvaluationCustomMetric array your specified the names "accuracy", "toxicity", "readability" as custom metrics then the metricNames array would need to look like the following ["accuracy", "toxicity", "readability"] in EvaluationDatasetMetricConfig .

type HumanEvaluationCustomMetric added in v1.8.0 

type HumanEvaluationCustomMetric struct {

	// The name of the metric. Your human evaluators will see this name in the
	// evaluation UI.
	//
	// This member is required.
	Name *string

	// Choose how you want your human workers to evaluation your model. Valid values
	// for rating methods are ThumbsUpDown , IndividualLikertScale ,
	// ComparisonLikertScale , ComparisonChoice , and ComparisonRank
	//
	// This member is required.
	RatingMethod *string

	// An optional description of the metric. Use this parameter to provide more
	// details about the metric.
	Description *string
	// contains filtered or unexported fields
}

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.

type HumanWorkflowConfig added in v1.8.0 

type HumanWorkflowConfig struct {

	// The Amazon Resource Number (ARN) for the flow definition
	//
	// This member is required.
	FlowDefinitionArn *string

	// Instructions for the flow definition
	Instructions *string
	// contains filtered or unexported fields
}

Contains SageMakerFlowDefinition object. The object is used to specify the prompt dataset, task type, rating method and metric names.

type ImplicitFilterConfiguration added in v1.38.0 

type ImplicitFilterConfiguration struct {

	// A list of metadata attribute schemas that define the structure and properties
	// of metadata fields used for implicit filtering. Each attribute defines a key,
	// type, and optional description.
	//
	// This member is required.
	MetadataAttributes []MetadataAttributeSchema

	// The Amazon Resource Name (ARN) of the foundation model used for implicit
	// filtering. This model processes the query to extract relevant filtering
	// criteria.
	//
	// This member is required.
	ModelArn *string
	// contains filtered or unexported fields
}

Configuration for implicit filtering in Knowledge Base vector searches. Implicit filtering allows you to automatically filter search results based on metadata attributes without requiring explicit filter expressions in each query.

type ImportedModelSummary added in v1.15.0 

type ImportedModelSummary struct {

	// Creation time of the imported model.
	//
	// This member is required.
	CreationTime *time.Time

	// The Amazon Resource Name (ARN) of the imported model.
	//
	// This member is required.
	ModelArn *string

	// Name of the imported model.
	//
	// This member is required.
	ModelName *string

	// Specifies if the imported model supports converse.
	InstructSupported *bool

	// The architecture of the imported model.
	ModelArchitecture *string
	// contains filtered or unexported fields
}

Information about the imported model.

type InferenceProfileModel added in v1.16.0 

type InferenceProfileModel struct {

	// The Amazon Resource Name (ARN) of the model.
	ModelArn *string
	// contains filtered or unexported fields
}

Contains information about a model.

type InferenceProfileModelSource added in v1.22.0 

type InferenceProfileModelSource interface {
	// contains filtered or unexported methods
}

Contains information about the model or system-defined inference profile that is the source for an inference profile..

The following types satisfy this interface: 

InferenceProfileModelSourceMemberCopyFrom
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.InferenceProfileModelSource
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.InferenceProfileModelSourceMemberCopyFrom:
		_ = v.Value // Value is string

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type InferenceProfileModelSourceMemberCopyFrom added in v1.22.0 

type InferenceProfileModelSourceMemberCopyFrom struct {
	Value string
	// contains filtered or unexported fields
}

The ARN of the model or system-defined inference profile that is the source for the inference profile.

type InferenceProfileStatus added in v1.16.0 

type InferenceProfileStatus string
const (
	InferenceProfileStatusActive InferenceProfileStatus = "ACTIVE"
)

Enum values for InferenceProfileStatus

func (InferenceProfileStatus) Values added in v1.16.0 

func (InferenceProfileStatus) Values() []InferenceProfileStatus

Values returns all known values for InferenceProfileStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type InferenceProfileSummary added in v1.16.0 

type InferenceProfileSummary struct {

	// The Amazon Resource Name (ARN) of the inference profile.
	//
	// This member is required.
	InferenceProfileArn *string

	// The unique identifier of the inference profile.
	//
	// This member is required.
	InferenceProfileId *string

	// The name of the inference profile.
	//
	// This member is required.
	InferenceProfileName *string

	// A list of information about each model in the inference profile.
	//
	// This member is required.
	Models []InferenceProfileModel

	// The status of the inference profile. ACTIVE means that the inference profile is
	// ready to be used.
	//
	// This member is required.
	Status InferenceProfileStatus

	// The type of the inference profile. The following types are possible:
	//
	//   - SYSTEM_DEFINED – The inference profile is defined by Amazon Bedrock. You can
	//   route inference requests across regions with these inference profiles.
	//
	//   - APPLICATION – The inference profile was created by a user. This type of
	//   inference profile can track metrics and costs when invoking the model in it. The
	//   inference profile may route requests to one or multiple regions.
	//
	// This member is required.
	Type InferenceProfileType

	// The time at which the inference profile was created.
	CreatedAt *time.Time

	// The description of the inference profile.
	Description *string

	// The time at which the inference profile was last updated.
	UpdatedAt *time.Time
	// contains filtered or unexported fields
}

Contains information about an inference profile.

type InferenceProfileType added in v1.16.0 

type InferenceProfileType string
const (
	InferenceProfileTypeSystemDefined InferenceProfileType = "SYSTEM_DEFINED"
	InferenceProfileTypeApplication   InferenceProfileType = "APPLICATION"
)

Enum values for InferenceProfileType

func (InferenceProfileType) Values added in v1.16.0 

func (InferenceProfileType) Values() []InferenceProfileType

Values returns all known values for InferenceProfileType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type InferenceType 

type InferenceType string
const (
	InferenceTypeOnDemand    InferenceType = "ON_DEMAND"
	InferenceTypeProvisioned InferenceType = "PROVISIONED"
)

Enum values for InferenceType

func (InferenceType) Values 

func (InferenceType) Values() []InferenceType

Values returns all known values for InferenceType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type InternalServerException 

type InternalServerException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

An internal server error occurred. Retry your request.

func (*InternalServerException) Error 

func (e *InternalServerException) Error() string

func (*InternalServerException) ErrorCode 

func (e *InternalServerException) ErrorCode() string

func (*InternalServerException) ErrorFault 

func (e *InternalServerException) ErrorFault() smithy.ErrorFault

func (*InternalServerException) ErrorMessage 

func (e *InternalServerException) ErrorMessage() string

type InvocationLogSource added in v1.24.0 

type InvocationLogSource interface {
	// contains filtered or unexported methods
}

A storage location for invocation logs.

The following types satisfy this interface: 

InvocationLogSourceMemberS3Uri
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.InvocationLogSource
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.InvocationLogSourceMemberS3Uri:
		_ = v.Value // Value is string

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type InvocationLogSourceMemberS3Uri added in v1.24.0 

type InvocationLogSourceMemberS3Uri struct {
	Value string
	// contains filtered or unexported fields
}

The URI of an invocation log in a bucket.

type InvocationLogsConfig added in v1.24.0 

type InvocationLogsConfig struct {

	// The source of the invocation logs.
	//
	// This member is required.
	InvocationLogSource InvocationLogSource

	// Rules for filtering invocation logs based on request metadata.
	RequestMetadataFilters RequestMetadataFilters

	// Whether to use the model's response for training, or just the prompt. The
	// default value is False .
	UsePromptResponse bool
	// contains filtered or unexported fields
}

Settings for using invocation logs to customize a model.

type JobStatusDetails added in v1.33.0 

type JobStatusDetails string
const (
	JobStatusDetailsInProgress JobStatusDetails = "InProgress"
	JobStatusDetailsCompleted  JobStatusDetails = "Completed"
	JobStatusDetailsStopping   JobStatusDetails = "Stopping"
	JobStatusDetailsStopped    JobStatusDetails = "Stopped"
	JobStatusDetailsFailed     JobStatusDetails = "Failed"
	JobStatusDetailsNotStarted JobStatusDetails = "NotStarted"
)

Enum values for JobStatusDetails

func (JobStatusDetails) Values added in v1.33.0 

func (JobStatusDetails) Values() []JobStatusDetails

Values returns all known values for JobStatusDetails. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type KbInferenceConfig added in v1.23.0 

type KbInferenceConfig struct {

	// Contains configuration details for text generation using a language model via
	// the RetrieveAndGenerate function.
	TextInferenceConfig *TextInferenceConfig
	// contains filtered or unexported fields
}

Contains configuration details of the inference for knowledge base retrieval and response generation.

type KnowledgeBaseConfig added in v1.23.0 

type KnowledgeBaseConfig interface {
	// contains filtered or unexported methods
}

The configuration details for retrieving information from a knowledge base and generating responses.

The following types satisfy this interface: 

KnowledgeBaseConfigMemberRetrieveAndGenerateConfig
KnowledgeBaseConfigMemberRetrieveConfig
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.KnowledgeBaseConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.KnowledgeBaseConfigMemberRetrieveAndGenerateConfig:
		_ = v.Value // Value is types.RetrieveAndGenerateConfiguration

	case *types.KnowledgeBaseConfigMemberRetrieveConfig:
		_ = v.Value // Value is types.RetrieveConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type KnowledgeBaseConfigMemberRetrieveAndGenerateConfig added in v1.23.0 

type KnowledgeBaseConfigMemberRetrieveAndGenerateConfig struct {
	Value RetrieveAndGenerateConfiguration
	// contains filtered or unexported fields
}

Contains configuration details for retrieving information from a knowledge base and generating responses.

type KnowledgeBaseConfigMemberRetrieveConfig added in v1.23.0 

type KnowledgeBaseConfigMemberRetrieveConfig struct {
	Value RetrieveConfig
	// contains filtered or unexported fields
}

Contains configuration details for retrieving information from a knowledge base.

type KnowledgeBaseRetrievalConfiguration added in v1.23.0 

type KnowledgeBaseRetrievalConfiguration struct {

	// Contains configuration details for returning the results from the vector search.
	//
	// This member is required.
	VectorSearchConfiguration *KnowledgeBaseVectorSearchConfiguration
	// contains filtered or unexported fields
}

Contains configuration details for retrieving information from a knowledge base.

type KnowledgeBaseRetrieveAndGenerateConfiguration added in v1.23.0 

type KnowledgeBaseRetrieveAndGenerateConfiguration struct {

	// The unique identifier of the knowledge base.
	//
	// This member is required.
	KnowledgeBaseId *string

	// The Amazon Resource Name (ARN) of the foundation model or [inference profile] used to generate
	// responses.
	//
	// [inference profile]: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html
	//
	// This member is required.
	ModelArn *string

	// Contains configurations details for response generation based on retrieved text
	// chunks.
	GenerationConfiguration *GenerationConfiguration

	// Contains configuration details for the model to process the prompt prior to
	// retrieval and response generation.
	OrchestrationConfiguration *OrchestrationConfiguration

	// Contains configuration details for retrieving text chunks.
	RetrievalConfiguration *KnowledgeBaseRetrievalConfiguration
	// contains filtered or unexported fields
}

Contains configuration details for retrieving information from a knowledge base and generating responses.

type KnowledgeBaseVectorSearchConfiguration added in v1.23.0 

type KnowledgeBaseVectorSearchConfiguration struct {

	// Specifies the filters to use on the metadata fields in the knowledge base data
	// sources before returning results.
	Filter RetrievalFilter

	// Configuration for implicit filtering in Knowledge Base vector searches. This
	// allows the system to automatically apply filters based on the query context
	// without requiring explicit filter expressions.
	ImplicitFilterConfiguration *ImplicitFilterConfiguration

	// The number of text chunks to retrieve; the number of results to return.
	NumberOfResults *int32

	// By default, Amazon Bedrock decides a search strategy for you. If you're using
	// an Amazon OpenSearch Serverless vector store that contains a filterable text
	// field, you can specify whether to query the knowledge base with a HYBRID search
	// using both vector embeddings and raw text, or SEMANTIC search using only vector
	// embeddings. For other vector store configurations, only SEMANTIC search is
	// available.
	OverrideSearchType SearchType

	// Configuration for reranking search results in Knowledge Base vector searches.
	// Reranking improves search relevance by reordering initial vector search results
	// using more sophisticated relevance models.
	RerankingConfiguration *VectorSearchRerankingConfiguration
	// contains filtered or unexported fields
}

The configuration details for returning the results from the knowledge base vector search.

type LegalTerm added in v1.37.0 

type LegalTerm struct {

	// URL to the legal term document.
	Url *string
	// contains filtered or unexported fields
}

The legal term of the agreement.

type LoggingConfig 

type LoggingConfig struct {

	// CloudWatch logging configuration.
	CloudWatchConfig *CloudWatchConfig

	// Set to include embeddings data in the log delivery.
	EmbeddingDataDeliveryEnabled *bool

	// Set to include image data in the log delivery.
	ImageDataDeliveryEnabled *bool

	// S3 configuration for storing log data.
	S3Config *S3Config

	// Set to include text data in the log delivery.
	TextDataDeliveryEnabled *bool

	// Set to include video data in the log delivery.
	VideoDataDeliveryEnabled *bool
	// contains filtered or unexported fields
}

Configuration fields for invocation logging.

type MarketplaceModelEndpoint added in v1.25.0 

type MarketplaceModelEndpoint struct {

	// The timestamp when the endpoint was registered.
	//
	// This member is required.
	CreatedAt *time.Time

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

	// The configuration of the endpoint, including the number and type of instances
	// used.
	//
	// This member is required.
	EndpointConfig EndpointConfig

	// The current status of the endpoint (e.g., Creating, InService, Updating,
	// Failed).
	//
	// This member is required.
	EndpointStatus *string

	// The ARN of the model from Amazon Bedrock Marketplace that is deployed on this
	// endpoint.
	//
	// This member is required.
	ModelSourceIdentifier *string

	// The timestamp when the endpoint was last updated.
	//
	// This member is required.
	UpdatedAt *time.Time

	// Additional information about the endpoint status, if available.
	EndpointStatusMessage *string

	// The overall status of the endpoint in Amazon Bedrock Marketplace (e.g., ACTIVE,
	// INACTIVE).
	Status Status

	// Additional information about the overall status, if available.
	StatusMessage *string
	// contains filtered or unexported fields
}

Contains details about an endpoint for a model from Amazon Bedrock Marketplace.

type MarketplaceModelEndpointSummary added in v1.25.0 

type MarketplaceModelEndpointSummary struct {

	// The timestamp when the endpoint was created.
	//
	// This member is required.
	CreatedAt *time.Time

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

	// The ARN of the model from Amazon Bedrock Marketplace that is deployed on this
	// endpoint.
	//
	// This member is required.
	ModelSourceIdentifier *string

	// The timestamp when the endpoint was last updated.
	//
	// This member is required.
	UpdatedAt *time.Time

	// The overall status of the endpoint in Amazon Bedrock Marketplace.
	Status Status

	// Additional information about the overall status, if available.
	StatusMessage *string
	// contains filtered or unexported fields
}

Provides a summary of an endpoint for a model from Amazon Bedrock Marketplace.

type MetadataAttributeSchema added in v1.38.0 

type MetadataAttributeSchema struct {

	// An optional description of the metadata attribute that provides additional
	// context about its purpose and usage.
	//
	// This member is required.
	Description *string

	// The unique identifier for the metadata attribute. This key is used to reference
	// the attribute in filter expressions and reranking configurations.
	//
	// This member is required.
	Key *string

	// The data type of the metadata attribute. The type determines how the attribute
	// can be used in filter expressions and reranking.
	//
	// This member is required.
	Type AttributeType
	// contains filtered or unexported fields
}

Defines the schema for a metadata attribute used in Knowledge Base vector searches. Metadata attributes provide additional context for documents and can be used for filtering and reranking search results.

type MetadataConfigurationForReranking added in v1.38.0 

type MetadataConfigurationForReranking struct {

	// The mode for selecting which metadata fields to include in the reranking
	// process. Valid values are ALL (use all available metadata fields) or SELECTIVE
	// (use only specified fields).
	//
	// This member is required.
	SelectionMode RerankingMetadataSelectionMode

	// Configuration for selective mode, which allows you to explicitly include or
	// exclude specific metadata fields during reranking. This is only used when
	// selectionMode is set to SELECTIVE.
	SelectiveModeConfiguration RerankingMetadataSelectiveModeConfiguration
	// contains filtered or unexported fields
}

Configuration for how metadata should be used during the reranking process in Knowledge Base vector searches. This determines which metadata fields are included or excluded when reordering search results.

type ModelCopyJobStatus added in v1.13.0 

type ModelCopyJobStatus string
const (
	ModelCopyJobStatusInProgress ModelCopyJobStatus = "InProgress"
	ModelCopyJobStatusCompleted  ModelCopyJobStatus = "Completed"
	ModelCopyJobStatusFailed     ModelCopyJobStatus = "Failed"
)

Enum values for ModelCopyJobStatus

func (ModelCopyJobStatus) Values added in v1.13.0 

func (ModelCopyJobStatus) Values() []ModelCopyJobStatus

Values returns all known values for ModelCopyJobStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ModelCopyJobSummary added in v1.13.0 

type ModelCopyJobSummary struct {

	// The time that the model copy job was created.
	//
	// This member is required.
	CreationTime *time.Time

	// The Amazon Resoource Name (ARN) of the model copy job.
	//
	// This member is required.
	JobArn *string

	// The unique identifier of the account that the model being copied originated
	// from.
	//
	// This member is required.
	SourceAccountId *string

	// The Amazon Resource Name (ARN) of the original model being copied.
	//
	// This member is required.
	SourceModelArn *string

	// The status of the model copy job.
	//
	// This member is required.
	Status ModelCopyJobStatus

	// The Amazon Resource Name (ARN) of the copied model.
	//
	// This member is required.
	TargetModelArn *string

	// If a model fails to be copied, a message describing why the job failed is
	// included here.
	FailureMessage *string

	// The name of the original model being copied.
	SourceModelName *string

	// The Amazon Resource Name (ARN) of the KMS key used to encrypt the copied model.
	TargetModelKmsKeyArn *string

	// The name of the copied model.
	TargetModelName *string

	// Tags associated with the copied model.
	TargetModelTags []Tag
	// contains filtered or unexported fields
}

Contains details about each model copy job.

This data type is used in the following API operations:

ListModelCopyJobs response

type ModelCustomization 

type ModelCustomization string
const (
	ModelCustomizationFineTuning           ModelCustomization = "FINE_TUNING"
	ModelCustomizationContinuedPreTraining ModelCustomization = "CONTINUED_PRE_TRAINING"
	ModelCustomizationDistillation         ModelCustomization = "DISTILLATION"
)

Enum values for ModelCustomization

func (ModelCustomization) Values 

func (ModelCustomization) Values() []ModelCustomization

Values returns all known values for ModelCustomization. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ModelCustomizationJobStatus 

type ModelCustomizationJobStatus string
const (
	ModelCustomizationJobStatusInProgress ModelCustomizationJobStatus = "InProgress"
	ModelCustomizationJobStatusCompleted  ModelCustomizationJobStatus = "Completed"
	ModelCustomizationJobStatusFailed     ModelCustomizationJobStatus = "Failed"
	ModelCustomizationJobStatusStopping   ModelCustomizationJobStatus = "Stopping"
	ModelCustomizationJobStatusStopped    ModelCustomizationJobStatus = "Stopped"
)

Enum values for ModelCustomizationJobStatus

func (ModelCustomizationJobStatus) Values 

func (ModelCustomizationJobStatus) Values() []ModelCustomizationJobStatus

Values returns all known values for ModelCustomizationJobStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ModelCustomizationJobSummary 

type ModelCustomizationJobSummary struct {

	// Amazon Resource Name (ARN) of the base model.
	//
	// This member is required.
	BaseModelArn *string

	// Creation time of the custom model.
	//
	// This member is required.
	CreationTime *time.Time

	// Amazon Resource Name (ARN) of the customization job.
	//
	// This member is required.
	JobArn *string

	// Name of the customization job.
	//
	// This member is required.
	JobName *string

	// Status of the customization job.
	//
	// This member is required.
	Status ModelCustomizationJobStatus

	// Amazon Resource Name (ARN) of the custom model.
	CustomModelArn *string

	// Name of the custom model.
	CustomModelName *string

	// Specifies whether to carry out continued pre-training of a model or whether to
	// fine-tune it. For more information, see [Custom models].
	//
	// [Custom models]: https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html
	CustomizationType CustomizationType

	// Time that the customization job ended.
	EndTime *time.Time

	// Time that the customization job was last modified.
	LastModifiedTime *time.Time

	// Details about the status of the data processing sub-task of the job.
	StatusDetails *StatusDetails
	// contains filtered or unexported fields
}

Information about one customization job

type ModelDataSource added in v1.15.0 

type ModelDataSource interface {
	// contains filtered or unexported methods
}

The data source of the model to import.

The following types satisfy this interface: 

ModelDataSourceMemberS3DataSource
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.ModelDataSource
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.ModelDataSourceMemberS3DataSource:
		_ = v.Value // Value is types.S3DataSource

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type ModelDataSourceMemberS3DataSource added in v1.15.0 

type ModelDataSourceMemberS3DataSource struct {
	Value S3DataSource
	// contains filtered or unexported fields
}

The Amazon S3 data source of the model to import.

type ModelImportJobStatus added in v1.15.0 

type ModelImportJobStatus string
const (
	ModelImportJobStatusInProgress ModelImportJobStatus = "InProgress"
	ModelImportJobStatusCompleted  ModelImportJobStatus = "Completed"
	ModelImportJobStatusFailed     ModelImportJobStatus = "Failed"
)

Enum values for ModelImportJobStatus

func (ModelImportJobStatus) Values added in v1.15.0 

func (ModelImportJobStatus) Values() []ModelImportJobStatus

Values returns all known values for ModelImportJobStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ModelImportJobSummary added in v1.15.0 

type ModelImportJobSummary struct {

	// The time import job was created.
	//
	// This member is required.
	CreationTime *time.Time

	// The Amazon Resource Name (ARN) of the import job.
	//
	// This member is required.
	JobArn *string

	// The name of the import job.
	//
	// This member is required.
	JobName *string

	// The status of the imported job.
	//
	// This member is required.
	Status ModelImportJobStatus

	// The time when import job ended.
	EndTime *time.Time

	// The Amazon resource Name (ARN) of the imported model.
	ImportedModelArn *string

	// The name of the imported model.
	ImportedModelName *string

	// The time when the import job was last modified.
	LastModifiedTime *time.Time
	// contains filtered or unexported fields
}

Information about the import job.

type ModelInvocationJobInputDataConfig added in v1.14.0 

type ModelInvocationJobInputDataConfig interface {
	// contains filtered or unexported methods
}

Details about the location of the input to the batch inference job.

The following types satisfy this interface: 

ModelInvocationJobInputDataConfigMemberS3InputDataConfig
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.ModelInvocationJobInputDataConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.ModelInvocationJobInputDataConfigMemberS3InputDataConfig:
		_ = v.Value // Value is types.ModelInvocationJobS3InputDataConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type ModelInvocationJobInputDataConfigMemberS3InputDataConfig added in v1.14.0 

type ModelInvocationJobInputDataConfigMemberS3InputDataConfig struct {
	Value ModelInvocationJobS3InputDataConfig
	// contains filtered or unexported fields
}

Contains the configuration of the S3 location of the input data.

type ModelInvocationJobOutputDataConfig added in v1.14.0 

type ModelInvocationJobOutputDataConfig interface {
	// contains filtered or unexported methods
}

Contains the configuration of the S3 location of the output data.

The following types satisfy this interface: 

ModelInvocationJobOutputDataConfigMemberS3OutputDataConfig
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.ModelInvocationJobOutputDataConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.ModelInvocationJobOutputDataConfigMemberS3OutputDataConfig:
		_ = v.Value // Value is types.ModelInvocationJobS3OutputDataConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type ModelInvocationJobOutputDataConfigMemberS3OutputDataConfig added in v1.14.0 

type ModelInvocationJobOutputDataConfigMemberS3OutputDataConfig struct {
	Value ModelInvocationJobS3OutputDataConfig
	// contains filtered or unexported fields
}

Contains the configuration of the S3 location of the output data.

type ModelInvocationJobS3InputDataConfig added in v1.14.0 

type ModelInvocationJobS3InputDataConfig struct {

	// The S3 location of the input data.
	//
	// This member is required.
	S3Uri *string

	// The ID of the Amazon Web Services account that owns the S3 bucket containing
	// the input data.
	S3BucketOwner *string

	// The format of the input data.
	S3InputFormat S3InputFormat
	// contains filtered or unexported fields
}

Contains the configuration of the S3 location of the input data.

type ModelInvocationJobS3OutputDataConfig added in v1.14.0 

type ModelInvocationJobS3OutputDataConfig struct {

	// The S3 location of the output data.
	//
	// This member is required.
	S3Uri *string

	// The ID of the Amazon Web Services account that owns the S3 bucket containing
	// the output data.
	S3BucketOwner *string

	// The unique identifier of the key that encrypts the S3 location of the output
	// data.
	S3EncryptionKeyId *string
	// contains filtered or unexported fields
}

Contains the configuration of the S3 location of the output data.

type ModelInvocationJobStatus added in v1.14.0 

type ModelInvocationJobStatus string
const (
	ModelInvocationJobStatusSubmitted          ModelInvocationJobStatus = "Submitted"
	ModelInvocationJobStatusInProgress         ModelInvocationJobStatus = "InProgress"
	ModelInvocationJobStatusCompleted          ModelInvocationJobStatus = "Completed"
	ModelInvocationJobStatusFailed             ModelInvocationJobStatus = "Failed"
	ModelInvocationJobStatusStopping           ModelInvocationJobStatus = "Stopping"
	ModelInvocationJobStatusStopped            ModelInvocationJobStatus = "Stopped"
	ModelInvocationJobStatusPartiallyCompleted ModelInvocationJobStatus = "PartiallyCompleted"
	ModelInvocationJobStatusExpired            ModelInvocationJobStatus = "Expired"
	ModelInvocationJobStatusValidating         ModelInvocationJobStatus = "Validating"
	ModelInvocationJobStatusScheduled          ModelInvocationJobStatus = "Scheduled"
)

Enum values for ModelInvocationJobStatus

func (ModelInvocationJobStatus) Values added in v1.14.0 

func (ModelInvocationJobStatus) Values() []ModelInvocationJobStatus

Values returns all known values for ModelInvocationJobStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ModelInvocationJobSummary added in v1.14.0 

type ModelInvocationJobSummary struct {

	// Details about the location of the input to the batch inference job.
	//
	// This member is required.
	InputDataConfig ModelInvocationJobInputDataConfig

	// The Amazon Resource Name (ARN) of the batch inference job.
	//
	// This member is required.
	JobArn *string

	// The name of the batch inference job.
	//
	// This member is required.
	JobName *string

	// The unique identifier of the foundation model used for model inference.
	//
	// This member is required.
	ModelId *string

	// Details about the location of the output of the batch inference job.
	//
	// This member is required.
	OutputDataConfig ModelInvocationJobOutputDataConfig

	// The Amazon Resource Name (ARN) of the service role with permissions to carry
	// out and manage batch inference. You can use the console to create a default
	// service role or follow the steps at [Create a service role for batch inference].
	//
	// [Create a service role for batch inference]: https://docs.aws.amazon.com/bedrock/latest/userguide/batch-iam-sr.html
	//
	// This member is required.
	RoleArn *string

	// The time at which the batch inference job was submitted.
	//
	// This member is required.
	SubmitTime *time.Time

	// A unique, case-sensitive identifier to ensure that the API request completes no
	// more than one time. If this token matches a previous request, Amazon Bedrock
	// ignores the request, but does not return an error. For more information, see [Ensuring idempotency].
	//
	// [Ensuring idempotency]: https://docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html
	ClientRequestToken *string

	// The time at which the batch inference job ended.
	EndTime *time.Time

	// The time at which the batch inference job times or timed out.
	JobExpirationTime *time.Time

	// The time at which the batch inference job was last modified.
	LastModifiedTime *time.Time

	// If the batch inference job failed, this field contains a message describing why
	// the job failed.
	Message *string

	// The status of the batch inference job.
	//
	// The following statuses are possible:
	//
	//   - Submitted – This job has been submitted to a queue for validation.
	//
	//   - Validating – This job is being validated for the requirements described in [Format and upload your batch inference data]
	//   . The criteria include the following:
	//
	//   - Your IAM service role has access to the Amazon S3 buckets containing your
	//   files.
	//
	//   - Your files are .jsonl files and each individual record is a JSON object in
	//   the correct format. Note that validation doesn't check if the modelInput value
	//   matches the request body for the model.
	//
	//   - Your files fulfill the requirements for file size and number of records.
	//   For more information, see [Quotas for Amazon Bedrock].
	//
	//   - Scheduled – This job has been validated and is now in a queue. The job will
	//   automatically start when it reaches its turn.
	//
	//   - Expired – This job timed out because it was scheduled but didn't begin
	//   before the set timeout duration. Submit a new job request.
	//
	//   - InProgress – This job has begun. You can start viewing the results in the
	//   output S3 location.
	//
	//   - Completed – This job has successfully completed. View the output files in
	//   the output S3 location.
	//
	//   - PartiallyCompleted – This job has partially completed. Not all of your
	//   records could be processed in time. View the output files in the output S3
	//   location.
	//
	//   - Failed – This job has failed. Check the failure message for any further
	//   details. For further assistance, reach out to the [Amazon Web ServicesSupport Center].
	//
	//   - Stopped – This job was stopped by a user.
	//
	//   - Stopping – This job is being stopped by a user.
	//
	// [Format and upload your batch inference data]: https://docs.aws.amazon.com/bedrock/latest/userguide/batch-inference-data.html
	// [Amazon Web ServicesSupport Center]: https://console.aws.amazon.com/support/home/
	// [Quotas for Amazon Bedrock]: https://docs.aws.amazon.com/bedrock/latest/userguide/quotas.html
	Status ModelInvocationJobStatus

	// The number of hours after which the batch inference job was set to time out.
	TimeoutDurationInHours *int32

	// The configuration of the Virtual Private Cloud (VPC) for the data in the batch
	// inference job. For more information, see [Protect batch inference jobs using a VPC].
	//
	// [Protect batch inference jobs using a VPC]: https://docs.aws.amazon.com/bedrock/latest/userguide/batch-vpc
	VpcConfig *VpcConfig
	// contains filtered or unexported fields
}

A summary of a batch inference job.

type ModelModality 

type ModelModality string
const (
	ModelModalityText      ModelModality = "TEXT"
	ModelModalityImage     ModelModality = "IMAGE"
	ModelModalityEmbedding ModelModality = "EMBEDDING"
)

Enum values for ModelModality

func (ModelModality) Values 

func (ModelModality) Values() []ModelModality

Values returns all known values for ModelModality. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ModelStatus added in v1.35.0 

type ModelStatus string
const (
	ModelStatusActive   ModelStatus = "Active"
	ModelStatusCreating ModelStatus = "Creating"
	ModelStatusFailed   ModelStatus = "Failed"
)

Enum values for ModelStatus

func (ModelStatus) Values added in v1.35.0 

func (ModelStatus) Values() []ModelStatus

Values returns all known values for ModelStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type Offer added in v1.37.0 

type Offer struct {

	// Offer token.
	//
	// This member is required.
	OfferToken *string

	// Details about the terms of the offer.
	//
	// This member is required.
	TermDetails *TermDetails

	// Offer Id for a model offer.
	OfferId *string
	// contains filtered or unexported fields
}

An offer dictates usage terms for the model.

type OfferType added in v1.37.0 

type OfferType string
const (
	OfferTypeAll    OfferType = "ALL"
	OfferTypePublic OfferType = "PUBLIC"
)

Enum values for OfferType

func (OfferType) Values added in v1.37.0 

func (OfferType) Values() []OfferType

Values returns all known values for OfferType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type OrchestrationConfiguration added in v1.23.0 

type OrchestrationConfiguration struct {

	// Contains configuration details for transforming the prompt.
	//
	// This member is required.
	QueryTransformationConfiguration *QueryTransformationConfiguration
	// contains filtered or unexported fields
}

The configuration details for the model to process the prompt prior to retrieval and response generation.

type OutputDataConfig 

type OutputDataConfig struct {

	// The S3 URI where the output data is stored.
	//
	// This member is required.
	S3Uri *string
	// contains filtered or unexported fields
}

S3 Location of the output data.

type PerformanceConfigLatency added in v1.26.0 

type PerformanceConfigLatency string
const (
	PerformanceConfigLatencyStandard  PerformanceConfigLatency = "standard"
	PerformanceConfigLatencyOptimized PerformanceConfigLatency = "optimized"
)

Enum values for PerformanceConfigLatency

func (PerformanceConfigLatency) Values added in v1.26.0 

func (PerformanceConfigLatency) Values() []PerformanceConfigLatency

Values returns all known values for PerformanceConfigLatency. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type PerformanceConfiguration added in v1.26.0 

type PerformanceConfiguration struct {

	// Specifies whether to use the latency-optimized or standard version of a model
	// or inference profile.
	Latency PerformanceConfigLatency
	// contains filtered or unexported fields
}

Contains performance settings for a model.

type PricingTerm added in v1.37.0 

type PricingTerm struct {

	// Describes a usage price for each dimension.
	//
	// This member is required.
	RateCard []DimensionalPriceRate
	// contains filtered or unexported fields
}

Describes the usage-based pricing term.

type PromptRouterStatus added in v1.25.0 

type PromptRouterStatus string
const (
	PromptRouterStatusAvailable PromptRouterStatus = "AVAILABLE"
)

Enum values for PromptRouterStatus

func (PromptRouterStatus) Values added in v1.25.0 

func (PromptRouterStatus) Values() []PromptRouterStatus

Values returns all known values for PromptRouterStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type PromptRouterSummary added in v1.25.0 

type PromptRouterSummary struct {

	// The router's fallback model.
	//
	// This member is required.
	FallbackModel *PromptRouterTargetModel

	// The router's models.
	//
	// This member is required.
	Models []PromptRouterTargetModel

	// The router's ARN.
	//
	// This member is required.
	PromptRouterArn *string

	// The router's name.
	//
	// This member is required.
	PromptRouterName *string

	// The router's routing criteria.
	//
	// This member is required.
	RoutingCriteria *RoutingCriteria

	// The router's status.
	//
	// This member is required.
	Status PromptRouterStatus

	// The summary's type.
	//
	// This member is required.
	Type PromptRouterType

	// When the router was created.
	CreatedAt *time.Time

	// The router's description.
	Description *string

	// When the router was updated.
	UpdatedAt *time.Time
	// contains filtered or unexported fields
}

Details about a prompt router.

type PromptRouterTargetModel added in v1.25.0 

type PromptRouterTargetModel struct {

	// The target model's ARN.
	//
	// This member is required.
	ModelArn *string
	// contains filtered or unexported fields
}

The target model for a prompt router.

type PromptRouterType added in v1.25.0 

type PromptRouterType string
const (
	PromptRouterTypeCustom  PromptRouterType = "custom"
	PromptRouterTypeDefault PromptRouterType = "default"
)

Enum values for PromptRouterType

func (PromptRouterType) Values added in v1.25.0 

func (PromptRouterType) Values() []PromptRouterType

Values returns all known values for PromptRouterType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type PromptTemplate added in v1.23.0 

type PromptTemplate struct {

	// The template for the prompt that's sent to the model for response generation.
	// You can include prompt placeholders, which become replaced before the prompt is
	// sent to the model to provide instructions and context to the model. In addition,
	// you can include XML tags to delineate meaningful sections of the prompt
	// template.
	//
	// For more information, see [Knowledge base prompt template] and [Use XML tags with Anthropic Claude models].
	//
	// [Knowledge base prompt template]: https://docs.aws.amazon.com/bedrock/latest/userguide/kb-test-config.html
	// [Use XML tags with Anthropic Claude models]: https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/use-xml-tags
	TextPromptTemplate *string
	// contains filtered or unexported fields
}

The template for the prompt that's sent to the model for response generation.

type ProvisionedModelStatus added in v1.1.0 

type ProvisionedModelStatus string
const (
	ProvisionedModelStatusCreating  ProvisionedModelStatus = "Creating"
	ProvisionedModelStatusInService ProvisionedModelStatus = "InService"
	ProvisionedModelStatusUpdating  ProvisionedModelStatus = "Updating"
	ProvisionedModelStatusFailed    ProvisionedModelStatus = "Failed"
)

Enum values for ProvisionedModelStatus

func (ProvisionedModelStatus) Values added in v1.1.0 

func (ProvisionedModelStatus) Values() []ProvisionedModelStatus

Values returns all known values for ProvisionedModelStatus. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ProvisionedModelSummary added in v1.1.0 

type ProvisionedModelSummary struct {

	// The time that the Provisioned Throughput was created.
	//
	// This member is required.
	CreationTime *time.Time

	// The Amazon Resource Name (ARN) of the model requested to be associated to this
	// Provisioned Throughput. This value differs from the modelArn if updating hasn't
	// completed.
	//
	// This member is required.
	DesiredModelArn *string

	// The number of model units that was requested to be allocated to the Provisioned
	// Throughput.
	//
	// This member is required.
	DesiredModelUnits *int32

	// The Amazon Resource Name (ARN) of the base model for which the Provisioned
	// Throughput was created, or of the base model that the custom model for which the
	// Provisioned Throughput was created was customized.
	//
	// This member is required.
	FoundationModelArn *string

	// The time that the Provisioned Throughput was last modified.
	//
	// This member is required.
	LastModifiedTime *time.Time

	// The Amazon Resource Name (ARN) of the model associated with the Provisioned
	// Throughput.
	//
	// This member is required.
	ModelArn *string

	// The number of model units allocated to the Provisioned Throughput.
	//
	// This member is required.
	ModelUnits *int32

	// The Amazon Resource Name (ARN) of the Provisioned Throughput.
	//
	// This member is required.
	ProvisionedModelArn *string

	// The name of the Provisioned Throughput.
	//
	// This member is required.
	ProvisionedModelName *string

	// The status of the Provisioned Throughput.
	//
	// This member is required.
	Status ProvisionedModelStatus

	// The duration for which the Provisioned Throughput was committed.
	CommitmentDuration CommitmentDuration

	// The timestamp for when the commitment term of the Provisioned Throughput
	// expires.
	CommitmentExpirationTime *time.Time
	// contains filtered or unexported fields
}

A summary of information about a Provisioned Throughput.

This data type is used in the following API operations:

ListProvisionedThroughputs response

type QueryTransformationConfiguration added in v1.23.0 

type QueryTransformationConfiguration struct {

	// The type of transformation to apply to the prompt.
	//
	// This member is required.
	Type QueryTransformationType
	// contains filtered or unexported fields
}

The configuration details for transforming the prompt.

type QueryTransformationType added in v1.23.0 

type QueryTransformationType string
const (
	QueryTransformationTypeQueryDecomposition QueryTransformationType = "QUERY_DECOMPOSITION"
)

Enum values for QueryTransformationType

func (QueryTransformationType) Values added in v1.23.0 

func (QueryTransformationType) Values() []QueryTransformationType

Values returns all known values for QueryTransformationType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type RAGConfig added in v1.23.0 

type RAGConfig interface {
	// contains filtered or unexported methods
}

Contains configuration details for retrieval of information and response generation.

The following types satisfy this interface: 

RAGConfigMemberKnowledgeBaseConfig
RAGConfigMemberPrecomputedRagSourceConfig
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.RAGConfig
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.RAGConfigMemberKnowledgeBaseConfig:
		_ = v.Value // Value is types.KnowledgeBaseConfig

	case *types.RAGConfigMemberPrecomputedRagSourceConfig:
		_ = v.Value // Value is types.EvaluationPrecomputedRagSourceConfig

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type RAGConfigMemberKnowledgeBaseConfig added in v1.23.0 

type RAGConfigMemberKnowledgeBaseConfig struct {
	Value KnowledgeBaseConfig
	// contains filtered or unexported fields
}

Contains configuration details for knowledge base retrieval and response generation.

type RAGConfigMemberPrecomputedRagSourceConfig added in v1.29.0 

type RAGConfigMemberPrecomputedRagSourceConfig struct {
	Value EvaluationPrecomputedRagSourceConfig
	// contains filtered or unexported fields
}

Contains configuration details about the RAG source used to generate inference response data for a Knowledge Base evaluation job.

type RatingScaleItem added in v1.32.0 

type RatingScaleItem struct {

	// Defines the definition for one rating in a custom metric rating scale.
	//
	// This member is required.
	Definition *string

	// Defines the value for one rating in a custom metric rating scale.
	//
	// This member is required.
	Value RatingScaleItemValue
	// contains filtered or unexported fields
}

Defines the value and corresponding definition for one rating in a custom metric rating scale.

type RatingScaleItemValue added in v1.32.0 

type RatingScaleItemValue interface {
	// contains filtered or unexported methods
}

Defines the value for one rating in a custom metric rating scale.

The following types satisfy this interface: 

RatingScaleItemValueMemberFloatValue
RatingScaleItemValueMemberStringValue
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.RatingScaleItemValue
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.RatingScaleItemValueMemberFloatValue:
		_ = v.Value // Value is float32

	case *types.RatingScaleItemValueMemberStringValue:
		_ = v.Value // Value is string

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type RatingScaleItemValueMemberFloatValue added in v1.32.0 

type RatingScaleItemValueMemberFloatValue struct {
	Value float32
	// contains filtered or unexported fields
}

A floating point number representing the value for a rating in a custom metric rating scale.

type RatingScaleItemValueMemberStringValue added in v1.32.0 

type RatingScaleItemValueMemberStringValue struct {
	Value string
	// contains filtered or unexported fields
}

A string representing the value for a rating in a custom metric rating scale.

type RegionAvailability added in v1.37.0 

type RegionAvailability string
const (
	RegionAvailabilityAvailable    RegionAvailability = "AVAILABLE"
	RegionAvailabilityNotAvailable RegionAvailability = "NOT_AVAILABLE"
)

Enum values for RegionAvailability

func (RegionAvailability) Values added in v1.37.0 

func (RegionAvailability) Values() []RegionAvailability

Values returns all known values for RegionAvailability. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type RequestMetadataBaseFilters added in v1.24.0 

type RequestMetadataBaseFilters struct {

	// Include results where the key equals the value.
	Equals map[string]string

	// Include results where the key does not equal the value.
	NotEquals map[string]string
	// contains filtered or unexported fields
}

A mapping of a metadata key to a value that it should or should not equal.

type RequestMetadataFilters added in v1.24.0 

type RequestMetadataFilters interface {
	// contains filtered or unexported methods
}

Rules for filtering invocation logs. A filter can be a mapping of a metadata key to a value that it should or should not equal (a base filter), or a list of base filters that are all applied with AND or OR logical operators

The following types satisfy this interface: 

RequestMetadataFiltersMemberAndAll
RequestMetadataFiltersMemberEquals
RequestMetadataFiltersMemberNotEquals
RequestMetadataFiltersMemberOrAll
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.RequestMetadataFilters
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.RequestMetadataFiltersMemberAndAll:
		_ = v.Value // Value is []types.RequestMetadataBaseFilters

	case *types.RequestMetadataFiltersMemberEquals:
		_ = v.Value // Value is map[string]string

	case *types.RequestMetadataFiltersMemberNotEquals:
		_ = v.Value // Value is map[string]string

	case *types.RequestMetadataFiltersMemberOrAll:
		_ = v.Value // Value is []types.RequestMetadataBaseFilters

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type RequestMetadataFiltersMemberAndAll added in v1.24.0 

type RequestMetadataFiltersMemberAndAll struct {
	Value []RequestMetadataBaseFilters
	// contains filtered or unexported fields
}

Include results where all of the based filters match.

type RequestMetadataFiltersMemberEquals added in v1.24.0 

type RequestMetadataFiltersMemberEquals struct {
	Value map[string]string
	// contains filtered or unexported fields
}

Include results where the key equals the value.

type RequestMetadataFiltersMemberNotEquals added in v1.24.0 

type RequestMetadataFiltersMemberNotEquals struct {
	Value map[string]string
	// contains filtered or unexported fields
}

Include results where the key does not equal the value.

type RequestMetadataFiltersMemberOrAll added in v1.24.0 

type RequestMetadataFiltersMemberOrAll struct {
	Value []RequestMetadataBaseFilters
	// contains filtered or unexported fields
}

Include results where any of the base filters match.

type RerankingMetadataSelectionMode added in v1.38.0 

type RerankingMetadataSelectionMode string
const (
	RerankingMetadataSelectionModeSelective RerankingMetadataSelectionMode = "SELECTIVE"
	RerankingMetadataSelectionModeAll       RerankingMetadataSelectionMode = "ALL"
)

Enum values for RerankingMetadataSelectionMode

func (RerankingMetadataSelectionMode) Values added in v1.38.0 

func (RerankingMetadataSelectionMode) Values() []RerankingMetadataSelectionMode

Values returns all known values for RerankingMetadataSelectionMode. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type RerankingMetadataSelectiveModeConfiguration added in v1.38.0 

type RerankingMetadataSelectiveModeConfiguration interface {
	// contains filtered or unexported methods
}

Configuration for selectively including or excluding metadata fields during the reranking process. This allows you to control which metadata attributes are considered when reordering search results.

The following types satisfy this interface: 

RerankingMetadataSelectiveModeConfigurationMemberFieldsToExclude
RerankingMetadataSelectiveModeConfigurationMemberFieldsToInclude
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.RerankingMetadataSelectiveModeConfiguration
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.RerankingMetadataSelectiveModeConfigurationMemberFieldsToExclude:
		_ = v.Value // Value is []types.FieldForReranking

	case *types.RerankingMetadataSelectiveModeConfigurationMemberFieldsToInclude:
		_ = v.Value // Value is []types.FieldForReranking

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type RerankingMetadataSelectiveModeConfigurationMemberFieldsToExclude added in v1.38.0 

type RerankingMetadataSelectiveModeConfigurationMemberFieldsToExclude struct {
	Value []FieldForReranking
	// contains filtered or unexported fields
}

A list of metadata field names to explicitly exclude from the reranking process. All metadata fields except these will be considered when reordering search results. This parameter cannot be used together with fieldsToInclude.

type RerankingMetadataSelectiveModeConfigurationMemberFieldsToInclude added in v1.38.0 

type RerankingMetadataSelectiveModeConfigurationMemberFieldsToInclude struct {
	Value []FieldForReranking
	// contains filtered or unexported fields
}

A list of metadata field names to explicitly include in the reranking process. Only these fields will be considered when reordering search results. This parameter cannot be used together with fieldsToExclude.

type ResourceInUseException added in v1.42.0 

type ResourceInUseException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

Thrown when attempting to delete or modify a resource that is currently being used by other resources or operations. For example, trying to delete an Automated Reasoning policy that is referenced by an active guardrail.

func (*ResourceInUseException) Error added in v1.42.0 

func (e *ResourceInUseException) Error() string

func (*ResourceInUseException) ErrorCode added in v1.42.0 

func (e *ResourceInUseException) ErrorCode() string

func (*ResourceInUseException) ErrorFault added in v1.42.0 

func (e *ResourceInUseException) ErrorFault() smithy.ErrorFault

func (*ResourceInUseException) ErrorMessage added in v1.42.0 

func (e *ResourceInUseException) ErrorMessage() string

type ResourceNotFoundException 

type ResourceNotFoundException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.

func (*ResourceNotFoundException) Error 

func (e *ResourceNotFoundException) Error() string

func (*ResourceNotFoundException) ErrorCode 

func (e *ResourceNotFoundException) ErrorCode() string

func (*ResourceNotFoundException) ErrorFault 

func (e *ResourceNotFoundException) ErrorFault() smithy.ErrorFault

func (*ResourceNotFoundException) ErrorMessage 

func (e *ResourceNotFoundException) ErrorMessage() string

type RetrievalFilter added in v1.23.0 

type RetrievalFilter interface {
	// contains filtered or unexported methods
}

Specifies the filters to use on the metadata attributes/fields in the knowledge base data sources before returning results.

The following types satisfy this interface: 

RetrievalFilterMemberAndAll
RetrievalFilterMemberEquals
RetrievalFilterMemberGreaterThan
RetrievalFilterMemberGreaterThanOrEquals
RetrievalFilterMemberIn
RetrievalFilterMemberLessThan
RetrievalFilterMemberLessThanOrEquals
RetrievalFilterMemberListContains
RetrievalFilterMemberNotEquals
RetrievalFilterMemberNotIn
RetrievalFilterMemberOrAll
RetrievalFilterMemberStartsWith
RetrievalFilterMemberStringContains
Example (OutputUsage) 
package main

import (
	"fmt"
	"github.com/aws/aws-sdk-go-v2/service/bedrock/types"
)

func main() {
	var union types.RetrievalFilter
	// type switches can be used to check the union value
	switch v := union.(type) {
	case *types.RetrievalFilterMemberAndAll:
		_ = v.Value // Value is []types.RetrievalFilter

	case *types.RetrievalFilterMemberEquals:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberGreaterThan:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberGreaterThanOrEquals:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberIn:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberLessThan:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberLessThanOrEquals:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberListContains:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberNotEquals:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberNotIn:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberOrAll:
		_ = v.Value // Value is []types.RetrievalFilter

	case *types.RetrievalFilterMemberStartsWith:
		_ = v.Value // Value is types.FilterAttribute

	case *types.RetrievalFilterMemberStringContains:
		_ = v.Value // Value is types.FilterAttribute

	case *types.UnknownUnionMember:
		fmt.Println("unknown tag:", v.Tag)

	default:
		fmt.Println("union is nil or unknown type")

	}
}

type RetrievalFilterMemberAndAll added in v1.23.0 

type RetrievalFilterMemberAndAll struct {
	Value []RetrievalFilter
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.

type RetrievalFilterMemberEquals added in v1.23.0 

type RetrievalFilterMemberEquals struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.

The following example would return data sources with an animal attribute whose value is 'cat': "equals": { "key": "animal", "value": "cat" }

type RetrievalFilterMemberGreaterThan added in v1.23.0 

type RetrievalFilterMemberGreaterThan struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.

The following example would return data sources with an year attribute whose value is greater than '1989': "greaterThan": { "key": "year", "value": 1989 }

type RetrievalFilterMemberGreaterThanOrEquals added in v1.23.0 

type RetrievalFilterMemberGreaterThanOrEquals struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.

The following example would return data sources with an year attribute whose value is greater than or equal to '1989': "greaterThanOrEquals": { "key": "year", "value": 1989 }

type RetrievalFilterMemberIn added in v1.23.0 

type RetrievalFilterMemberIn struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.

The following example would return data sources with an animal attribute that is either 'cat' or 'dog': "in": { "key": "animal", "value": ["cat", "dog"] }

type RetrievalFilterMemberLessThan added in v1.23.0 

type RetrievalFilterMemberLessThan struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.

The following example would return data sources with an year attribute whose value is less than to '1989': "lessThan": { "key": "year", "value": 1989 }

type RetrievalFilterMemberLessThanOrEquals added in v1.23.0 

type RetrievalFilterMemberLessThanOrEquals struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.

The following example would return data sources with an year attribute whose value is less than or equal to '1989': "lessThanOrEquals": { "key": "year", "value": 1989 }

type RetrievalFilterMemberListContains added in v1.23.0 

type RetrievalFilterMemberListContains struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.

The following example would return data sources with an animals attribute that is a list containing a cat member (for example, ["dog", "cat"] ): "listContains": { "key": "animals", "value": "cat" }

type RetrievalFilterMemberNotEquals added in v1.23.0 

type RetrievalFilterMemberNotEquals struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources that contain a metadata attribute whose name matches the key and whose value doesn't match the value in this object are returned.

The following example would return data sources that don't contain an animal attribute whose value is 'cat': "notEquals": { "key": "animal", "value": "cat" }

type RetrievalFilterMemberNotIn added in v1.23.0 

type RetrievalFilterMemberNotIn struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.

The following example would return data sources whose animal attribute is neither 'cat' nor 'dog': "notIn": { "key": "animal", "value": ["cat", "dog"] }

type RetrievalFilterMemberOrAll added in v1.23.0 

type RetrievalFilterMemberOrAll struct {
	Value []RetrievalFilter
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.

type RetrievalFilterMemberStartsWith added in v1.23.0 

type RetrievalFilterMemberStartsWith struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.

The following example would return data sources with an animal attribute starts with 'ca' (for example, 'cat' or 'camel'). "startsWith": { "key": "animal", "value": "ca" }

type RetrievalFilterMemberStringContains added in v1.23.0 

type RetrievalFilterMemberStringContains struct {
	Value FilterAttribute
	// contains filtered or unexported fields
}

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:

A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example, 'cat'): "stringContains": { "key": "animal", "value": "at" }

A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example, ["dog", "cat"] ): "stringContains": { "key": "animals", "value": "at" }

type RetrieveAndGenerateConfiguration added in v1.23.0 

type RetrieveAndGenerateConfiguration struct {

	// The type of resource that contains your data for retrieving information and
	// generating responses.
	//
	// If you choose to use EXTERNAL_SOURCES , then currently only Claude 3 Sonnet
	// models for knowledge bases are supported.
	//
	// This member is required.
	Type RetrieveAndGenerateType

	// The configuration for the external source wrapper object in the
	// retrieveAndGenerate function.
	ExternalSourcesConfiguration *ExternalSourcesRetrieveAndGenerateConfiguration

	// Contains configuration details for the knowledge base retrieval and response
	// generation.
	KnowledgeBaseConfiguration *KnowledgeBaseRetrieveAndGenerateConfiguration
	// contains filtered or unexported fields
}

Contains configuration details for a knowledge base retrieval and response generation.

type RetrieveAndGenerateType added in v1.23.0 

type RetrieveAndGenerateType string
const (
	RetrieveAndGenerateTypeKnowledgeBase   RetrieveAndGenerateType = "KNOWLEDGE_BASE"
	RetrieveAndGenerateTypeExternalSources RetrieveAndGenerateType = "EXTERNAL_SOURCES"
)

Enum values for RetrieveAndGenerateType

func (RetrieveAndGenerateType) Values added in v1.23.0 

func (RetrieveAndGenerateType) Values() []RetrieveAndGenerateType

Values returns all known values for RetrieveAndGenerateType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type RetrieveConfig added in v1.23.0 

type RetrieveConfig struct {

	// The unique identifier of the knowledge base.
	//
	// This member is required.
	KnowledgeBaseId *string

	// Contains configuration details for knowledge base retrieval.
	//
	// This member is required.
	KnowledgeBaseRetrievalConfiguration *KnowledgeBaseRetrievalConfiguration
	// contains filtered or unexported fields
}

The configuration details for retrieving information from a knowledge base.

type RoutingCriteria added in v1.25.0 

type RoutingCriteria struct {

	// The criteria's response quality difference.
	//
	// This member is required.
	ResponseQualityDifference *float64
	// contains filtered or unexported fields
}

Routing criteria for a prompt router.

type S3Config 

type S3Config struct {

	// S3 bucket name.
	//
	// This member is required.
	BucketName *string

	// S3 prefix.
	KeyPrefix *string
	// contains filtered or unexported fields
}

S3 configuration for storing log data.

type S3DataSource added in v1.15.0 

type S3DataSource struct {

	// The URI of the Amazon S3 data source.
	//
	// This member is required.
	S3Uri *string
	// contains filtered or unexported fields
}

The Amazon S3 data source of the model to import.

type S3InputFormat added in v1.14.0 

type S3InputFormat string
const (
	S3InputFormatJsonl S3InputFormat = "JSONL"
)

Enum values for S3InputFormat

func (S3InputFormat) Values added in v1.14.0 

func (S3InputFormat) Values() []S3InputFormat

Values returns all known values for S3InputFormat. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type S3ObjectDoc added in v1.23.0 

type S3ObjectDoc struct {

	// The S3 URI location for the wrapper object of the document.
	//
	// This member is required.
	Uri *string
	// contains filtered or unexported fields
}

The unique wrapper object of the document from the S3 location.

type SageMakerEndpoint added in v1.25.0 

type SageMakerEndpoint struct {

	// The ARN of the IAM role that Amazon SageMaker can assume to access model
	// artifacts and docker image for deployment on Amazon EC2 compute instances or for
	// batch transform jobs.
	//
	// This member is required.
	ExecutionRole *string

	// The number of Amazon EC2 compute instances to deploy for initial endpoint
	// creation.
	//
	// This member is required.
	InitialInstanceCount *int32

	// The Amazon EC2 compute instance type to deploy for hosting the model.
	//
	// This member is required.
	InstanceType *string

	// The Amazon Web Services KMS key that Amazon SageMaker uses to encrypt data on
	// the storage volume attached to the Amazon EC2 compute instance that hosts the
	// endpoint.
	KmsEncryptionKey *string

	// The VPC configuration for the endpoint.
	Vpc *VpcConfig
	// contains filtered or unexported fields
}

Specifies the configuration for a Amazon SageMaker endpoint.

type SearchType added in v1.23.0 

type SearchType string
const (
	SearchTypeHybrid   SearchType = "HYBRID"
	SearchTypeSemantic SearchType = "SEMANTIC"
)

Enum values for SearchType

func (SearchType) Values added in v1.23.0 

func (SearchType) Values() []SearchType

Values returns all known values for SearchType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type ServiceQuotaExceededException 

type ServiceQuotaExceededException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

The number of requests exceeds the service quota. Resubmit your request later.

func (*ServiceQuotaExceededException) Error 

func (e *ServiceQuotaExceededException) Error() string

func (*ServiceQuotaExceededException) ErrorCode 

func (e *ServiceQuotaExceededException) ErrorCode() string

func (*ServiceQuotaExceededException) ErrorFault 

func (e *ServiceQuotaExceededException) ErrorFault() smithy.ErrorFault

func (*ServiceQuotaExceededException) ErrorMessage 

func (e *ServiceQuotaExceededException) ErrorMessage() string

type ServiceUnavailableException added in v1.25.0 

type ServiceUnavailableException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

Returned if the service cannot complete the request.

func (*ServiceUnavailableException) Error added in v1.25.0 

func (e *ServiceUnavailableException) Error() string

func (*ServiceUnavailableException) ErrorCode added in v1.25.0 

func (e *ServiceUnavailableException) ErrorCode() string

func (*ServiceUnavailableException) ErrorFault added in v1.25.0 

func (e *ServiceUnavailableException) ErrorFault() smithy.ErrorFault

func (*ServiceUnavailableException) ErrorMessage added in v1.25.0 

func (e *ServiceUnavailableException) ErrorMessage() string

type SortByProvisionedModels added in v1.1.0 

type SortByProvisionedModels string
const (
	SortByProvisionedModelsCreationTime SortByProvisionedModels = "CreationTime"
)

Enum values for SortByProvisionedModels

func (SortByProvisionedModels) Values added in v1.1.0 

func (SortByProvisionedModels) Values() []SortByProvisionedModels

Values returns all known values for SortByProvisionedModels. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type SortJobsBy 

type SortJobsBy string
const (
	SortJobsByCreationTime SortJobsBy = "CreationTime"
)

Enum values for SortJobsBy

func (SortJobsBy) Values 

func (SortJobsBy) Values() []SortJobsBy

Values returns all known values for SortJobsBy. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type SortModelsBy 

type SortModelsBy string
const (
	SortModelsByCreationTime SortModelsBy = "CreationTime"
)

Enum values for SortModelsBy

func (SortModelsBy) Values 

func (SortModelsBy) Values() []SortModelsBy

Values returns all known values for SortModelsBy. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type SortOrder 

type SortOrder string
const (
	SortOrderAscending  SortOrder = "Ascending"
	SortOrderDescending SortOrder = "Descending"
)

Enum values for SortOrder

func (SortOrder) Values 

func (SortOrder) Values() []SortOrder

Values returns all known values for SortOrder. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type Status added in v1.25.0 

type Status string
const (
	StatusRegistered           Status = "REGISTERED"
	StatusIncompatibleEndpoint Status = "INCOMPATIBLE_ENDPOINT"
)

Enum values for Status

func (Status) Values added in v1.25.0 

func (Status) Values() []Status

Values returns all known values for Status. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type StatusDetails added in v1.33.0 

type StatusDetails struct {

	// The status details for the data processing sub-task of the job.
	DataProcessingDetails *DataProcessingDetails

	// The status details for the training sub-task of the job.
	TrainingDetails *TrainingDetails

	// The status details for the validation sub-task of the job.
	ValidationDetails *ValidationDetails
	// contains filtered or unexported fields
}

For a Distillation job, the status details for sub-tasks of the job. Possible statuses for each sub-task include the following:

  • NotStarted

  • InProgress

  • Completed

  • Stopping

  • Stopped

  • Failed

type SupportTerm added in v1.37.0 

type SupportTerm struct {

	// Describes the refund policy.
	RefundPolicyDescription *string
	// contains filtered or unexported fields
}

Describes a support term.

type Tag 

type Tag struct {

	// Key for the tag.
	//
	// This member is required.
	Key *string

	// Value for the tag.
	//
	// This member is required.
	Value *string
	// contains filtered or unexported fields
}

Definition of the key/value pair for a tag.

type TeacherModelConfig added in v1.24.0 

type TeacherModelConfig struct {

	// The identifier of the teacher model.
	//
	// This member is required.
	TeacherModelIdentifier *string

	// The maximum number of tokens requested when the customization job invokes the
	// teacher model.
	MaxResponseLengthForInference *int32
	// contains filtered or unexported fields
}

Details about a teacher model used for model customization.

type TermDetails added in v1.37.0 

type TermDetails struct {

	// Describes the legal terms.
	//
	// This member is required.
	LegalTerm *LegalTerm

	// Describes the support terms.
	//
	// This member is required.
	SupportTerm *SupportTerm

	// Describes the usage-based pricing term.
	//
	// This member is required.
	UsageBasedPricingTerm *PricingTerm

	// Describes the validity terms.
	ValidityTerm *ValidityTerm
	// contains filtered or unexported fields
}

Describes the usage terms of an offer.

type TextInferenceConfig added in v1.23.0 

type TextInferenceConfig struct {

	// The maximum number of tokens to generate in the output text. Do not use the
	// minimum of 0 or the maximum of 65536. The limit values described here are
	// arbitrary values, for actual values consult the limits defined by your specific
	// model.
	MaxTokens *int32

	// A list of sequences of characters that, if generated, will cause the model to
	// stop generating further tokens. Do not use a minimum length of 1 or a maximum
	// length of 1000. The limit values described here are arbitrary values, for actual
	// values consult the limits defined by your specific model.
	StopSequences []string

	// Controls the random-ness of text generated by the language model, influencing
	// how much the model sticks to the most predictable next words versus exploring
	// more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model
	// outputs more deterministic or predictable, while a higher temperature (e.g. 0.8
	// or 0.9) makes the outputs more creative or unpredictable.
	Temperature *float32

	// A probability distribution threshold which controls what the model considers
	// for the set of possible next tokens. The model will only consider the top p% of
	// the probability distribution when generating the next token.
	TopP *float32
	// contains filtered or unexported fields
}

The configuration details for text generation using a language model via the RetrieveAndGenerate function.

type ThrottlingException 

type ThrottlingException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

The number of requests exceeds the limit. Resubmit your request later.

func (*ThrottlingException) Error 

func (e *ThrottlingException) Error() string

func (*ThrottlingException) ErrorCode 

func (e *ThrottlingException) ErrorCode() string

func (*ThrottlingException) ErrorFault 

func (e *ThrottlingException) ErrorFault() smithy.ErrorFault

func (*ThrottlingException) ErrorMessage 

func (e *ThrottlingException) ErrorMessage() string

type TooManyTagsException 

type TooManyTagsException struct {
	Message *string

	ErrorCodeOverride *string

	ResourceName *string
	// contains filtered or unexported fields
}

The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.

func (*TooManyTagsException) Error 

func (e *TooManyTagsException) Error() string

func (*TooManyTagsException) ErrorCode 

func (e *TooManyTagsException) ErrorCode() string

func (*TooManyTagsException) ErrorFault 

func (e *TooManyTagsException) ErrorFault() smithy.ErrorFault

func (*TooManyTagsException) ErrorMessage 

func (e *TooManyTagsException) ErrorMessage() string

type TrainingDataConfig 

type TrainingDataConfig struct {

	// Settings for using invocation logs to customize a model.
	InvocationLogsConfig *InvocationLogsConfig

	// The S3 URI where the training data is stored.
	S3Uri *string
	// contains filtered or unexported fields
}

S3 Location of the training data.

type TrainingDetails added in v1.33.0 

type TrainingDetails struct {

	// The start time of the training sub-task of the job.
	CreationTime *time.Time

	// The latest update to the training sub-task of the job.
	LastModifiedTime *time.Time

	// The status of the training sub-task of the job.
	Status JobStatusDetails
	// contains filtered or unexported fields
}

For a Distillation job, the status details for the training sub-task of the job.

type TrainingMetrics 

type TrainingMetrics struct {

	// Loss metric associated with the custom job.
	TrainingLoss *float32
	// contains filtered or unexported fields
}

Metrics associated with the custom job.

type UnknownUnionMember added in v1.8.0 

type UnknownUnionMember struct {
	Tag   string
	Value []byte
	// contains filtered or unexported fields
}

UnknownUnionMember is returned when a union member is returned over the wire, but has an unknown tag.

type ValidationDataConfig 

type ValidationDataConfig struct {

	// Information about the validators.
	//
	// This member is required.
	Validators []Validator
	// contains filtered or unexported fields
}

Array of up to 10 validators.

type ValidationDetails added in v1.33.0 

type ValidationDetails struct {

	// The start time of the validation sub-task of the job.
	CreationTime *time.Time

	// The latest update to the validation sub-task of the job.
	LastModifiedTime *time.Time

	// The status of the validation sub-task of the job.
	Status JobStatusDetails
	// contains filtered or unexported fields
}

For a Distillation job, the status details for the validation sub-task of the job.

type ValidationException 

type ValidationException struct {
	Message *string

	ErrorCodeOverride *string
	// contains filtered or unexported fields
}

Input validation failed. Check your request parameters and retry the request.

func (*ValidationException) Error 

func (e *ValidationException) Error() string

func (*ValidationException) ErrorCode 

func (e *ValidationException) ErrorCode() string

func (*ValidationException) ErrorFault 

func (e *ValidationException) ErrorFault() smithy.ErrorFault

func (*ValidationException) ErrorMessage 

func (e *ValidationException) ErrorMessage() string

type Validator 

type Validator struct {

	// The S3 URI where the validation data is stored.
	//
	// This member is required.
	S3Uri *string
	// contains filtered or unexported fields
}

Information about a validator.

type ValidatorMetric 

type ValidatorMetric struct {

	// The validation loss associated with this validator.
	ValidationLoss *float32
	// contains filtered or unexported fields
}

The metric for the validator.

type ValidityTerm added in v1.37.0 

type ValidityTerm struct {

	// Describes the agreement duration.
	AgreementDuration *string
	// contains filtered or unexported fields
}

Describes the validity terms.

type VectorSearchBedrockRerankingConfiguration added in v1.38.0 

type VectorSearchBedrockRerankingConfiguration struct {

	// Configuration for the Amazon Bedrock foundation model used for reranking. This
	// includes the model ARN and any additional request fields required by the model.
	//
	// This member is required.
	ModelConfiguration *VectorSearchBedrockRerankingModelConfiguration

	// Configuration for how document metadata should be used during the reranking
	// process. This determines which metadata fields are included when reordering
	// search results.
	MetadataConfiguration *MetadataConfigurationForReranking

	// The maximum number of results to rerank. This limits how many of the initial
	// vector search results will be processed by the reranking model. A smaller number
	// improves performance but may exclude potentially relevant results.
	NumberOfRerankedResults *int32
	// contains filtered or unexported fields
}

Configuration for using Amazon Bedrock foundation models to rerank Knowledge Base vector search results. This enables more sophisticated relevance ranking using large language models.

type VectorSearchBedrockRerankingModelConfiguration added in v1.38.0 

type VectorSearchBedrockRerankingModelConfiguration struct {

	// The Amazon Resource Name (ARN) of the foundation model to use for reranking.
	// This model processes the query and search results to determine a more relevant
	// ordering.
	//
	// This member is required.
	ModelArn *string

	// A list of additional fields to include in the model request during reranking.
	// These fields provide extra context or configuration options specific to the
	// selected foundation model.
	AdditionalModelRequestFields map[string]document.Interface
	// contains filtered or unexported fields
}

Configuration for the Amazon Bedrock foundation model used for reranking vector search results. This specifies which model to use and any additional parameters required by the model.

type VectorSearchRerankingConfiguration added in v1.38.0 

type VectorSearchRerankingConfiguration struct {

	// The type of reranking to apply to vector search results. Currently, the only
	// supported value is BEDROCK, which uses Amazon Bedrock foundation models for
	// reranking.
	//
	// This member is required.
	Type VectorSearchRerankingConfigurationType

	// Configuration for using Amazon Bedrock foundation models to rerank search
	// results. This is required when the reranking type is set to BEDROCK.
	BedrockRerankingConfiguration *VectorSearchBedrockRerankingConfiguration
	// contains filtered or unexported fields
}

Configuration for reranking vector search results to improve relevance. Reranking applies additional relevance models to reorder the initial vector search results based on more sophisticated criteria.

type VectorSearchRerankingConfigurationType added in v1.38.0 

type VectorSearchRerankingConfigurationType string
const (
	VectorSearchRerankingConfigurationTypeBedrockRerankingModel VectorSearchRerankingConfigurationType = "BEDROCK_RERANKING_MODEL"
)

Enum values for VectorSearchRerankingConfigurationType

func (VectorSearchRerankingConfigurationType) Values added in v1.38.0 

func (VectorSearchRerankingConfigurationType) Values() []VectorSearchRerankingConfigurationType

Values returns all known values for VectorSearchRerankingConfigurationType. Note that this can be expanded in the future, and so it is only as up to date as the client.

The ordering of this slice is not guaranteed to be stable across updates.

type VpcConfig 

type VpcConfig struct {

	// An array of IDs for each security group in the VPC to use.
	//
	// This member is required.
	SecurityGroupIds []string

	// An array of IDs for each subnet in the VPC to use.
	//
	// This member is required.
	SubnetIds []string
	// contains filtered or unexported fields
}

The configuration of a virtual private cloud (VPC). For more information, see Protect your data using Amazon Virtual Private Cloud and Amazon Web Services PrivateLink.

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.