Namespace Glitch9.AIDevKit.AmazonAws

Classes

Details about the specific guardrail that was applied during this assessment, including its identifier, version, ARN, origin, and ownership information.

AwsClient

Bedrock doesn't have Stability Image Generation models anymore. They have been replaced by Amazon Titan Image Generator models.

AwsDeleteRequestBase<TRequest>

AwsServiceResource

Represents an AWS service resource configuration (region endpoint). Each service type can only have one entry.

AwsSigV4Signer

Implements AWS Signature Version 4 signing.
Generates Authorization, x-amz-date and optional x-amz-security-token headers.

BedrockRequest_AI21Labs_Jurassic2

BedrockRequest_AI21Labs_Jurassic2.PenaltySettings

BedrockToolChoice

Specifies which tool the model should choose (if multiple available).

CachePointBlock

Defines a section of content to be cached for reuse in subsequent API calls.

CitationLocation.DocumentLocation

CitationLocation.SearchResultLocation

A content block that contains both generated text and associated citation information. This block type is returned when document citations are enabled, providing traceability between the generated content and the source documents that informed the response.

ContentBlock

ContentBlockDelta

ConverseMessage

ConverseMetrics

ConverseOutput

The output from a call to Converse. This is a union type. Only one member should be set.

ConverseRequest

ConverseResponse

ConverseStreamMetadataEvent

A conversation stream metadata event.

ConverseTokensRequest

ConverseTrace

CountTokensInput

The input value for token counting. The value should be either an InvokeModel or Converse request body.

CreateVocabularyFilterRequest

CreateVocabularyRequest

DeleteLexiconRequest

DeleteVocabularyFilterRequest

DeleteVocabularyRequest

DocumentBlock

DocumentBlock.DocumentSource

GetLexiconRequest

GetVocabularyFilterRequest

GetVocabularyRequest

GuardrailAssessment

A behavior assessment of the guardrail policies used in a call to the Converse API.

GuardrailAutomatedReasoningFinding

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

GuardrailAutomatedReasoningImpossibleFinding

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

GuardrailAutomatedReasoningInputTextReference

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

GuardrailAutomatedReasoningInvalidFinding

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

GuardrailAutomatedReasoningLogicWarning

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

GuardrailAutomatedReasoningPolicyAssessment

Represents a logical validation result from automated reasoning policy evaluation. The finding indicates whether claims in the input are logically valid, invalid, satisfiable, impossible, or have other logical issues.

GuardrailAutomatedReasoningRule

GuardrailAutomatedReasoningSatisfiableFinding

GuardrailAutomatedReasoningScenario

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

GuardrailAutomatedReasoningStatement

A logical statement that includes both formal logic representation and natural language explanation.

GuardrailAutomatedReasoningTranslation

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

GuardrailAutomatedReasoningTranslationAmbiguousFinding

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

GuardrailAutomatedReasoningTranslationOption

GuardrailAutomatedReasoningValidFinding

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

GuardrailConfiguration

GuardrailContentFilter

The content filter for a guardrail.

GuardrailContentPolicyAssessment

An assessment of a content policy for a guardrail.

GuardrailContextualGroundingFilter

The details for the guardrails contextual grounding filter.

GuardrailContextualGroundingPolicyAssessment

The policy assessment details for the guardrails contextual grounding filter.

GuardrailConverseContentBlock

A content block for selective guarding with the Converse or ConverseStream API operations.

GuardrailCoverage

The action of the guardrail coverage details.

GuardrailCoverage.GuardrailCoverageInfo

The details of the guardrail image coverage
The guardrail coverage for the text characters

GuardrailCustomWord

A custom word defined by the user for filtering purposes in a guardrail.

GuardrailInvocationMetrics

The invocation metrics for the guardrail.

GuardrailManagedWord

A managed word list provided by AWS to detect predefined categories of sensitive words.

GuardrailPiiEntityFilter

A Personally Identifiable Information (PII) entity configured in a guardrail.

GuardrailRegexFilter

A Personally Identifiable Information (PII) entity configured in a guardrail.

GuardrailSensitiveInformationPolicyAssessment

The assessment for a Personally Identifiable Information (PII) policy.

GuardrailTopic

Information about a topic guardrail.

GuardrailTopicPolicyAssessment

A behavior assessment of a topic policy.

GuardrailTraceAssessment

A Top level guardrail trace object.

GuardrailUsage

The details on the use of the guardrail.

GuardrailWordPolicyAssessment

The word policy assessment that includes both custom and managed word filters.

ImageBlock

Image content for a message.

InferenceConfiguration

InputSchema

LexiconRequest<TRequest, TResponse>

ListLexiconsRequest

ListVocabulariesRequest

ListVocabularyFiltersRequest

MarengoEmbedData

MarengoEmbedInput

MarengoEmbedInput.DynamicSegmentation

MarengoEmbedInput.FixedSegmentation

MarengoEmbedInput.MarengoSegmentation

MarengoEmbedRequest

MarengoEmbedRequestBase

Compatible with both Marengo Embed 2.7 and 3.0 models.

MarengoEmbedResponse

The response object for Marengo embed API. Compatible with both Marengo Embed 2.7 and 3.0 models.

MarengoLegacyEmbedRequest

For 2.7 legacy model compatibility.

MediaContentData

The source for an image.

PerformanceConfiguration

PromptRouterTrace

A trace object that indicates which model was invoked by the prompt router.

PutLexiconRequest

ReasoningContentBlock

Contains content regarding the reasoning that is carried out by the model with respect to the content in the content block. Reasoning refers to a Chain of Thought (CoT) that the model generates to enhance the accuracy of its final response.

ReasoningContentBlock.Content

ReasoningContentBlockDelta

SearchResultBlock

StabilityEraseRequest

StabilityGenerationRequest

StabilityInpaintingRequest

StabilityOutpaintingRequest

StabilityRequest

StabilityResponse

StabilitySearchAndRecolorRequest

StabilitySearchAndReplaceRequest

StabilityStyleTransferRequest

SystemTool

TextBlock

TextBlockDelta

TitanBackgroundRemovalParams

TitanColorGuidedGenerationParams

TitanEmbeddingRequest

TitanEmbeddingRequestBase

TitanEmbeddingResponse

TitanEmbeddingResponseBase

TitanImageGenerationConfig

TitanImageRequest

TitanImageResponse

TitanImageVariationParams

TitanInPaintingParams

TitanMultimodalEmbeddingRequest

TitanMultimodalEmbeddingRequest.Config

TitanMultimodalEmbeddingResponse

TitanOutPaintingParams

TitanTextToImageConditionedParams

TitanTextToImageParams

ToolConfiguration

ToolResultBlock

ToolResultBlock.ToolResultContentBlock

The tool result content block. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.

ToolResultBlockDelta

Contains incremental updates to tool results information during streaming responses. This allows clients to build up tool results data progressively as the response is generated.