All Classes and Interfaces
Class
Description
The request is denied because you do not have sufficient permissions to perform the requested action.
The model must request at least one tool (no text is generated).
Details about the specific guardrail that was applied during this assessment, including its identifier, version, ARN,
origin, and ownership information.
ApplyGuardrailRequest MarshallerAn AWS Arn.
Asynchronous invocation output data settings.
Asynchronous invocation output data settings.
A summary of an asynchronous invocation.
An audio content block that contains audio data in various supported formats.
The source of audio data, which can be provided either as raw bytes or a reference to an S3 location.
The Model automatically decides if a tool should be called or whether to generate text instead.
Service client for accessing Amazon Bedrock Runtime asynchronously.
A builder for creating an instance of
BedrockRuntimeAsyncClient.The parameters object used to resolve the auth schemes for the BedrockRuntime service.
A builder for a
BedrockRuntimeAuthSchemeParams.An auth scheme provider for BedrockRuntime service.
This includes configuration specific to Amazon Bedrock Runtime that is supported by both
BedrockRuntimeClientBuilder and BedrockRuntimeAsyncClientBuilder.Service client for accessing Amazon Bedrock Runtime.
A builder for creating an instance of
BedrockRuntimeClient.The parameters object used to resolve an endpoint for the BedrockRuntime service.
An endpoint provider for BedrockRuntime.
Class to expose the service client settings to the user.
A builder for creating a
BedrockRuntimeServiceClientConfiguration
Payload content for the bidirectional input.
BidirectionalInputPayloadPart Marshaller
Output from the bidirectional stream.
Cache creation metrics for a specific TTL duration
Defines a section of content to be cached for reuse in subsequent API calls.
Time-to-live duration for ephemeral cache entries
Contains information about a citation that references a specific source document.
Contains the generated text content that corresponds to or is supported by a citation from a source document.
Specifies the precise location within a source document where cited content can be found.
Configuration settings for enabling and controlling document citations in Converse API responses.
A content block that contains both generated text and associated citation information.
Contains incremental updates to citation information during streaming responses.
Contains the actual text content from a source document that is being cited or referenced in the model's response.
Contains incremental updates to the source content text during streaming responses, allowing clients to build up the
cited content progressively.
Error occurred because of a conflict while performing an operation.
A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API
operations.
A block of content in a streaming response.
The content block delta event.
Content block start information.
Content block start event.
A content block stop event.
Metrics for a call to Converse.
The output from a call to Converse.
ConverseRequest Marshaller
A conversation stream metadata event.
Metrics for the stream.
Base interface for all event types in ConverseStreamOutput.
The known possible types of events for
ConverseStreamOutput.ConverseStreamRequest MarshallerResponse handler for the ConverseStream API.
Builder for
ConverseStreamResponseHandler.Visitor for subtypes of
ConverseStreamOutput.Builder for
ConverseStreamResponseHandler.Visitor.
The trace object in a response from ConverseStream.
The inputs from a
Converse API request for token counting.
The trace object in a response from Converse.
The input value for token counting.
CountTokensRequest MarshallerA specialization of
software.amazon.awssdk.services.bedrockruntime.model.BidirectionalInputPayloadPart that
represents the InvokeModelWithBidirectionalStreamInput$chunk event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.BidirectionalOutputPayloadPart that
represents the InvokeModelWithBidirectionalStreamOutput$chunk event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.PayloadPart that represents the
ResponseStream$chunk event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.ContentBlockDeltaEvent that
represents the ConverseStreamOutput$contentBlockDelta event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.ContentBlockStartEvent that
represents the ConverseStreamOutput$contentBlockStart event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.ContentBlockStopEvent that
represents the ConverseStreamOutput$contentBlockStop event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.MessageStartEvent that represents
the ConverseStreamOutput$messageStart event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.MessageStopEvent that represents the
ConverseStreamOutput$messageStop event.A specialization of
software.amazon.awssdk.services.bedrockruntime.model.ConverseStreamMetadataEvent that
represents the ConverseStreamOutput$metadata event.
A document to include in a message.
Specifies a character-level location within a document, providing precise positioning information for cited content
using start and end character indices.
Specifies a chunk-level location within a document, providing positioning information for cited content using logical
document segments or chunks.
Contains the actual content of a document that can be processed by the model and potentially cited in the response.
Specifies a page-level location within a document, providing positioning information for cited content using page
numbers.
Contains the content of a document.
Link between an endpoint property and the
AwsEndpointAttribute it represents.
A block containing error information when content processing fails.
GetAsyncInvokeRequest Marshaller
A behavior assessment of the guardrail policies used in a call to the Converse API.
Represents a logical validation result from automated reasoning policy evaluation.
Indicates that no valid claims can be made due to logical contradictions in the premises or rules.
References a portion of the original input text that corresponds to logical elements.
Indicates that the claims are logically false and contradictory to the established rules or premises.
Identifies logical issues in the translated statements that exist independent of any policy rules, such as statements
that are always true or always false.
Indicates that no relevant logical information could be extracted from the input for validation.
Contains the results of automated reasoning policy evaluation, including logical findings about the validity of
claims made in the input content.
References a specific automated reasoning policy rule that was applied during evaluation.
Indicates that the claims could be either true or false depending on additional assumptions not provided in the
input.
Represents a logical scenario where claims can be evaluated as true or false, containing specific logical
assignments.
A logical statement that includes both formal logic representation and natural language explanation.
Indicates that the input exceeds the processing capacity due to the volume or complexity of the logical information.
Contains the logical translation of natural language input into formal logical statements, including premises,
claims, and confidence scores.
Indicates that the input has multiple valid logical interpretations, requiring additional context or clarification.
Represents one possible logical interpretation of ambiguous input content.
Indicates that the claims are definitively true and logically implied by the premises, with no possible alternative
interpretations.
The configuration for inline guardrail checks.
A content block within a message to evaluate.
The category for content filter evaluation.
The configuration for a single content filter category to evaluate.
The configuration for the content filter check, specifying which categories to evaluate.
The content filter check results.
The evaluation result for a single content filter category.
The text unit usage for the content filter check.
A message to evaluate against guardrail checks, containing a role and content blocks.
The category for prompt attack evaluation.
The configuration for a single prompt attack category to evaluate.
The configuration for the prompt attack check, specifying which categories to evaluate.
The prompt attack check results.
The evaluation result for a single prompt attack category.
The text unit usage for the prompt attack check.
The results from the guardrail checks evaluation, organized by check type.
The role of the message sender in the conversation.
The configuration for the sensitive information check, specifying which entity types to detect.
The configuration for a single sensitive information entity type to detect.
The type of personally identifiable information (PII) entity to detect.
The sensitive information check results.
The detection result for a single sensitive information entity found in the evaluated messages.
The text unit usage for the sensitive information check.
The text unit usage for the guardrail checks evaluation, organized by check type.
Configuration information for a guardrail that you use with the Converse operation.
The content block to be evaluated by the guardrail.
The content filter for a guardrail.
An assessment of a content policy for a guardrail.
The details for the guardrails contextual grounding filter.
The policy assessment details for the guardrails contextual grounding filter.
An image block that contains images that you want to assess with a guardrail.
The image source (image bytes) of the guardrail converse image source.
A text block that contains text that you want to assess with a guardrail.
The action of the guardrail coverage details.
A custom word configured in a guardrail.
Contain an image which user wants guarded.
The details of the guardrail image coverage.
The image source (image bytes) of the guardrail image source.
The invocation metrics for the guardrail.
A managed word configured in a guardrail.
The output content produced by the guardrail.
A Personally Identifiable Information (PII) entity configured in a guardrail.
A Regex filter configured in a guardrail.
The assessment for a Personally Identifiable Information (PII) policy.
Configuration information for a guardrail that you use with the ConverseStream
action.
The text block to be evaluated by the guardrail.
The guardrail coverage for the text characters.
Information about a topic guardrail.
A behavior assessment of a topic policy.
A Top level guardrail trace object.
The details on the use of the guardrail.
The word policy assessment.
Identifiers for variables declared within the rule engine, e.g.
Image content for a message.
A streaming delta event that contains incremental image data during streaming responses.
The initial event in a streaming image block that indicates the start of image content.
The source for an image.
Base inference parameters to pass to a model in a call to Converse or ConverseStream.
An internal server error occurred.
InvokeGuardrailChecksRequest MarshallerInvokeModelRequest Marshaller
The body of an
InvokeModel API request for token counting.Base interface for all event types in InvokeModelWithBidirectionalStreamInput.
The known possible types of events for
InvokeModelWithBidirectionalStreamInput.Base interface for all event types in InvokeModelWithBidirectionalStreamOutput.
The known possible types of events for
InvokeModelWithBidirectionalStreamOutput.InvokeModelWithBidirectionalStreamRequest MarshallerResponse handler for the InvokeModelWithBidirectionalStream API.
Builder for
InvokeModelWithBidirectionalStreamResponseHandler.Visitor for subtypes of
InvokeModelWithBidirectionalStreamOutput.InvokeModelWithResponseStreamRequest MarshallerResponse handler for the InvokeModelWithResponseStream API.
Builder for
InvokeModelWithResponseStreamResponseHandler.Visitor for subtypes of
ResponseStream.Builder for
InvokeModelWithResponseStreamResponseHandler.Visitor.
JSON schema structured output format options.
Represents the output for the
BedrockRuntimeClient.listAsyncInvokesPaginator(software.amazon.awssdk.services.bedrockruntime.model.ListAsyncInvokesRequest)
operation which is a paginated operation.
Represents the output for the
BedrockRuntimeAsyncClient.listAsyncInvokesPaginator(software.amazon.awssdk.services.bedrockruntime.model.ListAsyncInvokesRequest)
operation which is a paginated operation.ListAsyncInvokesRequest Marshaller
A message input, or returned from, a call to Converse or ConverseStream.
The start of a message.
The stop event for a message.
The request failed due to an error while processing the model.
The model specified in the request is not ready to serve inference requests.
An error occurred while streaming the response.
The request took too long to process.
Output configuration for a model response in a call to Converse or ConverseStream.
Structured output parameters to control the model's response.
The structure that the model's output must adhere to.
The type of structured output format.
Payload content included in the response.
Performance settings for a model.
A prompt router trace.
Contains a map of variables in a prompt from Prompt management to an object containing the values to fill in for them
when running model invocation.
Contains content regarding the reasoning that is carried out by the model with respect to the content in the content
block.
Contains content regarding the reasoning that is carried out by the model with respect to the content in the content
block.
Contains the reasoning that the model used to return the output.
The specified resource ARN was not found.
Base interface for all event types in ResponseStream.
The known possible types of events for
ResponseStream.Represents a URL to be used internally for endpoint resolution.
A storage location in an Amazon S3 bucket.
A search result block that enables natural citations with proper source attribution for retrieved content.
A block within a search result that contains the content.
Specifies a search result location within the content array, providing positioning information for cited content
using search result index and block positions.
Your request exceeds the service quota for your account.
Specifies the processing tier configuration used for serving the request.
The service isn't currently available.
The model must request a specific tool.
StartAsyncInvokeRequest Marshaller
Contains configurations for instructions to provide the model for how to handle input.
Specifies a system-defined tool for the model to use.
A tag.
Your request was denied due to exceeding the account quotas for Amazon Bedrock.
The tokens used in a message API inference call.
Information about a tool that you can use with the Converse API.
A content block for adding a tool to the available tool set mid-conversation.
Determines which tools the model should request in a call to
Converse or ConverseStream.
Configuration information for the tools that you pass to a model.
The schema for the tool.
A reference to a tool in the tool configuration.
A content block for removing a tool from the available tool set mid-conversation.
A tool result block that contains the results for a tool request that the model previously made.
Contains incremental updates to tool results information during streaming responses.
The start of a tool result block.
The tool result content block.
The specification for the tool.
A tool use content block.
The delta for a tool use block.
The start of a tool use block.
The input fails to satisfy the constraints specified by Amazon Bedrock.
Base class for the types of values computable by the
RuleEngine.An array value.
A boolean value.
An integer value.
A record (map) value.
A string value.
A video block.
A video source.
Provides the URL and domain information for the website that was cited when performing a web search.