{ "version": "2.0", "service": "

Describes the API operations for running inference using Amazon Bedrock models.

", "operations": { "ApplyGuardrail": "

The action to apply a guardrail.

", "Converse": "

Sends messages to the specified Amazon Bedrock model. Converse provides a consistent interface that works with all models that support messages. This allows you to write code once and use it with different models. If a model has unique inference parameters, you can also pass those unique parameters to the model.

Amazon Bedrock doesn't store any text, images, or documents that you provide as content. The data is only used to generate the response.

You can submit a prompt by including it in the messages field, specifying the modelId of a foundation model or inference profile to run inference on it, and including any other fields that are relevant to your use case.

You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the promptVariables field. You can append more messages to the prompt by using the messages field. If you use a prompt from Prompt management, you can't include the following fields in the request: additionalModelRequestFields, inferenceConfig, system, or toolConfig. Instead, these fields must be defined through Prompt management. For more information, see Use a prompt from Prompt management.

For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

For example code, see Converse API examples in the Amazon Bedrock User Guide.

This operation requires permission for the bedrock:InvokeModel action.

", "ConverseStream": "

Sends messages to the specified Amazon Bedrock model and returns the response in a stream. ConverseStream provides a consistent API that works with all Amazon Bedrock models that support messages. This allows you to write code once and use it with different models. Should a model have unique inference parameters, you can also pass those unique parameters to the model.

To find out if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

The CLI doesn't support streaming operations in Amazon Bedrock, including ConverseStream.

Amazon Bedrock doesn't store any text, images, or documents that you provide as content. The data is only used to generate the response.

You can submit a prompt by including it in the messages field, specifying the modelId of a foundation model or inference profile to run inference on it, and including any other fields that are relevant to your use case.

You can also submit a prompt from Prompt management by specifying the ARN of the prompt version and including a map of variables to values in the promptVariables field. You can append more messages to the prompt by using the messages field. If you use a prompt from Prompt management, you can't include the following fields in the request: additionalModelRequestFields, inferenceConfig, system, or toolConfig. Instead, these fields must be defined through Prompt management. For more information, see Use a prompt from Prompt management.

For information about the Converse API, see Use the Converse API in the Amazon Bedrock User Guide. To use a guardrail, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. To use a tool with a model, see Tool use (Function calling) in the Amazon Bedrock User Guide

For example code, see Conversation streaming example in the Amazon Bedrock User Guide.

This operation requires permission for the bedrock:InvokeModelWithResponseStream action.

", "InvokeModel": "

Invokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. You use model inference to generate text, images, and embeddings.

For example code, see Invoke model code examples in the Amazon Bedrock User Guide.

This operation requires permission for the bedrock:InvokeModel action.

", "InvokeModelWithResponseStream": "

Invoke the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a stream.

To see if a model supports streaming, call GetFoundationModel and check the responseStreamingSupported field in the response.

The CLI doesn't support streaming operations in Amazon Bedrock, including InvokeModelWithResponseStream.

For example code, see Invoke model with streaming code example in the Amazon Bedrock User Guide.

This operation requires permissions to perform the bedrock:InvokeModelWithResponseStream action.

" }, "shapes": { "AccessDeniedException": { "base": "

The request is denied because of missing access permissions.

", "refs": { } }, "AnyToolChoice": { "base": "

The model must request at least one tool (no text is generated). For example, {\"any\" : {}}.

", "refs": { "ToolChoice$any": "

The model must request at least one tool (no text is generated).

" } }, "ApplyGuardrailRequest": { "base": null, "refs": { } }, "ApplyGuardrailResponse": { "base": null, "refs": { } }, "AutoToolChoice": { "base": "

The Model automatically decides if a tool should be called or whether to generate text instead. For example, {\"auto\" : {}}.

", "refs": { "ToolChoice$auto": "

(Default). The Model automatically decides if a tool should be called or whether to generate text instead.

" } }, "Body": { "base": null, "refs": { "InvokeModelRequest$body": "

The prompt and inference parameters in the format specified in the contentType in the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to Inference parameters. For more information, see Run inference in the Bedrock User Guide.

", "InvokeModelResponse$body": "

Inference response from the model in the format specified in the contentType header. To see the format and content of the request and response bodies for different models, refer to Inference parameters.

", "InvokeModelWithResponseStreamRequest$body": "

The prompt and inference parameters in the format specified in the contentType in the header. You must provide the body in JSON format. To see the format and content of the request and response bodies for different models, refer to Inference parameters. For more information, see Run inference in the Bedrock User Guide.

" } }, "ContentBlock": { "base": "

A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.

", "refs": { "ContentBlocks$member": null } }, "ContentBlockDelta": { "base": "

A bock of content in a streaming response.

", "refs": { "ContentBlockDeltaEvent$delta": "

The delta for a content block delta event.

" } }, "ContentBlockDeltaEvent": { "base": "

The content block delta event.

", "refs": { "ConverseStreamOutput$contentBlockDelta": "

The messages output content block delta.

" } }, "ContentBlockStart": { "base": "

Content block start information.

", "refs": { "ContentBlockStartEvent$start": "

Start information about a content block start event.

" } }, "ContentBlockStartEvent": { "base": "

Content block start event.

", "refs": { "ConverseStreamOutput$contentBlockStart": "

Start information for a content block.

" } }, "ContentBlockStopEvent": { "base": "

A content block stop event.

", "refs": { "ConverseStreamOutput$contentBlockStop": "

Stop information for a content block.

" } }, "ContentBlocks": { "base": null, "refs": { "Message$content": "

The message content. Note the following restrictions:

" } }, "ConversationRole": { "base": null, "refs": { "Message$role": "

The role that the message plays in the message.

", "MessageStartEvent$role": "

The role for the message.

" } }, "ConversationalModelId": { "base": null, "refs": { "ConverseRequest$modelId": "

Specifies the model or throughput with which to run inference, or the prompt resource to use in inference. The value depends on the resource that you use:

The Converse API doesn't support imported models.

", "ConverseStreamRequest$modelId": "

Specifies the model or throughput with which to run inference, or the prompt resource to use in inference. The value depends on the resource that you use:

The Converse API doesn't support imported models.

" } }, "ConverseMetrics": { "base": "

Metrics for a call to Converse.

", "refs": { "ConverseResponse$metrics": "

Metrics for the call to Converse.

" } }, "ConverseOutput": { "base": "

The output from a call to Converse.

", "refs": { "ConverseResponse$output": "

The result from the call to Converse.

" } }, "ConverseRequest": { "base": null, "refs": { } }, "ConverseRequestAdditionalModelResponseFieldPathsList": { "base": null, "refs": { "ConverseRequest$additionalModelResponseFieldPaths": "

Additional model parameters field paths to return in the response. Converse and ConverseStream return the requested fields as a JSON Pointer object in the additionalModelResponseFields field. The following is example JSON for additionalModelResponseFieldPaths.

[ \"/stop_sequence\" ]

For information about the JSON Pointer syntax, see the Internet Engineering Task Force (IETF) documentation.

Converse and ConverseStream reject an empty JSON Pointer or incorrectly structured JSON Pointer with a 400 error code. if the JSON Pointer is valid, but the requested field is not in the model response, it is ignored by Converse.

" } }, "ConverseRequestAdditionalModelResponseFieldPathsListMemberString": { "base": null, "refs": { "ConverseRequestAdditionalModelResponseFieldPathsList$member": null } }, "ConverseResponse": { "base": null, "refs": { } }, "ConverseStreamMetadataEvent": { "base": "

A conversation stream metadata event.

", "refs": { "ConverseStreamOutput$metadata": "

Metadata for the converse output stream.

" } }, "ConverseStreamMetrics": { "base": "

Metrics for the stream.

", "refs": { "ConverseStreamMetadataEvent$metrics": "

The metrics for the conversation stream metadata event.

" } }, "ConverseStreamOutput": { "base": "

The messages output stream

", "refs": { "ConverseStreamResponse$stream": "

The output stream that the model generated.

" } }, "ConverseStreamRequest": { "base": null, "refs": { } }, "ConverseStreamRequestAdditionalModelResponseFieldPathsList": { "base": null, "refs": { "ConverseStreamRequest$additionalModelResponseFieldPaths": "

Additional model parameters field paths to return in the response. Converse and ConverseStream return the requested fields as a JSON Pointer object in the additionalModelResponseFields field. The following is example JSON for additionalModelResponseFieldPaths.

[ \"/stop_sequence\" ]

For information about the JSON Pointer syntax, see the Internet Engineering Task Force (IETF) documentation.

Converse and ConverseStream reject an empty JSON Pointer or incorrectly structured JSON Pointer with a 400 error code. if the JSON Pointer is valid, but the requested field is not in the model response, it is ignored by Converse.

" } }, "ConverseStreamRequestAdditionalModelResponseFieldPathsListMemberString": { "base": null, "refs": { "ConverseStreamRequestAdditionalModelResponseFieldPathsList$member": null } }, "ConverseStreamResponse": { "base": null, "refs": { } }, "ConverseStreamTrace": { "base": "

The trace object in a response from ConverseStream. Currently, you can only trace guardrails.

", "refs": { "ConverseStreamMetadataEvent$trace": "

The trace object in the response from ConverseStream that contains information about the guardrail behavior.

" } }, "ConverseTrace": { "base": "

The trace object in a response from Converse. Currently, you can only trace guardrails.

", "refs": { "ConverseResponse$trace": "

A trace object that contains information about the Guardrail behavior.

" } }, "Document": { "base": null, "refs": { "ConverseRequest$additionalModelRequestFields": "

Additional inference parameters that the model supports, beyond the base set of inference parameters that Converse and ConverseStream support in the inferenceConfig field. For more information, see Model parameters.

", "ConverseResponse$additionalModelResponseFields": "

Additional fields in the response that are unique to the model.

", "ConverseStreamRequest$additionalModelRequestFields": "

Additional inference parameters that the model supports, beyond the base set of inference parameters that Converse and ConverseStream support in the inferenceConfig field. For more information, see Model parameters.

", "MessageStopEvent$additionalModelResponseFields": "

The additional model response fields.

", "ToolInputSchema$json": "

The JSON schema for the tool. For more information, see JSON Schema Reference.

", "ToolResultContentBlock$json": "

A tool result that is JSON format data.

", "ToolUseBlock$input": "

The input to pass to the tool.

" } }, "DocumentBlock": { "base": "

A document to include in a message.

", "refs": { "ContentBlock$document": "

A document to include in the message.

", "ToolResultContentBlock$document": "

A tool result that is a document.

" } }, "DocumentBlockNameString": { "base": null, "refs": { "DocumentBlock$name": "

A name for the document. The name can only contain the following characters:

This field is vulnerable to prompt injections, because the model might inadvertently interpret it as instructions. Therefore, we recommend that you specify a neutral name.

" } }, "DocumentFormat": { "base": null, "refs": { "DocumentBlock$format": "

The format of a document, or its extension.

" } }, "DocumentSource": { "base": "

Contains the content of a document.

", "refs": { "DocumentBlock$source": "

Contains the content of the document.

" } }, "DocumentSourceBytesBlob": { "base": null, "refs": { "DocumentSource$bytes": "

The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.

" } }, "GuardrailAction": { "base": null, "refs": { "ApplyGuardrailResponse$action": "

The action taken in the response from the guardrail.

" } }, "GuardrailAssessment": { "base": "

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

", "refs": { "GuardrailAssessmentList$member": null, "GuardrailAssessmentMap$value": null } }, "GuardrailAssessmentList": { "base": null, "refs": { "ApplyGuardrailResponse$assessments": "

The assessment details in the response from the guardrail.

", "GuardrailAssessmentListMap$value": null } }, "GuardrailAssessmentListMap": { "base": null, "refs": { "GuardrailTraceAssessment$outputAssessments": "

the output assessments.

" } }, "GuardrailAssessmentMap": { "base": null, "refs": { "GuardrailTraceAssessment$inputAssessment": "

The input assessment.

" } }, "GuardrailConfiguration": { "base": "

Configuration information for a guardrail that you use with the Converse operation.

", "refs": { "ConverseRequest$guardrailConfig": "

Configuration information for a guardrail that you want to use in the request. If you include guardContent blocks in the content field in the messages field, the guardrail operates only on those messages. If you include no guardContent blocks, the guardrail operates on all messages in the request body and in any included prompt resource.

" } }, "GuardrailContentBlock": { "base": "

The content block to be evaluated by the guardrail.

", "refs": { "GuardrailContentBlockList$member": null } }, "GuardrailContentBlockList": { "base": null, "refs": { "ApplyGuardrailRequest$content": "

The content details used in the request to apply the guardrail.

" } }, "GuardrailContentFilter": { "base": "

The content filter for a guardrail.

", "refs": { "GuardrailContentFilterList$member": null } }, "GuardrailContentFilterConfidence": { "base": null, "refs": { "GuardrailContentFilter$confidence": "

The guardrail confidence.

" } }, "GuardrailContentFilterList": { "base": null, "refs": { "GuardrailContentPolicyAssessment$filters": "

The content policy filters.

" } }, "GuardrailContentFilterStrength": { "base": null, "refs": { "GuardrailContentFilter$filterStrength": "

The filter strength setting for the guardrail content filter.

" } }, "GuardrailContentFilterType": { "base": null, "refs": { "GuardrailContentFilter$type": "

The guardrail type.

" } }, "GuardrailContentPolicyAction": { "base": null, "refs": { "GuardrailContentFilter$action": "

The guardrail action.

" } }, "GuardrailContentPolicyAssessment": { "base": "

An assessment of a content policy for a guardrail.

", "refs": { "GuardrailAssessment$contentPolicy": "

The content policy.

" } }, "GuardrailContentPolicyUnitsProcessed": { "base": null, "refs": { "GuardrailUsage$contentPolicyUnits": "

The content policy units processed by the guardrail.

" } }, "GuardrailContentQualifier": { "base": null, "refs": { "GuardrailContentQualifierList$member": null } }, "GuardrailContentQualifierList": { "base": null, "refs": { "GuardrailTextBlock$qualifiers": "

The qualifiers describing the text block.

" } }, "GuardrailContentSource": { "base": null, "refs": { "ApplyGuardrailRequest$source": "

The source of data used in the request to apply the guardrail.

" } }, "GuardrailContextualGroundingFilter": { "base": "

The details for the guardrails contextual grounding filter.

", "refs": { "GuardrailContextualGroundingFilters$member": null } }, "GuardrailContextualGroundingFilterScoreDouble": { "base": null, "refs": { "GuardrailContextualGroundingFilter$score": "

The score generated by contextual grounding filter.

" } }, "GuardrailContextualGroundingFilterThresholdDouble": { "base": null, "refs": { "GuardrailContextualGroundingFilter$threshold": "

The threshold used by contextual grounding filter to determine whether the content is grounded or not.

" } }, "GuardrailContextualGroundingFilterType": { "base": null, "refs": { "GuardrailContextualGroundingFilter$type": "

The contextual grounding filter type.

" } }, "GuardrailContextualGroundingFilters": { "base": null, "refs": { "GuardrailContextualGroundingPolicyAssessment$filters": "

The filter details for the guardrails contextual grounding filter.

" } }, "GuardrailContextualGroundingPolicyAction": { "base": null, "refs": { "GuardrailContextualGroundingFilter$action": "

The action performed by the guardrails contextual grounding filter.

" } }, "GuardrailContextualGroundingPolicyAssessment": { "base": "

The policy assessment details for the guardrails contextual grounding filter.

", "refs": { "GuardrailAssessment$contextualGroundingPolicy": "

The contextual grounding policy used for the guardrail assessment.

" } }, "GuardrailContextualGroundingPolicyUnitsProcessed": { "base": null, "refs": { "GuardrailUsage$contextualGroundingPolicyUnits": "

The contextual grounding policy units processed by the guardrail.

" } }, "GuardrailConverseContentBlock": { "base": "

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

", "refs": { "ContentBlock$guardContent": "

Contains the content to assess with the guardrail. If you don't specify guardContent in a call to the Converse API, the guardrail (if passed in the Converse API) assesses the entire message.

For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide. 

 </p>
", "SystemContentBlock$guardContent": "

A content block to assess with the guardrail. Use with the Converse or ConverseStream API operations.

For more information, see Use a guardrail with the Converse API in the Amazon Bedrock User Guide.

" } }, "GuardrailConverseContentQualifier": { "base": null, "refs": { "GuardrailConverseContentQualifierList$member": null } }, "GuardrailConverseContentQualifierList": { "base": null, "refs": { "GuardrailConverseTextBlock$qualifiers": "

The qualifier details for the guardrails contextual grounding filter.

" } }, "GuardrailConverseTextBlock": { "base": "

A text block that contains text that you want to assess with a guardrail. For more information, see GuardrailConverseContentBlock.

", "refs": { "GuardrailConverseContentBlock$text": "

The text to guard.

" } }, "GuardrailCoverage": { "base": "

The action of the guardrail coverage details.

", "refs": { "ApplyGuardrailResponse$guardrailCoverage": "

The guardrail coverage details in the apply guardrail response.

", "GuardrailInvocationMetrics$guardrailCoverage": "

The coverage details for the guardrail invocation metrics.

" } }, "GuardrailCustomWord": { "base": "

A custom word configured in a guardrail.

", "refs": { "GuardrailCustomWordList$member": null } }, "GuardrailCustomWordList": { "base": null, "refs": { "GuardrailWordPolicyAssessment$customWords": "

Custom words in the assessment.

" } }, "GuardrailIdentifier": { "base": null, "refs": { "ApplyGuardrailRequest$guardrailIdentifier": "

The guardrail identifier used in the request to apply the guardrail.

", "GuardrailConfiguration$guardrailIdentifier": "

The identifier for the guardrail.

", "GuardrailStreamConfiguration$guardrailIdentifier": "

The identifier for the guardrail.

", "InvokeModelRequest$guardrailIdentifier": "

The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.

An error will be thrown in the following situations.

", "InvokeModelWithResponseStreamRequest$guardrailIdentifier": "

The unique identifier of the guardrail that you want to use. If you don't provide a value, no guardrail is applied to the invocation.

An error is thrown in the following situations.

" } }, "GuardrailInvocationMetrics": { "base": "

The invocation metrics for the guardrail.

", "refs": { "GuardrailAssessment$invocationMetrics": "

The invocation metrics for the guardrail assessment.

" } }, "GuardrailManagedWord": { "base": "

A managed word configured in a guardrail.

", "refs": { "GuardrailManagedWordList$member": null } }, "GuardrailManagedWordList": { "base": null, "refs": { "GuardrailWordPolicyAssessment$managedWordLists": "

Managed word lists in the assessment.

" } }, "GuardrailManagedWordType": { "base": null, "refs": { "GuardrailManagedWord$type": "

The type for the managed word.

" } }, "GuardrailOutputContent": { "base": "

The output content produced by the guardrail.

", "refs": { "GuardrailOutputContentList$member": null } }, "GuardrailOutputContentList": { "base": null, "refs": { "ApplyGuardrailResponse$outputs": "

The output details in the response from the guardrail.

" } }, "GuardrailOutputText": { "base": null, "refs": { "GuardrailOutputContent$text": "

The specific text for the output content produced by the guardrail.

", "ModelOutputs$member": null } }, "GuardrailPiiEntityFilter": { "base": "

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

", "refs": { "GuardrailPiiEntityFilterList$member": null } }, "GuardrailPiiEntityFilterList": { "base": null, "refs": { "GuardrailSensitiveInformationPolicyAssessment$piiEntities": "

The PII entities in the assessment.

" } }, "GuardrailPiiEntityType": { "base": null, "refs": { "GuardrailPiiEntityFilter$type": "

The PII entity filter type.

" } }, "GuardrailProcessingLatency": { "base": null, "refs": { "GuardrailInvocationMetrics$guardrailProcessingLatency": "

The processing latency details for the guardrail invocation metrics.

" } }, "GuardrailRegexFilter": { "base": "

A Regex filter configured in a guardrail.

", "refs": { "GuardrailRegexFilterList$member": null } }, "GuardrailRegexFilterList": { "base": null, "refs": { "GuardrailSensitiveInformationPolicyAssessment$regexes": "

The regex queries in the assessment.

" } }, "GuardrailSensitiveInformationPolicyAction": { "base": null, "refs": { "GuardrailPiiEntityFilter$action": "

The PII entity filter action.

", "GuardrailRegexFilter$action": "

The region filter action.

" } }, "GuardrailSensitiveInformationPolicyAssessment": { "base": "

The assessment for aPersonally Identifiable Information (PII) policy.

", "refs": { "GuardrailAssessment$sensitiveInformationPolicy": "

The sensitive information policy.

" } }, "GuardrailSensitiveInformationPolicyFreeUnitsProcessed": { "base": null, "refs": { "GuardrailUsage$sensitiveInformationPolicyFreeUnits": "

The sensitive information policy free units processed by the guardrail.

" } }, "GuardrailSensitiveInformationPolicyUnitsProcessed": { "base": null, "refs": { "GuardrailUsage$sensitiveInformationPolicyUnits": "

The sensitive information policy units processed by the guardrail.

" } }, "GuardrailStreamConfiguration": { "base": "

Configuration information for a guardrail that you use with the ConverseStream action.

", "refs": { "ConverseStreamRequest$guardrailConfig": "

Configuration information for a guardrail that you want to use in the request. If you include guardContent blocks in the content field in the messages field, the guardrail operates only on those messages. If you include no guardContent blocks, the guardrail operates on all messages in the request body and in any included prompt resource.

" } }, "GuardrailStreamProcessingMode": { "base": null, "refs": { "GuardrailStreamConfiguration$streamProcessingMode": "

The processing mode.

The processing mode. For more information, see Configure streaming response behavior in the Amazon Bedrock User Guide.

" } }, "GuardrailTextBlock": { "base": "

The text block to be evaluated by the guardrail.

", "refs": { "GuardrailContentBlock$text": "

Text within content block to be evaluated by the guardrail.

" } }, "GuardrailTextCharactersCoverage": { "base": "

The guardrail coverage for the text characters.

", "refs": { "GuardrailCoverage$textCharacters": "

The text characters of the guardrail coverage details.

" } }, "GuardrailTopic": { "base": "

Information about a topic guardrail.

", "refs": { "GuardrailTopicList$member": null } }, "GuardrailTopicList": { "base": null, "refs": { "GuardrailTopicPolicyAssessment$topics": "

The topics in the assessment.

" } }, "GuardrailTopicPolicyAction": { "base": null, "refs": { "GuardrailTopic$action": "

The action the guardrail should take when it intervenes on a topic.

" } }, "GuardrailTopicPolicyAssessment": { "base": "

A behavior assessment of a topic policy.

", "refs": { "GuardrailAssessment$topicPolicy": "

The topic policy.

" } }, "GuardrailTopicPolicyUnitsProcessed": { "base": null, "refs": { "GuardrailUsage$topicPolicyUnits": "

The topic policy units processed by the guardrail.

" } }, "GuardrailTopicType": { "base": null, "refs": { "GuardrailTopic$type": "

The type behavior that the guardrail should perform when the model detects the topic.

" } }, "GuardrailTrace": { "base": null, "refs": { "GuardrailConfiguration$trace": "

The trace behavior for the guardrail.

", "GuardrailStreamConfiguration$trace": "

The trace behavior for the guardrail.

" } }, "GuardrailTraceAssessment": { "base": "

A Top level guardrail trace object. For more information, see ConverseTrace.

", "refs": { "ConverseStreamTrace$guardrail": "

The guardrail trace object.

", "ConverseTrace$guardrail": "

The guardrail trace object.

" } }, "GuardrailUsage": { "base": "

The details on the use of the guardrail.

", "refs": { "ApplyGuardrailResponse$usage": "

The usage details in the response from the guardrail.

", "GuardrailInvocationMetrics$usage": "

The usage details for the guardrail invocation metrics.

" } }, "GuardrailVersion": { "base": null, "refs": { "ApplyGuardrailRequest$guardrailVersion": "

The guardrail version used in the request to apply the guardrail.

", "GuardrailConfiguration$guardrailVersion": "

The version of the guardrail.

", "GuardrailStreamConfiguration$guardrailVersion": "

The version of the guardrail.

", "InvokeModelRequest$guardrailVersion": "

The version number for the guardrail. The value can also be DRAFT.

", "InvokeModelWithResponseStreamRequest$guardrailVersion": "

The version number for the guardrail. The value can also be DRAFT.

" } }, "GuardrailWordPolicyAction": { "base": null, "refs": { "GuardrailCustomWord$action": "

The action for the custom word.

", "GuardrailManagedWord$action": "

The action for the managed word.

" } }, "GuardrailWordPolicyAssessment": { "base": "

The word policy assessment.

", "refs": { "GuardrailAssessment$wordPolicy": "

The word policy.

" } }, "GuardrailWordPolicyUnitsProcessed": { "base": null, "refs": { "GuardrailUsage$wordPolicyUnits": "

The word policy units processed by the guardrail.

" } }, "ImageBlock": { "base": "

Image content for a message.

", "refs": { "ContentBlock$image": "

Image to include in the message.

This field is only supported by Anthropic Claude 3 models.

", "ToolResultContentBlock$image": "

A tool result that is an image.

This field is only supported by Anthropic Claude 3 models.

" } }, "ImageFormat": { "base": null, "refs": { "ImageBlock$format": "

The format of the image.

" } }, "ImageSource": { "base": "

The source for an image.

", "refs": { "ImageBlock$source": "

The source for the image.

" } }, "ImageSourceBytesBlob": { "base": null, "refs": { "ImageSource$bytes": "

The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.

" } }, "InferenceConfiguration": { "base": "

Base inference parameters to pass to a model in a call to Converse or ConverseStream. For more information, see Inference parameters for foundation models.

If you need to pass additional parameters that the model supports, use the additionalModelRequestFields request field in the call to Converse or ConverseStream. For more information, see Model parameters.

", "refs": { "ConverseRequest$inferenceConfig": "

Inference parameters to pass to the model. Converse and ConverseStream support a base set of inference parameters. If you need to pass additional parameters that the model supports, use the additionalModelRequestFields request field.

", "ConverseStreamRequest$inferenceConfig": "

Inference parameters to pass to the model. Converse and ConverseStream support a base set of inference parameters. If you need to pass additional parameters that the model supports, use the additionalModelRequestFields request field.

" } }, "InferenceConfigurationMaxTokensInteger": { "base": null, "refs": { "InferenceConfiguration$maxTokens": "

The maximum number of tokens to allow in the generated response. The default value is the maximum allowed value for the model that you are using. For more information, see Inference parameters for foundation models.

" } }, "InferenceConfigurationStopSequencesList": { "base": null, "refs": { "InferenceConfiguration$stopSequences": "

A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.

" } }, "InferenceConfigurationTemperatureFloat": { "base": null, "refs": { "InferenceConfiguration$temperature": "

The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.

The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.

" } }, "InferenceConfigurationTopPFloat": { "base": null, "refs": { "InferenceConfiguration$topP": "

The percentage of most-likely candidates that the model considers for the next token. For example, if you choose a value of 0.8 for topP, the model selects from the top 80% of the probability distribution of tokens that could be next in the sequence.

The default value is the default value for the model that you are using. For more information, see Inference parameters for foundation models.

" } }, "InternalServerException": { "base": "

An internal server error occurred. Retry your request.

", "refs": { "ConverseStreamOutput$internalServerException": "

An internal server error occurred. Retry your request.

", "ResponseStream$internalServerException": "

An internal server error occurred. Retry your request.

" } }, "InvokeModelIdentifier": { "base": null, "refs": { "InvokeModelRequest$modelId": "

The unique identifier of the model to invoke to run inference.

The modelId to provide depends on the type of model that you use:

", "InvokeModelWithResponseStreamRequest$modelId": "

The unique identifier of the model to invoke to run inference.

The modelId to provide depends on the type of model that you use:

" } }, "InvokeModelRequest": { "base": null, "refs": { } }, "InvokeModelResponse": { "base": null, "refs": { } }, "InvokeModelWithResponseStreamRequest": { "base": null, "refs": { } }, "InvokeModelWithResponseStreamResponse": { "base": null, "refs": { } }, "Long": { "base": null, "refs": { "ConverseMetrics$latencyMs": "

The latency of the call to Converse, in milliseconds.

", "ConverseStreamMetrics$latencyMs": "

The latency for the streaming request, in milliseconds.

" } }, "Message": { "base": "

A message input, or returned from, a call to Converse or ConverseStream.

", "refs": { "ConverseOutput$message": "

The message that the model generates.

", "Messages$member": null } }, "MessageStartEvent": { "base": "

The start of a message.

", "refs": { "ConverseStreamOutput$messageStart": "

Message start information.

" } }, "MessageStopEvent": { "base": "

The stop event for a message.

", "refs": { "ConverseStreamOutput$messageStop": "

Message stop information.

" } }, "Messages": { "base": null, "refs": { "ConverseRequest$messages": "

The messages that you want to send to the model.

", "ConverseStreamRequest$messages": "

The messages that you want to send to the model.

" } }, "MimeType": { "base": null, "refs": { "InvokeModelRequest$contentType": "

The MIME type of the input data in the request. You must specify application/json.

", "InvokeModelRequest$accept": "

The desired MIME type of the inference body in the response. The default value is application/json.

", "InvokeModelResponse$contentType": "

The MIME type of the inference result.

", "InvokeModelWithResponseStreamRequest$contentType": "

The MIME type of the input data in the request. You must specify application/json.

", "InvokeModelWithResponseStreamRequest$accept": "

The desired MIME type of the inference body in the response. The default value is application/json.

", "InvokeModelWithResponseStreamResponse$contentType": "

The MIME type of the inference result.

" } }, "ModelErrorException": { "base": "

The request failed due to an error while processing the model.

", "refs": { } }, "ModelNotReadyException": { "base": "

The model specified in the request is not ready to serve inference requests. The AWS SDK will automatically retry the operation up to 5 times. For information about configuring automatic retries, see Retry behavior in the AWS SDKs and Tools reference guide.

", "refs": { } }, "ModelOutputs": { "base": null, "refs": { "GuardrailTraceAssessment$modelOutput": "

The output from the model.

" } }, "ModelStreamErrorException": { "base": "

An error occurred while streaming the response. Retry your request.

", "refs": { "ConverseStreamOutput$modelStreamErrorException": "

A streaming error occurred. Retry your request.

", "ResponseStream$modelStreamErrorException": "

An error occurred while streaming the response. Retry your request.

" } }, "ModelTimeoutException": { "base": "

The request took too long to process. Processing time exceeded the model timeout length.

", "refs": { "ResponseStream$modelTimeoutException": "

The request took too long to process. Processing time exceeded the model timeout length.

" } }, "NonBlankString": { "base": null, "refs": { "AccessDeniedException$message": null, "InternalServerException$message": null, "ModelErrorException$message": null, "ModelErrorException$resourceName": "

The resource name.

", "ModelNotReadyException$message": null, "ModelStreamErrorException$message": null, "ModelStreamErrorException$originalMessage": "

The original message.

", "ModelTimeoutException$message": null, "ResourceNotFoundException$message": null, "ServiceQuotaExceededException$message": null, "ServiceUnavailableException$message": null, "ThrottlingException$message": null, "ValidationException$message": null } }, "NonEmptyString": { "base": null, "refs": { "InferenceConfigurationStopSequencesList$member": null, "SystemContentBlock$text": "

A system prompt for the model.

", "ToolSpecification$description": "

The description for the tool.

" } }, "NonNegativeInteger": { "base": null, "refs": { "ContentBlockDeltaEvent$contentBlockIndex": "

The block index for a content block delta event.

", "ContentBlockStartEvent$contentBlockIndex": "

The index for a content block start event.

", "ContentBlockStopEvent$contentBlockIndex": "

The index for a content block.

" } }, "PartBody": { "base": null, "refs": { "PayloadPart$bytes": "

Base64-encoded bytes of payload data.

" } }, "PayloadPart": { "base": "

Payload content included in the response.

", "refs": { "ResponseStream$chunk": "

Content included in the response.

" } }, "PromptVariableMap": { "base": null, "refs": { "ConverseRequest$promptVariables": "

Contains a map of variables in a prompt from Prompt management to objects containing the values to fill in for them when running model invocation. This field is ignored if you don't specify a prompt resource in the modelId field.

", "ConverseStreamRequest$promptVariables": "

Contains a map of variables in a prompt from Prompt management to objects containing the values to fill in for them when running model invocation. This field is ignored if you don't specify a prompt resource in the modelId field.

" } }, "PromptVariableValues": { "base": "

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. For more information, see How Prompt management works.

", "refs": { "PromptVariableMap$value": null } }, "ResourceNotFoundException": { "base": "

The specified resource ARN was not found. Check the ARN and try your request again.

", "refs": { } }, "ResponseStream": { "base": "

Definition of content in the response stream.

", "refs": { "InvokeModelWithResponseStreamResponse$body": "

Inference response from the model in the format specified by the contentType header. To see the format and content of this field for different models, refer to Inference parameters.

" } }, "ServiceQuotaExceededException": { "base": "

Your request exceeds the service quota for your account. You can view your quotas at Viewing service quotas. You can resubmit your request later.

", "refs": { } }, "ServiceUnavailableException": { "base": "

The service isn't currently available. Try again later.

", "refs": { "ConverseStreamOutput$serviceUnavailableException": "

The service isn't currently available. Try again later.

", "ResponseStream$serviceUnavailableException": null } }, "SpecificToolChoice": { "base": "

The model must request a specific tool. For example, {\"tool\" : {\"name\" : \"Your tool name\"}}.

This field is only supported by Anthropic Claude 3 models.

", "refs": { "ToolChoice$tool": "

The Model must request the specified tool. Only supported by Anthropic Claude 3 models.

" } }, "StatusCode": { "base": null, "refs": { "ModelErrorException$originalStatusCode": "

The original status code.

", "ModelStreamErrorException$originalStatusCode": "

The original status code.

" } }, "StopReason": { "base": null, "refs": { "ConverseResponse$stopReason": "

The reason why the model stopped generating output.

", "MessageStopEvent$stopReason": "

The reason why the model stopped generating output.

" } }, "String": { "base": null, "refs": { "ContentBlock$text": "

Text to include in the message.

", "ContentBlockDelta$text": "

The content text.

", "GuardrailAssessmentListMap$key": null, "GuardrailAssessmentMap$key": null, "GuardrailConverseTextBlock$text": "

The text that you want to guard.

", "GuardrailCustomWord$match": "

The match for the custom word.

", "GuardrailManagedWord$match": "

The match for the managed word.

", "GuardrailPiiEntityFilter$match": "

The PII entity filter match.

", "GuardrailRegexFilter$name": "

The regex filter name.

", "GuardrailRegexFilter$match": "

The regesx filter match.

", "GuardrailRegexFilter$regex": "

The regex query.

", "GuardrailTextBlock$text": "

The input text details to be evaluated by the guardrail.

", "GuardrailTopic$name": "

The name for the guardrail.

", "PromptVariableMap$key": null, "PromptVariableValues$text": "

The text value that the variable maps to.

", "ToolResultContentBlock$text": "

A tool result that is text.

", "ToolUseBlockDelta$input": "

The input for a requested tool.

" } }, "SystemContentBlock": { "base": "

A system content block.

", "refs": { "SystemContentBlocks$member": null } }, "SystemContentBlocks": { "base": null, "refs": { "ConverseRequest$system": "

A prompt that provides instructions or context to the model about the task it should perform, or the persona it should adopt during the conversation.

", "ConverseStreamRequest$system": "

A prompt that provides instructions or context to the model about the task it should perform, or the persona it should adopt during the conversation.

" } }, "TextCharactersGuarded": { "base": null, "refs": { "GuardrailTextCharactersCoverage$guarded": "

The text characters that were guarded by the guardrail coverage.

" } }, "TextCharactersTotal": { "base": null, "refs": { "GuardrailTextCharactersCoverage$total": "

The total text characters by the guardrail coverage.

" } }, "ThrottlingException": { "base": "

Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase Provisioned Throughput to increase the rate or number of tokens you can process.

", "refs": { "ConverseStreamOutput$throttlingException": "

The number of requests exceeds the limit. Resubmit your request later.

", "ResponseStream$throttlingException": "

Your request was throttled because of service-wide limitations. Resubmit your request later or in a different region. You can also purchase Provisioned Throughput to increase the rate or number of tokens you can process.

" } }, "TokenUsage": { "base": "

The tokens used in a message API inference call.

", "refs": { "ConverseResponse$usage": "

The total number of tokens used in the call to Converse. The total includes the tokens input to the model and the tokens generated by the model.

", "ConverseStreamMetadataEvent$usage": "

Usage information for the conversation stream event.

" } }, "TokenUsageInputTokensInteger": { "base": null, "refs": { "TokenUsage$inputTokens": "

The number of tokens sent in the request to the model.

" } }, "TokenUsageOutputTokensInteger": { "base": null, "refs": { "TokenUsage$outputTokens": "

The number of tokens that the model generated for the request.

" } }, "TokenUsageTotalTokensInteger": { "base": null, "refs": { "TokenUsage$totalTokens": "

The total of input tokens and tokens generated by the model.

" } }, "Tool": { "base": "

Information about a tool that you can use with the Converse API. For more information, see Tool use (function calling) in the Amazon Bedrock User Guide.

", "refs": { "ToolConfigurationToolsList$member": null } }, "ToolChoice": { "base": "

Determines which tools the model should request in a call to Converse or ConverseStream. ToolChoice is only supported by Anthropic Claude 3 models and by Mistral AI Mistral Large.

", "refs": { "ToolConfiguration$toolChoice": "

If supported by model, forces the model to request a tool.

" } }, "ToolConfiguration": { "base": "

Configuration information for the tools that you pass to a model. For more information, see Tool use (function calling) in the Amazon Bedrock User Guide.

This field is only supported by Anthropic Claude 3, Cohere Command R, Cohere Command R+, and Mistral Large models.

", "refs": { "ConverseRequest$toolConfig": "

Configuration information for the tools that the model can use when generating a response.

This field is only supported by Anthropic Claude 3, Cohere Command R, Cohere Command R+, and Mistral Large models.

", "ConverseStreamRequest$toolConfig": "

Configuration information for the tools that the model can use when generating a response.

This field is only supported by Anthropic Claude 3 models.

" } }, "ToolConfigurationToolsList": { "base": null, "refs": { "ToolConfiguration$tools": "

An array of tools that you want to pass to a model.

" } }, "ToolInputSchema": { "base": "

The schema for the tool. The top level schema type must be object.

", "refs": { "ToolSpecification$inputSchema": "

The input schema for the tool in JSON format.

" } }, "ToolName": { "base": null, "refs": { "SpecificToolChoice$name": "

The name of the tool that the model must request.

", "ToolSpecification$name": "

The name for the tool.

", "ToolUseBlock$name": "

The name of the tool that the model wants to use.

", "ToolUseBlockStart$name": "

The name of the tool that the model is requesting to use.

" } }, "ToolResultBlock": { "base": "

A tool result block that contains the results for a tool request that the model previously made.

", "refs": { "ContentBlock$toolResult": "

The result for a tool request that a model makes.

" } }, "ToolResultContentBlock": { "base": "

The tool result content block.

", "refs": { "ToolResultContentBlocks$member": null } }, "ToolResultContentBlocks": { "base": null, "refs": { "ToolResultBlock$content": "

The content for tool result content block.

" } }, "ToolResultStatus": { "base": null, "refs": { "ToolResultBlock$status": "

The status for the tool result content block.

This field is only supported Anthropic Claude 3 models.

" } }, "ToolSpecification": { "base": "

The specification for the tool.

", "refs": { "Tool$toolSpec": "

The specfication for the tool.

" } }, "ToolUseBlock": { "base": "

A tool use content block. Contains information about a tool that the model is requesting be run., The model uses the result from the tool to generate a response.

", "refs": { "ContentBlock$toolUse": "

Information about a tool use request from a model.

" } }, "ToolUseBlockDelta": { "base": "

The delta for a tool use block.

", "refs": { "ContentBlockDelta$toolUse": "

Information about a tool that the model is requesting to use.

" } }, "ToolUseBlockStart": { "base": "

The start of a tool use block.

", "refs": { "ContentBlockStart$toolUse": "

Information about a tool that the model is requesting to use.

" } }, "ToolUseId": { "base": null, "refs": { "ToolResultBlock$toolUseId": "

The ID of the tool request that this is the result for.

", "ToolUseBlock$toolUseId": "

The ID for the tool request.

", "ToolUseBlockStart$toolUseId": "

The ID for the tool request.

" } }, "Trace": { "base": null, "refs": { "InvokeModelRequest$trace": "

Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.

", "InvokeModelWithResponseStreamRequest$trace": "

Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.

" } }, "ValidationException": { "base": "

Input validation failed. Check your request parameters and retry the request.

", "refs": { "ConverseStreamOutput$validationException": "

Input validation failed. Check your request parameters and retry the request.

", "ResponseStream$validationException": "

Input validation failed. Check your request parameters and retry the request.

" } } } }