The action to apply a guardrail.
For troubleshooting some of the common errors you might encounter when using the ApplyGuardrail API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
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.
To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the base inference actions (InvokeModel and InvokeModelWithResponseStream). For more information see Deny access for inference on specific models.
For troubleshooting some of the common errors you might encounter when using the Converse API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
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.
To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the base inference actions (InvokeModel and InvokeModelWithResponseStream). For more information see Deny access for inference on specific models.
For troubleshooting some of the common errors you might encounter when using the ConverseStream API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
Retrieve information about an asynchronous invocation.
" }, "InvokeModel":{ "name":"InvokeModel", "http":{ "method":"POST", "requestUri":"/model/{modelId}/invoke", "responseCode":200 }, "input":{"shape":"InvokeModelRequest"}, "output":{"shape":"InvokeModelResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ThrottlingException"}, {"shape":"ModelTimeoutException"}, {"shape":"InternalServerException"}, {"shape":"ServiceUnavailableException"}, {"shape":"ValidationException"}, {"shape":"ModelNotReadyException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ModelErrorException"} ], "documentation":"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.
To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the Converse API actions (Converse and ConverseStream). For more information see Deny access for inference on specific models.
For troubleshooting some of the common errors you might encounter when using the InvokeModel API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
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.
To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the Converse API actions (Converse and ConverseStream). For more information see Deny access for inference on specific models.
For troubleshooting some of the common errors you might encounter when using the InvokeModelWithResponseStream API, see Troubleshooting Amazon Bedrock API Error Codes in the Amazon Bedrock User Guide
Lists asynchronous invocations.
" }, "StartAsyncInvoke":{ "name":"StartAsyncInvoke", "http":{ "method":"POST", "requestUri":"/async-invoke", "responseCode":200 }, "input":{"shape":"StartAsyncInvokeRequest"}, "output":{"shape":"StartAsyncInvokeResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ResourceNotFoundException"}, {"shape":"ThrottlingException"}, {"shape":"InternalServerException"}, {"shape":"ServiceUnavailableException"}, {"shape":"ValidationException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ConflictException"} ], "documentation":"Starts an asynchronous invocation.
This operation requires permission for the bedrock:InvokeModel action.
To deny all inference access to resources that you specify in the modelId field, you need to deny access to the bedrock:InvokeModel and bedrock:InvokeModelWithResponseStream actions. Doing this also denies access to the resource through the Converse API actions (Converse and ConverseStream). For more information see Deny access for inference on specific models.
The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error, see AccessDeniedException in the Amazon Bedrock User Guide
", "error":{ "httpStatusCode":403, "senderFault":true }, "exception":true }, "AccountId":{ "type":"string", "pattern":"[0-9]{12}" }, "AnyToolChoice":{ "type":"structure", "members":{ }, "documentation":"The model must request at least one tool (no text is generated). For example, {\"any\" : {}}.
The guardrail identifier used in the request to apply the guardrail.
", "location":"uri", "locationName":"guardrailIdentifier" }, "guardrailVersion":{ "shape":"GuardrailVersion", "documentation":"The guardrail version used in the request to apply the guardrail.
", "location":"uri", "locationName":"guardrailVersion" }, "source":{ "shape":"GuardrailContentSource", "documentation":"The source of data used in the request to apply the guardrail.
" }, "content":{ "shape":"GuardrailContentBlockList", "documentation":"The content details used in the request to apply the guardrail.
" } } }, "ApplyGuardrailResponse":{ "type":"structure", "required":[ "usage", "action", "outputs", "assessments" ], "members":{ "usage":{ "shape":"GuardrailUsage", "documentation":"The usage details in the response from the guardrail.
" }, "action":{ "shape":"GuardrailAction", "documentation":"The action taken in the response from the guardrail.
" }, "outputs":{ "shape":"GuardrailOutputContentList", "documentation":"The output details in the response from the guardrail.
" }, "assessments":{ "shape":"GuardrailAssessmentList", "documentation":"The assessment details in the response from the guardrail.
" }, "guardrailCoverage":{ "shape":"GuardrailCoverage", "documentation":"The guardrail coverage details in the apply guardrail response.
" } } }, "AsyncInvokeArn":{ "type":"string", "max":2048, "min":1, "pattern":"arn:[a-z0-9\\-]+:bedrock:[a-z0-9\\-]*:[0-9]*:(provisioned-model|foundation-model)/.+" }, "AsyncInvokeIdempotencyToken":{ "type":"string", "max":256, "min":1, "pattern":"[!-~]*" }, "AsyncInvokeIdentifier":{ "type":"string", "max":256, "min":1, "pattern":"[a-zA-Z_\\.\\-/0-9:]+" }, "AsyncInvokeMessage":{ "type":"string", "max":2048, "min":0, "sensitive":true }, "AsyncInvokeOutputDataConfig":{ "type":"structure", "members":{ "s3OutputDataConfig":{ "shape":"AsyncInvokeS3OutputDataConfig", "documentation":"A storage location for the output data in an S3 bucket
" } }, "documentation":"Asynchronous invocation output data settings.
", "union":true }, "AsyncInvokeS3OutputDataConfig":{ "type":"structure", "required":["s3Uri"], "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"An object URI starting with s3://.
A KMS encryption key ID.
" }, "bucketOwner":{ "shape":"AccountId", "documentation":"If the bucket belongs to another AWS account, specify that account's ID.
" } }, "documentation":"Asynchronous invocation output data settings.
" }, "AsyncInvokeStatus":{ "type":"string", "enum":[ "InProgress", "Completed", "Failed" ] }, "AsyncInvokeSummaries":{ "type":"list", "member":{"shape":"AsyncInvokeSummary"} }, "AsyncInvokeSummary":{ "type":"structure", "required":[ "invocationArn", "modelArn", "submitTime", "outputDataConfig" ], "members":{ "invocationArn":{ "shape":"InvocationArn", "documentation":"The invocation's ARN.
" }, "modelArn":{ "shape":"AsyncInvokeArn", "documentation":"The invoked model's ARN.
" }, "clientRequestToken":{ "shape":"AsyncInvokeIdempotencyToken", "documentation":"The invocation's idempotency token.
" }, "status":{ "shape":"AsyncInvokeStatus", "documentation":"The invocation's status.
" }, "failureMessage":{ "shape":"AsyncInvokeMessage", "documentation":"An error message.
" }, "submitTime":{ "shape":"Timestamp", "documentation":"When the invocation was submitted.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"When the invocation was last modified.
" }, "endTime":{ "shape":"Timestamp", "documentation":"When the invocation ended.
" }, "outputDataConfig":{ "shape":"AsyncInvokeOutputDataConfig", "documentation":"The invocation's output data settings.
" } }, "documentation":"A summary of an asynchronous invocation.
" }, "AutoToolChoice":{ "type":"structure", "members":{ }, "documentation":"The Model automatically decides if a tool should be called or whether to generate text instead. For example, {\"auto\" : {}}.
Error occurred because of a conflict while performing an operation.
", "error":{ "httpStatusCode":400, "senderFault":true }, "exception":true }, "ContentBlock":{ "type":"structure", "members":{ "text":{ "shape":"String", "documentation":"Text to include in the message.
" }, "image":{ "shape":"ImageBlock", "documentation":"Image to include in the message.
This field is only supported by Anthropic Claude 3 models.
A document to include in the message.
" }, "video":{ "shape":"VideoBlock", "documentation":"Video to include in the message.
" }, "toolUse":{ "shape":"ToolUseBlock", "documentation":"Information about a tool use request from a model.
" }, "toolResult":{ "shape":"ToolResultBlock", "documentation":"The result for a tool request that a model makes.
" }, "guardContent":{ "shape":"GuardrailConverseContentBlock", "documentation":"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> Contains content regarding the reasoning that is carried out by the model. Reasoning refers to a Chain of Thought (CoT) that the model generates to enhance the accuracy of its final response.
" } }, "documentation":"A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.
", "union":true }, "ContentBlockDelta":{ "type":"structure", "members":{ "text":{ "shape":"String", "documentation":"The content text.
" }, "toolUse":{ "shape":"ToolUseBlockDelta", "documentation":"Information about a tool that the model is requesting to use.
" }, "reasoningContent":{ "shape":"ReasoningContentBlockDelta", "documentation":"Contains content regarding the reasoning that is carried out by the model. Reasoning refers to a Chain of Thought (CoT) that the model generates to enhance the accuracy of its final response.
" } }, "documentation":"A block of content in a streaming response.
", "union":true }, "ContentBlockDeltaEvent":{ "type":"structure", "required":[ "delta", "contentBlockIndex" ], "members":{ "delta":{ "shape":"ContentBlockDelta", "documentation":"The delta for a content block delta event.
" }, "contentBlockIndex":{ "shape":"NonNegativeInteger", "documentation":"The block index for a content block delta event.
" } }, "documentation":"The content block delta event.
", "event":true }, "ContentBlockStart":{ "type":"structure", "members":{ "toolUse":{ "shape":"ToolUseBlockStart", "documentation":"Information about a tool that the model is requesting to use.
" } }, "documentation":"Content block start information.
", "union":true }, "ContentBlockStartEvent":{ "type":"structure", "required":[ "start", "contentBlockIndex" ], "members":{ "start":{ "shape":"ContentBlockStart", "documentation":"Start information about a content block start event.
" }, "contentBlockIndex":{ "shape":"NonNegativeInteger", "documentation":"The index for a content block start event.
" } }, "documentation":"Content block start event.
", "event":true }, "ContentBlockStopEvent":{ "type":"structure", "required":["contentBlockIndex"], "members":{ "contentBlockIndex":{ "shape":"NonNegativeInteger", "documentation":"The index for a content block.
" } }, "documentation":"A content block stop event.
", "event":true }, "ContentBlocks":{ "type":"list", "member":{"shape":"ContentBlock"} }, "ConversationRole":{ "type":"string", "enum":[ "user", "assistant" ] }, "ConversationalModelId":{ "type":"string", "max":2048, "min":1, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:imported-model/[a-z0-9]{12})|([0-9]{12}:provisioned-model/[a-z0-9]{12})|([0-9]{12}:(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+)))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)|([a-zA-Z0-9-:.]+)|(^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:prompt/[0-9a-zA-Z]{10}(?::[0-9]{1,5})?))$|(^arn:aws:sagemaker:[a-z0-9-]+:[0-9]{12}:endpoint/[a-zA-Z0-9-]+$)|(^arn:aws(-[^:]+)?:bedrock:([0-9a-z-]{1,20}):([0-9]{12}):(default-)?prompt-router/[a-zA-Z0-9-:.]+$)" }, "ConverseMetrics":{ "type":"structure", "required":["latencyMs"], "members":{ "latencyMs":{ "shape":"Long", "documentation":"The latency of the call to Converse, in milliseconds.
Metrics for a call to Converse.
" }, "ConverseOutput":{ "type":"structure", "members":{ "message":{ "shape":"Message", "documentation":"The message that the model generates.
" } }, "documentation":"The output from a call to Converse.
", "union":true }, "ConverseRequest":{ "type":"structure", "required":["modelId"], "members":{ "modelId":{ "shape":"ConversationalModelId", "documentation":"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:
If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.
If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for cross-region inference in the Amazon Bedrock User Guide.
If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.
If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.
To include a prompt that was defined in Prompt management, specify the ARN of the prompt version to use.
The Converse API doesn't support imported models.
", "location":"uri", "locationName":"modelId" }, "messages":{ "shape":"Messages", "documentation":"The messages that you want to send to the model.
" }, "system":{ "shape":"SystemContentBlocks", "documentation":"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.
" }, "inferenceConfig":{ "shape":"InferenceConfiguration", "documentation":"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.
Configuration information for the tools that the model can use when generating a response.
For information about models that support tool use, see Supported models and model features.
" }, "guardrailConfig":{ "shape":"GuardrailConfiguration", "documentation":"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.
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.
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.
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.
Key-value pairs that you can use to filter invocation logs.
" }, "performanceConfig":{ "shape":"PerformanceConfiguration", "documentation":"Model performance settings for the request.
" } } }, "ConverseRequestAdditionalModelResponseFieldPathsList":{ "type":"list", "member":{"shape":"ConverseRequestAdditionalModelResponseFieldPathsListMemberString"}, "max":10, "min":0 }, "ConverseRequestAdditionalModelResponseFieldPathsListMemberString":{ "type":"string", "max":256, "min":1 }, "ConverseResponse":{ "type":"structure", "required":[ "output", "stopReason", "usage", "metrics" ], "members":{ "output":{ "shape":"ConverseOutput", "documentation":"The result from the call to Converse.
The reason why the model stopped generating output.
" }, "usage":{ "shape":"TokenUsage", "documentation":"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.
Metrics for the call to Converse.
Additional fields in the response that are unique to the model.
" }, "trace":{ "shape":"ConverseTrace", "documentation":"A trace object that contains information about the Guardrail behavior.
" }, "performanceConfig":{ "shape":"PerformanceConfiguration", "documentation":"Model performance settings for the request.
" } } }, "ConverseStreamMetadataEvent":{ "type":"structure", "required":[ "usage", "metrics" ], "members":{ "usage":{ "shape":"TokenUsage", "documentation":"Usage information for the conversation stream event.
" }, "metrics":{ "shape":"ConverseStreamMetrics", "documentation":"The metrics for the conversation stream metadata event.
" }, "trace":{ "shape":"ConverseStreamTrace", "documentation":"The trace object in the response from ConverseStream that contains information about the guardrail behavior.
" }, "performanceConfig":{ "shape":"PerformanceConfiguration", "documentation":"Model performance configuration metadata for the conversation stream event.
" } }, "documentation":"A conversation stream metadata event.
", "event":true }, "ConverseStreamMetrics":{ "type":"structure", "required":["latencyMs"], "members":{ "latencyMs":{ "shape":"Long", "documentation":"The latency for the streaming request, in milliseconds.
" } }, "documentation":"Metrics for the stream.
" }, "ConverseStreamOutput":{ "type":"structure", "members":{ "messageStart":{ "shape":"MessageStartEvent", "documentation":"Message start information.
" }, "contentBlockStart":{ "shape":"ContentBlockStartEvent", "documentation":"Start information for a content block.
" }, "contentBlockDelta":{ "shape":"ContentBlockDeltaEvent", "documentation":"The messages output content block delta.
" }, "contentBlockStop":{ "shape":"ContentBlockStopEvent", "documentation":"Stop information for a content block.
" }, "messageStop":{ "shape":"MessageStopEvent", "documentation":"Message stop information.
" }, "metadata":{ "shape":"ConverseStreamMetadataEvent", "documentation":"Metadata for the converse output stream.
" }, "internalServerException":{ "shape":"InternalServerException", "documentation":"An internal server error occurred. Retry your request.
" }, "modelStreamErrorException":{ "shape":"ModelStreamErrorException", "documentation":"A streaming error occurred. Retry your request.
" }, "validationException":{ "shape":"ValidationException", "documentation":"The input fails to satisfy the constraints specified by Amazon Bedrock. For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide
" }, "throttlingException":{ "shape":"ThrottlingException", "documentation":"Your request was denied due to exceeding the account quotas for Amazon Bedrock. For troubleshooting this error, see ThrottlingException in the Amazon Bedrock User Guide
" }, "serviceUnavailableException":{ "shape":"ServiceUnavailableException", "documentation":"The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide
" } }, "documentation":"The messages output stream
", "eventstream":true }, "ConverseStreamRequest":{ "type":"structure", "required":["modelId"], "members":{ "modelId":{ "shape":"ConversationalModelId", "documentation":"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:
If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.
If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for cross-region inference in the Amazon Bedrock User Guide.
If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.
If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.
To include a prompt that was defined in Prompt management, specify the ARN of the prompt version to use.
The Converse API doesn't support imported models.
", "location":"uri", "locationName":"modelId" }, "messages":{ "shape":"Messages", "documentation":"The messages that you want to send to the model.
" }, "system":{ "shape":"SystemContentBlocks", "documentation":"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.
" }, "inferenceConfig":{ "shape":"InferenceConfiguration", "documentation":"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.
Configuration information for the tools that the model can use when generating a response.
For information about models that support streaming tool use, see Supported models and model features.
" }, "guardrailConfig":{ "shape":"GuardrailStreamConfiguration", "documentation":"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.
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.
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.
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.
Key-value pairs that you can use to filter invocation logs.
" }, "performanceConfig":{ "shape":"PerformanceConfiguration", "documentation":"Model performance settings for the request.
" } } }, "ConverseStreamRequestAdditionalModelResponseFieldPathsList":{ "type":"list", "member":{"shape":"ConverseStreamRequestAdditionalModelResponseFieldPathsListMemberString"}, "max":10, "min":0 }, "ConverseStreamRequestAdditionalModelResponseFieldPathsListMemberString":{ "type":"string", "max":256, "min":1 }, "ConverseStreamResponse":{ "type":"structure", "members":{ "stream":{ "shape":"ConverseStreamOutput", "documentation":"The output stream that the model generated.
" } }, "payload":"stream" }, "ConverseStreamTrace":{ "type":"structure", "members":{ "guardrail":{ "shape":"GuardrailTraceAssessment", "documentation":"The guardrail trace object.
" }, "promptRouter":{ "shape":"PromptRouterTrace", "documentation":"The request's prompt router.
" } }, "documentation":"The trace object in a response from ConverseStream. Currently, you can only trace guardrails.
" }, "ConverseTrace":{ "type":"structure", "members":{ "guardrail":{ "shape":"GuardrailTraceAssessment", "documentation":"The guardrail trace object.
" }, "promptRouter":{ "shape":"PromptRouterTrace", "documentation":"The request's prompt router.
" } }, "documentation":"The trace object in a response from Converse. Currently, you can only trace guardrails.
" }, "Document":{ "type":"structure", "members":{ }, "document":true }, "DocumentBlock":{ "type":"structure", "required":[ "format", "name", "source" ], "members":{ "format":{ "shape":"DocumentFormat", "documentation":"The format of a document, or its extension.
" }, "name":{ "shape":"DocumentBlockNameString", "documentation":"A name for the document. The name can only contain the following characters:
Alphanumeric characters
Whitespace characters (no more than one in a row)
Hyphens
Parentheses
Square brackets
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.
Contains the content of the document.
" } }, "documentation":"A document to include in a message.
" }, "DocumentBlockNameString":{ "type":"string", "max":200, "min":1 }, "DocumentFormat":{ "type":"string", "enum":[ "pdf", "csv", "doc", "docx", "xls", "xlsx", "html", "txt", "md" ] }, "DocumentSource":{ "type":"structure", "members":{ "bytes":{ "shape":"DocumentSourceBytesBlob", "documentation":"The raw bytes for the document. If you use an Amazon Web Services SDK, you don't need to encode the bytes in base64.
" } }, "documentation":"Contains the content of a document.
", "union":true }, "DocumentSourceBytesBlob":{ "type":"blob", "min":1 }, "GetAsyncInvokeRequest":{ "type":"structure", "required":["invocationArn"], "members":{ "invocationArn":{ "shape":"InvocationArn", "documentation":"The invocation's ARN.
", "location":"uri", "locationName":"invocationArn" } } }, "GetAsyncInvokeResponse":{ "type":"structure", "required":[ "invocationArn", "modelArn", "status", "submitTime", "outputDataConfig" ], "members":{ "invocationArn":{ "shape":"InvocationArn", "documentation":"The invocation's ARN.
" }, "modelArn":{ "shape":"AsyncInvokeArn", "documentation":"The invocation's model ARN.
" }, "clientRequestToken":{ "shape":"AsyncInvokeIdempotencyToken", "documentation":"The invocation's idempotency token.
" }, "status":{ "shape":"AsyncInvokeStatus", "documentation":"The invocation's status.
" }, "failureMessage":{ "shape":"AsyncInvokeMessage", "documentation":"An error message.
" }, "submitTime":{ "shape":"Timestamp", "documentation":"When the invocation request was submitted.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"The invocation's last modified time.
" }, "endTime":{ "shape":"Timestamp", "documentation":"When the invocation ended.
" }, "outputDataConfig":{ "shape":"AsyncInvokeOutputDataConfig", "documentation":"Output data settings.
" } } }, "GuardrailAction":{ "type":"string", "enum":[ "NONE", "GUARDRAIL_INTERVENED" ] }, "GuardrailAssessment":{ "type":"structure", "members":{ "topicPolicy":{ "shape":"GuardrailTopicPolicyAssessment", "documentation":"The topic policy.
" }, "contentPolicy":{ "shape":"GuardrailContentPolicyAssessment", "documentation":"The content policy.
" }, "wordPolicy":{ "shape":"GuardrailWordPolicyAssessment", "documentation":"The word policy.
" }, "sensitiveInformationPolicy":{ "shape":"GuardrailSensitiveInformationPolicyAssessment", "documentation":"The sensitive information policy.
" }, "contextualGroundingPolicy":{ "shape":"GuardrailContextualGroundingPolicyAssessment", "documentation":"The contextual grounding policy used for the guardrail assessment.
" }, "invocationMetrics":{ "shape":"GuardrailInvocationMetrics", "documentation":"The invocation metrics for the guardrail assessment.
" } }, "documentation":"A behavior assessment of the guardrail policies used in a call to the Converse API.
" }, "GuardrailAssessmentList":{ "type":"list", "member":{"shape":"GuardrailAssessment"} }, "GuardrailAssessmentListMap":{ "type":"map", "key":{"shape":"String"}, "value":{"shape":"GuardrailAssessmentList"} }, "GuardrailAssessmentMap":{ "type":"map", "key":{"shape":"String"}, "value":{"shape":"GuardrailAssessment"} }, "GuardrailConfiguration":{ "type":"structure", "required":[ "guardrailIdentifier", "guardrailVersion" ], "members":{ "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"The identifier for the guardrail.
" }, "guardrailVersion":{ "shape":"GuardrailVersion", "documentation":"The version of the guardrail.
" }, "trace":{ "shape":"GuardrailTrace", "documentation":"The trace behavior for the guardrail.
" } }, "documentation":"Configuration information for a guardrail that you use with the Converse operation.
" }, "GuardrailContentBlock":{ "type":"structure", "members":{ "text":{ "shape":"GuardrailTextBlock", "documentation":"Text within content block to be evaluated by the guardrail.
" }, "image":{ "shape":"GuardrailImageBlock", "documentation":"Image within guardrail content block to be evaluated by the guardrail.
" } }, "documentation":"The content block to be evaluated by the guardrail.
", "union":true }, "GuardrailContentBlockList":{ "type":"list", "member":{"shape":"GuardrailContentBlock"} }, "GuardrailContentFilter":{ "type":"structure", "required":[ "type", "confidence", "action" ], "members":{ "type":{ "shape":"GuardrailContentFilterType", "documentation":"The guardrail type.
" }, "confidence":{ "shape":"GuardrailContentFilterConfidence", "documentation":"The guardrail confidence.
" }, "filterStrength":{ "shape":"GuardrailContentFilterStrength", "documentation":"The filter strength setting for the guardrail content filter.
" }, "action":{ "shape":"GuardrailContentPolicyAction", "documentation":"The guardrail action.
" } }, "documentation":"The content filter for a guardrail.
" }, "GuardrailContentFilterConfidence":{ "type":"string", "enum":[ "NONE", "LOW", "MEDIUM", "HIGH" ] }, "GuardrailContentFilterList":{ "type":"list", "member":{"shape":"GuardrailContentFilter"} }, "GuardrailContentFilterStrength":{ "type":"string", "enum":[ "NONE", "LOW", "MEDIUM", "HIGH" ] }, "GuardrailContentFilterType":{ "type":"string", "enum":[ "INSULTS", "HATE", "SEXUAL", "VIOLENCE", "MISCONDUCT", "PROMPT_ATTACK" ] }, "GuardrailContentPolicyAction":{ "type":"string", "enum":["BLOCKED"] }, "GuardrailContentPolicyAssessment":{ "type":"structure", "required":["filters"], "members":{ "filters":{ "shape":"GuardrailContentFilterList", "documentation":"The content policy filters.
" } }, "documentation":"An assessment of a content policy for a guardrail.
" }, "GuardrailContentPolicyUnitsProcessed":{ "type":"integer", "box":true }, "GuardrailContentQualifier":{ "type":"string", "enum":[ "grounding_source", "query", "guard_content" ] }, "GuardrailContentQualifierList":{ "type":"list", "member":{"shape":"GuardrailContentQualifier"} }, "GuardrailContentSource":{ "type":"string", "enum":[ "INPUT", "OUTPUT" ] }, "GuardrailContextualGroundingFilter":{ "type":"structure", "required":[ "type", "threshold", "score", "action" ], "members":{ "type":{ "shape":"GuardrailContextualGroundingFilterType", "documentation":"The contextual grounding filter type.
" }, "threshold":{ "shape":"GuardrailContextualGroundingFilterThresholdDouble", "documentation":"The threshold used by contextual grounding filter to determine whether the content is grounded or not.
" }, "score":{ "shape":"GuardrailContextualGroundingFilterScoreDouble", "documentation":"The score generated by contextual grounding filter.
" }, "action":{ "shape":"GuardrailContextualGroundingPolicyAction", "documentation":"The action performed by the guardrails contextual grounding filter.
" } }, "documentation":"The details for the guardrails contextual grounding filter.
" }, "GuardrailContextualGroundingFilterScoreDouble":{ "type":"double", "box":true, "max":1, "min":0 }, "GuardrailContextualGroundingFilterThresholdDouble":{ "type":"double", "box":true, "max":1, "min":0 }, "GuardrailContextualGroundingFilterType":{ "type":"string", "enum":[ "GROUNDING", "RELEVANCE" ] }, "GuardrailContextualGroundingFilters":{ "type":"list", "member":{"shape":"GuardrailContextualGroundingFilter"} }, "GuardrailContextualGroundingPolicyAction":{ "type":"string", "enum":[ "BLOCKED", "NONE" ] }, "GuardrailContextualGroundingPolicyAssessment":{ "type":"structure", "members":{ "filters":{ "shape":"GuardrailContextualGroundingFilters", "documentation":"The filter details for the guardrails contextual grounding filter.
" } }, "documentation":"The policy assessment details for the guardrails contextual grounding filter.
" }, "GuardrailContextualGroundingPolicyUnitsProcessed":{ "type":"integer", "box":true }, "GuardrailConverseContentBlock":{ "type":"structure", "members":{ "text":{ "shape":"GuardrailConverseTextBlock", "documentation":"The text to guard.
" }, "image":{ "shape":"GuardrailConverseImageBlock", "documentation":"Image within converse content block to be evaluated by the guardrail.
" } }, "documentation":"A content block for selective guarding with the Converse or ConverseStream API operations.
", "union":true }, "GuardrailConverseContentQualifier":{ "type":"string", "enum":[ "grounding_source", "query", "guard_content" ] }, "GuardrailConverseContentQualifierList":{ "type":"list", "member":{"shape":"GuardrailConverseContentQualifier"} }, "GuardrailConverseImageBlock":{ "type":"structure", "required":[ "format", "source" ], "members":{ "format":{ "shape":"GuardrailConverseImageFormat", "documentation":"The format details for the image type of the guardrail converse image block.
" }, "source":{ "shape":"GuardrailConverseImageSource", "documentation":"The image source (image bytes) of the guardrail converse image block.
" } }, "documentation":"An image block that contains images that you want to assess with a guardrail.
", "sensitive":true }, "GuardrailConverseImageFormat":{ "type":"string", "enum":[ "png", "jpeg" ] }, "GuardrailConverseImageSource":{ "type":"structure", "members":{ "bytes":{ "shape":"GuardrailConverseImageSourceBytesBlob", "documentation":"The raw image bytes for the image.
" } }, "documentation":"The image source (image bytes) of the guardrail converse image source.
", "sensitive":true, "union":true }, "GuardrailConverseImageSourceBytesBlob":{ "type":"blob", "min":1 }, "GuardrailConverseTextBlock":{ "type":"structure", "required":["text"], "members":{ "text":{ "shape":"String", "documentation":"The text that you want to guard.
" }, "qualifiers":{ "shape":"GuardrailConverseContentQualifierList", "documentation":"The qualifier details for the guardrails contextual grounding filter.
" } }, "documentation":"A text block that contains text that you want to assess with a guardrail. For more information, see GuardrailConverseContentBlock.
" }, "GuardrailCoverage":{ "type":"structure", "members":{ "textCharacters":{ "shape":"GuardrailTextCharactersCoverage", "documentation":"The text characters of the guardrail coverage details.
" }, "images":{ "shape":"GuardrailImageCoverage", "documentation":"The guardrail coverage for images (the number of images that guardrails guarded).
" } }, "documentation":"The action of the guardrail coverage details.
" }, "GuardrailCustomWord":{ "type":"structure", "required":[ "match", "action" ], "members":{ "match":{ "shape":"String", "documentation":"The match for the custom word.
" }, "action":{ "shape":"GuardrailWordPolicyAction", "documentation":"The action for the custom word.
" } }, "documentation":"A custom word configured in a guardrail.
" }, "GuardrailCustomWordList":{ "type":"list", "member":{"shape":"GuardrailCustomWord"} }, "GuardrailIdentifier":{ "type":"string", "max":2048, "min":0, "pattern":"(([a-z0-9]+)|(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:guardrail/[a-z0-9]+))" }, "GuardrailImageBlock":{ "type":"structure", "required":[ "format", "source" ], "members":{ "format":{ "shape":"GuardrailImageFormat", "documentation":"The format details for the file type of the image blocked by the guardrail.
" }, "source":{ "shape":"GuardrailImageSource", "documentation":"The image source (image bytes) details of the image blocked by the guardrail.
" } }, "documentation":"Contain an image which user wants guarded. This block is accepted by the guardrails independent API.
", "sensitive":true }, "GuardrailImageCoverage":{ "type":"structure", "members":{ "guarded":{ "shape":"ImagesGuarded", "documentation":"The count (integer) of images guardrails guarded.
" }, "total":{ "shape":"ImagesTotal", "documentation":"Represents the total number of images (integer) that were in the request (guarded and unguarded).
" } }, "documentation":"The details of the guardrail image coverage.
" }, "GuardrailImageFormat":{ "type":"string", "enum":[ "png", "jpeg" ] }, "GuardrailImageSource":{ "type":"structure", "members":{ "bytes":{ "shape":"GuardrailImageSourceBytesBlob", "documentation":"The bytes details of the guardrail image source. Object used in independent api.
" } }, "documentation":"The image source (image bytes) of the guardrail image source. Object used in independent api.
", "sensitive":true, "union":true }, "GuardrailImageSourceBytesBlob":{ "type":"blob", "min":1 }, "GuardrailInvocationMetrics":{ "type":"structure", "members":{ "guardrailProcessingLatency":{ "shape":"GuardrailProcessingLatency", "documentation":"The processing latency details for the guardrail invocation metrics.
" }, "usage":{ "shape":"GuardrailUsage", "documentation":"The usage details for the guardrail invocation metrics.
" }, "guardrailCoverage":{ "shape":"GuardrailCoverage", "documentation":"The coverage details for the guardrail invocation metrics.
" } }, "documentation":"The invocation metrics for the guardrail.
" }, "GuardrailManagedWord":{ "type":"structure", "required":[ "match", "type", "action" ], "members":{ "match":{ "shape":"String", "documentation":"The match for the managed word.
" }, "type":{ "shape":"GuardrailManagedWordType", "documentation":"The type for the managed word.
" }, "action":{ "shape":"GuardrailWordPolicyAction", "documentation":"The action for the managed word.
" } }, "documentation":"A managed word configured in a guardrail.
" }, "GuardrailManagedWordList":{ "type":"list", "member":{"shape":"GuardrailManagedWord"} }, "GuardrailManagedWordType":{ "type":"string", "enum":["PROFANITY"] }, "GuardrailOutputContent":{ "type":"structure", "members":{ "text":{ "shape":"GuardrailOutputText", "documentation":"The specific text for the output content produced by the guardrail.
" } }, "documentation":"The output content produced by the guardrail.
" }, "GuardrailOutputContentList":{ "type":"list", "member":{"shape":"GuardrailOutputContent"} }, "GuardrailOutputText":{"type":"string"}, "GuardrailPiiEntityFilter":{ "type":"structure", "required":[ "match", "type", "action" ], "members":{ "match":{ "shape":"String", "documentation":"The PII entity filter match.
" }, "type":{ "shape":"GuardrailPiiEntityType", "documentation":"The PII entity filter type.
" }, "action":{ "shape":"GuardrailSensitiveInformationPolicyAction", "documentation":"The PII entity filter action.
" } }, "documentation":"A Personally Identifiable Information (PII) entity configured in a guardrail.
" }, "GuardrailPiiEntityFilterList":{ "type":"list", "member":{"shape":"GuardrailPiiEntityFilter"} }, "GuardrailPiiEntityType":{ "type":"string", "enum":[ "ADDRESS", "AGE", "AWS_ACCESS_KEY", "AWS_SECRET_KEY", "CA_HEALTH_NUMBER", "CA_SOCIAL_INSURANCE_NUMBER", "CREDIT_DEBIT_CARD_CVV", "CREDIT_DEBIT_CARD_EXPIRY", "CREDIT_DEBIT_CARD_NUMBER", "DRIVER_ID", "EMAIL", "INTERNATIONAL_BANK_ACCOUNT_NUMBER", "IP_ADDRESS", "LICENSE_PLATE", "MAC_ADDRESS", "NAME", "PASSWORD", "PHONE", "PIN", "SWIFT_CODE", "UK_NATIONAL_HEALTH_SERVICE_NUMBER", "UK_NATIONAL_INSURANCE_NUMBER", "UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER", "URL", "USERNAME", "US_BANK_ACCOUNT_NUMBER", "US_BANK_ROUTING_NUMBER", "US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER", "US_PASSPORT_NUMBER", "US_SOCIAL_SECURITY_NUMBER", "VEHICLE_IDENTIFICATION_NUMBER" ] }, "GuardrailProcessingLatency":{ "type":"long", "box":true }, "GuardrailRegexFilter":{ "type":"structure", "required":["action"], "members":{ "name":{ "shape":"String", "documentation":"The regex filter name.
" }, "match":{ "shape":"String", "documentation":"The regesx filter match.
" }, "regex":{ "shape":"String", "documentation":"The regex query.
" }, "action":{ "shape":"GuardrailSensitiveInformationPolicyAction", "documentation":"The region filter action.
" } }, "documentation":"A Regex filter configured in a guardrail.
" }, "GuardrailRegexFilterList":{ "type":"list", "member":{"shape":"GuardrailRegexFilter"} }, "GuardrailSensitiveInformationPolicyAction":{ "type":"string", "enum":[ "ANONYMIZED", "BLOCKED" ] }, "GuardrailSensitiveInformationPolicyAssessment":{ "type":"structure", "required":[ "piiEntities", "regexes" ], "members":{ "piiEntities":{ "shape":"GuardrailPiiEntityFilterList", "documentation":"The PII entities in the assessment.
" }, "regexes":{ "shape":"GuardrailRegexFilterList", "documentation":"The regex queries in the assessment.
" } }, "documentation":"The assessment for aPersonally Identifiable Information (PII) policy.
" }, "GuardrailSensitiveInformationPolicyFreeUnitsProcessed":{ "type":"integer", "box":true }, "GuardrailSensitiveInformationPolicyUnitsProcessed":{ "type":"integer", "box":true }, "GuardrailStreamConfiguration":{ "type":"structure", "required":[ "guardrailIdentifier", "guardrailVersion" ], "members":{ "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"The identifier for the guardrail.
" }, "guardrailVersion":{ "shape":"GuardrailVersion", "documentation":"The version of the guardrail.
" }, "trace":{ "shape":"GuardrailTrace", "documentation":"The trace behavior for the guardrail.
" }, "streamProcessingMode":{ "shape":"GuardrailStreamProcessingMode", "documentation":"The processing mode.
The processing mode. For more information, see Configure streaming response behavior in the Amazon Bedrock User Guide.
" } }, "documentation":"Configuration information for a guardrail that you use with the ConverseStream action.
" }, "GuardrailStreamProcessingMode":{ "type":"string", "enum":[ "sync", "async" ] }, "GuardrailTextBlock":{ "type":"structure", "required":["text"], "members":{ "text":{ "shape":"String", "documentation":"The input text details to be evaluated by the guardrail.
" }, "qualifiers":{ "shape":"GuardrailContentQualifierList", "documentation":"The qualifiers describing the text block.
" } }, "documentation":"The text block to be evaluated by the guardrail.
" }, "GuardrailTextCharactersCoverage":{ "type":"structure", "members":{ "guarded":{ "shape":"TextCharactersGuarded", "documentation":"The text characters that were guarded by the guardrail coverage.
" }, "total":{ "shape":"TextCharactersTotal", "documentation":"The total text characters by the guardrail coverage.
" } }, "documentation":"The guardrail coverage for the text characters.
" }, "GuardrailTopic":{ "type":"structure", "required":[ "name", "type", "action" ], "members":{ "name":{ "shape":"String", "documentation":"The name for the guardrail.
" }, "type":{ "shape":"GuardrailTopicType", "documentation":"The type behavior that the guardrail should perform when the model detects the topic.
" }, "action":{ "shape":"GuardrailTopicPolicyAction", "documentation":"The action the guardrail should take when it intervenes on a topic.
" } }, "documentation":"Information about a topic guardrail.
" }, "GuardrailTopicList":{ "type":"list", "member":{"shape":"GuardrailTopic"} }, "GuardrailTopicPolicyAction":{ "type":"string", "enum":["BLOCKED"] }, "GuardrailTopicPolicyAssessment":{ "type":"structure", "required":["topics"], "members":{ "topics":{ "shape":"GuardrailTopicList", "documentation":"The topics in the assessment.
" } }, "documentation":"A behavior assessment of a topic policy.
" }, "GuardrailTopicPolicyUnitsProcessed":{ "type":"integer", "box":true }, "GuardrailTopicType":{ "type":"string", "enum":["DENY"] }, "GuardrailTrace":{ "type":"string", "enum":[ "enabled", "disabled" ] }, "GuardrailTraceAssessment":{ "type":"structure", "members":{ "modelOutput":{ "shape":"ModelOutputs", "documentation":"The output from the model.
" }, "inputAssessment":{ "shape":"GuardrailAssessmentMap", "documentation":"The input assessment.
" }, "outputAssessments":{ "shape":"GuardrailAssessmentListMap", "documentation":"the output assessments.
" } }, "documentation":"A Top level guardrail trace object. For more information, see ConverseTrace.
" }, "GuardrailUsage":{ "type":"structure", "required":[ "topicPolicyUnits", "contentPolicyUnits", "wordPolicyUnits", "sensitiveInformationPolicyUnits", "sensitiveInformationPolicyFreeUnits", "contextualGroundingPolicyUnits" ], "members":{ "topicPolicyUnits":{ "shape":"GuardrailTopicPolicyUnitsProcessed", "documentation":"The topic policy units processed by the guardrail.
" }, "contentPolicyUnits":{ "shape":"GuardrailContentPolicyUnitsProcessed", "documentation":"The content policy units processed by the guardrail.
" }, "wordPolicyUnits":{ "shape":"GuardrailWordPolicyUnitsProcessed", "documentation":"The word policy units processed by the guardrail.
" }, "sensitiveInformationPolicyUnits":{ "shape":"GuardrailSensitiveInformationPolicyUnitsProcessed", "documentation":"The sensitive information policy units processed by the guardrail.
" }, "sensitiveInformationPolicyFreeUnits":{ "shape":"GuardrailSensitiveInformationPolicyFreeUnitsProcessed", "documentation":"The sensitive information policy free units processed by the guardrail.
" }, "contextualGroundingPolicyUnits":{ "shape":"GuardrailContextualGroundingPolicyUnitsProcessed", "documentation":"The contextual grounding policy units processed by the guardrail.
" } }, "documentation":"The details on the use of the guardrail.
" }, "GuardrailVersion":{ "type":"string", "pattern":"(([1-9][0-9]{0,7})|(DRAFT))" }, "GuardrailWordPolicyAction":{ "type":"string", "enum":["BLOCKED"] }, "GuardrailWordPolicyAssessment":{ "type":"structure", "required":[ "customWords", "managedWordLists" ], "members":{ "customWords":{ "shape":"GuardrailCustomWordList", "documentation":"Custom words in the assessment.
" }, "managedWordLists":{ "shape":"GuardrailManagedWordList", "documentation":"Managed word lists in the assessment.
" } }, "documentation":"The word policy assessment.
" }, "GuardrailWordPolicyUnitsProcessed":{ "type":"integer", "box":true }, "ImageBlock":{ "type":"structure", "required":[ "format", "source" ], "members":{ "format":{ "shape":"ImageFormat", "documentation":"The format of the image.
" }, "source":{ "shape":"ImageSource", "documentation":"The source for the image.
" } }, "documentation":"Image content for a message.
" }, "ImageFormat":{ "type":"string", "enum":[ "png", "jpeg", "gif", "webp" ] }, "ImageSource":{ "type":"structure", "members":{ "bytes":{ "shape":"ImageSourceBytesBlob", "documentation":"The raw image bytes for the image. If you use an AWS SDK, you don't need to encode the image bytes in base64.
" } }, "documentation":"The source for an image.
", "union":true }, "ImageSourceBytesBlob":{ "type":"blob", "min":1 }, "ImagesGuarded":{ "type":"integer", "box":true }, "ImagesTotal":{ "type":"integer", "box":true }, "InferenceConfiguration":{ "type":"structure", "members":{ "maxTokens":{ "shape":"InferenceConfigurationMaxTokensInteger", "documentation":"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.
" }, "temperature":{ "shape":"InferenceConfigurationTemperatureFloat", "documentation":"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.
" }, "topP":{ "shape":"InferenceConfigurationTopPFloat", "documentation":"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.
" }, "stopSequences":{ "shape":"InferenceConfigurationStopSequencesList", "documentation":"A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
" } }, "documentation":"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.
An internal server error occurred. For troubleshooting this error, see InternalFailure in the Amazon Bedrock User Guide
", "error":{"httpStatusCode":500}, "exception":true, "fault":true }, "InvocationArn":{ "type":"string", "max":2048, "min":1, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:async-invoke/[a-z0-9]{12}" }, "InvokeModelIdentifier":{ "type":"string", "max":2048, "min":1, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:imported-model/[a-z0-9]{12})|([0-9]{12}:provisioned-model/[a-z0-9]{12})|([0-9]{12}:(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+)))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)|([a-zA-Z0-9-:.]+)$|(^(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:prompt/[0-9a-zA-Z]{10}(?::[0-9]{1,5})?))$|(^arn:aws:sagemaker:[a-z0-9-]+:[0-9]{12}:endpoint/[a-zA-Z0-9-]+$)|(^arn:aws(-[^:]+)?:bedrock:([0-9a-z-]{1,20}):([0-9]{12}):(default-)?prompt-router/[a-zA-Z0-9-:.]+$)" }, "InvokeModelRequest":{ "type":"structure", "required":["modelId"], "members":{ "body":{ "shape":"Body", "documentation":"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.
The MIME type of the input data in the request. You must specify application/json.
The desired MIME type of the inference body in the response. The default value is application/json.
The unique identifier of the model to invoke to run inference.
The modelId to provide depends on the type of model or throughput that you use:
If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.
If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for cross-region inference in the Amazon Bedrock User Guide.
If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.
If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.
If you use an imported model, specify the ARN of the imported model. You can get the model ARN from a successful call to CreateModelImportJob or from the Imported models page in the Amazon Bedrock console.
Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
", "location":"header", "locationName":"X-Amzn-Bedrock-Trace" }, "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"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.
You don't provide a guardrail identifier but you specify the amazon-bedrock-guardrailConfig field in the request body.
You enable the guardrail but the contentType isn't application/json.
You provide a guardrail identifier, but guardrailVersion isn't specified.
The version number for the guardrail. The value can also be DRAFT.
Model performance settings for the request.
", "location":"header", "locationName":"X-Amzn-Bedrock-PerformanceConfig-Latency" } }, "payload":"body" }, "InvokeModelResponse":{ "type":"structure", "required":[ "body", "contentType" ], "members":{ "body":{ "shape":"Body", "documentation":"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.
The MIME type of the inference result.
", "location":"header", "locationName":"Content-Type" }, "performanceConfigLatency":{ "shape":"PerformanceConfigLatency", "documentation":"Model performance settings for the request.
", "location":"header", "locationName":"X-Amzn-Bedrock-PerformanceConfig-Latency" } }, "payload":"body" }, "InvokeModelWithResponseStreamRequest":{ "type":"structure", "required":["modelId"], "members":{ "body":{ "shape":"Body", "documentation":"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.
The MIME type of the input data in the request. You must specify application/json.
The desired MIME type of the inference body in the response. The default value is application/json.
The unique identifier of the model to invoke to run inference.
The modelId to provide depends on the type of model or throughput that you use:
If you use a base model, specify the model ID or its ARN. For a list of model IDs for base models, see Amazon Bedrock base model IDs (on-demand throughput) in the Amazon Bedrock User Guide.
If you use an inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for cross-region inference in the Amazon Bedrock User Guide.
If you use a provisioned model, specify the ARN of the Provisioned Throughput. For more information, see Run inference using a Provisioned Throughput in the Amazon Bedrock User Guide.
If you use a custom model, first purchase Provisioned Throughput for it. Then specify the ARN of the resulting provisioned model. For more information, see Use a custom model in Amazon Bedrock in the Amazon Bedrock User Guide.
If you use an imported model, specify the ARN of the imported model. You can get the model ARN from a successful call to CreateModelImportJob or from the Imported models page in the Amazon Bedrock console.
Specifies whether to enable or disable the Bedrock trace. If enabled, you can see the full Bedrock trace.
", "location":"header", "locationName":"X-Amzn-Bedrock-Trace" }, "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"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.
You don't provide a guardrail identifier but you specify the amazon-bedrock-guardrailConfig field in the request body.
You enable the guardrail but the contentType isn't application/json.
You provide a guardrail identifier, but guardrailVersion isn't specified.
The version number for the guardrail. The value can also be DRAFT.
Model performance settings for the request.
", "location":"header", "locationName":"X-Amzn-Bedrock-PerformanceConfig-Latency" } }, "payload":"body" }, "InvokeModelWithResponseStreamResponse":{ "type":"structure", "required":[ "body", "contentType" ], "members":{ "body":{ "shape":"ResponseStream", "documentation":"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.
The MIME type of the inference result.
", "location":"header", "locationName":"X-Amzn-Bedrock-Content-Type" }, "performanceConfigLatency":{ "shape":"PerformanceConfigLatency", "documentation":"Model performance settings for the request.
", "location":"header", "locationName":"X-Amzn-Bedrock-PerformanceConfig-Latency" } }, "payload":"body" }, "InvokedModelId":{ "type":"string", "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}::foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2})|(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):inference-profile/[a-zA-Z0-9-:.]+)" }, "KmsKeyId":{ "type":"string", "max":2048, "min":1, "pattern":"arn:aws(-[^:]+)?:kms:[a-zA-Z0-9-]*:[0-9]{12}:((key/[a-zA-Z0-9-]{36})|(alias/[a-zA-Z0-9-_/]+))" }, "ListAsyncInvokesRequest":{ "type":"structure", "members":{ "submitTimeAfter":{ "shape":"Timestamp", "documentation":"Include invocations submitted after this time.
", "location":"querystring", "locationName":"submitTimeAfter" }, "submitTimeBefore":{ "shape":"Timestamp", "documentation":"Include invocations submitted before this time.
", "location":"querystring", "locationName":"submitTimeBefore" }, "statusEquals":{ "shape":"AsyncInvokeStatus", "documentation":"Filter invocations by status.
", "location":"querystring", "locationName":"statusEquals" }, "maxResults":{ "shape":"MaxResults", "documentation":"The maximum number of invocations to return in one page of results.
", "location":"querystring", "locationName":"maxResults" }, "nextToken":{ "shape":"PaginationToken", "documentation":"Specify the pagination token from a previous request to retrieve the next page of results.
", "location":"querystring", "locationName":"nextToken" }, "sortBy":{ "shape":"SortAsyncInvocationBy", "documentation":"How to sort the response.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"The sorting order for the response.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListAsyncInvokesResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"Specify the pagination token from a previous request to retrieve the next page of results.
" }, "asyncInvokeSummaries":{ "shape":"AsyncInvokeSummaries", "documentation":"A list of invocation summaries.
" } } }, "Long":{ "type":"long", "box":true }, "MaxResults":{ "type":"integer", "box":true, "max":1000, "min":1 }, "Message":{ "type":"structure", "required":[ "role", "content" ], "members":{ "role":{ "shape":"ConversationRole", "documentation":"The role that the message plays in the message.
" }, "content":{ "shape":"ContentBlocks", "documentation":"The message content. Note the following restrictions:
You can include up to 20 images. Each image's size, height, and width must be no more than 3.75 MB, 8000 px, and 8000 px, respectively.
You can include up to five documents. Each document's size must be no more than 4.5 MB.
If you include a ContentBlock with a document field in the array, you must also include a ContentBlock with a text field.
You can only include images and documents if the role is user.
A message input, or returned from, a call to Converse or ConverseStream.
" }, "MessageStartEvent":{ "type":"structure", "required":["role"], "members":{ "role":{ "shape":"ConversationRole", "documentation":"The role for the message.
" } }, "documentation":"The start of a message.
", "event":true }, "MessageStopEvent":{ "type":"structure", "required":["stopReason"], "members":{ "stopReason":{ "shape":"StopReason", "documentation":"The reason why the model stopped generating output.
" }, "additionalModelResponseFields":{ "shape":"Document", "documentation":"The additional model response fields.
" } }, "documentation":"The stop event for a message.
", "event":true }, "Messages":{ "type":"list", "member":{"shape":"Message"} }, "MimeType":{"type":"string"}, "ModelErrorException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"}, "originalStatusCode":{ "shape":"StatusCode", "documentation":"The original status code.
" }, "resourceName":{ "shape":"NonBlankString", "documentation":"The resource name.
" } }, "documentation":"The request failed due to an error while processing the model.
", "error":{ "httpStatusCode":424, "senderFault":true }, "exception":true }, "ModelInputPayload":{ "type":"structure", "members":{ }, "document":true, "sensitive":true }, "ModelNotReadyException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"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.
", "error":{ "httpStatusCode":429, "senderFault":true }, "exception":true, "retryable":{"throttling":false} }, "ModelOutputs":{ "type":"list", "member":{"shape":"GuardrailOutputText"} }, "ModelStreamErrorException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"}, "originalStatusCode":{ "shape":"StatusCode", "documentation":"The original status code.
" }, "originalMessage":{ "shape":"NonBlankString", "documentation":"The original message.
" } }, "documentation":"An error occurred while streaming the response. Retry your request.
", "error":{ "httpStatusCode":424, "senderFault":true }, "exception":true }, "ModelTimeoutException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"The request took too long to process. Processing time exceeded the model timeout length.
", "error":{ "httpStatusCode":408, "senderFault":true }, "exception":true }, "NonBlankString":{ "type":"string", "pattern":"[\\s\\S]*" }, "NonEmptyString":{ "type":"string", "min":1 }, "NonNegativeInteger":{ "type":"integer", "box":true, "min":0 }, "PaginationToken":{ "type":"string", "max":2048, "min":1, "pattern":"\\S*" }, "PartBody":{ "type":"blob", "max":1000000, "min":0, "sensitive":true }, "PayloadPart":{ "type":"structure", "members":{ "bytes":{ "shape":"PartBody", "documentation":"Base64-encoded bytes of payload data.
" } }, "documentation":"Payload content included in the response.
", "event":true, "sensitive":true }, "PerformanceConfigLatency":{ "type":"string", "enum":[ "standard", "optimized" ] }, "PerformanceConfiguration":{ "type":"structure", "members":{ "latency":{ "shape":"PerformanceConfigLatency", "documentation":"To use a latency-optimized version of the model, set to optimized.
Performance settings for a model.
" }, "PromptRouterTrace":{ "type":"structure", "members":{ "invokedModelId":{ "shape":"InvokedModelId", "documentation":"The ID of the invoked model.
" } }, "documentation":"A prompt router trace.
" }, "PromptVariableMap":{ "type":"map", "key":{"shape":"String"}, "value":{"shape":"PromptVariableValues"}, "sensitive":true }, "PromptVariableValues":{ "type":"structure", "members":{ "text":{ "shape":"String", "documentation":"The text value that the variable maps to.
" } }, "documentation":"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.
", "union":true }, "ReasoningContentBlock":{ "type":"structure", "members":{ "reasoningText":{ "shape":"ReasoningTextBlock", "documentation":"The reasoning that the model used to return the output.
" }, "redactedContent":{ "shape":"Blob", "documentation":"The content in the reasoning that was encrypted by the model provider for safety reasons. The encryption doesn't affect the quality of responses.
" } }, "documentation":"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.
", "sensitive":true, "union":true }, "ReasoningContentBlockDelta":{ "type":"structure", "members":{ "text":{ "shape":"String", "documentation":"The reasoning that the model used to return the output.
" }, "redactedContent":{ "shape":"Blob", "documentation":"The content in the reasoning that was encrypted by the model provider for safety reasons. The encryption doesn't affect the quality of responses.
" }, "signature":{ "shape":"String", "documentation":"A token that verifies that the reasoning text was generated by the model. If you pass a reasoning block back to the API in a multi-turn conversation, include the text and its signature unmodified.
" } }, "documentation":"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.
", "sensitive":true, "union":true }, "ReasoningTextBlock":{ "type":"structure", "required":["text"], "members":{ "text":{ "shape":"String", "documentation":"The reasoning that the model used to return the output.
" }, "signature":{ "shape":"String", "documentation":"A token that verifies that the reasoning text was generated by the model. If you pass a reasoning block back to the API in a multi-turn conversation, include the text and its signature unmodified.
" } }, "documentation":"Contains the reasoning that the model used to return the output.
", "sensitive":true }, "RequestMetadata":{ "type":"map", "key":{"shape":"RequestMetadataKeyString"}, "value":{"shape":"RequestMetadataValueString"}, "max":16, "min":1, "sensitive":true }, "RequestMetadataKeyString":{ "type":"string", "max":256, "min":1, "pattern":"[a-zA-Z0-9\\s:_@$#=/+,-.]{1,256}" }, "RequestMetadataValueString":{ "type":"string", "max":256, "min":0, "pattern":"[a-zA-Z0-9\\s:_@$#=/+,-.]{0,256}" }, "ResourceNotFoundException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"The specified resource ARN was not found. For troubleshooting this error, see ResourceNotFound in the Amazon Bedrock User Guide
", "error":{ "httpStatusCode":404, "senderFault":true }, "exception":true }, "ResponseStream":{ "type":"structure", "members":{ "chunk":{ "shape":"PayloadPart", "documentation":"Content included in the response.
" }, "internalServerException":{ "shape":"InternalServerException", "documentation":"An internal server error occurred. Retry your request.
" }, "modelStreamErrorException":{ "shape":"ModelStreamErrorException", "documentation":"An error occurred while streaming the response. Retry your request.
" }, "validationException":{ "shape":"ValidationException", "documentation":"Input validation failed. Check your request parameters and retry the request.
" }, "throttlingException":{ "shape":"ThrottlingException", "documentation":"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.
" }, "modelTimeoutException":{ "shape":"ModelTimeoutException", "documentation":"The request took too long to process. Processing time exceeded the model timeout length.
" }, "serviceUnavailableException":{ "shape":"ServiceUnavailableException", "documentation":"The service isn't available. Try again later.
" } }, "documentation":"Definition of content in the response stream.
", "eventstream":true }, "S3Location":{ "type":"structure", "required":["uri"], "members":{ "uri":{ "shape":"S3Uri", "documentation":"An object URI starting with s3://.
If the bucket belongs to another AWS account, specify that account's ID.
" } }, "documentation":"A storage location in an S3 bucket.
" }, "S3Uri":{ "type":"string", "max":1024, "min":1, "pattern":"s3://[a-z0-9][\\.\\-a-z0-9]{1,61}[a-z0-9](/.*)?" }, "ServiceQuotaExceededException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"Your request exceeds the service quota for your account. You can view your quotas at Viewing service quotas. You can resubmit your request later.
", "error":{ "httpStatusCode":400, "senderFault":true }, "exception":true }, "ServiceUnavailableException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide
", "error":{"httpStatusCode":503}, "exception":true, "fault":true }, "SortAsyncInvocationBy":{ "type":"string", "enum":["SubmissionTime"] }, "SortOrder":{ "type":"string", "enum":[ "Ascending", "Descending" ] }, "SpecificToolChoice":{ "type":"structure", "required":["name"], "members":{ "name":{ "shape":"ToolName", "documentation":"The name of the tool that the model must request.
" } }, "documentation":"The model must request a specific tool. For example, {\"tool\" : {\"name\" : \"Your tool name\"}}.
This field is only supported by Anthropic Claude 3 models.
Specify idempotency token to ensure that requests are not duplicated.
", "idempotencyToken":true }, "modelId":{ "shape":"AsyncInvokeIdentifier", "documentation":"The model to invoke.
" }, "modelInput":{ "shape":"ModelInputPayload", "documentation":"Input to send to the model.
" }, "outputDataConfig":{ "shape":"AsyncInvokeOutputDataConfig", "documentation":"Where to store the output.
" }, "tags":{ "shape":"TagList", "documentation":"Tags to apply to the invocation.
" } } }, "StartAsyncInvokeResponse":{ "type":"structure", "required":["invocationArn"], "members":{ "invocationArn":{ "shape":"InvocationArn", "documentation":"The ARN of the invocation.
" } } }, "StatusCode":{ "type":"integer", "box":true, "max":599, "min":100 }, "StopReason":{ "type":"string", "enum":[ "end_turn", "tool_use", "max_tokens", "stop_sequence", "guardrail_intervened", "content_filtered" ] }, "String":{"type":"string"}, "SystemContentBlock":{ "type":"structure", "members":{ "text":{ "shape":"NonEmptyString", "documentation":"A system prompt for the model.
" }, "guardContent":{ "shape":"GuardrailConverseContentBlock", "documentation":"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.
" } }, "documentation":"A system content block.
", "union":true }, "SystemContentBlocks":{ "type":"list", "member":{"shape":"SystemContentBlock"} }, "Tag":{ "type":"structure", "required":[ "key", "value" ], "members":{ "key":{ "shape":"TagKey", "documentation":"The tag's key.
" }, "value":{ "shape":"TagValue", "documentation":"The tag's value.
" } }, "documentation":"A tag.
" }, "TagKey":{ "type":"string", "max":128, "min":1, "pattern":"[a-zA-Z0-9\\s._:/=+@-]*" }, "TagList":{ "type":"list", "member":{"shape":"Tag"}, "max":200, "min":0 }, "TagValue":{ "type":"string", "max":256, "min":0, "pattern":"[a-zA-Z0-9\\s._:/=+@-]*" }, "TextCharactersGuarded":{ "type":"integer", "box":true }, "TextCharactersTotal":{ "type":"integer", "box":true }, "ThrottlingException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"Your request was denied due to exceeding the account quotas for Amazon Bedrock. For troubleshooting this error, see ThrottlingException in the Amazon Bedrock User Guide
", "error":{ "httpStatusCode":429, "senderFault":true }, "exception":true }, "Timestamp":{ "type":"timestamp", "timestampFormat":"iso8601" }, "TokenUsage":{ "type":"structure", "required":[ "inputTokens", "outputTokens", "totalTokens" ], "members":{ "inputTokens":{ "shape":"TokenUsageInputTokensInteger", "documentation":"The number of tokens sent in the request to the model.
" }, "outputTokens":{ "shape":"TokenUsageOutputTokensInteger", "documentation":"The number of tokens that the model generated for the request.
" }, "totalTokens":{ "shape":"TokenUsageTotalTokensInteger", "documentation":"The total of input tokens and tokens generated by the model.
" } }, "documentation":"The tokens used in a message API inference call.
" }, "TokenUsageInputTokensInteger":{ "type":"integer", "box":true, "min":0 }, "TokenUsageOutputTokensInteger":{ "type":"integer", "box":true, "min":0 }, "TokenUsageTotalTokensInteger":{ "type":"integer", "box":true, "min":0 }, "Tool":{ "type":"structure", "members":{ "toolSpec":{ "shape":"ToolSpecification", "documentation":"The specfication for the tool.
" } }, "documentation":"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.
", "union":true }, "ToolChoice":{ "type":"structure", "members":{ "auto":{ "shape":"AutoToolChoice", "documentation":"(Default). The Model automatically decides if a tool should be called or whether to generate text instead.
" }, "any":{ "shape":"AnyToolChoice", "documentation":"The model must request at least one tool (no text is generated).
" }, "tool":{ "shape":"SpecificToolChoice", "documentation":"The Model must request the specified tool. Only supported by Anthropic Claude 3 models.
" } }, "documentation":"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.
An array of tools that you want to pass to a model.
" }, "toolChoice":{ "shape":"ToolChoice", "documentation":"If supported by model, forces the model to request a tool.
" } }, "documentation":"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.
" }, "ToolConfigurationToolsList":{ "type":"list", "member":{"shape":"Tool"}, "min":1 }, "ToolInputSchema":{ "type":"structure", "members":{ "json":{ "shape":"Document", "documentation":"The JSON schema for the tool. For more information, see JSON Schema Reference.
" } }, "documentation":"The schema for the tool. The top level schema type must be object.
The ID of the tool request that this is the result for.
" }, "content":{ "shape":"ToolResultContentBlocks", "documentation":"The content for tool result content block.
" }, "status":{ "shape":"ToolResultStatus", "documentation":"The status for the tool result content block.
This field is only supported Anthropic Claude 3 models.
A tool result block that contains the results for a tool request that the model previously made.
" }, "ToolResultContentBlock":{ "type":"structure", "members":{ "json":{ "shape":"Document", "documentation":"A tool result that is JSON format data.
" }, "text":{ "shape":"String", "documentation":"A tool result that is text.
" }, "image":{ "shape":"ImageBlock", "documentation":"A tool result that is an image.
This field is only supported by Anthropic Claude 3 models.
A tool result that is a document.
" }, "video":{ "shape":"VideoBlock", "documentation":"A tool result that is video.
" } }, "documentation":"The tool result content block.
", "union":true }, "ToolResultContentBlocks":{ "type":"list", "member":{"shape":"ToolResultContentBlock"} }, "ToolResultStatus":{ "type":"string", "enum":[ "success", "error" ] }, "ToolSpecification":{ "type":"structure", "required":[ "name", "inputSchema" ], "members":{ "name":{ "shape":"ToolName", "documentation":"The name for the tool.
" }, "description":{ "shape":"NonEmptyString", "documentation":"The description for the tool.
" }, "inputSchema":{ "shape":"ToolInputSchema", "documentation":"The input schema for the tool in JSON format.
" } }, "documentation":"The specification for the tool.
" }, "ToolUseBlock":{ "type":"structure", "required":[ "toolUseId", "name", "input" ], "members":{ "toolUseId":{ "shape":"ToolUseId", "documentation":"The ID for the tool request.
" }, "name":{ "shape":"ToolName", "documentation":"The name of the tool that the model wants to use.
" }, "input":{ "shape":"Document", "documentation":"The input to pass to the tool.
" } }, "documentation":"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.
" }, "ToolUseBlockDelta":{ "type":"structure", "required":["input"], "members":{ "input":{ "shape":"String", "documentation":"The input for a requested tool.
" } }, "documentation":"The delta for a tool use block.
" }, "ToolUseBlockStart":{ "type":"structure", "required":[ "toolUseId", "name" ], "members":{ "toolUseId":{ "shape":"ToolUseId", "documentation":"The ID for the tool request.
" }, "name":{ "shape":"ToolName", "documentation":"The name of the tool that the model is requesting to use.
" } }, "documentation":"The start of a tool use block.
" }, "ToolUseId":{ "type":"string", "max":64, "min":1, "pattern":"[a-zA-Z0-9_-]+" }, "Trace":{ "type":"string", "enum":[ "ENABLED", "DISABLED" ] }, "ValidationException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"The input fails to satisfy the constraints specified by Amazon Bedrock. For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide
", "error":{ "httpStatusCode":400, "senderFault":true }, "exception":true }, "VideoBlock":{ "type":"structure", "required":[ "format", "source" ], "members":{ "format":{ "shape":"VideoFormat", "documentation":"The block's format.
" }, "source":{ "shape":"VideoSource", "documentation":"The block's source.
" } }, "documentation":"A video block.
" }, "VideoFormat":{ "type":"string", "enum":[ "mkv", "mov", "mp4", "webm", "flv", "mpeg", "mpg", "wmv", "three_gp" ] }, "VideoSource":{ "type":"structure", "members":{ "bytes":{ "shape":"VideoSourceBytesBlob", "documentation":"Video content encoded in base64.
" }, "s3Location":{ "shape":"S3Location", "documentation":"The location of a video object in an S3 bucket.
" } }, "documentation":"A video source. You can upload a smaller video as a base64-encoded string as long as the encoded file is less than 25MB. You can also transfer videos up to 1GB in size from an S3 bucket.
", "union":true }, "VideoSourceBytesBlob":{ "type":"blob", "min":1 } }, "documentation":"Describes the API operations for running inference using Amazon Bedrock models.
" }