Awso_bedrock_runtime.ValuesSourceval structure_to_value_aux :
('a * 'b option) list ->
f:(('a * 'b) list -> 'c) ->
[> `Structure of 'c ]val structure_to_wrapped_value :
wrapper:'a ->
response:'a ->
('b * 'c option) list ->
[> `Structure of ('a * [> `Structure of ('b * 'c) list ]) list ]References a portion of the original input text that corresponds to logical elements.
A logical statement that includes both formal logic representation and natural language explanation.
Contains the logical translation of natural language input into formal logical statements, including premises, claims, and confidence scores.
Contains the actual content of a document that can be processed by the model and potentially cited in the response.
References a specific automated reasoning policy rule that was applied during evaluation.
Represents a logical scenario where claims can be evaluated as true or false, containing specific logical assignments.
Represents one possible logical interpretation of ambiguous input content.
A storage location in an Amazon S3 bucket.
A block within a search result that contains the content.
Identifies logical issues in the translated statements that exist independent of any policy rules, such as statements that are always true or always false.
Specifies a character-level location within a document, providing precise positioning information for cited content using start and end character indices.
Specifies a chunk-level location within a document, providing positioning information for cited content using logical document segments or chunks.
Specifies a page-level location within a document, providing positioning information for cited content using page numbers.
Specifies a search result location within the content array, providing positioning information for cited content using search result index and block positions.
Provides the URL and domain information for the website that was cited when performing a web search.
Contains the actual text content from a source document that is being cited or referenced in the model's response.
Configuration settings for enabling and controlling document citations in Converse API responses. When enabled, the model can include citation information that links generated content back to specific source documents.
Contains the content of a document.
A block containing error information when content processing fails.
The source for an image.
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.
Indicates that no valid claims can be made due to logical contradictions in the premises or rules.
Indicates that the claims are logically false and contradictory to the established rules or premises.
Indicates that no relevant logical information could be extracted from the input for validation.
Indicates that the claims could be either true or false depending on additional assumptions not provided in the input.
Indicates that the input exceeds the processing capacity due to the volume or complexity of the logical information.
Indicates that the input has multiple valid logical interpretations, requiring additional context or clarification.
Indicates that the claims are definitively true and logically implied by the premises, with no possible alternative interpretations.
Specifies the precise location within a source document where cited content can be found. This can include character-level positions, page numbers, or document chunks depending on the document type and indexing method.
A document to include in a message.
Image content for a message.
A search result block that enables natural citations with proper source attribution for retrieved content. This field is only supported by Anthropic Claude Opus 4.1, Opus 4, Sonnet 4.5, Sonnet 4, Sonnet 3.7, and 3.5 Haiku models.
A video block.
Represents a logical validation result from automated reasoning policy evaluation. The finding indicates whether claims in the input are logically valid, invalid, satisfiable, impossible, or have other logical issues.
The content filter for a guardrail.
The details for the guardrails contextual grounding filter.
The details of the guardrail image coverage.
The guardrail coverage for the text characters.
A Personally Identifiable Information (PII) entity configured in a guardrail.
A Regex filter configured in a guardrail.
Information about a topic guardrail.
A custom word configured in a guardrail.
A managed word configured in a guardrail.
Contains the generated text content that corresponds to or is supported by a citation from a source document.
Contains information about a citation that references a specific source document. Citations provide traceability between the model's generated response and the source documents that informed that response.
The image source (image bytes) of the guardrail converse image source.
The tool result content block. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
The action of the guardrail coverage details.
The details on the use of the guardrail.
The source of audio data, which can be provided either as raw bytes or a reference to an S3 location.
An image block that contains images that you want to assess with a guardrail.
A text block that contains text that you want to assess with a guardrail. For more information, see GuardrailConverseContentBlock.
Contains the reasoning that the model used to return the output.
Details about the specific guardrail that was applied during this assessment, including its identifier, version, ARN, origin, and ownership information.
Contains the results of automated reasoning policy evaluation, including logical findings about the validity of claims made in the input content.
An assessment of a content policy for a guardrail.
The policy assessment details for the guardrails contextual grounding filter.
The invocation metrics for the guardrail.
The assessment for a Personally Identifiable Information (PII) policy.
A behavior assessment of a topic policy.
The word policy assessment.
An audio content block that contains audio data in various supported formats.
Defines a section of content to be cached for reuse in subsequent API calls.
A content block that contains both generated text and associated citation information. This block type is returned when document citations are enabled, providing traceability between the generated content and the source documents that informed the response.
A content block for selective guarding with the Converse or ConverseStream API operations.
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.
A tool result block that contains the results for a tool request that the model previously made. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
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. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
The schema for the tool. The top level schema type must be object. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
A behavior assessment of the guardrail policies used in a call to the Converse API.
A block of content for a message that you pass to, or receive from, a model with the Converse or ConverseStream API operations.
Specifies a system-defined tool for the model to use. System-defined tools are tools that are created and provided by the model provider.
The specification for the tool. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
Contains incremental updates to the source content text during streaming responses, allowing clients to build up the cited content progressively.
The model must request at least one tool (no text is generated). For example, {"any" : {}}. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
The Model automatically decides if a tool should be called or whether to generate text instead. For example, {"auto" : {}}. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide
The model must request a specific tool. For example, {"tool" : {"name" : "Your tool name"}}. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide This field is only supported by Anthropic Claude 3 models.
Information about a tool that you can use with the Converse API. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
Contains incremental updates to tool results information during streaming responses. This allows clients to build up tool results data progressively as the response is generated.
Cache creation metrics for a specific TTL duration
Asynchronous invocation output data settings.
A message input, or returned from, a call to Converse or ConverseStream.
Contains configurations for instructions to provide the model for how to handle input. To learn more, see Using the Converse API.
Determines which tools the model should request in a call to Converse or ConverseStream. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
Contains incremental updates to citation information during streaming responses. This allows clients to build up citation data progressively as the response is generated.
A streaming delta event that contains incremental image data during streaming responses.
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.
The delta for a tool use block.
The initial event in a streaming image block that indicates the start of image content.
The start of a tool result block. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
The start of a tool use block. For more information, see Call a tool with the Converse API in the Amazon Bedrock User Guide.
A Top level guardrail trace object. For more information, see ConverseTrace.
A prompt router trace.
JSON schema structured output format options.
The image source (image bytes) of the guardrail image source. Object used in independent api.
Asynchronous invocation output data settings.
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.
A block of content in a streaming response.
Content block start information.
Metrics for the stream.
The trace object in a response from ConverseStream.
Performance settings for a model.
Specifies the processing tier configuration used for serving the request.
The tokens used in a message API inference call.
The structure that the model's output must adhere to.
Contain an image which user wants guarded. This block is accepted by the guardrails independent API.
The text block to be evaluated by the guardrail.
A summary of an asynchronous invocation.
An internal server error occurred. For troubleshooting this error, see InternalFailure in the Amazon Bedrock User Guide
An error occurred while streaming the response. Retry your request.
The request took too long to process. Processing time exceeded the model timeout length.
Payload content included in the response.
The service isn't currently available. For troubleshooting this error, see ServiceUnavailable in the Amazon Bedrock User Guide
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
The input fails to satisfy the constraints specified by Amazon Bedrock. For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide
Output from the bidirectional stream. The output is speech and a text transcription.
Payload content for the bidirectional input. The input is an audio stream.
The inputs from a Converse API request for token counting. This structure mirrors the input format for the Converse operation, allowing you to count tokens for conversation-based inference requests.
The body of an InvokeModel API request for token counting. This structure mirrors the input format for the InvokeModel operation, allowing you to count tokens for raw text inference requests.
The content block delta event.
Content block start event.
A content block stop event.
A conversation stream metadata event.
The start of a message.
The stop event for a message.
Structured output parameters to control the model's response.
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.
The output content produced by the guardrail.
The content block to be evaluated by the guardrail.
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 occurred because of a conflict while performing an operation.
The specified resource ARN was not found. For troubleshooting this error, see ResourceNotFound in the Amazon Bedrock User Guide
Your request exceeds the service quota for your account. You can view your quotas at Viewing service quotas. You can resubmit your request later.
The request failed due to an error while processing the model.
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.
Definition of content in the response stream.
Output from the bidirectional stream that was used for model invocation.
Payload content, the speech chunk, for the bidirectional input of the invocation step.
The input value for token counting. The value should be either an InvokeModel or Converse request body.
ARN or ID of a Bedrock model
The messages output stream
Configuration information for a guardrail that you use with the ConverseStream action.
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.
Output configuration for a model response in a call to Converse or ConverseStream.
Metrics for a call to Converse.
The output from a call to Converse.
The trace object in a response from Converse.
Configuration information for a guardrail that you use with the Converse operation.
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.
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.
Lists asynchronous invocations.
Lists asynchronous invocations.
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
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
Invoke the specified Amazon Bedrock model to run inference using the bidirectional stream. The response is returned in a stream that remains open for 8 minutes. A single session can contain multiple prompts and responses from the model. The prompts to the model are provided as audio files and the model's responses are spoken back to the user and transcribed. It is possible for users to interrupt the model's response with a new prompt, which will halt the response speech. The model will retain contextual awareness of the conversation while pivoting to respond to the new prompt.
Invoke the specified Amazon Bedrock model to run inference using the bidirectional stream. The response is returned in a stream that remains open for 8 minutes. A single session can contain multiple prompts and responses from the model. The prompts to the model are provided as audio files and the model's responses are spoken back to the user and transcribed. It is possible for users to interrupt the model's response with a new prompt, which will halt the response speech. The model will retain contextual awareness of the conversation while pivoting to respond to the new prompt.
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
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
Retrieve information about an asynchronous invocation.
Retrieve information about an asynchronous invocation.
Returns the token count for a given inference request. This operation helps you estimate token usage before sending requests to foundation models by returning the token count that would be used if the same input were sent to the model in an inference request. Token counting is model-specific because different models use different tokenization strategies. The token count returned by this operation will match the token count that would be charged if the same input were sent to the model in an InvokeModel or Converse request. You can use this operation to: Estimate costs before sending inference requests. Optimize prompts to fit within token limits. Plan for token usage in your applications. This operation accepts the same input formats as InvokeModel and Converse, allowing you to count tokens for both raw text inputs and structured conversation formats. The following operations are related to CountTokens: InvokeModel - Sends inference requests to foundation models Converse - Sends conversation-based inference requests to foundation models
Returns the token count for a given inference request. This operation helps you estimate token usage before sending requests to foundation models by returning the token count that would be used if the same input were sent to the model in an inference request. Token counting is model-specific because different models use different tokenization strategies. The token count returned by this operation will match the token count that would be charged if the same input were sent to the model in an InvokeModel or Converse request. You can use this operation to: Estimate costs before sending inference requests. Optimize prompts to fit within token limits. Plan for token usage in your applications. This operation accepts the same input formats as InvokeModel and Converse, allowing you to count tokens for both raw text inputs and structured conversation formats. The following operations are related to CountTokens: InvokeModel - Sends inference requests to foundation models Converse - Sends conversation-based inference requests to foundation models
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
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
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. 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
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
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