Enum values for ActionGroupSignature.

Enum values for ActionGroupSignature.

Enum values for ActionInvocationType.

Enum values for ActionInvocationType.

Enum values for ActionInvocationType.

Enum values for AttributeType.

Enum values for AttributeType.

Enum values for AttributeType.

Enum values for AttributeType.

Enum values for ConfirmationState.

Enum values for ConfirmationState.

Enum values for ConversationRole.

Enum values for ConversationRole.

Enum values for CreationMode.

Enum values for CreationMode.

Enum values for CustomControlMethod.

Enum values for ExecutionType.

Enum values for ExecutionType.

Enum values for ExternalSourceType.

Enum values for ExternalSourceType.

Enum values for FileSourceType.

Enum values for FileSourceType.

Enum values for FileUseCase.

Enum values for FileUseCase.

Enum values for FlowCompletionReason.

Enum values for FlowCompletionReason.

Enum values for GeneratedQueryType.

Enum values for GuadrailAction.

Enum values for GuadrailAction.

Enum values for GuardrailAction.

Enum values for GuardrailAction.

Enum values for GuardrailContentFilterConfidence.

Enum values for GuardrailContentFilterConfidence.

Enum values for GuardrailContentFilterConfidence.

Enum values for GuardrailContentFilterConfidence.

Enum values for GuardrailContentFilterType.

Enum values for GuardrailContentFilterType.

Enum values for GuardrailContentFilterType.

Enum values for GuardrailContentFilterType.

Enum values for GuardrailContentFilterType.

Enum values for GuardrailContentFilterType.

Enum values for GuardrailContentPolicyAction.

Enum values for GuardrailManagedWordType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailPiiEntityType.

Enum values for GuardrailSensitiveInformationPolicyAction.

Enum values for GuardrailSensitiveInformationPolicyAction.

Enum values for GuardrailTopicPolicyAction.

Enum values for GuardrailTopicType.

Enum values for GuardrailWordPolicyAction.

Enum values for ImageFormat.

Enum values for ImageFormat.

Enum values for ImageFormat.

Enum values for ImageFormat.

Enum values for InputQueryType.

Enum values for InvocationType.

Enum values for InvocationType.

Enum values for InvocationType.

Enum values for InvocationType.

Enum values for InvocationType.

Enum values for MemoryType.

Enum values for NodeType.

Enum values for NodeType.

Enum values for NodeType.

Enum values for NodeType.

Enum values for NodeType.

Enum values for NodeType.

Enum values for NodeType.

Enum values for ParameterType.

Enum values for ParameterType.

Enum values for ParameterType.

Enum values for ParameterType.

Enum values for ParameterType.

Enum values for PayloadType.

Enum values for PayloadType.

Enum values for PerformanceConfigLatency.

Enum values for PerformanceConfigLatency.

Enum values for PromptState.

Enum values for PromptState.

Enum values for PromptType.

Enum values for PromptType.

Enum values for PromptType.

Enum values for PromptType.

Enum values for PromptType.

Enum values for QueryTransformationMode.

Enum values for QueryTransformationType.

Enum values for RequireConfirmation.

Enum values for RequireConfirmation.

Enum values for RerankDocumentType.

Enum values for RerankDocumentType.

Enum values for RerankingConfigurationType.

Enum values for RerankingMetadataSelectionMode.

Enum values for RerankingMetadataSelectionMode.

Enum values for RerankQueryContentType.

Enum values for RerankSourceType.

Enum values for ResponseState.

Enum values for ResponseState.

Enum values for RetrievalResultContentColumnType.

Enum values for RetrievalResultContentColumnType.

Enum values for RetrievalResultContentColumnType.

Enum values for RetrievalResultContentColumnType.

Enum values for RetrievalResultContentColumnType.

Enum values for RetrievalResultContentColumnType.

Enum values for RetrievalResultContentType.

Enum values for RetrievalResultContentType.

Enum values for RetrievalResultContentType.

Enum values for RetrievalResultLocationType.

Enum values for RetrievalResultLocationType.

Enum values for RetrievalResultLocationType.

Enum values for RetrievalResultLocationType.

Enum values for RetrievalResultLocationType.

Enum values for RetrievalResultLocationType.

Enum values for RetrievalResultLocationType.

Enum values for RetrievalResultLocationType.

Enum values for RetrieveAndGenerateType.

Enum values for RetrieveAndGenerateType.

Enum values for SearchType.

Enum values for SearchType.

Enum values for SessionStatus.

Enum values for SessionStatus.

Enum values for SessionStatus.

Enum values for Source.

Enum values for Source.

Enum values for Source.

Enum values for TextToSqlConfigurationType.

Enum values for Type.

Enum values for Type.

Enum values for Type.

Enum values for Type.

Enum values for Type.

Enum values for Type.

Enum values for VectorSearchRerankingConfigurationType.

The request is denied because of missing access permissions.

To return the action group invocation results directly in the InvokeInlineAgent response, specify RETURN_CONTROL .

The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action.

Contains information about the action group being invoked.

Contains the JSON-formatted string returned by the API invoked by the action group.

Contains details of the inline agent's action group.

Input for an agent collaborator.

An agent collaborator invocation input.

Output from an agent collaborator.

Output from an agent collaborator.

An event in which the prompt was analyzed in preparation for optimization.

Contains information about the API operation that the agent predicts should be called.

Information about a parameter to provide to the API request.

The request body to provide for the API request, as the agent elicited from the user.

Contains information about the API operation that was called from the action group and the response body that was returned.

The JSON or YAML-formatted payload defining the OpenAPI schema for the action group.

Contains details about the S3 object containing the OpenAPI schema for the action group.

Contains citations for a part of an agent response.

There was an issue with a dependency due to a server issue.

Settings for a model called with InvokeAgent.

Contains configurations for an Amazon Bedrock reranker model.

Contains configurations for a reranker model.

The image in the invocation step.

The text in the invocation step.

This property contains the document to chat with, along with its attributes.

The property contains the file to chat with, along with its attributes.

The caller's agent alias ARN.

An object containing a segment of the generated response that is based on a source in the knowledge base, alongside information about the source.

A citation event.

Contains information about the code interpreter being invoked.

Contains the JSON-formatted string returned by the API invoked by the code interpreter.

There was a conflict performing an operation.

The block's text.

Contains the body of the API response.

A conversation history.

The trace behavior for the custom orchestration.

The event in the custom orchestration sequence.

There was an issue with a dependency.

The unique external source of the content contained in the wrapper object.

Contains the generation configuration of the external source wrapper object.

The configurations of the external source wrapper object in the retrieveAndGenerate function.

Contains information about the failure of the interaction.

Contains information for a metadata field to include in or exclude from consideration when reranking.

Contains intermediate response for code interpreter if any files have been generated.

The source file of the content contained in the wrapper object.

Specifies the name that the metadata attribute must match and the value to which to compare the value of the metadata attribute.

Contains details about the response to the user.

Contains information about why a flow completed.

Contains information about an input into the prompt flow and where to send it.

The input to send to the prompt flow input node.

The requested additional input to send back to the multi-turn flow node.

Response object from the flow multi-turn node requesting additional information.

The content in the output.

Contains information about an output from prompt flow invoction.

Contains information about why the flow completed.

The event stream containing the multi-turn input request information from the flow.

Contains information about an output from flow invocation.

Contains information about a trace, which tracks an input or output for a node in the flow.

Contains information about a condition that was satisfied.

Contains information about an output from a condition node.

Contains information about a trace, which tracks an input or output for a node in the flow.

Contains information about an output from a condition node.

Contains information about the input into a node.

Contains information about the output from a node.

The content of the node input.

Contains information about the input into a node.

Contains information about a field in the input into a node.

The content of the node output.

Contains information about the output from a node.

Contains information about a field in the output from a node.

Defines parameters that the agent needs to invoke from the user to complete the function.

Contains information about the function that the agent predicts should be called.

Contains information about a parameter of the function.

Contains information about the function that was called from the action group and the response that was returned.

A list of functions that each define an action in the action group.

Contains information about a query generated for a natural language query.

Contains metadata about a part of the generated response that is accompanied by a citation.

Contains configurations for response generation based on the knowledge base query results.

Assessment details of the content analyzed by Guardrails.

The configuration details for the guardrail.

The configuration details for the guardrail.

Details of the content filter used in the Guardrail.

The details of the policy assessment in the Guardrails filter.

The custom word details for the filter in the Guardrail.

A guardrail event.

The managed word details for the filter in the Guardrail.

The Guardrail filter to identify and remove personally identifiable information (PII).

The details for the regex filter used in the Guardrail.

The details of the sensitive policy assessment used in the Guardrail.

The details for a specific topic defined in the Guardrail.

The details of the policy assessment used in the Guardrail.

The trace details used in the Guardrail.

The assessment details for words defined in the Guardrail filter.

Image content for an invocation step.

The raw image bytes for the image.

The path to the Amazon S3 bucket where the image is stored.

Settings for implicit filtering, where a model generates a metadata filter based on the prompt.

The configuration for inference settings when generating responses using RetrieveAndGenerate.

Specifications about the inference parameters that were provided alongside the prompt.

Contains intermediate response for code interpreter if any files have been generated.

Contains a part of an agent response and citations for it.

Contains a part of an agent response and citations for it.

Contains intermediate response for code interpreter if any files have been generated.

Contains the parameters and information that the agent elicited from the customer to carry out an action.

Contains information about the agent and session, alongside the agent's reasoning process and results from calling actions and querying knowledge bases and metadata about the trace.

Contains information to return from the action group that the agent has predicted to invoke.

Contains information about the agent and session, alongside the agent's reasoning process and results from calling API actions and querying knowledge bases and metadata about the trace.

Settings for a model called with InvokeInlineAgent.

Contains parameters that specify various attributes that persist across a session or prompt.

Contains details of the source files.

Contains information about the text prompt to optimize.

An internal server error occurred.

Contains information pertaining to the action group or knowledge base that is being invoked.

Contains information about the API operation that the agent predicts should be called.

Contains information about the function that the agent predicts should be called.

The result from the API response from the action group invocation.

The result from the function from the action group invocation.

Stores fine-grained state checkpoints, including text and images, for each interaction in an invocation in a session.

The content for the invocation step.

Contains details about an invocation step within an invocation in a session.

Contains details about an invocation in a session.

Details of the knowledge base associated withe inline agent.

Configurations to apply to a knowledge base attached to the agent during query.

Contains details about the knowledge base to look up and the query to be made.

Contains details about the results from looking up the knowledge base.

Contains the query made to the knowledge base.

Contains configurations for knowledge base query.

Details about a result from querying the knowledge base.

Contains details about the resource being queried.

Configurations for how to perform the search query and return results.

Contains summary of a session.

Contains details of a session summary.

Details about a message.

Provides details of the foundation model.

Details about a metadata attribute.

Contains configurations for the metadata to use in reranking.

The input for the pre-processing step.

The model specified in the request is not ready to serve inference requests.

The performance configuration for a model called with InvokeFlow.

Contains the result or output of an action group or knowledge base, or the response to the user.

An event in which the prompt was optimized.

Contains information about the text in the prompt that was optimized.

An event in which the prompt was analyzed in preparation for optimization.

An event in which the prompt was optimized.

Settings for how the model processes the prompt prior to retrieval and generation.

The foundation model output from the orchestration step.

Contains information pertaining to the action group or knowledge base that is being invoked.

The input for the orchestration step.

Contains information pertaining to the output from the foundation model that is being invoked.

Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.

Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

Contains details of the response from code interpreter.

A parameter for the API request or function.

Contains details about a parameter in a function for an action group.

Contains a part of an agent response and citations for it.

Performance settings for a model.

The foundation model output from the post-processing step.

Details about the response from the Lambda parsing of the output from the post-processing step.

The input for the post-processing step.

The foundation model output from the post-processing step.

The foundation model output from the pre-processing step.

Details about the response from the Lambda parsing of the output from the pre-processing step.

The input for the pre-processing step.

The foundation model output from the pre-processing step.

Contains configurations to override a prompt template in one part of an agent sequence.

Contains configurations to override prompts in different parts of an agent sequence.

Contains the template for the prompt that's sent to the model for response generation.

Contains the parameters in the request body.

Contains information about a natural language query to transform into SQL.

To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION .

Contains the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.

Contains the raw output from the foundation model.

Contains information about the reasoning that the model used to return the content in the content block.

The content in the reasoning that was encrypted by the model provider for trust and safety reasons.

Contains information about the reasoning that the model used to return the content in the content block.

Contains details about the agent's response to reprompt the input.

The parameters in the API request body.

Contains information about a document to rerank.

Contains configurations for reranking.

An array of objects, each of which specifies a metadata field to exclude from consideration when reranking.

An array of objects, each of which specifies a metadata field to include in consideration when reranking.

Contains information about a query to submit to the reranker model.

Contains information about a document that was reranked.

Contains information about a source for reranking.

Contains information about a text document to rerank.

The specified resource Amazon Resource Name (ARN) was not found.

Contains a part of an agent response and citations for it.

Contains intermediate response for code interpreter if any files have been generated.

Contains the parameters and information that the agent elicited from the customer to carry out an action.

Contains information about the agent and session, alongside the agent's reasoning process and results from calling actions and querying knowledge bases and metadata about the trace.

Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.

Knowledge base data sources that contain a metadata attribute whose name matches the key and whose value doesn't match the value in this object are returned.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.

Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object.

Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following: - A string that contains the value as a substring.

The Confluence data source location.

Contains information about a chunk of text from a data source in the knowledge base.

Contains information about a column with a cell to return in retrieval.

Contains information about the location of a document in a custom data source.

The location of a result in Amazon Kendra.

Contains information about the data source location.

The S3 data source location.

The Salesforce data source location.

The SharePoint data source location.

Contains information about the SQL query used to retrieve the result.

The web URL/URLs data source location.

Contains details about the resource being queried.

Contains the query made to the knowledge base.

Contains the response generated from querying the knowledge base.

A retrieve and generate output event.

Contains configuration about the session with the knowledge base.

A citation event.

A guardrail event.

An output event.

Contains metadata about a source cited for the generated response.

Contains information to return from the action group that the agent has predicted to invoke.

An action invocation result.

Invocation output from a routing classifier model.

The classifier's invocation input.

The classifier's model invocation input.

The classifier's model invocation output.

The classifier's observation.

The identifier information for an Amazon S3 bucket.

Information about the Amazon S3 bucket where the image is stored.

The unique wrapper object of the document from the S3 location.

Contains details of the s3 object where the source file is located.

The number of requests exceeds the service quota.

Contains parameters that specify various attributes that persist across a session or prompt.

Contains details about a session.

Contains information about where the text with a citation begins and ends in the generated output.

Configurations for streaming.

Configuration settings for text generation using a language model via the RetrieveAndGenerate operation.

Contains information about the text prompt to optimize.

Contains the part of the generated text that contains a citation, alongside where it begins and ends.

Contains configurations for transforming text to SQL.

Contains configurations for a knowledge base to use in transformation.

The number of requests exceeds the limit.

Details about the custom orchestration step in which the agent determines the order in which actions are executed.

Contains information about the failure of the interaction.

The trace details for a trace defined in the Guardrail filter.

Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.

Details about the post-processing step, in which the agent shapes the response..

Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.

A routing classifier's trace.

Contains information about the agent and session, alongside the agent's reasoning process and results from calling API actions and querying knowledge bases and metadata about the trace.

Contains configurations for transforming the natural language query into SQL.

UnknownUnionMember is returned when a union member is returned over the wire, but has an unknown tag.

Contains information of the usage of the foundation model.

Input validation failed.

Contains configurations for reranking with an Amazon Bedrock reranker model.

Contains configurations for an Amazon Bedrock reranker model.

Contains configurations for reranking the retrieved results.

Contains details about the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.

Contains details about the OpenAPI schema for the action group.

A block of content that you pass to, or receive from, a Amazon Bedrock session in an invocation step.

Details about a caller.

A content block.

Contains information about an input into the flow.

The content structure containing input information for multi-turn flow interactions.

Contains information about the content in an output from prompt flow invocation.

The output of the flow.

Contains information about an input or output for a node in the flow.

Contains the content of the node input.

Contains the content of the node output.

Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.

The source for an image.

The response from invoking the agent and associated citations and trace information.

Contains information about the prompt to optimize.

Contains details about the API operation or function that the agent predicts should be called.

A result from the invocation of an action.

Payload content, such as text and images, for the invocation step.

Contains sessions summaries.

Contains information about the optimized prompt.

The stream containing events in the prompt optimization process.

Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.

Details about the post-processing step, in which the agent shapes the response.

Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.

Contains content regarding the reasoning that the foundation model made with respect to the content in the content block.

Contains configurations for the metadata fields to include or exclude when considering reranking.

The response from invoking the agent and associated citations and trace information.

Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results.

A retrieve and generate stream response output.

A trace for a routing classifier.

Contains one part of the agent's reasoning process and results from calling API actions and querying knowledge bases.