Contains APIs related to model invocation and querying of knowledge bases.
", "operations": { "DeleteAgentMemory": "Deletes memory from the specified memory identifier.
", "GetAgentMemory": "Gets the sessions stored in the memory of the agent.
", "InvokeAgent": "The CLI doesn't support streaming operations in Amazon Bedrock, including InvokeAgent.
Sends a prompt for the agent to process and respond to. Note the following fields for the request:
To continue the same conversation with an agent, use the same sessionId value in the request.
To activate trace enablement, turn enableTrace to true. Trace enablement helps you follow the agent's reasoning process that led it to the information it processed, the actions it took, and the final result it yielded. For more information, see Trace enablement.
End a conversation by setting endSession to true.
In the sessionState object, you can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group.
The response is returned in the bytes field of the chunk object.
The attribution object contains citations for parts of the response.
If you set enableTrace to true in the request, you can trace the agent's steps and reasoning process that led it to the response.
If the action predicted was configured to return control, the response returns parameters for the action, elicited from the user, in the returnControl field.
Errors are also surfaced in the response.
Invokes an alias of a flow to run the inputs that you specify and return the output of each node as a stream. If there's an error, the error is returned. For more information, see Test a flow in Amazon Bedrock in the Amazon Bedrock User Guide.
The CLI doesn't support streaming operations in Amazon Bedrock, including InvokeFlow.
Queries a knowledge base and retrieves information from it.
", "RetrieveAndGenerate": "Queries a knowledge base and generates responses based on the retrieved results and using the specified foundation model or inference profile. The response only cites sources that are relevant to the query.
" }, "shapes": { "AccessDeniedException": { "base": "The request is denied because of missing access permissions. Check your permissions and retry your request.
", "refs": { "FlowResponseStream$accessDeniedException": "The request is denied because of missing access permissions. Check your permissions and retry your request.
", "ResponseStream$accessDeniedException": "The request is denied because of missing access permissions. Check your permissions and retry your request.
" } }, "ActionGroupInvocationInput": { "base": "Contains information about the action group being invoked. For more information about the possible structures, see the InvocationInput tab in OrchestrationTrace in the Amazon Bedrock User Guide.
", "refs": { "InvocationInput$actionGroupInvocationInput": "Contains information about the action group to be invoked.
" } }, "ActionGroupInvocationOutput": { "base": "Contains the JSON-formatted string returned by the API invoked by the action group.
", "refs": { "Observation$actionGroupInvocationOutput": "Contains the JSON-formatted string returned by the API invoked by the action group.
" } }, "ActionGroupName": { "base": null, "refs": { "ActionGroupInvocationInput$actionGroupName": "The name of the action group.
" } }, "ActionGroupOutputString": { "base": null, "refs": { "ActionGroupInvocationOutput$text": "The JSON-formatted string returned by the API invoked by the action group.
" } }, "ActionInvocationType": { "base": null, "refs": { "ApiInvocationInput$actionInvocationType": "Contains information about the API operation to invoke.
", "FunctionInvocationInput$actionInvocationType": "Contains information about the function to invoke,
" } }, "AdditionalModelRequestFields": { "base": null, "refs": { "ExternalSourcesGenerationConfiguration$additionalModelRequestFields": "Additional model parameters and their corresponding values not included in the textInferenceConfig structure for an external source. Takes in custom model parameters specific to the language model being used.
", "GenerationConfiguration$additionalModelRequestFields": "Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.
", "OrchestrationConfiguration$additionalModelRequestFields": "Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.
" } }, "AdditionalModelRequestFieldsKey": { "base": null, "refs": { "AdditionalModelRequestFields$key": null } }, "AdditionalModelRequestFieldsValue": { "base": null, "refs": { "AdditionalModelRequestFields$value": null } }, "AgentAliasId": { "base": null, "refs": { "DeleteAgentMemoryRequest$agentAliasId": "The unique identifier of an alias of an agent.
", "GetAgentMemoryRequest$agentAliasId": "The unique identifier of an alias of an agent.
", "InvokeAgentRequest$agentAliasId": "The alias of the agent to use.
", "TracePart$agentAliasId": "The unique identifier of the alias of the agent.
" } }, "AgentId": { "base": null, "refs": { "DeleteAgentMemoryRequest$agentId": "The unique identifier of the agent to which the alias belongs.
", "GetAgentMemoryRequest$agentId": "The unique identifier of the agent to which the alias belongs.
", "InvokeAgentRequest$agentId": "The unique identifier of the agent to use.
", "TracePart$agentId": "The unique identifier of the agent.
" } }, "AgentVersion": { "base": null, "refs": { "TracePart$agentVersion": "The version of the agent.
" } }, "ApiContentMap": { "base": null, "refs": { "ApiRequestBody$content": "The content of the request body. The key of the object in this field is a media type defining the format of the request body.
" } }, "ApiInvocationInput": { "base": "Contains information about the API operation that the agent predicts should be called.
This data type is used in the following API operations:
In the returnControl field of the InvokeAgent response
Contains information about the API operation that the agent predicts should be called.
" } }, "ApiParameter": { "base": "Information about a parameter to provide to the API request.
This data type is used in the following API operations:
", "refs": { "ApiParameters$member": null } }, "ApiParameters": { "base": null, "refs": { "ApiInvocationInput$parameters": "The parameters to provide for the API request, as the agent elicited from the user.
" } }, "ApiPath": { "base": null, "refs": { "ActionGroupInvocationInput$apiPath": "The path to the API to call, based off the action group.
", "ApiInvocationInput$apiPath": "The path to the API operation.
", "ApiResult$apiPath": "The path to the API operation.
" } }, "ApiRequestBody": { "base": "The request body to provide for the API request, as the agent elicited from the user.
This data type is used in the following API operations:
", "refs": { "ApiInvocationInput$requestBody": "The request body to provide for the API request, as the agent elicited from the user.
" } }, "ApiResult": { "base": "Contains information about the API operation that was called from the action group and the response body that was returned.
This data type is used in the following API operations:
In the returnControlInvocationResults of the InvokeAgent request
The result from the API response from the action group invocation.
" } }, "Attribution": { "base": "Contains citations for a part of an agent response.
", "refs": { "PayloadPart$attribution": "Contains citations for a part of an agent response.
" } }, "BadGatewayException": { "base": "There was an issue with a dependency due to a server issue. Retry your request.
", "refs": { "FlowResponseStream$badGatewayException": "There was an issue with a dependency due to a server issue. Retry your request.
", "ResponseStream$badGatewayException": "There was an issue with a dependency due to a server issue. Retry your request.
" } }, "BedrockModelArn": { "base": null, "refs": { "ExternalSourcesRetrieveAndGenerateConfiguration$modelArn": "The model Amazon Resource Name (ARN) for the external source wrapper object in the retrieveAndGenerate function.
The ARN of the foundation model or inference profile used to generate a response.
" } }, "Boolean": { "base": null, "refs": { "CodeInterpreterInvocationOutput$executionTimeout": "Indicates if the execution of the code timed out.
", "InvokeAgentRequest$enableTrace": "Specifies whether to turn on the trace or not to track the agent's reasoning process. For more information, see Trace enablement.
", "InvokeAgentRequest$endSession": "Specifies whether to end the session with the agent or not.
", "InvokeFlowRequest$enableTrace": "Specifies whether to return the trace for the flow or not. Traces track inputs and outputs for nodes in the flow. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "PreProcessingParsedResponse$isValid": "Whether the user input is valid or not. If false, the agent doesn't proceed to orchestration.
The byte value of the file to upload, encoded as a Base-64 string.
", "ByteContentFile$data": "The raw bytes of the file to attach. The maximum size of all files that is attached is 10MB. You can attach a maximum of 5 files.
" } }, "ByteContentDoc": { "base": "This property contains the document to chat with, along with its attributes.
", "refs": { "ExternalSource$byteContent": "The identifier, contentType, and data of the external source wrapper object.
" } }, "ByteContentFile": { "base": "The property contains the file to chat with, along with its attributes.
", "refs": { "FileSource$byteContent": "The data and the text of the attached files.
" } }, "Citation": { "base": "An object containing a segment of the generated response that is based on a source in the knowledge base, alongside information about the source.
This data type is used in the following API operations:
InvokeAgent response – in the citations field
RetrieveAndGenerate response – in the citations field
A list of citations and related information for a part of an agent response.
", "RetrieveAndGenerateResponse$citations": "A list of segments of the generated response that are based on sources in the knowledge base, alongside information about the sources.
" } }, "CodeInterpreterInvocationInput": { "base": "Contains information about the code interpreter being invoked.
", "refs": { "InvocationInput$codeInterpreterInvocationInput": "Contains information about the code interpreter to be invoked.
" } }, "CodeInterpreterInvocationOutput": { "base": "Contains the JSON-formatted string returned by the API invoked by the code interpreter.
", "refs": { "Observation$codeInterpreterInvocationOutput": "Contains the JSON-formatted string returned by the API invoked by the code interpreter.
" } }, "ConfirmationState": { "base": null, "refs": { "ApiResult$confirmationState": "Controls the API operations or functions to invoke based on the user confirmation.
", "FunctionResult$confirmationState": "Contains the user confirmation information about the function that was called.
" } }, "ConflictException": { "base": "There was a conflict performing an operation. Resolve the conflict and retry your request.
", "refs": { "FlowResponseStream$conflictException": "There was a conflict performing an operation. Resolve the conflict and retry your request.
", "ResponseStream$conflictException": "There was a conflict performing an operation. Resolve the conflict and retry your request.
" } }, "ContentBody": { "base": "Contains the body of the API response.
This data type is used in the following API operations:
In the returnControlInvocationResults field of the InvokeAgent request
The content in the request body.
" } }, "ContentType": { "base": null, "refs": { "ByteContentDoc$contentType": "The MIME type of the document contained in the wrapper object.
" } }, "CreationMode": { "base": null, "refs": { "ModelInvocationInput$parserMode": "Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType.
Specifies whether the default prompt template was OVERRIDDEN. If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.
Time Stamp.
", "refs": { "FlowTraceConditionNodeResultEvent$timestamp": "The date and time that the trace was returned.
", "FlowTraceNodeInputEvent$timestamp": "The date and time that the trace was returned.
", "FlowTraceNodeOutputEvent$timestamp": "The date and time that the trace was returned.
", "MemorySessionSummary$sessionExpiryTime": "The time when the memory duration for the session is set to end.
", "MemorySessionSummary$sessionStartTime": "The start time for this session.
" } }, "DeleteAgentMemoryRequest": { "base": null, "refs": { } }, "DeleteAgentMemoryResponse": { "base": null, "refs": { } }, "DependencyFailedException": { "base": "There was an issue with a dependency. Check the resource configurations and retry the request.
", "refs": { "FlowResponseStream$dependencyFailedException": "There was an issue with a dependency. Check the resource configurations and retry the request.
", "ResponseStream$dependencyFailedException": "There was an issue with a dependency. Check the resource configurations and retry the request.
" } }, "Document": { "base": null, "refs": { "FlowInputContent$document": "The input to send to the prompt flow input node.
", "FlowOutputContent$document": "The content in the output.
", "FlowTraceNodeInputContent$document": "The content of the node input.
", "FlowTraceNodeOutputContent$document": "The content of the node output.
" } }, "Double": { "base": null, "refs": { "KnowledgeBaseRetrievalResult$score": "The level of relevance of the result to the query.
" } }, "ExecutionType": { "base": null, "refs": { "ActionGroupInvocationInput$executionType": "How fulfillment of the action is handled. For more information, see Handling fulfillment of the action.
" } }, "ExternalSource": { "base": "The unique external source of the content contained in the wrapper object.
", "refs": { "ExternalSources$member": null } }, "ExternalSourceType": { "base": null, "refs": { "ExternalSource$sourceType": "The source type of the external source wrapper object.
" } }, "ExternalSources": { "base": null, "refs": { "ExternalSourcesRetrieveAndGenerateConfiguration$sources": "The document for the external source wrapper object in the retrieveAndGenerate function.
Contains the generation configuration of the external source wrapper object.
", "refs": { "ExternalSourcesRetrieveAndGenerateConfiguration$generationConfiguration": "The prompt used with the external source wrapper object with the retrieveAndGenerate function.
The configurations of the external source wrapper object in the retrieveAndGenerate function.
The configuration for the external source wrapper object in the retrieveAndGenerate function.
The reason the interaction failed.
" } }, "FailureTrace": { "base": "Contains information about the failure of the interaction.
", "refs": { "Trace$failureTrace": "Contains information about the failure of the interaction.
" } }, "FileBody": { "base": null, "refs": { "OutputFile$bytes": "The byte count of files that contains response from code interpreter.
" } }, "FilePart": { "base": "Contains intermediate response for code interpreter if any files have been generated.
", "refs": { "ResponseStream$files": "Contains intermediate response for code interpreter if any files have been generated.
" } }, "FileSource": { "base": "The source file of the content contained in the wrapper object.
", "refs": { "InputFile$source": "Specifies where the files are located.
" } }, "FileSourceType": { "base": null, "refs": { "FileSource$sourceType": "The source type of the files to attach.
" } }, "FileUseCase": { "base": null, "refs": { "InputFile$useCase": "Specifies how the source files will be used by the code interpreter.
" } }, "Files": { "base": null, "refs": { "CodeInterpreterInvocationInput$files": "Files that are uploaded for code interpreter to use.
", "CodeInterpreterInvocationOutput$files": "Contains output files, if generated by code execution.
" } }, "FilterAttribute": { "base": "Specifies the name that the metadata attribute must match and the value to which to compare the value of the metadata attribute. For more information, see Query configurations.
This data type is used in the following API operations:
", "refs": { "RetrievalFilter$equals": "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.
The following example would return data sources with an animal attribute whose value is cat:
\"equals\": { \"key\": \"animal\", \"value\": \"cat\" }
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.
The following example would return data sources with an year attribute whose value is greater than 1989:
\"greaterThan\": { \"key\": \"year\", \"value\": 1989 }
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.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989:
\"greaterThanOrEquals\": { \"key\": \"year\", \"value\": 1989 }
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.
The following example would return data sources with an animal attribute that is either cat or dog:
\"in\": { \"key\": \"animal\", \"value\": [\"cat\", \"dog\"] }
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.
The following example would return data sources with an year attribute whose value is less than to 1989.
\"lessThan\": { \"key\": \"year\", \"value\": 1989 }
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.
The following example would return data sources with an year attribute whose value is less than or equal to 1989.
\"lessThanOrEquals\": { \"key\": \"year\", \"value\": 1989 }
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.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example [\"dog\", \"cat\"]).
\"listContains\": { \"key\": \"animals\", \"value\": \"cat\" }
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.
The following example would return data sources that don't contain an animal attribute whose value is cat.
\"notEquals\": { \"key\": \"animal\", \"value\": \"cat\" }
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.
The following example would return data sources whose animal attribute is neither cat nor dog.
\"notIn\": { \"key\": \"animal\", \"value\": [\"cat\", \"dog\"] }
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. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).
\"startsWith\": { \"key\": \"animal\", \"value\": \"ca\" }
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 following example would return data sources with an animal attribute that contains the substring at (for example cat).
\"stringContains\": { \"key\": \"animal\", \"value\": \"at\" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example [\"dog\", \"cat\"]).
\"stringContains\": { \"key\": \"animals\", \"value\": \"at\" }
The name that the metadata attribute must match.
" } }, "FilterValue": { "base": null, "refs": { "FilterAttribute$value": "The value to whcih to compare the value of the metadata attribute.
" } }, "FinalResponse": { "base": "Contains details about the response to the user.
", "refs": { "Observation$finalResponse": "Contains details about the response to the user.
" } }, "FinalResponseString": { "base": null, "refs": { "FinalResponse$text": "The text in the response to the user.
" } }, "FlowAliasIdentifier": { "base": null, "refs": { "InvokeFlowRequest$flowAliasIdentifier": "The unique identifier of the flow alias.
" } }, "FlowCompletionEvent": { "base": "Contains information about why a flow completed.
", "refs": { "FlowResponseStream$flowCompletionEvent": "Contains information about why the flow completed.
" } }, "FlowCompletionReason": { "base": null, "refs": { "FlowCompletionEvent$completionReason": "The reason that the flow completed.
" } }, "FlowIdentifier": { "base": null, "refs": { "InvokeFlowRequest$flowIdentifier": "The unique identifier of the flow.
" } }, "FlowInput": { "base": "Contains information about an input into the prompt flow and where to send it.
", "refs": { "FlowInputs$member": null } }, "FlowInputContent": { "base": "Contains information about an input into the flow.
", "refs": { "FlowInput$content": "Contains information about an input into the prompt flow.
" } }, "FlowInputs": { "base": null, "refs": { "InvokeFlowRequest$inputs": "A list of objects, each containing information about an input into the flow.
" } }, "FlowOutputContent": { "base": "Contains information about the content in an output from prompt flow invocation.
", "refs": { "FlowOutputEvent$content": "The content in the output.
" } }, "FlowOutputEvent": { "base": "Contains information about an output from prompt flow invoction.
", "refs": { "FlowResponseStream$flowOutputEvent": "Contains information about an output from flow invocation.
" } }, "FlowResponseStream": { "base": "The output of the flow.
", "refs": { "InvokeFlowResponse$responseStream": "The output of the flow, returned as a stream. If there's an error, the error is returned.
" } }, "FlowTrace": { "base": "Contains information about an input or output for a node in the flow. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTraceEvent$trace": "The trace object containing information about an input or output for a node in the flow.
" } }, "FlowTraceCondition": { "base": "Contains information about a condition that was satisfied. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTraceConditions$member": null } }, "FlowTraceConditionNodeResultEvent": { "base": "Contains information about an output from a condition node. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTrace$conditionNodeResultTrace": "Contains information about an output from a condition node.
" } }, "FlowTraceConditions": { "base": null, "refs": { "FlowTraceConditionNodeResultEvent$satisfiedConditions": "An array of objects containing information about the conditions that were satisfied.
" } }, "FlowTraceEvent": { "base": "Contains information about a trace, which tracks an input or output for a node in the flow. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowResponseStream$flowTraceEvent": "Contains information about a trace, which tracks an input or output for a node in the flow.
" } }, "FlowTraceNodeInputContent": { "base": "Contains the content of the node input. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTraceNodeInputField$content": "The content of the node input.
" } }, "FlowTraceNodeInputEvent": { "base": "Contains information about the input into a node. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTrace$nodeInputTrace": "Contains information about the input into a node.
" } }, "FlowTraceNodeInputField": { "base": "Contains information about a field in the input into a node. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTraceNodeInputFields$member": null } }, "FlowTraceNodeInputFields": { "base": null, "refs": { "FlowTraceNodeInputEvent$fields": "An array of objects containing information about each field in the input.
" } }, "FlowTraceNodeOutputContent": { "base": "Contains the content of the node output. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTraceNodeOutputField$content": "The content of the node output.
" } }, "FlowTraceNodeOutputEvent": { "base": "Contains information about the output from a node. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTrace$nodeOutputTrace": "Contains information about the output from a node.
" } }, "FlowTraceNodeOutputField": { "base": "Contains information about a field in the output from a node. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
", "refs": { "FlowTraceNodeOutputFields$member": null } }, "FlowTraceNodeOutputFields": { "base": null, "refs": { "FlowTraceNodeOutputEvent$fields": "An array of objects containing information about each field in the output.
" } }, "Function": { "base": null, "refs": { "ActionGroupInvocationInput$function": "The function in the action group to call.
" } }, "FunctionInvocationInput": { "base": "Contains information about the function that the agent predicts should be called.
This data type is used in the following API operations:
In the returnControl field of the InvokeAgent response
Contains information about the function that the agent predicts should be called.
" } }, "FunctionParameter": { "base": "Contains information about a parameter of the function.
This data type is used in the following API operations:
In the returnControl field of the InvokeAgent response
A list of parameters of the function.
" } }, "FunctionResult": { "base": "Contains information about the function that was called from the action group and the response that was returned.
This data type is used in the following API operations:
In the returnControlInvocationResults of the InvokeAgent request
The result from the function from the action group invocation.
" } }, "GeneratedResponsePart": { "base": "Contains metadata about a part of the generated response that is accompanied by a citation.
This data type is used in the following API operations:
InvokeAgent response – in the generatedResponsePart field
RetrieveAndGenerate response – in the generatedResponsePart field
Contains the generated response and metadata
" } }, "GenerationConfiguration": { "base": "Contains configurations for response generation based on the knowledge base query results.
This data type is used in the following API operations:
", "refs": { "KnowledgeBaseRetrieveAndGenerateConfiguration$generationConfiguration": "Contains configurations for response generation based on the knowledge base query results.
" } }, "GetAgentMemoryRequest": { "base": null, "refs": { } }, "GetAgentMemoryResponse": { "base": null, "refs": { } }, "GuadrailAction": { "base": null, "refs": { "RetrieveAndGenerateResponse$guardrailAction": "Specifies if there is a guardrail intervention in the response.
" } }, "GuardrailAction": { "base": null, "refs": { "GuardrailTrace$action": "The trace action details used with the Guardrail.
" } }, "GuardrailAssessment": { "base": "Assessment details of the content analyzed by Guardrails.
", "refs": { "GuardrailAssessmentList$member": null } }, "GuardrailAssessmentList": { "base": null, "refs": { "GuardrailTrace$inputAssessments": "The details of the input assessments used in the Guardrail Trace.
", "GuardrailTrace$outputAssessments": "The details of the output assessments used in the Guardrail Trace.
" } }, "GuardrailConfiguration": { "base": "The configuration details for the guardrail.
", "refs": { "ExternalSourcesGenerationConfiguration$guardrailConfiguration": "The configuration details for the guardrail.
", "GenerationConfiguration$guardrailConfiguration": "The configuration details for the guardrail.
" } }, "GuardrailConfigurationGuardrailIdString": { "base": null, "refs": { "GuardrailConfiguration$guardrailId": "The unique identifier for the guardrail.
" } }, "GuardrailConfigurationGuardrailVersionString": { "base": null, "refs": { "GuardrailConfiguration$guardrailVersion": "The version of the guardrail.
" } }, "GuardrailContentFilter": { "base": "Details of the content filter used in the Guardrail.
", "refs": { "GuardrailContentFilterList$member": null } }, "GuardrailContentFilterConfidence": { "base": null, "refs": { "GuardrailContentFilter$confidence": "The confidence level regarding the content detected in the filter by the Guardrail.
" } }, "GuardrailContentFilterList": { "base": null, "refs": { "GuardrailContentPolicyAssessment$filters": "The filter details of the policy assessment used in the Guardrails filter.
" } }, "GuardrailContentFilterType": { "base": null, "refs": { "GuardrailContentFilter$type": "The type of content detected in the filter by the Guardrail.
" } }, "GuardrailContentPolicyAction": { "base": null, "refs": { "GuardrailContentFilter$action": "The action placed on the content by the Guardrail filter.
" } }, "GuardrailContentPolicyAssessment": { "base": "The details of the policy assessment in the Guardrails filter.
", "refs": { "GuardrailAssessment$contentPolicy": "Content policy details of the Guardrail.
" } }, "GuardrailCustomWord": { "base": "The custom word details for the filter in the Guardrail.
", "refs": { "GuardrailCustomWordList$member": null } }, "GuardrailCustomWordList": { "base": null, "refs": { "GuardrailWordPolicyAssessment$customWords": "The custom word details for words defined in the Guardrail filter.
" } }, "GuardrailManagedWord": { "base": "The managed word details for the filter in the Guardrail.
", "refs": { "GuardrailManagedWordList$member": null } }, "GuardrailManagedWordList": { "base": null, "refs": { "GuardrailWordPolicyAssessment$managedWordLists": "The managed word lists for words defined in the Guardrail filter.
" } }, "GuardrailManagedWordType": { "base": null, "refs": { "GuardrailManagedWord$type": "The type details for the managed word filter in the Guardrail.
" } }, "GuardrailPiiEntityFilter": { "base": "The Guardrail filter to identify and remove personally identifiable information (PII).
", "refs": { "GuardrailPiiEntityFilterList$member": null } }, "GuardrailPiiEntityFilterList": { "base": null, "refs": { "GuardrailSensitiveInformationPolicyAssessment$piiEntities": "The details of the PII entities used in the sensitive policy assessment for the Guardrail.
" } }, "GuardrailPiiEntityType": { "base": null, "refs": { "GuardrailPiiEntityFilter$type": "The type of PII the Guardrail filter has identified and removed.
" } }, "GuardrailRegexFilter": { "base": "The details for the regex filter used in the Guardrail.
", "refs": { "GuardrailRegexFilterList$member": null } }, "GuardrailRegexFilterList": { "base": null, "refs": { "GuardrailSensitiveInformationPolicyAssessment$regexes": "The details of the regexes used in the sensitive policy assessment for the Guardrail.
" } }, "GuardrailSensitiveInformationPolicyAction": { "base": null, "refs": { "GuardrailPiiEntityFilter$action": "The action of the Guardrail filter to identify and remove PII.
", "GuardrailRegexFilter$action": "The action details for the regex filter used in the Guardrail.
" } }, "GuardrailSensitiveInformationPolicyAssessment": { "base": "The details of the sensitive policy assessment used in the Guardrail.
", "refs": { "GuardrailAssessment$sensitiveInformationPolicy": "Sensitive Information policy details of Guardrail.
" } }, "GuardrailTopic": { "base": "The details for a specific topic defined in the Guardrail.
", "refs": { "GuardrailTopicList$member": null } }, "GuardrailTopicList": { "base": null, "refs": { "GuardrailTopicPolicyAssessment$topics": "The topic details of the policy assessment used in the Guardrail.
" } }, "GuardrailTopicPolicyAction": { "base": null, "refs": { "GuardrailTopic$action": "The action details on a specific topic in the Guardrail.
" } }, "GuardrailTopicPolicyAssessment": { "base": "The details of the policy assessment used in the Guardrail.
", "refs": { "GuardrailAssessment$topicPolicy": "Topic policy details of the Guardrail.
" } }, "GuardrailTopicType": { "base": null, "refs": { "GuardrailTopic$type": "The type details on a specific topic in the Guardrail.
" } }, "GuardrailTrace": { "base": "The trace details used in the Guardrail.
", "refs": { "Trace$guardrailTrace": "The trace details for a trace defined in the Guardrail filter.
" } }, "GuardrailWordPolicyAction": { "base": null, "refs": { "GuardrailCustomWord$action": "The action details for the custom word filter in the Guardrail.
", "GuardrailManagedWord$action": "The action details for the managed word filter in the Guardrail.
" } }, "GuardrailWordPolicyAssessment": { "base": "The assessment details for words defined in the Guardrail filter.
", "refs": { "GuardrailAssessment$wordPolicy": "Word policy details of the Guardrail.
" } }, "Identifier": { "base": null, "refs": { "ByteContentDoc$identifier": "The file name of the document contained in the wrapper object.
" } }, "InferenceConfig": { "base": "The configuration for inference settings when generating responses using RetrieveAndGenerate.
", "refs": { "ExternalSourcesGenerationConfiguration$inferenceConfig": "Configuration settings for inference when using RetrieveAndGenerate to generate responses while using an external source.
", "GenerationConfiguration$inferenceConfig": "Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
", "OrchestrationConfiguration$inferenceConfig": "Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
" } }, "InferenceConfiguration": { "base": "Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.
", "refs": { "ModelInvocationInput$inferenceConfiguration": "Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.
" } }, "InputFile": { "base": "Contains details of the source files.
", "refs": { "InputFiles$member": null } }, "InputFiles": { "base": null, "refs": { "SessionState$files": "Contains information about the files used by code interpreter.
" } }, "InputText": { "base": null, "refs": { "InvokeAgentRequest$inputText": "The prompt text to send the agent.
If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.
http status code from API execution response (for example: 200, 400, 500).
", "Usage$inputTokens": "Contains information about the input tokens from the foundation model usage.
", "Usage$outputTokens": "Contains information about the output tokens from the foundation model usage.
" } }, "InternalServerException": { "base": "An internal server error occurred. Retry your request.
", "refs": { "FlowResponseStream$internalServerException": "An internal server error occurred. Retry your request.
", "ResponseStream$internalServerException": "An internal server error occurred. Retry your request.
" } }, "InvocationInput": { "base": "Contains information pertaining to the action group or knowledge base that is being invoked.
", "refs": { "OrchestrationTrace$invocationInput": "Contains information pertaining to the action group or knowledge base that is being invoked.
" } }, "InvocationInputMember": { "base": "Contains details about the API operation or function that the agent predicts should be called.
This data type is used in the following API operations:
In the returnControl field of the InvokeAgent response
A list of objects that contain information about the parameters and inputs that need to be sent into the API operation or function, based on what the agent determines from its session with the user.
" } }, "InvocationResultMember": { "base": "A result from the invocation of an action. For more information, see Return control to the agent developer and Control session context.
This data type is used in the following API operations:
", "refs": { "ReturnControlInvocationResults$member": null } }, "InvocationType": { "base": null, "refs": { "InvocationInput$invocationType": "Specifies whether the agent is invoking an action group or a knowledge base.
" } }, "InvokeAgentRequest": { "base": null, "refs": { } }, "InvokeAgentResponse": { "base": null, "refs": { } }, "InvokeFlowRequest": { "base": null, "refs": { } }, "InvokeFlowResponse": { "base": null, "refs": { } }, "KmsKeyArn": { "base": null, "refs": { "RetrieveAndGenerateSessionConfiguration$kmsKeyArn": "The ARN of the KMS key encrypting the session.
" } }, "KnowledgeBaseConfiguration": { "base": "Configurations to apply to a knowledge base attached to the agent during query. For more information, see Knowledge base retrieval configurations.
", "refs": { "KnowledgeBaseConfigurations$member": null } }, "KnowledgeBaseConfigurations": { "base": null, "refs": { "SessionState$knowledgeBaseConfigurations": "An array of configurations, each of which applies to a knowledge base attached to the agent.
" } }, "KnowledgeBaseId": { "base": null, "refs": { "KnowledgeBaseConfiguration$knowledgeBaseId": "The unique identifier for a knowledge base attached to the agent.
", "KnowledgeBaseRetrieveAndGenerateConfiguration$knowledgeBaseId": "The unique identifier of the knowledge base that is queried.
", "RetrieveRequest$knowledgeBaseId": "The unique identifier of the knowledge base to query.
" } }, "KnowledgeBaseLookupInput": { "base": "Contains details about the knowledge base to look up and the query to be made.
", "refs": { "InvocationInput$knowledgeBaseLookupInput": "Contains details about the knowledge base to look up and the query to be made.
" } }, "KnowledgeBaseLookupInputString": { "base": null, "refs": { "KnowledgeBaseLookupInput$text": "The query made to the knowledge base.
" } }, "KnowledgeBaseLookupOutput": { "base": "Contains details about the results from looking up the knowledge base.
", "refs": { "Observation$knowledgeBaseLookupOutput": "Contains details about the results from looking up the knowledge base.
" } }, "KnowledgeBaseQuery": { "base": "Contains the query made to the knowledge base.
This data type is used in the following API operations:
Retrieve request – in the retrievalQuery field
Contains the query to send the knowledge base.
" } }, "KnowledgeBaseQueryTextString": { "base": null, "refs": { "KnowledgeBaseQuery$text": "The text of the query made to the knowledge base.
" } }, "KnowledgeBaseRetrievalConfiguration": { "base": "Contains configurations for knowledge base query. For more information, see Query configurations.
This data type is used in the following API operations:
Retrieve request – in the retrievalConfiguration field
RetrieveAndGenerate request – in the retrievalConfiguration field
The configurations to apply to the knowledge base during query. For more information, see Query configurations.
", "KnowledgeBaseRetrieveAndGenerateConfiguration$retrievalConfiguration": "Contains configurations for how to retrieve and return the knowledge base query.
", "RetrieveRequest$retrievalConfiguration": "Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
" } }, "KnowledgeBaseRetrievalResult": { "base": "Details about a result from querying the knowledge base.
This data type is used in the following API operations:
Retrieve response – in the retrievalResults field
A list of results from querying the knowledge base.
" } }, "KnowledgeBaseRetrieveAndGenerateConfiguration": { "base": "Contains details about the resource being queried.
This data type is used in the following API operations:
Retrieve request – in the knowledgeBaseConfiguration field
RetrieveAndGenerate request – in the knowledgeBaseConfiguration field
Contains details about the knowledge base for retrieving information and generating responses.
" } }, "KnowledgeBaseVectorSearchConfiguration": { "base": "Configurations for how to perform the search query and return results. For more information, see Query configurations.
This data type is used in the following API operations:
Retrieve request – in the vectorSearchConfiguration field
RetrieveAndGenerate request – in the vectorSearchConfiguration field
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
" } }, "KnowledgeBaseVectorSearchConfigurationNumberOfResultsInteger": { "base": null, "refs": { "KnowledgeBaseVectorSearchConfiguration$numberOfResults": "The number of source chunks to retrieve.
" } }, "LambdaArn": { "base": null, "refs": { "ModelInvocationInput$overrideLambda": "The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.
" } }, "MaxResults": { "base": "Max Results.
", "refs": { "GetAgentMemoryRequest$maxItems": "The maximum number of items to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
" } }, "MaximumLength": { "base": null, "refs": { "InferenceConfiguration$maximumLength": "The maximum number of tokens allowed in the generated response.
" } }, "Memories": { "base": null, "refs": { "GetAgentMemoryResponse$memoryContents": "Contains details of the sessions stored in the memory
" } }, "Memory": { "base": "Contains sessions summaries.
", "refs": { "Memories$member": null } }, "MemoryId": { "base": null, "refs": { "DeleteAgentMemoryRequest$memoryId": "The unique identifier of the memory.
", "GetAgentMemoryRequest$memoryId": "The unique identifier of the memory.
", "InvokeAgentRequest$memoryId": "The unique identifier of the agent memory.
", "InvokeAgentResponse$memoryId": "The unique identifier of the agent memory.
", "MemorySessionSummary$memoryId": "The unique identifier of the memory where the session summary is stored.
" } }, "MemorySessionSummary": { "base": "Contains details of a session summary.
", "refs": { "Memory$sessionSummary": "Contains summary of a session.
" } }, "MemoryType": { "base": null, "refs": { "GetAgentMemoryRequest$memoryType": "The type of memory.
" } }, "Metadata": { "base": "Provides details of the foundation model.
", "refs": { "OrchestrationModelInvocationOutput$metadata": "Contains information about the foundation model output from the orchestration step.
", "PostProcessingModelInvocationOutput$metadata": "Contains information about the foundation model output from the post-processing step.
", "PreProcessingModelInvocationOutput$metadata": "Contains information about the foundation model output from the pre-processing step.
" } }, "MimeType": { "base": null, "refs": { "ByteContentFile$mediaType": "The MIME type of data contained in the file used for chat.
", "InvokeAgentResponse$contentType": "The MIME type of the input data in the request. The default value is application/json.
The type of file that contains response from the code interpreter.
" } }, "ModelInvocationInput": { "base": "The input for the pre-processing step.
The type matches the agent step.
The text contains the prompt.
The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
The input for the orchestration step.
The type is ORCHESTRATION.
The text contains the prompt.
The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
The input for the post-processing step.
The type is POST_PROCESSING.
The text contains the prompt.
The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
The input for the pre-processing step.
The type is PRE_PROCESSING.
The text contains the prompt.
The inferenceConfiguration, parserMode, and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
If the total number of results is greater than the maxItems value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.
If the total number of results is greater than the maxItems value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.
If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.
If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.
The name of the node input.
" } }, "NodeName": { "base": null, "refs": { "FlowInput$nodeName": "The name of the flow input node that begins the prompt flow.
", "FlowOutputEvent$nodeName": "The name of the flow output node that the output is from.
", "FlowTraceConditionNodeResultEvent$nodeName": "The name of the condition node.
", "FlowTraceNodeInputEvent$nodeName": "The name of the node that received the input.
", "FlowTraceNodeOutputEvent$nodeName": "The name of the node that yielded the output.
" } }, "NodeOutputName": { "base": null, "refs": { "FlowInput$nodeOutputName": "The name of the output from the flow input node that begins the prompt flow.
", "FlowTraceNodeOutputField$nodeOutputName": "The name of the node output.
" } }, "NodeType": { "base": null, "refs": { "FlowOutputEvent$nodeType": "The type of the node that the output is from.
" } }, "NonBlankString": { "base": null, "refs": { "AccessDeniedException$message": null, "BadGatewayException$message": null, "BadGatewayException$resourceName": "The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
", "ConflictException$message": null, "DependencyFailedException$message": null, "DependencyFailedException$resourceName": "The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
", "InternalServerException$message": null, "ResourceNotFoundException$message": null, "ServiceQuotaExceededException$message": null, "ThrottlingException$message": null, "ValidationException$message": null } }, "Observation": { "base": "Contains the result or output of an action group or knowledge base, or the response to the user.
", "refs": { "OrchestrationTrace$observation": "Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.
" } }, "OrchestrationConfiguration": { "base": "Settings for how the model processes the prompt prior to retrieval and generation.
", "refs": { "KnowledgeBaseRetrieveAndGenerateConfiguration$orchestrationConfiguration": "Settings for how the model processes the prompt prior to retrieval and generation.
" } }, "OrchestrationModelInvocationOutput": { "base": "The foundation model output from the orchestration step.
", "refs": { "OrchestrationTrace$modelInvocationOutput": "Contains information pertaining to the output from the foundation model that is being invoked.
" } }, "OrchestrationTrace": { "base": "Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.
", "refs": { "Trace$orchestrationTrace": "Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.
" } }, "OutputFile": { "base": "Contains details of the response from code interpreter.
", "refs": { "OutputFiles$member": null } }, "OutputFiles": { "base": null, "refs": { "FilePart$files": "Files containing intermediate response for the user.
" } }, "OutputString": { "base": null, "refs": { "PostProcessingParsedResponse$text": "The text returned by the parser.
" } }, "Parameter": { "base": "A parameter for the API request or function.
", "refs": { "ParameterList$member": null, "Parameters$member": null } }, "ParameterList": { "base": null, "refs": { "PropertyParameters$properties": "A list of parameters in the request body.
" } }, "Parameters": { "base": null, "refs": { "ActionGroupInvocationInput$parameters": "The parameters in the Lambda input event.
", "ContentMap$value": null } }, "PartBody": { "base": null, "refs": { "PayloadPart$bytes": "A part of the agent response in bytes.
" } }, "PayloadPart": { "base": "Contains a part of an agent response and citations for it.
", "refs": { "ResponseStream$chunk": "Contains a part of an agent response and citations for it.
" } }, "PostProcessingModelInvocationOutput": { "base": "The foundation model output from the post-processing step.
", "refs": { "PostProcessingTrace$modelInvocationOutput": "The foundation model output from the post-processing step.
" } }, "PostProcessingParsedResponse": { "base": "Details about the response from the Lambda parsing of the output from the post-processing step.
", "refs": { "PostProcessingModelInvocationOutput$parsedResponse": "Details about the response from the Lambda parsing of the output of the post-processing step.
" } }, "PostProcessingTrace": { "base": "Details about the post-processing step, in which the agent shapes the response.
", "refs": { "Trace$postProcessingTrace": "Details about the post-processing step, in which the agent shapes the response..
" } }, "PreProcessingModelInvocationOutput": { "base": "The foundation model output from the pre-processing step.
", "refs": { "PreProcessingTrace$modelInvocationOutput": "The foundation model output from the pre-processing step.
" } }, "PreProcessingParsedResponse": { "base": "Details about the response from the Lambda parsing of the output from the pre-processing step.
", "refs": { "PreProcessingModelInvocationOutput$parsedResponse": "Details about the response from the Lambda parsing of the output of the pre-processing step.
" } }, "PreProcessingTrace": { "base": "Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.
", "refs": { "Trace$preProcessingTrace": "Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.
" } }, "PromptSessionAttributesMap": { "base": null, "refs": { "SessionState$promptSessionAttributes": "Contains attributes that persist across a prompt and the values of those attributes. These attributes replace the $prompt_session_attributes$ placeholder variable in the orchestration prompt template. For more information, see Prompt template placeholder variables.
" } }, "PromptTemplate": { "base": "Contains the template for the prompt that's sent to the model for response generation. For more information, see Knowledge base prompt templates.
This data type is used in the following API operations:
RetrieveAndGenerate request – in the filter field
Contain the textPromptTemplate string for the external source wrapper object.
", "GenerationConfiguration$promptTemplate": "Contains the template for the prompt that's sent to the model for response generation. Generation prompts must include the $search_results$ variable. For more information, see Use placeholder variables in the user guide.
Contains the template for the prompt that's sent to the model. Orchestration prompts must include the $conversation_history$ and $output_format_instructions$ variables. For more information, see Use placeholder variables in the user guide.
The text that prompted the agent at this step.
" } }, "PromptType": { "base": null, "refs": { "ModelInvocationInput$type": "The step in the agent sequence.
" } }, "PropertyParameters": { "base": "Contains the parameters in the request body.
", "refs": { "ApiContentMap$value": null } }, "QueryTransformationConfiguration": { "base": "To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.
To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.
The type of transformation to apply to the prompt.
" } }, "RAGStopSequences": { "base": null, "refs": { "TextInferenceConfig$stopSequences": "A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
" } }, "RAGStopSequencesMemberString": { "base": null, "refs": { "RAGStopSequences$member": null } }, "Rationale": { "base": "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.
", "refs": { "OrchestrationTrace$rationale": "Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.
" } }, "RationaleString": { "base": null, "refs": { "PreProcessingParsedResponse$rationale": "The text returned by the parsing of the pre-processing step, explaining the steps that the agent plans to take in orchestration, if the user input is valid.
", "Rationale$text": "The reasoning or thought process of the agent, based on the input.
" } }, "RawResponse": { "base": "Contains the raw output from the foundation model.
", "refs": { "OrchestrationModelInvocationOutput$rawResponse": "Contains details of the raw response from the foundation model output.
", "PostProcessingModelInvocationOutput$rawResponse": "Details of the raw response from the foundation model output.
", "PreProcessingModelInvocationOutput$rawResponse": "Details of the raw response from the foundation model output.
" } }, "RepromptResponse": { "base": "Contains details about the agent's response to reprompt the input.
", "refs": { "Observation$repromptResponse": "Contains details about the response to reprompt the input.
" } }, "RequestBody": { "base": "The parameters in the API request body.
", "refs": { "ActionGroupInvocationInput$requestBody": "The parameters in the request body for the Lambda input event.
" } }, "ResourceNotFoundException": { "base": "The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.
", "refs": { "FlowResponseStream$resourceNotFoundException": "The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.
", "ResponseStream$resourceNotFoundException": "The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.
" } }, "ResponseBody": { "base": null, "refs": { "ApiResult$responseBody": "The response body from the API operation. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.
The response from the function call using the parameters. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.
Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
", "FunctionResult$responseState": "Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
" } }, "ResponseStream": { "base": "The response from invoking the agent and associated citations and trace information.
", "refs": { "InvokeAgentResponse$completion": "The agent's response to the user prompt.
" } }, "RetrievalFilter": { "base": "Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
", "RetrievalFilterList$member": null } }, "RetrievalFilterList": { "base": null, "refs": { "RetrievalFilter$andAll": "Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
", "RetrievalFilter$orAll": "Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
" } }, "RetrievalResultConfluenceLocation": { "base": "The Confluence data source location.
", "refs": { "RetrievalResultLocation$confluenceLocation": "The Confluence data source location.
" } }, "RetrievalResultContent": { "base": "Contains the cited text from the data source.
This data type is used in the following API operations:
Retrieve response – in the content field
RetrieveAndGenerate response – in the content field
InvokeAgent response – in the content field
Contains a chunk of text from a data source in the knowledge base.
", "RetrievedReference$content": "Contains the cited text from the data source.
" } }, "RetrievalResultLocation": { "base": "Contains information about the data source location.
This data type is used in the following API operations:
Retrieve response – in the location field
RetrieveAndGenerate response – in the location field
InvokeAgent response – in the locatino field
Contains information about the location of the data source.
", "RetrievedReference$location": "Contains information about the location of the data source.
" } }, "RetrievalResultLocationType": { "base": null, "refs": { "RetrievalResultLocation$type": "The type of data source location.
" } }, "RetrievalResultMetadata": { "base": null, "refs": { "KnowledgeBaseRetrievalResult$metadata": "Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
", "RetrievedReference$metadata": "Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
" } }, "RetrievalResultMetadataKey": { "base": null, "refs": { "RetrievalResultMetadata$key": null } }, "RetrievalResultMetadataValue": { "base": null, "refs": { "RetrievalResultMetadata$value": null } }, "RetrievalResultS3Location": { "base": "The S3 data source location.
This data type is used in the following API operations:
Retrieve response – in the s3Location field
RetrieveAndGenerate response – in the s3Location field
InvokeAgent response – in the s3Location field
The S3 data source location.
" } }, "RetrievalResultSalesforceLocation": { "base": "The Salesforce data source location.
", "refs": { "RetrievalResultLocation$salesforceLocation": "The Salesforce data source location.
" } }, "RetrievalResultSharePointLocation": { "base": "The SharePoint data source location.
", "refs": { "RetrievalResultLocation$sharePointLocation": "The SharePoint data source location.
" } }, "RetrievalResultWebLocation": { "base": "The web URL/URLs data source location.
", "refs": { "RetrievalResultLocation$webLocation": "The web URL/URLs data source location.
" } }, "RetrieveAndGenerateConfiguration": { "base": "Contains details about the resource being queried.
This data type is used in the following API operations:
RetrieveAndGenerate request – in the retrieveAndGenerateConfiguration field
Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
" } }, "RetrieveAndGenerateInput": { "base": "Contains the query made to the knowledge base.
This data type is used in the following API operations:
RetrieveAndGenerate request – in the input field
Contains the query to be made to the knowledge base.
" } }, "RetrieveAndGenerateInputTextString": { "base": null, "refs": { "RetrieveAndGenerateInput$text": "The query made to the knowledge base.
" } }, "RetrieveAndGenerateOutput": { "base": "Contains the response generated from querying the knowledge base.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the output field
Contains the response generated from querying the knowledge base.
" } }, "RetrieveAndGenerateRequest": { "base": null, "refs": { } }, "RetrieveAndGenerateResponse": { "base": null, "refs": { } }, "RetrieveAndGenerateSessionConfiguration": { "base": "Contains configuration about the session with the knowledge base.
This data type is used in the following API operations:
RetrieveAndGenerate request – in the sessionConfiguration field
Contains details about the session with the knowledge base.
" } }, "RetrieveAndGenerateType": { "base": null, "refs": { "RetrieveAndGenerateConfiguration$type": "The type of resource that contains your data for retrieving information and generating responses.
If you choose ot use EXTERNAL_SOURCES, then currently only Claude 3 Sonnet models for knowledge bases are supported.
Contains metadata about a source cited for the generated response.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the retrievedReferences field
InvokeAgent response – in the retrievedReferences field
Contains metadata about the sources cited for the generated response.
", "KnowledgeBaseLookupOutput$retrievedReferences": "Contains metadata about the sources cited for the generated response.
" } }, "ReturnControlInvocationResults": { "base": null, "refs": { "SessionState$returnControlInvocationResults": "Contains information about the results from the action group invocation. For more information, see Return control to the agent developer and Control session context.
If you include this field, the inputText field will be ignored.
Contains information to return from the action group that the agent has predicted to invoke.
This data type is used in the following API operations:
", "refs": { "ResponseStream$returnControl": "Contains the parameters and information that the agent elicited from the customer to carry out an action. This information is returned to the system and can be used in your own setup for fulfilling the action.
" } }, "S3ObjectDoc": { "base": "The unique wrapper object of the document from the S3 location.
", "refs": { "ExternalSource$s3Location": "The S3 location of the external source wrapper object.
" } }, "S3ObjectFile": { "base": "Contains details of the s3 object where the source file is located.
", "refs": { "FileSource$s3Location": "The s3 location of the files to attach.
" } }, "S3Uri": { "base": null, "refs": { "S3ObjectDoc$uri": "The file location of the S3 wrapper object.
", "S3ObjectFile$uri": "The uri of the s3 object.
" } }, "SearchType": { "base": null, "refs": { "KnowledgeBaseVectorSearchConfiguration$overrideSearchType": "By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
The number of requests exceeds the service quota. Resubmit your request later.
", "refs": { "FlowResponseStream$serviceQuotaExceededException": "The number of requests exceeds the service quota. Resubmit your request later.
", "ResponseStream$serviceQuotaExceededException": "The number of requests exceeds the service quota. Resubmit your request later.
" } }, "SessionAttributesMap": { "base": null, "refs": { "SessionState$sessionAttributes": "Contains attributes that persist across a session and the values of those attributes.
" } }, "SessionId": { "base": null, "refs": { "InvokeAgentRequest$sessionId": "The unique identifier of the session. Use the same value across requests to continue the same conversation.
", "InvokeAgentResponse$sessionId": "The unique identifier of the session with the agent.
", "MemorySessionSummary$sessionId": "The identifier for this session.
", "RetrieveAndGenerateRequest$sessionId": "The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can't explicitly set the sessionId yourself.
The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can't explicitly set the sessionId yourself.
The unique identifier of the session with the agent.
" } }, "SessionState": { "base": "Contains parameters that specify various attributes that persist across a session or prompt. You can define session state attributes as key-value pairs when writing a Lambda function for an action group or pass them when making an InvokeAgent request. Use session state attributes to control and provide conversational context for your agent and to help customize your agent's behavior. For more information, see Control session context.
", "refs": { "InvokeAgentRequest$sessionState": "Contains parameters that specify various attributes of the session. For more information, see Control session context.
If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.
Specifies what output is prompting the agent to reprompt the input.
" } }, "Span": { "base": "Contains information about where the text with a citation begins and ends in the generated output.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the span field
InvokeAgent response – in the span field
Contains information about where the text with a citation begins and ends in the generated output.
" } }, "SpanEndInteger": { "base": null, "refs": { "Span$end": "Where the text with a citation ends in the generated output.
" } }, "SpanStartInteger": { "base": null, "refs": { "Span$start": "Where the text with a citation starts in the generated output.
" } }, "StopSequences": { "base": null, "refs": { "InferenceConfiguration$stopSequences": "A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
" } }, "String": { "base": null, "refs": { "ActionGroupInvocationInput$invocationId": "The unique identifier of the invocation. Only returned if the executionType is RETURN_CONTROL.
The action group that the API operation belongs to.
", "ApiInvocationInput$httpMethod": "The HTTP method of the API operation.
", "ApiParameter$name": "The name of the parameter.
", "ApiParameter$type": "The data type for the parameter.
", "ApiParameter$value": "The value of the parameter.
", "ApiResult$actionGroup": "The action group that the API operation belongs to.
", "ApiResult$httpMethod": "The HTTP method for the API operation.
", "CodeInterpreterInvocationInput$code": "The code for the code interpreter to use.
", "CodeInterpreterInvocationOutput$executionError": "Contains the error returned from code execution.
", "CodeInterpreterInvocationOutput$executionOutput": "Contains the successful output returned from code execution
", "ContentBody$body": "The body of the API response.
", "ContentMap$key": null, "Files$member": null, "FlowTraceCondition$conditionName": "The name of the condition.
", "FunctionInvocationInput$actionGroup": "The action group that the function belongs to.
", "FunctionInvocationInput$function": "The name of the function.
", "FunctionParameter$name": "The name of the parameter.
", "FunctionParameter$type": "The data type of the parameter.
", "FunctionParameter$value": "The value of the parameter.
", "FunctionResult$actionGroup": "The action group that the function belongs to.
", "FunctionResult$function": "The name of the function that was called.
", "GuardrailCustomWord$match": "The match details for the custom word filter in the Guardrail.
", "GuardrailManagedWord$match": "The match details for the managed word filter in the Guardrail.
", "GuardrailPiiEntityFilter$match": "The match to settings in the Guardrail filter to identify and remove PII.
", "GuardrailRegexFilter$match": "The match details for the regex filter used in the Guardrail.
", "GuardrailRegexFilter$name": "The name details for the regex filter used in the Guardrail.
", "GuardrailRegexFilter$regex": "The regex details for the regex filter used in the Guardrail.
", "GuardrailTopic$name": "The name details on a specific topic in the Guardrail.
", "InputFile$name": "The name of the source file.
", "OutputFile$name": "The name of the file containing response from code interpreter.
", "Parameter$name": "The name of the parameter.
", "Parameter$type": "The type of the parameter.
", "Parameter$value": "The value of the parameter.
", "PromptSessionAttributesMap$key": null, "PromptSessionAttributesMap$value": null, "RawResponse$content": "The foundation model's raw output content.
", "RepromptResponse$text": "The text reprompting the input.
", "ResponseBody$key": null, "RetrievalResultConfluenceLocation$url": "The Confluence host URL for the data source location.
", "RetrievalResultContent$text": "The cited text from the data source.
", "RetrievalResultS3Location$uri": "The S3 URI for the data source location.
", "RetrievalResultSalesforceLocation$url": "The Salesforce host URL for the data source location.
", "RetrievalResultSharePointLocation$url": "The SharePoint site URL for the data source location.
", "RetrievalResultWebLocation$url": "The web URL/URLs for the data source location.
", "RetrieveAndGenerateOutput$text": "The response generated from querying the knowledge base.
", "ReturnControlPayload$invocationId": "The identifier of the action group invocation.
", "SessionAttributesMap$key": null, "SessionAttributesMap$value": null, "SessionState$invocationId": "The identifier of the invocation of an action. This value must match the invocationId returned in the InvokeAgent response for the action whose results are provided in the returnControlInvocationResults field. For more information, see Return control to the agent developer and Control session context.
The part of the generated text that contains a citation.
" } }, "SummaryText": { "base": null, "refs": { "MemorySessionSummary$summaryText": "The summarized text for this session.
" } }, "Temperature": { "base": null, "refs": { "InferenceConfiguration$temperature": "The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
", "TextInferenceConfig$temperature": "Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
" } }, "TextInferenceConfig": { "base": "Configuration settings for text generation using a language model via the RetrieveAndGenerate operation. Includes parameters like temperature, top-p, maximum token count, and stop sequences.
The valid range of maxTokens depends on the accepted values for your chosen model's inference parameters. To see the inference parameters for your model, see Inference parameters for foundation models.
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
" } }, "TextPromptTemplate": { "base": null, "refs": { "PromptTemplate$textPromptTemplate": "The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
" } }, "TextResponsePart": { "base": "Contains the part of the generated text that contains a citation, alongside where it begins and ends.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the textResponsePart field
InvokeAgent response – in the textResponsePart field
Contains metadata about a textual part of the generated response that is accompanied by a citation.
" } }, "ThrottlingException": { "base": "The number of requests exceeds the limit. Resubmit your request later.
", "refs": { "FlowResponseStream$throttlingException": "The number of requests exceeds the limit. Resubmit your request later.
", "ResponseStream$throttlingException": "The number of requests exceeds the limit. Resubmit your request later.
" } }, "TopK": { "base": null, "refs": { "InferenceConfiguration$topK": "While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.
While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
" } }, "Trace": { "base": "Contains one part of the agent's reasoning process and results from calling API actions and querying knowledge bases. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement.
", "refs": { "TracePart$trace": "Contains one part of the agent's reasoning process and results from calling API actions and querying knowledge bases. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement.
" } }, "TraceId": { "base": null, "refs": { "FailureTrace$traceId": "The unique identifier of the trace.
", "GuardrailTrace$traceId": "The details of the trace Id used in the Guardrail Trace.
", "InvocationInput$traceId": "The unique identifier of the trace.
", "ModelInvocationInput$traceId": "The unique identifier of the trace.
", "Observation$traceId": "The unique identifier of the trace.
", "OrchestrationModelInvocationOutput$traceId": "The unique identifier of the trace.
", "PostProcessingModelInvocationOutput$traceId": "The unique identifier of the trace.
", "PreProcessingModelInvocationOutput$traceId": "The unique identifier of the trace.
", "Rationale$traceId": "The unique identifier of the trace step.
" } }, "TraceKnowledgeBaseId": { "base": null, "refs": { "KnowledgeBaseLookupInput$knowledgeBaseId": "The unique identifier of the knowledge base to look up.
" } }, "TracePart": { "base": "Contains information about the agent and session, alongside the agent's reasoning process and results from calling API actions and querying knowledge bases and metadata about the trace. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement.
", "refs": { "ResponseStream$trace": "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. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace events.
" } }, "Type": { "base": null, "refs": { "Observation$type": "Specifies what kind of information the agent returns in the observation. The following values are possible.
ACTION_GROUP – The agent returns the result of an action group.
KNOWLEDGE_BASE – The agent returns information from a knowledge base.
FINISH – The agent returns a final response to the user with no follow-up.
ASK_USER – The agent asks the user a question.
REPROMPT – The agent prompts the user again for the same information.
Contains information of the usage of the foundation model.
", "refs": { "Metadata$usage": "Contains details of the foundation model usage.
" } }, "ValidationException": { "base": "Input validation failed. Check your request parameters and retry the request.
", "refs": { "FlowResponseStream$validationException": "Input validation failed. Check your request parameters and retry the request.
", "ResponseStream$validationException": "Input validation failed. Check your request parameters and retry the request.
" } }, "Verb": { "base": null, "refs": { "ActionGroupInvocationInput$verb": "The API method being used, based off the action group.
" } } } }