Expand description
Data structures used by operation inputs/outputs.
Modules§
Structs§
- Action
Group Invocation Input 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.
- Action
Group Invocation Output Contains the JSON-formatted string returned by the API invoked by the action group.
- Agent
Action Group Contains details of the inline agent's action group.
- Agent
Collaborator Input Payload Input for an agent collaborator. The input can be text or an action invocation result.
- Agent
Collaborator Invocation Input An agent collaborator invocation input.
- Agent
Collaborator Invocation Output Output from an agent collaborator.
- Agent
Collaborator Output Payload Output from an agent collaborator. The output can be text or an action invocation result.
- Analyze
Prompt Event An event in which the prompt was analyzed in preparation for optimization.
- ApiInvocation
Input 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
-
- ApiParameter
Information about a parameter to provide to the API request.
This data type is used in the following API operations:
- ApiRequest
Body 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:
- ApiResult
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
-
- Attribution
Contains citations for a part of an agent response.
- Bedrock
Model Configurations Settings for a model called with
InvokeAgent
.- Bedrock
Reranking Configuration Contains configurations for an Amazon Bedrock reranker model.
- Bedrock
Reranking Model Configuration Contains configurations for a reranker model.
- Byte
Content Doc This property contains the document to chat with, along with its attributes.
- Byte
Content File The property contains the file to chat with, along with its attributes.
- Citation
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
-
- Citation
Event A citation event.
- Code
Interpreter Invocation Input Contains information about the code interpreter being invoked.
- Code
Interpreter Invocation Output Contains the JSON-formatted string returned by the API invoked by the code interpreter.
- Collaborator
List of inline collaborators.
- Collaborator
Configuration Settings of an inline collaborator agent.
- Condition
Result Event Contains information about a condition evaluation result during a flow execution. This event is generated when a condition node in the flow evaluates its conditions.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Content
Body 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
-
- Conversation
History A conversation history.
- Custom
Orchestration Contains details of the custom orchestration configured for the agent.
- Custom
Orchestration Trace The trace behavior for the custom orchestration.
- Custom
Orchestration Trace Event The event in the custom orchestration sequence. Events are the responses which the custom orchestration Lambda function sends as response to the agent.
- External
Source The unique external source of the content contained in the wrapper object.
- External
Sources Generation Configuration Contains the generation configuration of the external source wrapper object.
- External
Sources Retrieve AndGenerate Configuration The configurations of the external source wrapper object in the
retrieveAndGenerate
function.- Failure
Trace Contains information about the failure of the interaction.
- Field
ForReranking Contains information for a metadata field to include in or exclude from consideration when reranking.
- File
Part Contains intermediate response for code interpreter if any files have been generated.
- File
Source The source file of the content contained in the wrapper object.
- Filter
Attribute 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:
- Final
Response Contains details about the response to the user.
- Flow
Completion Event Contains information about why a flow completed.
- Flow
Execution Error Contains information about an error that occurred during an flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Execution Input Event Contains information about the inputs provided to the flow at the start of a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Execution Output Event Contains information about the outputs produced by the flow during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Execution Summary Contains summary information about a flow execution, including its status, timestamps, and identifiers.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Failure Event Contains information about a failure that occurred at the flow level during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Input Contains information about an input into the prompt flow and where to send it.
- Flow
Input Field Represents an input field provided to a flow during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Multi Turn Input Request Event Response object from the flow multi-turn node requesting additional information.
- Flow
Output Event Contains information about an output from prompt flow invoction.
- Flow
Output Field Represents an output field produced by a flow during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Trace Condition 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.
- Flow
Trace Condition Node Result Event 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.
- Flow
Trace Event 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.
- Flow
Trace Node Action Event Contains information about an action (operation) called by a node in an Amazon Bedrock flow. The service generates action events for calls made by prompt nodes, agent nodes, and Amazon Web Services Lambda nodes.
- Flow
Trace Node Input Event 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.
- Flow
Trace Node Input Field 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.
- Flow
Trace Node Output Event 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.
- Flow
Trace Node Output Field 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.
- Function
Definition Defines parameters that the agent needs to invoke from the user to complete the function. Corresponds to an action in an action group.
- Function
Invocation Input 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
-
- Function
Parameter 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
-
- Function
Result 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
-
- Generated
Query Contains information about a query generated for a natural language query.
- Generated
Response Part 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
-
- Generation
Configuration Contains configurations for response generation based on the knowledge base query results.
This data type is used in the following API operations:
- Guardrail
Assessment Assessment details of the content analyzed by Guardrails.
- Guardrail
Configuration The configuration details for the guardrail.
- Guardrail
Configuration With Arn The configuration details for the guardrail.
- Guardrail
Content Filter Details of the content filter used in the Guardrail.
- Guardrail
Content Policy Assessment The details of the policy assessment in the Guardrails filter.
- Guardrail
Custom Word The custom word details for the filter in the Guardrail.
- Guardrail
Event A guardrail event.
- Guardrail
Managed Word The managed word details for the filter in the Guardrail.
- Guardrail
PiiEntity Filter The Guardrail filter to identify and remove personally identifiable information (PII).
- Guardrail
Regex Filter The details for the regex filter used in the Guardrail.
- Guardrail
Sensitive Information Policy Assessment The details of the sensitive policy assessment used in the Guardrail.
- Guardrail
Topic The details for a specific topic defined in the Guardrail.
- Guardrail
Topic Policy Assessment The details of the policy assessment used in the Guardrail.
- Guardrail
Trace The trace details used in the Guardrail.
- Guardrail
Word Policy Assessment The assessment details for words defined in the Guardrail filter.
- Image
Block Image content for an invocation step.
- Image
Input Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
- Implicit
Filter Configuration Settings for implicit filtering, where a model generates a metadata filter based on the prompt.
- Inference
Config The configuration for inference settings when generating responses using RetrieveAndGenerate.
- Inference
Configuration 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.
- Inline
Agent File Part Contains intermediate response for code interpreter if any files have been generated.
- Inline
Agent Payload Part Contains a part of an agent response and citations for it.
- Inline
Agent Return Control Payload Contains information to return from the action group that the agent has predicted to invoke.
This data type is used in the InvokeAgent response API operation.
- Inline
Agent Trace Part 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.
- Inline
Bedrock Model Configurations Settings for a model called with
InvokeInlineAgent
.- Inline
Session State 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
InvokeInlineAgent
request. Use session state attributes to control and provide conversational context for your inline agent and to help customize your agent's behavior. For more information, see Control session context- Input
File Contains details of the source files.
- Invocation
Input Contains information pertaining to the action group or knowledge base that is being invoked.
- Invocation
Step Stores fine-grained state checkpoints, including text and images, for each interaction in an invocation in a session. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.
- Invocation
Step Summary Contains details about an invocation step within an invocation in a session. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.
- Invocation
Summary Contains details about an invocation in a session. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.
- Knowledge
Base Details of the knowledge base associated withe inline agent.
- Knowledge
Base Configuration Configurations to apply to a knowledge base attached to the agent during query. For more information, see Knowledge base retrieval configurations.
- Knowledge
Base Lookup Input Contains details about the knowledge base to look up and the query to be made.
- Knowledge
Base Lookup Output Contains details about the results from looking up the knowledge base.
- Knowledge
Base Query Contains the query made to the knowledge base.
This data type is used in the following API operations:
-
Retrieve request – in the
retrievalQuery
field
-
- Knowledge
Base Retrieval Configuration 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
-
- Knowledge
Base Retrieval Result 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
-
- Knowledge
Base Retrieve AndGenerate Configuration 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
-
- Knowledge
Base Vector Search Configuration 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
-
- Memory
Session Summary Contains details of a session summary.
- Message
Details about a message.
- Metadata
Provides information about the execution process for different types of invocations, such as model invocation, knowledge base invocation, agent collaborator invocation, guardrail invocation, and code interpreter Invocation.
- Metadata
Attribute Schema Details about a metadata attribute.
- Metadata
Configuration ForReranking Contains configurations for the metadata to use in reranking.
- Model
Invocation Input The input for the pre-processing step.
-
The
type
matches the agent step. -
The
text
contains the prompt. -
The
inferenceConfiguration
,parserMode
, andoverrideLambda
values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
-
- Model
Performance Configuration The performance configuration for a model called with
InvokeFlow
.- Node
Failure Event Contains information about a failure that occurred at a specific node during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Node
Input Event Contains information about the inputs provided to a specific node during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Node
Input Field Represents an input field provided to a node during a flow execution.
- Node
Output Event Contains information about the outputs produced by a specific node during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Node
Output Field Represents an output field produced by a node during a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Observation
Contains the result or output of an action group or knowledge base, or the response to the user.
- Optimized
Prompt Event An event in which the prompt was optimized.
- Orchestration
Configuration Settings for how the model processes the prompt prior to retrieval and generation.
- Orchestration
Model Invocation Output The foundation model output from the orchestration step.
- Output
File Contains details of the response from code interpreter.
- Parameter
A parameter for the API request or function.
- Parameter
Detail Contains details about a parameter in a function for an action group.
- Payload
Part Contains a part of an agent response and citations for it.
- Performance
Configuration Performance settings for a model.
- Post
Processing Model Invocation Output The foundation model output from the post-processing step.
- Post
Processing Parsed Response Details about the response from the Lambda parsing of the output from the post-processing step.
- PreProcessing
Model Invocation Output The foundation model output from the pre-processing step.
- PreProcessing
Parsed Response Details about the response from the Lambda parsing of the output from the pre-processing step.
- Prompt
Configuration Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.
- Prompt
Creation Configurations Specifies parameters that control how the service populates the agent prompt for an
InvokeAgent
orInvokeInlineAgent
request. You can control which aspects of previous invocations in the same agent session the service uses to populate the agent prompt. This gives you more granular control over the contextual history that is used to process the current request.- Prompt
Override Configuration Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.
- Prompt
Template 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
-
- Property
Parameters Contains the parameters in the request body.
- Query
Generation Input Contains information about a natural language query to transform into SQL.
- Query
Transformation Configuration To split up the prompt and retrieve multiple sources, set the transformation type to
QUERY_DECOMPOSITION
.- Rationale
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.
- RawResponse
Contains the raw output from the foundation model.
- Reasoning
Text Block Contains information about the reasoning that the model used to return the content in the content block.
- Reprompt
Response Contains details about the agent's response to reprompt the input.
- Request
Body The parameters in the API request body.
- Rerank
Document Contains information about a document to rerank. Choose the
type
to define and include the field that corresponds to the type.- Rerank
Query Contains information about a query to submit to the reranker model.
- Rerank
Result Contains information about a document that was reranked.
- Rerank
Source Contains information about a source for reranking.
- Rerank
Text Document Contains information about a text document to rerank.
- Reranking
Configuration Contains configurations for reranking.
- Retrieval
Result Confluence Location The Confluence data source location.
- Retrieval
Result Content Contains information about a chunk of text from a data source in the knowledge base. If the result is from a structured data source, the cell in the database and the type of the value is also identified.
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
-
- Retrieval
Result Content Column Contains information about a column with a cell to return in retrieval.
- Retrieval
Result Custom Document Location Contains information about the location of a document in a custom data source.
- Retrieval
Result Kendra Document Location The location of a result in Amazon Kendra.
- Retrieval
Result Location 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
location
field
-
- Retrieval
Result S3Location 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
-
- Retrieval
Result Salesforce Location The Salesforce data source location.
- Retrieval
Result Share Point Location The SharePoint data source location.
- Retrieval
Result SqlLocation Contains information about the SQL query used to retrieve the result.
- Retrieval
Result WebLocation The web URL/URLs data source location.
- Retrieve
AndGenerate Configuration Contains details about the resource being queried.
This data type is used in the following API operations:
-
RetrieveAndGenerate request – in the
retrieveAndGenerateConfiguration
field
-
- Retrieve
AndGenerate Input Contains the query made to the knowledge base.
This data type is used in the following API operations:
-
RetrieveAndGenerate request – in the
input
field
-
- Retrieve
AndGenerate Output 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
-
- Retrieve
AndGenerate Output Event A retrieve and generate output event.
- Retrieve
AndGenerate Session Configuration 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
-
- Retrieved
Reference 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
-
- Return
Control Payload 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:
- Return
Control Results An action invocation result.
- Routing
Classifier Model Invocation Output Invocation output from a routing classifier model.
- S3Identifier
The identifier information for an Amazon S3 bucket.
- S3Location
Information about the Amazon S3 bucket where the image is stored.
- S3Object
Doc The unique wrapper object of the document from the S3 location.
- S3Object
File Contains details of the s3 object where the source file is located.
- Satisfied
Condition Represents a condition that was satisfied during a condition node evaluation in a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Session
State 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.
- Session
Summary Contains details about a session. For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.
- Span
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
-
- Streaming
Configurations Configurations for streaming.
- Text
Inference Config 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.- Text
Prompt Contains information about the text prompt to optimize.
- Text
Response Part 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
-
- Text
ToSql Configuration Contains configurations for transforming text to SQL.
- Text
ToSql Knowledge Base Configuration Contains configurations for a knowledge base to use in transformation.
- Trace
Part 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.
- Transformation
Configuration Contains configurations for transforming the natural language query into SQL.
- Usage
Contains information of the usage of the foundation model.
- Vector
Search Bedrock Reranking Configuration Contains configurations for reranking with an Amazon Bedrock reranker model.
- Vector
Search Bedrock Reranking Model Configuration Contains configurations for an Amazon Bedrock reranker model.
- Vector
Search Reranking Configuration Contains configurations for reranking the retrieved results.
Enums§
- Action
Group Executor 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.
- Action
Group Signature - When writing a match expression against
ActionGroupSignature
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Action
Invocation Type - When writing a match expression against
ActionInvocationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Agent
Collaboration - When writing a match expression against
AgentCollaboration
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - ApiSchema
Contains details about the OpenAPI schema for the action group. For more information, see Action group OpenAPI schemas. You can either include the schema directly in the payload field or you can upload it to an S3 bucket and specify the S3 bucket location in the s3 field.
- Attribute
Type - When writing a match expression against
AttributeType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Bedrock
Session Content Block A block of content that you pass to, or receive from, a Amazon Bedrock session in an invocation step. You pass the content to a session in the
payLoad
of the PutInvocationStep API operation. You retrieve the content with the GetInvocationStep API operation.For more information about sessions, see Store and retrieve conversation history and context with Amazon Bedrock sessions.
- Caller
Details about a caller.
- Confirmation
State - When writing a match expression against
ConfirmationState
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Content
Block A content block.
- Conversation
Role - When writing a match expression against
ConversationRole
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Creation
Mode - When writing a match expression against
CreationMode
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Custom
Control Method - When writing a match expression against
CustomControlMethod
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Execution
Type - When writing a match expression against
ExecutionType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - External
Source Type - When writing a match expression against
ExternalSourceType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - File
Source Type - When writing a match expression against
FileSourceType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - File
UseCase - When writing a match expression against
FileUseCase
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Flow
Completion Reason - When writing a match expression against
FlowCompletionReason
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Flow
Error Code - When writing a match expression against
FlowErrorCode
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Flow
Execution Content Contains the content of an flow execution input or output field.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Execution Error Type - When writing a match expression against
FlowExecutionErrorType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Flow
Execution Event Represents an event that occurred during an flow execution. This is a union type that can contain one of several event types, such as node input and output events; flow input and output events; condition node result events, or failure events.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Flow
Execution Event Type - When writing a match expression against
FlowExecutionEventType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Flow
Execution Status - When writing a match expression against
FlowExecutionStatus
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Flow
Input Content Contains information about an input into the flow.
- Flow
Multi Turn Input Content The content structure containing input information for multi-turn flow interactions.
- Flow
Output Content Contains information about the content in an output from prompt flow invocation.
- Flow
Response Stream The output of the flow.
- Flow
Trace 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.
- Flow
Trace Node Input Content 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.
- Flow
Trace Node Output Content 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.
- Function
Schema Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
- Generated
Query Type - When writing a match expression against
GeneratedQueryType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guadrail
Action - When writing a match expression against
GuadrailAction
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Action - When writing a match expression against
GuardrailAction
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Content Filter Confidence - When writing a match expression against
GuardrailContentFilterConfidence
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Content Filter Type - When writing a match expression against
GuardrailContentFilterType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Content Policy Action - When writing a match expression against
GuardrailContentPolicyAction
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Managed Word Type - When writing a match expression against
GuardrailManagedWordType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
PiiEntity Type - When writing a match expression against
GuardrailPiiEntityType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Sensitive Information Policy Action - When writing a match expression against
GuardrailSensitiveInformationPolicyAction
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Topic Policy Action - When writing a match expression against
GuardrailTopicPolicyAction
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Topic Type - When writing a match expression against
GuardrailTopicType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Guardrail
Word Policy Action - When writing a match expression against
GuardrailWordPolicyAction
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Image
Format - When writing a match expression against
ImageFormat
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Image
Input Format - When writing a match expression against
ImageInputFormat
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Image
Input Source Details about the source of an input image in the result from a function in the action group invocation.
- Image
Source The source for an image.
- Inline
Agent Response Stream The response from invoking the agent and associated citations and trace information.
- Input
Prompt Contains information about the prompt to optimize.
- Input
Query Type - When writing a match expression against
InputQueryType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Invocation
Input Member 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
-
- Invocation
Result Member 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:
- Invocation
Step Payload Payload content, such as text and images, for the invocation step.
- Invocation
Type - When writing a match expression against
InvocationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Memory
Contains sessions summaries.
- Memory
Type - When writing a match expression against
MemoryType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Node
Error Code - When writing a match expression against
NodeErrorCode
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Node
Execution Content Contains the content of a flow node's input or output field for a flow execution.
Flow executions is in preview release for Amazon Bedrock and is subject to change.
- Node
Type - When writing a match expression against
NodeType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Optimized
Prompt Contains information about the optimized prompt.
- Optimized
Prompt Stream The stream containing events in the prompt optimization process.
- Orchestration
Executor The structure of the executor invoking the actions in custom orchestration.
- Orchestration
Trace Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.
- Orchestration
Type - When writing a match expression against
OrchestrationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Parameter
Type - When writing a match expression against
ParameterType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Payload
Type - When writing a match expression against
PayloadType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Performance
Config Latency - When writing a match expression against
PerformanceConfigLatency
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Post
Processing Trace Details about the post-processing step, in which the agent shapes the response.
- PreProcessing
Trace Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.
- Prompt
State - When writing a match expression against
PromptState
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Prompt
Type - When writing a match expression against
PromptType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Query
Transformation Mode - When writing a match expression against
QueryTransformationMode
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Query
Transformation Type - When writing a match expression against
QueryTransformationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Reasoning
Content Block Contains content regarding the reasoning that the foundation model made with respect to the content in the content block. Reasoning refers to a Chain of Thought (CoT) that the model generates to enhance the accuracy of its final response.
- Relay
Conversation History - When writing a match expression against
RelayConversationHistory
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Require
Confirmation - When writing a match expression against
RequireConfirmation
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Rerank
Document Type - When writing a match expression against
RerankDocumentType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Rerank
Query Content Type - When writing a match expression against
RerankQueryContentType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Rerank
Source Type - When writing a match expression against
RerankSourceType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Reranking
Configuration Type - When writing a match expression against
RerankingConfigurationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Reranking
Metadata Selection Mode - When writing a match expression against
RerankingMetadataSelectionMode
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Reranking
Metadata Selective Mode Configuration Contains configurations for the metadata fields to include or exclude when considering reranking. If you include the
fieldsToExclude
field, the reranker ignores all the metadata fields that you specify. If you include thefieldsToInclude
field, the reranker uses only the metadata fields that you specify and ignores all others. You can include only one of these fields.- Response
State - When writing a match expression against
ResponseState
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Response
Stream The response from invoking the agent and associated citations and trace information.
- Retrieval
Filter 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
-
- Retrieval
Result Content Column Type - When writing a match expression against
RetrievalResultContentColumnType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Retrieval
Result Content Type - When writing a match expression against
RetrievalResultContentType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Retrieval
Result Location Type - When writing a match expression against
RetrievalResultLocationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Retrieve
AndGenerate Stream Response Output A retrieve and generate stream response output.
- Retrieve
AndGenerate Type - When writing a match expression against
RetrieveAndGenerateType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Routing
Classifier Trace A trace for a routing classifier.
- Search
Type - When writing a match expression against
SearchType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Session
Status - When writing a match expression against
SessionStatus
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Source
- When writing a match expression against
Source
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Text
ToSql Configuration Type - When writing a match expression against
TextToSqlConfigurationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - 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.
- Type
- When writing a match expression against
Type
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature. - Vector
Search Reranking Configuration Type - When writing a match expression against
VectorSearchRerankingConfigurationType
, it is important to ensure your code is forward-compatible. That is, if a match arm handles a case for a feature that is supported by the service but has not been represented as an enum variant in a current version of SDK, your code should continue to work when you upgrade SDK to a future version in which the enum does include a variant for that feature.