String actionGroupId
The unique identifier of the action group.
String actionGroupName
The name of the action group.
String actionGroupState
Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
String description
The description of the action group.
Date updatedAt
The time at which the action group was last updated.
String agentArn
The Amazon Resource Name (ARN) of the agent.
String agentId
The unique identifier of the agent.
String agentName
The name of the agent.
String agentResourceRoleArn
The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.
String agentStatus
The status of the agent and whether it is ready for use. The following statuses are possible:
CREATING – The agent is being created.
PREPARING – The agent is being prepared.
PREPARED – The agent is prepared and ready to be invoked.
NOT_PREPARED – The agent has been created but not yet prepared.
FAILED – The agent API operation failed.
UPDATING – The agent is being updated.
DELETING – The agent is being deleted.
String agentVersion
The version of the agent.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
Date createdAt
The time at which the agent was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that encrypts the agent.
String description
The description of the agent.
List<E> failureReasons
Contains reasons that the agent-related API that you invoked failed.
String foundationModel
The foundation model used for orchestration by the agent.
GuardrailConfiguration guardrailConfiguration
Details about the guardrail associated with the agent.
Integer idleSessionTTLInSeconds
The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent.
A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.
String instruction
Instructions that tell the agent what it should do and how it should interact with users.
MemoryConfiguration memoryConfiguration
Contains memory configuration for the agent.
Date preparedAt
The time at which the agent was last prepared.
PromptOverrideConfiguration promptOverrideConfiguration
Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts.
List<E> recommendedActions
Contains recommended actions to take for the agent-related API that you invoked to succeed.
Date updatedAt
The time at which the agent was last updated.
ActionGroupExecutor actionGroupExecutor
The Amazon Resource Name (ARN) of 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.
String actionGroupId
The unique identifier of the action group.
String actionGroupName
The name of the action group.
String actionGroupState
Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
String agentId
The unique identifier of the agent to which the action group belongs.
String agentVersion
The version of the agent to which the action group belongs.
APISchema apiSchema
Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
Date createdAt
The time at which the action group was created.
String description
The description of the action group.
FunctionSchema functionSchema
Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.
String parentActionSignature
If this field is set as AMAZON.UserInput, the agent can request the user for additional information
when trying to complete a task. The description, apiSchema, and
actionGroupExecutor fields must be blank for this action group.
During orchestration, if the agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.
Date updatedAt
The time at which the action group was last updated.
String agentAliasArn
The Amazon Resource Name (ARN) of the alias of the agent.
List<E> agentAliasHistoryEvents
Contains details about the history of the alias.
String agentAliasId
The unique identifier of the alias of the agent.
String agentAliasName
The name of the alias of the agent.
String agentAliasStatus
The status of the alias of the agent and whether it is ready for use. The following statuses are possible:
CREATING – The agent alias is being created.
PREPARED – The agent alias is finished being created or updated and is ready to be invoked.
FAILED – The agent alias API operation failed.
UPDATING – The agent alias is being updated.
DELETING – The agent alias is being deleted.
String agentId
The unique identifier of the agent.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
Date createdAt
The time at which the alias of the agent was created.
String description
The description of the alias of the agent.
List<E> failureReasons
Information on the failure of Provisioned Throughput assigned to an agent alias.
List<E> routingConfiguration
Contains details about the routing configuration of the alias.
Date updatedAt
The time at which the alias was last updated.
Date endDate
The date that the alias stopped being associated to the version in the routingConfiguration object
List<E> routingConfiguration
Contains details about the version of the agent with which the alias is associated.
Date startDate
The date that the alias began being associated to the version in the routingConfiguration object.
String agentAliasId
Contains details about
String agentAliasName
The name of the alias.
String agentAliasStatus
The status of the alias.
Date createdAt
The time at which the alias of the agent was created.
String description
The description of the alias.
List<E> routingConfiguration
Contains details about the version of the agent with which the alias is associated.
Date updatedAt
The time at which the alias was last updated.
String agentAliasArn
The Amazon Resource Name (ARN) of the alias of the agent to invoke.
String agentId
The unique identifier of the agent with which the knowledge base is associated.
String agentVersion
The version of the agent with which the knowledge base is associated.
Date createdAt
The time at which the association between the agent and the knowledge base was created.
String description
The description of the association between the agent and the knowledge base.
String knowledgeBaseId
The unique identifier of the association between the agent and the knowledge base.
String knowledgeBaseState
Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
Date updatedAt
The time at which the association between the agent and the knowledge base was last updated.
String description
The description of the knowledge base associated with an agent.
String knowledgeBaseId
The unique identifier of the knowledge base associated with an agent.
String knowledgeBaseState
Specifies whether the agent uses the knowledge base or not when sending an InvokeAgent request.
Date updatedAt
The time at which the knowledge base associated with an agent was last updated.
String agentId
The unique identifier of the agent.
String agentName
The name of the agent.
String agentStatus
The status of the agent.
String description
The description of the agent.
GuardrailConfiguration guardrailConfiguration
Details about the guardrail associated with the agent.
String latestAgentVersion
The latest version of the agent.
Date updatedAt
The time at which the agent was last updated.
String agentArn
The Amazon Resource Name (ARN) of the agent that the version belongs to.
String agentId
The unique identifier of the agent that the version belongs to.
String agentName
The name of the agent that the version belongs to.
String agentResourceRoleArn
The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.
String agentStatus
The status of the agent that the version belongs to.
Date createdAt
The time at which the version was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that encrypts the agent.
String description
The description of the version.
List<E> failureReasons
A list of reasons that the API operation on the version failed.
String foundationModel
The foundation model that the version invokes.
GuardrailConfiguration guardrailConfiguration
Details about the guardrail associated with the agent.
Integer idleSessionTTLInSeconds
The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent.
A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.
String instruction
The instructions provided to the agent.
MemoryConfiguration memoryConfiguration
Contains details of the memory configuration on the version of the agent.
PromptOverrideConfiguration promptOverrideConfiguration
Contains configurations to override prompt templates in different parts of an agent sequence. For more information, see Advanced prompts.
List<E> recommendedActions
A list of recommended actions to take for the failed API operation on the version to succeed.
Date updatedAt
The time at which the version was last updated.
String version
The version number.
String agentName
The name of the agent to which the version belongs.
String agentStatus
The status of the agent to which the version belongs.
String agentVersion
The version of the agent.
Date createdAt
The time at which the version was created.
String description
The description of the version of the agent.
GuardrailConfiguration guardrailConfiguration
Details about the guardrail associated with the agent.
Date updatedAt
The time at which the version was last updated.
String payload
The JSON or YAML-formatted payload defining the OpenAPI schema for the action group. For more information, see Action group OpenAPI schemas.
S3Identifier s3
Contains details about the S3 object containing the OpenAPI schema for the action group. For more information, see Action group OpenAPI schemas.
String agentId
The unique identifier of the agent with which you want to associate the knowledge base.
String agentVersion
The version of the agent with which you want to associate the knowledge base.
String description
A description of what the agent should use the knowledge base for.
String knowledgeBaseId
The unique identifier of the knowledge base to associate with the agent.
String knowledgeBaseState
Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
AgentKnowledgeBase agentKnowledgeBase
Contains details about the knowledge base that has been associated with the agent.
Integer dimensions
The dimensions details for the vector configuration used on the Bedrock embeddings model.
String modelArn
The model's ARN.
ParsingPrompt parsingPrompt
Instructions for interpreting the contents of a document.
String chunkingStrategy
Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source
that is returned when the knowledge base that it belongs to is queried. You have the following options for
chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting
them up such that each file corresponds to a chunk.
FIXED_SIZE – Amazon Bedrock splits your source data into chunks of the approximate size that you set
in the fixedSizeChunkingConfiguration.
HIERARCHICAL – Split documents into layers of chunks where the first layer contains large chunks,
and the second layer contains smaller chunks derived from the first layer.
SEMANTIC – Split documents into chunks based on groups of similar content derived with natural
language processing.
NONE – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want to
pre-process your documents by splitting them into separate files.
FixedSizeChunkingConfiguration fixedSizeChunkingConfiguration
Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as
NONE, exclude this field.
HierarchicalChunkingConfiguration hierarchicalChunkingConfiguration
Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
SemanticChunkingConfiguration semanticChunkingConfiguration
Settings for semantic document chunking for a data source. Semantic chunking splits a document into into smaller documents based on groups of similar content derived from the text with natural language processing.
CrawlFilterConfiguration filterConfiguration
The configuration of filtering the Confluence content. For example, configuring regular expression patterns to include or exclude certain content.
ConfluenceCrawlerConfiguration crawlerConfiguration
The configuration of the Confluence content. For example, configuring specific types of Confluence content.
ConfluenceSourceConfiguration sourceConfiguration
The endpoint information to connect to your Confluence data source.
String authType
The supported authentication type to authenticate and connect to your Confluence instance.
String credentialsSecretArn
The Amazon Resource Name of an Secrets Manager secret that stores your authentication credentials for your SharePoint site/sites. For more information on the key-value pairs that must be included in your secret, depending on your authentication type, see Confluence connection configuration.
String hostType
The supported host type, whether online/cloud or server/on-premises.
String hostUrl
The Confluence host URL or instance URL.
PatternObjectFilterConfiguration patternObjectFilter
The configuration of filtering certain objects or content types of the data source.
String type
The type of filtering that you want to apply to certain objects or content of the data source. For example, the
PATTERN type is regular expression patterns you can apply to filter your content.
ActionGroupExecutor actionGroupExecutor
The Amazon Resource Name (ARN) of 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.
String actionGroupName
The name to give the action group.
String actionGroupState
Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
String agentId
The unique identifier of the agent for which to create the action group.
String agentVersion
The version of the agent for which to create the action group.
APISchema apiSchema
Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String description
A description of the action group.
FunctionSchema functionSchema
Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
String parentActionGroupSignature
To allow your agent to request the user for additional information when trying to complete a task, set this field
to AMAZON.UserInput. You must leave the description, apiSchema, and
actionGroupExecutor fields blank for this action group.
To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to
AMAZON.CodeInterpreter. You must leave the description, apiSchema, and
actionGroupExecutor fields blank for this action group.
During orchestration, if your agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.
AgentActionGroup agentActionGroup
Contains details about the action group that was created.
String agentAliasName
The name of the alias.
String agentId
The unique identifier of the agent.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String description
A description of the alias of the agent.
List<E> routingConfiguration
Contains details about the routing configuration of the alias.
Map<K,V> tags
Any tags that you want to attach to the alias of the agent.
AgentAlias agentAlias
Contains details about the alias that was created.
String agentName
A name for the agent that you create.
String agentResourceRoleArn
The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent.
String description
A description of the agent.
String foundationModel
The foundation model to be used for orchestration by the agent you create.
GuardrailConfiguration guardrailConfiguration
The unique Guardrail configuration assigned to the agent when it is created.
Integer idleSessionTTLInSeconds
The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent.
A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.
String instruction
Instructions that tell the agent what it should do and how it should interact with users.
MemoryConfiguration memoryConfiguration
Contains the details of the memory configured for the agent.
PromptOverrideConfiguration promptOverrideConfiguration
Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.
Map<K,V> tags
Any tags that you want to attach to the agent.
Agent agent
Contains details about the agent created.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String dataDeletionPolicy
The data deletion policy for the data source.
You can set the data deletion policy to:
DELETE: Deletes all underlying data belonging to the data source from the vector store upon deletion of a knowledge base or data source resource. Note that the vector store itself is not deleted, only the underlying data. This flag is ignored if an Amazon Web Services account is deleted.
RETAIN: Retains all underlying data in your vector store upon deletion of a knowledge base or data source resource.
DataSourceConfiguration dataSourceConfiguration
The connection configuration for the data source.
String description
A description of the data source.
String knowledgeBaseId
The unique identifier of the knowledge base to which to add the data source.
String name
The name of the data source.
ServerSideEncryptionConfiguration serverSideEncryptionConfiguration
Contains details about the server-side encryption for the data source.
VectorIngestionConfiguration vectorIngestionConfiguration
Contains details about how to ingest the documents in the data source.
DataSource dataSource
Contains details about the data source.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String description
A description for the alias.
String flowIdentifier
The unique identifier of the flow for which to create an alias.
String name
A name for the alias.
List<E> routingConfiguration
Contains information about the version to which to map the alias.
Map<K,V> tags
Any tags that you want to attach to the alias of the flow. For more information, see Tagging resources in Amazon Bedrock.
String arn
The Amazon Resource Name (ARN) of the alias.
Date createdAt
The time at which the alias was created.
String description
The description of the alias.
String flowId
The unique identifier of the flow that the alias belongs to.
String id
The unique identifier of the alias.
String name
The name of the alias.
List<E> routingConfiguration
Contains information about the version that the alias is mapped to.
Date updatedAt
The time at which the alias of the flow was last updated.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key to encrypt the flow.
FlowDefinition definition
A definition of the nodes and connections between nodes in the flow.
String description
A description for the flow.
String executionRoleArn
The Amazon Resource Name (ARN) of the service role with permissions to create and manage a flow. For more information, see Create a service role for flows in Amazon Bedrock in the Amazon Bedrock User Guide.
String name
A name for the flow.
Map<K,V> tags
Any tags that you want to attach to the flow. For more information, see Tagging resources in Amazon Bedrock.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that you encrypted the flow with.
FlowDefinition definition
A definition of the nodes and connections between nodes in the flow.
String description
The description of the flow.
String executionRoleArn
The Amazon Resource Name (ARN) of the service role with permissions to create a flow. For more information, see Create a service role for flows in Amazon Bedrock in the Amazon Bedrock User Guide.
String id
The unique identifier of the flow.
String name
The name of the flow.
String status
The status of the flow. When you submit this request, the status will be NotPrepared. If creation
fails, the status becomes Failed.
Date updatedAt
The time at which the flow was last updated.
String version
The version of the flow. When you create a flow, the version created is the DRAFT version.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String description
A description of the version of the flow.
String flowIdentifier
The unique identifier of the flow that you want to create a version of.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String customerEncryptionKeyArn
The KMS key that the flow is encrypted with.
FlowDefinition definition
A definition of the nodes and connections in the flow.
String description
The description of the flow version.
String executionRoleArn
The Amazon Resource Name (ARN) of the service role with permissions to create a flow. For more information, see Create a service role for flows in Amazon Bedrock in the Amazon Bedrock User Guide.
String id
The unique identifier of the flow.
String name
The name of the flow version.
String status
The status of the flow.
String version
The version of the flow that was created. Versions are numbered incrementally, starting from 1.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String description
A description of the knowledge base.
KnowledgeBaseConfiguration knowledgeBaseConfiguration
Contains details about the embeddings model used for the knowledge base.
String name
A name for the knowledge base.
String roleArn
The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base.
StorageConfiguration storageConfiguration
Contains details about the configuration of the vector database used for the knowledge base.
Map<K,V> tags
Specify the key-value pairs for the tags that you want to attach to your knowledge base in this object.
KnowledgeBase knowledgeBase
Contains details about the knowledge base.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key to encrypt the prompt.
String defaultVariant
The name of the default variant for the prompt. This value must match the name field in the relevant
PromptVariant
object.
String description
A description for the prompt.
String name
A name for the prompt.
Map<K,V> tags
Any tags that you want to attach to the prompt. For more information, see Tagging resources in Amazon Bedrock.
List<E> variants
A list of objects, each containing details about a variant of the prompt.
String arn
The Amazon Resource Name (ARN) of the prompt.
Date createdAt
The time at which the prompt was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that you encrypted the prompt with.
String defaultVariant
The name of the default variant for your prompt.
String description
The description of the prompt.
String id
The unique identifier of the prompt.
String name
The name of the prompt.
Date updatedAt
The time at which the prompt was last updated.
List<E> variants
A list of objects, each containing details about a variant of the prompt.
String version
The version of the prompt. When you create a prompt, the version created is the DRAFT version.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String description
A description for the version of the prompt.
String promptIdentifier
The unique identifier of the prompt that you want to create a version of.
Map<K,V> tags
Any tags that you want to attach to the version of the prompt. For more information, see Tagging resources in Amazon Bedrock.
String arn
The Amazon Resource Name (ARN) of the version of the prompt.
Date createdAt
The time at which the prompt was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key to encrypt the version of the prompt.
String defaultVariant
The name of the default variant for the prompt. This value must match the name field in the relevant
PromptVariant
object.
String description
A description for the prompt version.
String id
The unique identifier of the prompt.
String name
The name of the prompt version.
Date updatedAt
The time at which the prompt was last updated.
List<E> variants
A list of objects, each containing details about a variant of the prompt.
String version
The version of the prompt that was created. Versions are numbered incrementally, starting from 1.
IntermediateStorage intermediateStorage
An S3 bucket path for input and output objects.
List<E> transformations
A Lambda function that processes documents.
Date createdAt
The time at which the data source was created.
String dataDeletionPolicy
The data deletion policy for the data source.
DataSourceConfiguration dataSourceConfiguration
The connection configuration for the data source.
String dataSourceId
The unique identifier of the data source.
String description
The description of the data source.
List<E> failureReasons
The detailed reasons on the failure to delete a data source.
String knowledgeBaseId
The unique identifier of the knowledge base to which the data source belongs.
String name
The name of the data source.
ServerSideEncryptionConfiguration serverSideEncryptionConfiguration
Contains details about the configuration of the server-side encryption.
String status
The status of the data source. The following statuses are possible:
Available – The data source has been created and is ready for ingestion into the knowledge base.
Deleting – The data source is being deleted.
Date updatedAt
The time at which the data source was last updated.
VectorIngestionConfiguration vectorIngestionConfiguration
Contains details about how to ingest the documents in the data source.
ConfluenceDataSourceConfiguration confluenceConfiguration
The configuration information to connect to Confluence as your data source.
Confluence data source connector is in preview release and is subject to change.
S3DataSourceConfiguration s3Configuration
The configuration information to connect to Amazon S3 as your data source.
SalesforceDataSourceConfiguration salesforceConfiguration
The configuration information to connect to Salesforce as your data source.
Salesforce data source connector is in preview release and is subject to change.
SharePointDataSourceConfiguration sharePointConfiguration
The configuration information to connect to SharePoint as your data source.
SharePoint data source connector is in preview release and is subject to change.
String type
The type of data source.
WebDataSourceConfiguration webConfiguration
The configuration of web URLs to crawl for your data source. You should be authorized to crawl the URLs.
Crawling web URLs as your data source is in preview release and is subject to change.
String dataSourceId
The unique identifier of the data source.
String description
The description of the data source.
String knowledgeBaseId
The unique identifier of the knowledge base to which the data source belongs.
String name
The name of the data source.
String status
The status of the data source.
Date updatedAt
The time at which the data source was last updated.
String actionGroupId
The unique identifier of the action group to delete.
String agentId
The unique identifier of the agent that the action group belongs to.
String agentVersion
The version of the agent that the action group belongs to.
Boolean skipResourceInUseCheck
By default, this value is false and deletion is stopped if the resource is in use. If you set it to
true, the resource will be deleted even if the resource is in use.
String agentId
The unique identifier of the agent that the version belongs to.
String agentVersion
The version of the agent to delete.
Boolean skipResourceInUseCheck
By default, this value is false and deletion is stopped if the resource is in use. If you set it to
true, the resource will be deleted even if the resource is in use.
String id
The unique identifier of the flow.
String flowIdentifier
The unique identifier of the flow whose version that you want to delete
String flowVersion
The version of the flow that you want to delete.
Boolean skipResourceInUseCheck
By default, this value is false and deletion is stopped if the resource is in use. If you set it to
true, the resource will be deleted even if the resource is in use.
String knowledgeBaseId
The unique identifier of the knowledge base to delete.
String agentId
The unique identifier of the agent from which to disassociate the knowledge base.
String agentVersion
The version of the agent from which to disassociate the knowledge base.
String knowledgeBaseId
The unique identifier of the knowledge base to disassociate.
BedrockEmbeddingModelConfiguration bedrockEmbeddingModelConfiguration
The vector configuration details on the Bedrock embeddings model.
String flowVersion
The version that the alias maps to.
String arn
The Amazon Resource Name (ARN) of the flow alias.
Date createdAt
The time at which the alias was created.
String description
A description of the alias.
String flowId
The unique identifier of the flow.
String id
The unique identifier of the alias of the flow.
String name
The name of the alias.
List<E> routingConfiguration
A list of configurations about the versions that the alias maps to. Currently, you can only specify one.
Date updatedAt
The time at which the alias was last updated.
String expression
Defines the condition. You must refer to at least one of the inputs in the condition. For more information, expand the Condition node section in Node types in prompt flows.
String name
A name for the condition that you can reference.
String condition
The condition that triggers this connection. For more information about how to write conditions, see the Condition node type in the Node types topic in the Amazon Bedrock User Guide.
FlowConnectionConfiguration configuration
The configuration of the connection.
String name
A name for the connection that you can reference.
String source
The node that the connection starts at.
String target
The node that the connection ends at.
String type
Whether the source node that the connection begins from is a condition node (Conditional) or not (
Data).
FlowConditionalConnectionConfiguration conditional
The configuration of a connection originating from a Condition node.
FlowDataConnectionConfiguration data
The configuration of a connection originating from a node that isn't a Condition node.
FlowNodeConfiguration configuration
Contains configurations for the node.
List<E> inputs
An array of objects, each of which contains information about an input into the node.
String name
A name for the node.
List<E> outputs
A list of objects, each of which contains information about an output from the node.
String type
The type of node. This value must match the name of the key that you provide in the configuration you provide in
the FlowNodeConfiguration field.
AgentFlowNodeConfiguration agent
Contains configurations for an agent node in your flow. Invokes an alias of an agent and returns the response.
CollectorFlowNodeConfiguration collector
Contains configurations for a collector node in your flow. Collects an iteration of inputs and consolidates them into an array of outputs.
ConditionFlowNodeConfiguration condition
Contains configurations for a Condition node in your flow. Defines conditions that lead to different branches of the flow.
InputFlowNodeConfiguration input
Contains configurations for an input flow node in your flow. The first node in the flow. inputs
can't be specified for this node.
IteratorFlowNodeConfiguration iterator
Contains configurations for an iterator node in your flow. Takes an input that is an array and iteratively sends each item of the array as an output to the following node. The size of the array is also returned in the output.
The output flow node at the end of the flow iteration will return a response for each member of the array. To return only one response, you can include a collector node downstream from the iterator node.
KnowledgeBaseFlowNodeConfiguration knowledgeBase
Contains configurations for a knowledge base node in your flow. Queries a knowledge base and returns the retrieved results or generated response.
LambdaFunctionFlowNodeConfiguration lambdaFunction
Contains configurations for a Lambda function node in your flow. Invokes an Lambda function.
LexFlowNodeConfiguration lex
Contains configurations for a Lex node in your flow. Invokes an Amazon Lex bot to identify the intent of the input and return the intent as the output.
OutputFlowNodeConfiguration output
Contains configurations for an output flow node in your flow. The last node in the flow. outputs
can't be specified for this node.
PromptFlowNodeConfiguration prompt
Contains configurations for a prompt node in your flow. Runs a prompt and generates the model response as the output. You can use a prompt from Prompt management or you can configure one in this node.
RetrievalFlowNodeConfiguration retrieval
Contains configurations for a Retrieval node in your flow. Retrieves data from an Amazon S3 location and returns it as the output.
StorageFlowNodeConfiguration storage
Contains configurations for a Storage node in your flow. Stores an input in an Amazon S3 location.
String expression
An expression that formats the input for the node. For an explanation of how to create expressions, see Expressions in Prompt flows in Amazon Bedrock.
String name
A name for the input that you can reference.
String type
The data type of the input. If the input doesn't match this type at runtime, a validation error will be thrown.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String description
A description of the flow.
String id
The unique identifier of the flow.
String name
The name of the flow.
String status
The status of the flow. The following statuses are possible:
NotPrepared – The flow has been created or updated, but hasn't been prepared. If you just created the flow, you
can't test it. If you updated the flow, the DRAFT version won't contain the latest changes for
testing. Send a PrepareFlow request
to package the latest changes into the DRAFT version.
Preparing – The flow is being prepared so that the DRAFT version contains the latest changes for
testing.
Prepared – The flow is prepared and the DRAFT version contains the latest changes for testing.
Failed – The last API operation that you invoked on the flow failed. Send a GetFlow request and
check the error message in the validations field.
Date updatedAt
The time at which the flow was last updated.
String version
The latest version of the flow.
AgentActionGroup agentActionGroup
Contains details about the action group.
AgentAlias agentAlias
Contains information about the alias.
String agentId
The unique identifier of the agent with which the knowledge base is associated.
String agentVersion
The version of the agent with which the knowledge base is associated.
String knowledgeBaseId
The unique identifier of the knowledge base associated with the agent.
AgentKnowledgeBase agentKnowledgeBase
Contains details about a knowledge base attached to an agent.
String agentId
The unique identifier of the agent.
Agent agent
Contains details about the agent.
AgentVersion agentVersion
Contains details about the version of the agent.
DataSource dataSource
Contains details about the data source.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String description
The description of the flow.
String flowId
The unique identifier of the flow that the alias belongs to.
String id
The unique identifier of the alias of the flow.
String name
The name of the flow alias.
List<E> routingConfiguration
Contains information about the version that the alias is mapped to.
Date updatedAt
The time at which the flow alias was last updated.
String flowIdentifier
The unique identifier of the flow.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that the flow is encrypted with.
FlowDefinition definition
The definition of the nodes and connections between the nodes in the flow.
String description
The description of the flow.
String executionRoleArn
The Amazon Resource Name (ARN) of the service role with permissions to create a flow. For more information, see Create a service row for flows in the Amazon Bedrock User Guide.
String id
The unique identifier of the flow.
String name
The name of the flow.
String status
The status of the flow. The following statuses are possible:
NotPrepared – The flow has been created or updated, but hasn't been prepared. If you just created the flow, you
can't test it. If you updated the flow, the DRAFT version won't contain the latest changes for
testing. Send a PrepareFlow request
to package the latest changes into the DRAFT version.
Preparing – The flow is being prepared so that the DRAFT version contains the latest changes for
testing.
Prepared – The flow is prepared and the DRAFT version contains the latest changes for testing.
Failed – The last API operation that you invoked on the flow failed. Send a GetFlow request and
check the error message in the validations field.
Date updatedAt
The time at which the flow was last updated.
List<E> validations
A list of validation error messages related to the last failed operation on the flow.
String version
The version of the flow for which information was retrieved.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that the version of the flow is encrypted with.
FlowDefinition definition
The definition of the nodes and connections between nodes in the flow.
String description
The description of the flow.
String executionRoleArn
The Amazon Resource Name (ARN) of the service role with permissions to create a flow. For more information, see Create a service role for flows in Amazon Bedrock in the Amazon Bedrock User Guide.
String id
The unique identifier of the flow.
String name
The name of the flow version.
String status
The status of the flow.
String version
The version of the flow for which information was retrieved.
IngestionJob ingestionJob
Contains details about the ingestion job.
String knowledgeBaseId
The unique identifier of the knowledge base for which to get information.
KnowledgeBase knowledgeBase
Contains details about the knowledge base.
String arn
The Amazon Resource Name (ARN) of the prompt.
Date createdAt
The time at which the prompt was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that the prompt is encrypted with.
String defaultVariant
The name of the default variant for the prompt. This value must match the name field in the relevant
PromptVariant
object.
String description
The descriptino of the prompt.
String id
The unique identifier of the prompt.
String name
The name of the prompt.
Date updatedAt
The time at which the prompt was last updated.
List<E> variants
A list of objects, each containing details about a variant of the prompt.
String version
The version of the prompt.
Integer maxTokens
The maximum number of tokens that a chunk can contain in this layer.
Integer maximumLength
The maximum number of tokens to allow in the generated response.
List<E> stopSequences
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
Float 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.
Integer 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.
Float topP
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 80, the
model only selects the next token from the top 80% of the probability distribution of next tokens.
String dataSourceId
The unique identifier of the ingested data source.
String description
The description of the ingestion job.
List<E> failureReasons
A list of reasons that the ingestion job failed.
String ingestionJobId
The unique identifier of the ingestion job.
String knowledgeBaseId
The unique identifier of the knowledge base to which the data source is being added.
Date startedAt
The time at which the ingestion job started.
IngestionJobStatistics statistics
Contains statistics about the ingestion job.
String status
The status of the ingestion job.
Date updatedAt
The time at which the ingestion job was last updated.
Long numberOfDocumentsDeleted
The number of source documents that was deleted.
Long numberOfDocumentsFailed
The number of source documents that failed to be ingested.
Long numberOfDocumentsScanned
The total number of source documents that were scanned. Includes new, updated, and unchanged documents.
Long numberOfMetadataDocumentsModified
The number of metadata files that were updated or deleted.
Long numberOfMetadataDocumentsScanned
The total number of metadata files that were scanned. Includes new, updated, and unchanged files.
Long numberOfModifiedDocumentsIndexed
The number of modified source documents in the data source that were successfully indexed.
Long numberOfNewDocumentsIndexed
The number of new source documents in the data source that were successfully indexed.
String dataSourceId
The unique identifier of the data source in the ingestion job.
String description
The description of the ingestion job.
String ingestionJobId
The unique identifier of the ingestion job.
String knowledgeBaseId
The unique identifier of the knowledge base to which the data source is added.
Date startedAt
The time at which the ingestion job was started.
IngestionJobStatistics statistics
Contains statistics for the ingestion job.
String status
The status of the ingestion job.
Date updatedAt
The time at which the ingestion job was last updated.
S3Location s3Location
An S3 bucket path.
Date createdAt
The time at which the knowledge base was created.
String description
The description of the knowledge base.
List<E> failureReasons
A list of reasons that the API operation on the knowledge base failed.
String knowledgeBaseArn
The Amazon Resource Name (ARN) of the knowledge base.
KnowledgeBaseConfiguration knowledgeBaseConfiguration
Contains details about the embeddings configuration of the knowledge base.
String knowledgeBaseId
The unique identifier of the knowledge base.
String name
The name of the knowledge base.
String roleArn
The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base.
String status
The status of the knowledge base. The following statuses are possible:
CREATING – The knowledge base is being created.
ACTIVE – The knowledge base is ready to be queried.
DELETING – The knowledge base is being deleted.
UPDATING – The knowledge base is being updated.
FAILED – The knowledge base API operation failed.
StorageConfiguration storageConfiguration
Contains details about the storage configuration of the knowledge base.
Date updatedAt
The time at which the knowledge base was last updated.
String type
The type of data that the data source is converted into for the knowledge base.
VectorKnowledgeBaseConfiguration vectorKnowledgeBaseConfiguration
Contains details about the embeddings model that'sused to convert the data source.
String description
The description of the knowledge base.
String knowledgeBaseId
The unique identifier of the knowledge base.
String name
The name of the knowledge base.
String status
The status of the knowledge base.
Date updatedAt
The time at which the knowledge base was last updated.
String lambdaArn
The Amazon Resource Name (ARN) of the Lambda function to invoke.
String agentId
The unique identifier of the agent.
String agentVersion
The version of the agent.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> actionGroupSummaries
A list of objects, each of which contains information about an action group.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
String agentId
The unique identifier of the agent.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> agentAliasSummaries
A list of objects, each of which contains information about an alias of the agent.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
String agentId
The unique identifier of the agent for which to return information about knowledge bases associated with it.
String agentVersion
The version of the agent for which to return information about knowledge bases associated with it.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> agentKnowledgeBaseSummaries
A list of objects, each of which contains information about a knowledge base associated with the agent.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> agentSummaries
A list of objects, each of which contains information about an agent.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
String agentId
The unique identifier of the agent.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> agentVersionSummaries
A list of objects, each of which contains information about a version of the agent.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
String knowledgeBaseId
The unique identifier of the knowledge base for which to return a list of information.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> dataSourceSummaries
A list of objects, each of which contains information about a data source.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
String flowIdentifier
The unique identifier of the flow for which aliases are being returned.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> flowAliasSummaries
A list, each member of which contains information about a flow alias.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> flowSummaries
A list, each member of which contains information about a flow.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
String flowIdentifier
The unique identifier of the flow.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> flowVersionSummaries
A list, each member of which contains information about a flow.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
String dataSourceId
The unique identifier of the data source for which to return ingestion jobs.
List<E> filters
Contains a definition of a filter for which to filter the results.
String knowledgeBaseId
The unique identifier of the knowledge base for which to return ingestion jobs.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
IngestionJobSortBy sortBy
Contains details about how to sort the results.
List<E> ingestionJobSummaries
A list of objects, each of which contains information about an ingestion job.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
List<E> knowledgeBaseSummaries
A list of objects, each of which contains information about a knowledge base.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
Integer maxResults
The maximum number of results 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.
String nextToken
If the total number of results is greater than the maxResults 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.
String promptIdentifier
The unique identifier of the prompt.
String nextToken
If the total number of results is greater than the maxResults value provided in the request, use
this token when making another request in the nextToken field to return the next batch of results.
List<E> promptSummaries
A list, each member of which contains information about a prompt using Prompt management.
String resourceArn
The Amazon Resource Name (ARN) of the resource for which to list tags.
String collectionName
The collection name of the knowledge base in MongoDB Atlas.
String credentialsSecretArn
The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that contains user credentials for your MongoDB Atlas cluster.
String databaseName
The database name in your MongoDB Atlas cluster for your knowledge base.
String endpoint
The endpoint URL of your MongoDB Atlas cluster for your knowledge base.
String endpointServiceName
The name of the VPC endpoint service in your account that is connected to your MongoDB Atlas cluster.
MongoDbAtlasFieldMapping fieldMapping
Contains the names of the fields to which to map information about the vector store.
String vectorIndexName
The name of the MongoDB Atlas vector search index.
String metadataField
The name of the field in which Amazon Bedrock stores metadata about the vector store.
String textField
The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.
String vectorField
The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources.
String collectionArn
The Amazon Resource Name (ARN) of the OpenSearch Service vector store.
OpenSearchServerlessFieldMapping fieldMapping
Contains the names of the fields to which to map information about the vector store.
String vectorIndexName
The name of the vector store.
String metadataField
The name of the field in which Amazon Bedrock stores metadata about the vector store.
String textField
The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.
String vectorField
The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources.
String description
A description of the parameter. Helps the foundation model determine how to elicit the parameters from the user.
Boolean required
Whether the parameter is required for the agent to complete the function for action group invocation.
String type
The data type of the parameter.
BedrockFoundationModelConfiguration bedrockFoundationModelConfiguration
Settings for a foundation model used to parse documents for a data source.
String parsingStrategy
The parsing strategy for the data source.
String parsingPromptText
Instructions for interpreting the contents of a document.
List<E> exclusionFilters
A list of one or more exclusion regular expression patterns to exclude certain object types that adhere to the pattern. If you specify an inclusion and exclusion filter/pattern and both match a document, the exclusion filter takes precedence and the document isn’t crawled.
List<E> inclusionFilters
A list of one or more inclusion regular expression patterns to include certain object types that adhere to the pattern. If you specify an inclusion and exclusion filter/pattern and both match a document, the exclusion filter takes precedence and the document isn’t crawled.
String objectType
The supported object type or content type of the data source.
String connectionString
The endpoint URL for your index management page.
String credentialsSecretArn
The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that is linked to your Pinecone API key.
PineconeFieldMapping fieldMapping
Contains the names of the fields to which to map information about the vector store.
String namespace
The namespace to be used to write new data to your database.
String agentId
The unique identifier of the agent for which to create a DRAFT version.
String agentId
The unique identifier of the agent for which the DRAFT version was created.
String agentStatus
The status of the DRAFT version and whether it is ready for use.
String agentVersion
The version of the agent.
Date preparedAt
The time at which the DRAFT version of the agent was last prepared.
String flowIdentifier
The unique identifier of the flow.
String basePromptTemplate
Defines the prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables. For more information, see Configure the prompt templates.
InferenceConfiguration inferenceConfiguration
Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence
defined by the promptType. For more information, see Inference parameters for
foundation models.
String 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. If you set the field as
OVERRIDEN, the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
String promptCreationMode
Specifies whether to override the default prompt template for this promptType. Set this value to
OVERRIDDEN to use the prompt that you provide in the basePromptTemplate. If you leave
it as DEFAULT, the agent uses a default prompt template.
String promptState
Specifies whether to allow the agent to carry out the step specified in the promptType. If you set
this value to DISABLED, the agent skips that step. The default state for each
promptType is as follows.
PRE_PROCESSING – ENABLED
ORCHESTRATION – ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION – ENABLED
POST_PROCESSING – DISABLED
String promptType
The step in the agent sequence that this prompt configuration applies to.
PromptFlowNodeSourceConfiguration sourceConfiguration
Specifies whether the prompt is from Prompt management or defined inline.
PromptInferenceConfiguration inferenceConfiguration
Contains inference configurations for the prompt.
String modelId
The unique identifier of the model to run inference with.
PromptTemplateConfiguration templateConfiguration
Contains a prompt and variables in the prompt that can be replaced with values at runtime.
String templateType
The type of prompt template.
String promptArn
The Amazon Resource Name (ARN) of the prompt from Prompt management.
PromptFlowNodeInlineConfiguration inline
Contains configurations for a prompt that is defined inline
PromptFlowNodeResourceConfiguration resource
Contains configurations for a prompt from Prompt management.
PromptModelInferenceConfiguration text
Contains inference configurations for a text prompt.
String name
The name of the variable.
Integer maxTokens
The maximum number of tokens to return in the response.
List<E> stopSequences
A list of strings that define sequences after which the model will stop generating.
Float temperature
Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.
Integer topK
The number of most-likely candidates that the model considers for the next token during generation.
Float topP
The percentage of most-likely candidates that the model considers for the next token.
String overrideLambda
The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent
sequence. If you specify this field, at least one of the promptConfigurations must contain a
parserMode value that is set to OVERRIDDEN. For more information, see Parser Lambda function in Agents
for Amazon Bedrock.
List<E> promptConfigurations
Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.
String arn
The Amazon Resource Name (ARN) of the prompt.
Date createdAt
The time at which the prompt was created.
String description
The description of the prompt.
String id
The unique identifier of the prompt.
String name
The name of the prompt.
Date updatedAt
The time at which the prompt was last updated.
String version
The version of the prompt that this summary applies to.
TextPromptTemplateConfiguration text
Contains configurations for the text in a message for a prompt.
PromptInferenceConfiguration inferenceConfiguration
Contains inference configurations for the prompt variant.
String modelId
The unique identifier of the model with which to run inference on the prompt.
String name
The name of the prompt variant.
PromptTemplateConfiguration templateConfiguration
Contains configurations for the prompt template.
String templateType
The type of prompt template to use.
String credentialsSecretArn
The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that is linked to your Amazon RDS database.
String databaseName
The name of your Amazon RDS database.
RdsFieldMapping fieldMapping
Contains the names of the fields to which to map information about the vector store.
String resourceArn
The Amazon Resource Name (ARN) of the vector store.
String tableName
The name of the table in the database.
String metadataField
The name of the field in which Amazon Bedrock stores metadata about the vector store.
String primaryKeyField
The name of the field in which Amazon Bedrock stores the ID for each entry.
String textField
The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.
String vectorField
The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources.
String credentialsSecretArn
The Amazon Resource Name (ARN) of the secret that you created in Secrets Manager that is linked to your Redis Enterprise Cloud database.
String endpoint
The endpoint URL of the Redis Enterprise Cloud database.
RedisEnterpriseCloudFieldMapping fieldMapping
Contains the names of the fields to which to map information about the vector store.
String vectorIndexName
The name of the vector index.
String metadataField
The name of the field in which Amazon Bedrock stores metadata about the vector store.
String textField
The name of the field in which Amazon Bedrock stores the raw text from your data. The text is split according to the chunking strategy you choose.
String vectorField
The name of the field in which Amazon Bedrock stores the vector embeddings for your data sources.
RetrievalFlowNodeServiceConfiguration serviceConfiguration
Contains configurations for the service to use for retrieving data to return as the output from the node.
String bucketName
The name of the Amazon S3 bucket from which to retrieve data.
RetrievalFlowNodeS3Configuration s3
Contains configurations for the Amazon S3 location from which to retrieve data to return as the output from the node.
String bucketArn
The Amazon Resource Name (ARN) of the S3 bucket that contains your data.
String bucketOwnerAccountId
The account ID for the owner of the S3 bucket.
List<E> inclusionPrefixes
A list of S3 prefixes to include certain files or content. For more information, see Organizing objects using prefixes.
String uri
The location's URI. For example, s3://my-bucket/chunk-processor/.
CrawlFilterConfiguration filterConfiguration
The configuration of filtering the Salesforce content. For example, configuring regular expression patterns to include or exclude certain content.
SalesforceCrawlerConfiguration crawlerConfiguration
The configuration of the Salesforce content. For example, configuring specific types of Salesforce content.
SalesforceSourceConfiguration sourceConfiguration
The endpoint information to connect to your Salesforce data source.
String authType
The supported authentication type to authenticate and connect to your Salesforce instance.
String credentialsSecretArn
The Amazon Resource Name of an Secrets Manager secret that stores your authentication credentials for your SharePoint site/sites. For more information on the key-value pairs that must be included in your secret, depending on your authentication type, see Salesforce connection configuration.
String hostUrl
The Salesforce host URL or instance URL.
String url
A seed or starting point URL.
String kmsKeyArn
The Amazon Resource Name (ARN) of the KMS key used to encrypt the resource.
CrawlFilterConfiguration filterConfiguration
The configuration of filtering the SharePoint content. For example, configuring regular expression patterns to include or exclude certain content.
SharePointCrawlerConfiguration crawlerConfiguration
The configuration of the SharePoint content. For example, configuring specific types of SharePoint content.
SharePointSourceConfiguration sourceConfiguration
The endpoint information to connect to your SharePoint data source.
String authType
The supported authentication type to authenticate and connect to your SharePoint site/sites.
String credentialsSecretArn
The Amazon Resource Name of an Secrets Manager secret that stores your authentication credentials for your SharePoint site/sites. For more information on the key-value pairs that must be included in your secret, depending on your authentication type, see SharePoint connection configuration.
String domain
The domain of your SharePoint instance or site URL/URLs.
String hostType
The supported host type, whether online/cloud or server/on-premises.
List<E> siteUrls
A list of one or more SharePoint site URLs.
String tenantId
The identifier of your Microsoft 365 tenant.
String clientToken
A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
String dataSourceId
The unique identifier of the data source to ingest.
String description
A description of the ingestion job.
String knowledgeBaseId
The unique identifier of the knowledge base to which to add the data source.
IngestionJob ingestionJob
An object containing information about the ingestion job.
MongoDbAtlasConfiguration mongoDbAtlasConfiguration
Contains the storage configuration of the knowledge base in MongoDB Atlas.
OpenSearchServerlessConfiguration opensearchServerlessConfiguration
Contains the storage configuration of the knowledge base in Amazon OpenSearch Service.
PineconeConfiguration pineconeConfiguration
Contains the storage configuration of the knowledge base in Pinecone.
RdsConfiguration rdsConfiguration
Contains details about the storage configuration of the knowledge base in Amazon RDS. For more information, see Create a vector index in Amazon RDS.
RedisEnterpriseCloudConfiguration redisEnterpriseCloudConfiguration
Contains the storage configuration of the knowledge base in Redis Enterprise Cloud.
String type
The vector store service in which the knowledge base is stored.
StorageFlowNodeServiceConfiguration serviceConfiguration
Contains configurations for the service to use for storing the input into the node.
String bucketName
The name of the Amazon S3 bucket in which to store the input into the node.
StorageFlowNodeS3Configuration s3
Contains configurations for the Amazon S3 location in which to store the input into the node.
String stepToApply
When the service applies the transformation.
TransformationFunction transformationFunction
A Lambda function that processes documents.
TransformationLambdaConfiguration transformationLambdaConfiguration
The Lambda function.
String lambdaArn
The function's ARN identifier.
ActionGroupExecutor actionGroupExecutor
The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action.
String actionGroupId
The unique identifier of the action group.
String actionGroupName
Specifies a new name for the action group.
String actionGroupState
Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
String agentId
The unique identifier of the agent for which to update the action group.
String agentVersion
The unique identifier of the agent version for which to update the action group.
APISchema apiSchema
Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas.
String description
Specifies a new name for the action group.
FunctionSchema functionSchema
Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
String parentActionGroupSignature
To allow your agent to request the user for additional information when trying to complete a task, set this field
to AMAZON.UserInput. You must leave the description, apiSchema, and
actionGroupExecutor fields blank for this action group.
During orchestration, if your agent determines that it needs to invoke an API in an action group, but doesn't have enough information to complete the API request, it will invoke this action group instead and return an Observation reprompting the user for more information.
AgentActionGroup agentActionGroup
Contains details about the action group that was updated.
String agentAliasId
The unique identifier of the alias.
String agentAliasName
Specifies a new name for the alias.
String agentId
The unique identifier of the agent.
String description
Specifies a new description for the alias.
List<E> routingConfiguration
Contains details about the routing configuration of the alias.
AgentAlias agentAlias
Contains details about the alias that was updated.
String agentId
The unique identifier of the agent associated with the knowledge base that you want to update.
String agentVersion
The version of the agent associated with the knowledge base that you want to update.
String description
Specifies a new description for the knowledge base associated with an agent.
String knowledgeBaseId
The unique identifier of the knowledge base that has been associated with an agent.
String knowledgeBaseState
Specifies whether the agent uses the knowledge base or not when sending an InvokeAgent request.
AgentKnowledgeBase agentKnowledgeBase
Contains details about the knowledge base that has been associated with an agent.
String agentId
The unique identifier of the agent.
String agentName
Specifies a new name for the agent.
String agentResourceRoleArn
The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent.
String description
Specifies a new description of the agent.
String foundationModel
Specifies a new foundation model to be used for orchestration by the agent.
GuardrailConfiguration guardrailConfiguration
The unique Guardrail configuration assigned to the agent when it is updated.
Integer idleSessionTTLInSeconds
The number of seconds for which Amazon Bedrock keeps information about a user's conversation with the agent.
A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.
String instruction
Specifies new instructions that tell the agent what it should do and how it should interact with users.
MemoryConfiguration memoryConfiguration
Specifies the new memory configuration for the agent.
PromptOverrideConfiguration promptOverrideConfiguration
Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.
Agent agent
Contains details about the agent that was updated.
String dataDeletionPolicy
The data deletion policy for the data source that you want to update.
DataSourceConfiguration dataSourceConfiguration
The connection configuration for the data source that you want to update.
String dataSourceId
The unique identifier of the data source.
String description
Specifies a new description for the data source.
String knowledgeBaseId
The unique identifier of the knowledge base for the data source.
String name
Specifies a new name for the data source.
ServerSideEncryptionConfiguration serverSideEncryptionConfiguration
Contains details about server-side encryption of the data source.
VectorIngestionConfiguration vectorIngestionConfiguration
Contains details about how to ingest the documents in the data source.
DataSource dataSource
Contains details about the data source.
String aliasIdentifier
The unique identifier of the alias.
String description
A description for the flow alias.
String flowIdentifier
The unique identifier of the flow.
String name
The name of the flow alias.
List<E> routingConfiguration
Contains information about the version to which to map the alias.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String description
The description of the flow.
String flowId
The unique identifier of the flow.
String id
The unique identifier of the alias.
String name
The name of the flow alias.
List<E> routingConfiguration
Contains information about the version that the alias is mapped to.
Date updatedAt
The time at which the flow alias was last updated.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key to encrypt the flow.
FlowDefinition definition
A definition of the nodes and the connections between the nodes in the flow.
String description
A description for the flow.
String executionRoleArn
The Amazon Resource Name (ARN) of the service role with permissions to create and manage a flow. For more information, see Create a service role for flows in Amazon Bedrock in the Amazon Bedrock User Guide.
String flowIdentifier
The unique identifier of the flow.
String name
A name for the flow.
String arn
The Amazon Resource Name (ARN) of the flow.
Date createdAt
The time at which the flow was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key that the flow was encrypted with.
FlowDefinition definition
A definition of the nodes and the connections between nodes in the flow.
String description
The description of the flow.
String executionRoleArn
The Amazon Resource Name (ARN) of the service role with permissions to create a flow. For more information, see Create a service role for flows in Amazon Bedrock in the Amazon Bedrock User Guide.
String id
The unique identifier of the flow.
String name
The name of the flow.
String status
The status of the flow. When you submit this request, the status will be NotPrepared. If updating
fails, the status becomes Failed.
Date updatedAt
The time at which the flow was last updated.
String version
The version of the flow. When you update a flow, the version updated is the DRAFT version.
String description
Specifies a new description for the knowledge base.
KnowledgeBaseConfiguration knowledgeBaseConfiguration
Specifies the configuration for the embeddings model used for the knowledge base. You must use the same configuration as when the knowledge base was created.
String knowledgeBaseId
The unique identifier of the knowledge base to update.
String name
Specifies a new name for the knowledge base.
String roleArn
Specifies a different Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base.
StorageConfiguration storageConfiguration
Specifies the configuration for the vector store used for the knowledge base. You must use the same configuration as when the knowledge base was created.
KnowledgeBase knowledgeBase
Contains details about the knowledge base.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key to encrypt the prompt.
String defaultVariant
The name of the default variant for the prompt. This value must match the name field in the relevant
PromptVariant
object.
String description
A description for the prompt.
String name
A name for the prompt.
String promptIdentifier
The unique identifier of the prompt.
List<E> variants
A list of objects, each containing details about a variant of the prompt.
String arn
The Amazon Resource Name (ARN) of the prompt.
Date createdAt
The time at which the prompt was created.
String customerEncryptionKeyArn
The Amazon Resource Name (ARN) of the KMS key to encrypt the prompt.
String defaultVariant
The name of the default variant for the prompt. This value must match the name field in the relevant
PromptVariant
object.
String description
The description of the prompt.
String id
The unique identifier of the prompt.
String name
The name of the prompt.
Date updatedAt
The time at which the prompt was last updated.
List<E> variants
A list of objects, each containing details about a variant of the prompt.
String version
The version of the prompt. When you update a prompt, the version updated is the DRAFT version.
ChunkingConfiguration chunkingConfiguration
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
CustomTransformationConfiguration customTransformationConfiguration
A custom document transformer for parsed data source documents.
ParsingConfiguration parsingConfiguration
A custom parser for data source documents.
String embeddingModelArn
The Amazon Resource Name (ARN) of the model used to create vector embeddings for the knowledge base.
EmbeddingModelConfiguration embeddingModelConfiguration
The embeddings model configuration details for the vector model used in Knowledge Base.
WebCrawlerLimits crawlerLimits
The configuration of crawl limits for the web URLs.
List<E> exclusionFilters
A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
List<E> inclusionFilters
A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
String scope
The scope of what is crawled for your URLs.
You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL "https://docs.aws.amazon.com/bedrock/latest/userguide/" and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain "aws.amazon.com" can also include sub domain "docs.aws.amazon.com".
Integer rateLimit
The max rate at which pages are crawled, up to 300 per minute per host.
WebCrawlerConfiguration crawlerConfiguration
The Web Crawler configuration details for the web data source.
WebSourceConfiguration sourceConfiguration
The source configuration details for the web data source.
UrlConfiguration urlConfiguration
The configuration of the URL/URLs.
Copyright © 2025. All rights reserved.