Bedrock Agent

This page documents function available when using the Bedrock_Agent module, created with @service Bedrock_Agent.

Index

Documentation

Main.Bedrock_Agent.associate_agent_knowledge_baseMethod
associate_agent_knowledge_base(agent_id, agent_version, description, knowledge_base_id)
associate_agent_knowledge_base(agent_id, agent_version, description, knowledge_base_id, params::Dict{String,<:Any})

Associates a knowledge base with an agent. If a knowledge base is associated and its indexState is set to Enabled, the agent queries the knowledge base for information to augment its response to the user.

Arguments

  • agent_id: The unique identifier of the agent with which you want to associate the knowledge base.
  • agent_version: The version of the agent with which you want to associate the knowledge base.
  • description: A description of what the agent should use the knowledge base for.
  • knowledge_base_id: The unique identifier of the knowledge base to associate with the agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "knowledgeBaseState": Specifies whether to use the knowledge base or not when sending an InvokeAgent request.
source
Main.Bedrock_Agent.create_agentMethod
create_agent(agent_name)
create_agent(agent_name, params::Dict{String,<:Any})

Creates an agent that orchestrates interactions between foundation models, data sources, software applications, user conversations, and APIs to carry out tasks to help customers. Specify the following fields for security purposes. agentResourceRoleArn – The Amazon Resource Name (ARN) of the role with permissions to invoke API operations on an agent. (Optional) customerEncryptionKeyArn – The Amazon Resource Name (ARN) of a KMS key to encrypt the creation of the agent. (Optional) idleSessionTTLinSeconds – Specify the number of seconds for which the agent should maintain session information. After this time expires, the subsequent InvokeAgent request begins a new session. To override the default prompt behavior for agent orchestration and to use advanced prompts, include a promptOverrideConfiguration object. For more information, see Advanced prompts. If you agent fails to be created, the response returns a list of failureReasons alongside a list of recommendedActions for you to troubleshoot.

Arguments

  • agent_name: A name for the agent that you create.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "agentResourceRoleArn": The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.
  • "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.
  • "customerEncryptionKeyArn": The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent.
  • "description": A description of the agent.
  • "foundationModel": The foundation model to be used for orchestration by the agent you create.
  • "guardrailConfiguration": The unique Guardrail configuration assigned to the agent when it is created.
  • "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.
  • "instruction": Instructions that tell the agent what it should do and how it should interact with users.
  • "promptOverrideConfiguration": Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.
  • "tags": Any tags that you want to attach to the agent.
source
Main.Bedrock_Agent.create_agent_action_groupMethod
create_agent_action_group(action_group_name, agent_id, agent_version)
create_agent_action_group(action_group_name, agent_id, agent_version, params::Dict{String,<:Any})

Creates an action group for an agent. An action group represents the actions that an agent can carry out for the customer by defining the APIs that an agent can call and the logic for calling them. To allow your agent to request the user for additional information when trying to complete a task, add an action group with the parentActionGroupSignature field set 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.

Arguments

  • action_group_name: The name to give the action group.
  • agent_id: The unique identifier of the agent for which to create the action group.
  • agent_version: The version of the agent for which to create the action group.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "actionGroupState": Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
  • "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.
  • "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.
  • "description": A description of the action group.
  • "functionSchema": Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
  • "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.
source
Main.Bedrock_Agent.create_agent_aliasMethod
create_agent_alias(agent_alias_name, agent_id)
create_agent_alias(agent_alias_name, agent_id, params::Dict{String,<:Any})

Creates an alias of an agent that can be used to deploy the agent.

Arguments

  • agent_alias_name: The name of the alias.
  • agent_id: The unique identifier of the agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "description": A description of the alias of the agent.
  • "routingConfiguration": Contains details about the routing configuration of the alias.
  • "tags": Any tags that you want to attach to the alias of the agent.
source
Main.Bedrock_Agent.create_data_sourceMethod
create_data_source(data_source_configuration, knowledge_base_id, name)
create_data_source(data_source_configuration, knowledge_base_id, name, params::Dict{String,<:Any})

Sets up a data source to be added to a knowledge base. You can't change the chunkingConfiguration after you create the data source.

Arguments

  • data_source_configuration: Contains metadata about where the data source is stored.
  • knowledge_base_id: The unique identifier of the knowledge base to which to add the data source.
  • name: The name of the data source.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "dataDeletionPolicy": The data deletion policy assigned to the data source.
  • "description": A description of the data source.
  • "serverSideEncryptionConfiguration": Contains details about the server-side encryption for the data source.
  • "vectorIngestionConfiguration": Contains details about how to ingest the documents in the data source.
source
Main.Bedrock_Agent.create_knowledge_baseMethod
create_knowledge_base(knowledge_base_configuration, name, role_arn, storage_configuration)
create_knowledge_base(knowledge_base_configuration, name, role_arn, storage_configuration, params::Dict{String,<:Any})

Creates a knowledge base that contains data sources from which information can be queried and used by LLMs. To create a knowledge base, you must first set up your data sources and configure a supported vector store. For more information, see Set up your data for ingestion. If you prefer to let Amazon Bedrock create and manage a vector store for you in Amazon OpenSearch Service, use the console. For more information, see Create a knowledge base. Provide the name and an optional description. Provide the Amazon Resource Name (ARN) with permissions to create a knowledge base in the roleArn field. Provide the embedding model to use in the embeddingModelArn field in the knowledgeBaseConfiguration object. Provide the configuration for your vector store in the storageConfiguration object. For an Amazon OpenSearch Service database, use the opensearchServerlessConfiguration object. For more information, see Create a vector store in Amazon OpenSearch Service. For an Amazon Aurora database, use the RdsConfiguration object. For more information, see Create a vector store in Amazon Aurora. For a Pinecone database, use the pineconeConfiguration object. For more information, see Create a vector store in Pinecone. For a Redis Enterprise Cloud database, use the redisEnterpriseCloudConfiguration object. For more information, see Create a vector store in Redis Enterprise Cloud.

Arguments

  • knowledge_base_configuration: Contains details about the embeddings model used for the knowledge base.
  • name: A name for the knowledge base.
  • role_arn: The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base.
  • storage_configuration: Contains details about the configuration of the vector database used for the knowledge base.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "description": A description of the knowledge base.
  • "tags": Specify the key-value pairs for the tags that you want to attach to your knowledge base in this object.
source
Main.Bedrock_Agent.delete_agentMethod
delete_agent(agent_id)
delete_agent(agent_id, params::Dict{String,<:Any})

Deletes an agent.

Arguments

  • agent_id: The unique identifier of the agent to delete.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
source
Main.Bedrock_Agent.delete_agent_action_groupMethod
delete_agent_action_group(action_group_id, agent_id, agent_version)
delete_agent_action_group(action_group_id, agent_id, agent_version, params::Dict{String,<:Any})

Deletes an action group in an agent.

Arguments

  • action_group_id: The unique identifier of the action group to delete.
  • agent_id: The unique identifier of the agent that the action group belongs to.
  • agent_version: The version of the agent that the action group belongs to.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
source
Main.Bedrock_Agent.delete_agent_aliasMethod
delete_agent_alias(agent_alias_id, agent_id)
delete_agent_alias(agent_alias_id, agent_id, params::Dict{String,<:Any})

Deletes an alias of an agent.

Arguments

  • agent_alias_id: The unique identifier of the alias to delete.
  • agent_id: The unique identifier of the agent that the alias belongs to.
source
Main.Bedrock_Agent.delete_agent_versionMethod
delete_agent_version(agent_id, agent_version)
delete_agent_version(agent_id, agent_version, params::Dict{String,<:Any})

Deletes a version of an agent.

Arguments

  • agent_id: The unique identifier of the agent that the version belongs to.
  • agent_version: The version of the agent to delete.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
source
Main.Bedrock_Agent.delete_data_sourceMethod
delete_data_source(data_source_id, knowledge_base_id)
delete_data_source(data_source_id, knowledge_base_id, params::Dict{String,<:Any})

Deletes a data source from a knowledge base.

Arguments

  • data_source_id: The unique identifier of the data source to delete.
  • knowledge_base_id: The unique identifier of the knowledge base from which to delete the data source.
source
Main.Bedrock_Agent.delete_knowledge_baseMethod
delete_knowledge_base(knowledge_base_id)
delete_knowledge_base(knowledge_base_id, params::Dict{String,<:Any})

Deletes a knowledge base. Before deleting a knowledge base, you should disassociate the knowledge base from any agents that it is associated with by making a DisassociateAgentKnowledgeBase request.

Arguments

  • knowledge_base_id: The unique identifier of the knowledge base to delete.
source
Main.Bedrock_Agent.disassociate_agent_knowledge_baseMethod
disassociate_agent_knowledge_base(agent_id, agent_version, knowledge_base_id)
disassociate_agent_knowledge_base(agent_id, agent_version, knowledge_base_id, params::Dict{String,<:Any})

Disassociates a knowledge base from an agent.

Arguments

  • agent_id: The unique identifier of the agent from which to disassociate the knowledge base.
  • agent_version: The version of the agent from which to disassociate the knowledge base.
  • knowledge_base_id: The unique identifier of the knowledge base to disassociate.
source
Main.Bedrock_Agent.get_agentMethod
get_agent(agent_id)
get_agent(agent_id, params::Dict{String,<:Any})

Gets information about an agent.

Arguments

  • agent_id: The unique identifier of the agent.
source
Main.Bedrock_Agent.get_agent_action_groupMethod
get_agent_action_group(action_group_id, agent_id, agent_version)
get_agent_action_group(action_group_id, agent_id, agent_version, params::Dict{String,<:Any})

Gets information about an action group for an agent.

Arguments

  • action_group_id: The unique identifier of the action group for which to get information.
  • agent_id: The unique identifier of the agent that the action group belongs to.
  • agent_version: The version of the agent that the action group belongs to.
source
Main.Bedrock_Agent.get_agent_aliasMethod
get_agent_alias(agent_alias_id, agent_id)
get_agent_alias(agent_alias_id, agent_id, params::Dict{String,<:Any})

Gets information about an alias of an agent.

Arguments

  • agent_alias_id: The unique identifier of the alias for which to get information.
  • agent_id: The unique identifier of the agent to which the alias to get information belongs.
source
Main.Bedrock_Agent.get_agent_knowledge_baseMethod
get_agent_knowledge_base(agent_id, agent_version, knowledge_base_id)
get_agent_knowledge_base(agent_id, agent_version, knowledge_base_id, params::Dict{String,<:Any})

Gets information about a knowledge base associated with an agent.

Arguments

  • agent_id: The unique identifier of the agent with which the knowledge base is associated.
  • agent_version: The version of the agent with which the knowledge base is associated.
  • knowledge_base_id: The unique identifier of the knowledge base associated with the agent.
source
Main.Bedrock_Agent.get_agent_versionMethod
get_agent_version(agent_id, agent_version)
get_agent_version(agent_id, agent_version, params::Dict{String,<:Any})

Gets details about a version of an agent.

Arguments

  • agent_id: The unique identifier of the agent.
  • agent_version: The version of the agent.
source
Main.Bedrock_Agent.get_data_sourceMethod
get_data_source(data_source_id, knowledge_base_id)
get_data_source(data_source_id, knowledge_base_id, params::Dict{String,<:Any})

Gets information about a data source.

Arguments

  • data_source_id: The unique identifier of the data source.
  • knowledge_base_id: The unique identifier of the knowledge base that the data source was added to.
source
Main.Bedrock_Agent.get_ingestion_jobMethod
get_ingestion_job(data_source_id, ingestion_job_id, knowledge_base_id)
get_ingestion_job(data_source_id, ingestion_job_id, knowledge_base_id, params::Dict{String,<:Any})

Gets information about a ingestion job, in which a data source is added to a knowledge base.

Arguments

  • data_source_id: The unique identifier of the data source in the ingestion job.
  • ingestion_job_id: The unique identifier of the ingestion job.
  • knowledge_base_id: The unique identifier of the knowledge base for which the ingestion job applies.
source
Main.Bedrock_Agent.get_knowledge_baseMethod
get_knowledge_base(knowledge_base_id)
get_knowledge_base(knowledge_base_id, params::Dict{String,<:Any})

Gets information about a knoweldge base.

Arguments

  • knowledge_base_id: The unique identifier of the knowledge base for which to get information.
source
Main.Bedrock_Agent.list_agent_action_groupsMethod
list_agent_action_groups(agent_id, agent_version)
list_agent_action_groups(agent_id, agent_version, params::Dict{String,<:Any})

Lists the action groups for an agent and information about each one.

Arguments

  • agent_id: The unique identifier of the agent.
  • agent_version: The version of the agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "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.
source
Main.Bedrock_Agent.list_agent_aliasesMethod
list_agent_aliases(agent_id)
list_agent_aliases(agent_id, params::Dict{String,<:Any})

Lists the aliases of an agent and information about each one.

Arguments

  • agent_id: The unique identifier of the agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "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.
source
Main.Bedrock_Agent.list_agent_knowledge_basesMethod
list_agent_knowledge_bases(agent_id, agent_version)
list_agent_knowledge_bases(agent_id, agent_version, params::Dict{String,<:Any})

Lists knowledge bases associated with an agent and information about each one.

Arguments

  • agent_id: The unique identifier of the agent for which to return information about knowledge bases associated with it.
  • agent_version: The version of the agent for which to return information about knowledge bases associated with it.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "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.
source
Main.Bedrock_Agent.list_agent_versionsMethod
list_agent_versions(agent_id)
list_agent_versions(agent_id, params::Dict{String,<:Any})

Lists the versions of an agent and information about each version.

Arguments

  • agent_id: The unique identifier of the agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "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.
source
Main.Bedrock_Agent.list_agentsMethod
list_agents()
list_agents(params::Dict{String,<:Any})

Lists the agents belonging to an account and information about each agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "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.
source
Main.Bedrock_Agent.list_data_sourcesMethod
list_data_sources(knowledge_base_id)
list_data_sources(knowledge_base_id, params::Dict{String,<:Any})

Lists the data sources in a knowledge base and information about each one.

Arguments

  • knowledge_base_id: The unique identifier of the knowledge base for which to return a list of information.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "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.
source
Main.Bedrock_Agent.list_ingestion_jobsMethod
list_ingestion_jobs(data_source_id, knowledge_base_id)
list_ingestion_jobs(data_source_id, knowledge_base_id, params::Dict{String,<:Any})

Lists the ingestion jobs for a data source and information about each of them.

Arguments

  • data_source_id: The unique identifier of the data source for which to return ingestion jobs.
  • knowledge_base_id: The unique identifier of the knowledge base for which to return ingestion jobs.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "filters": Contains a definition of a filter for which to filter the results.
  • "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.
  • "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.
  • "sortBy": Contains details about how to sort the results.
source
Main.Bedrock_Agent.list_knowledge_basesMethod
list_knowledge_bases()
list_knowledge_bases(params::Dict{String,<:Any})

Lists the knowledge bases in an account and information about each of them.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "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.
source
Main.Bedrock_Agent.list_tags_for_resourceMethod
list_tags_for_resource(resource_arn)
list_tags_for_resource(resource_arn, params::Dict{String,<:Any})

List all the tags for the resource you specify.

Arguments

  • resource_arn: The Amazon Resource Name (ARN) of the resource for which to list tags.
source
Main.Bedrock_Agent.prepare_agentMethod
prepare_agent(agent_id)
prepare_agent(agent_id, params::Dict{String,<:Any})

Creates a DRAFT version of the agent that can be used for internal testing.

Arguments

  • agent_id: The unique identifier of the agent for which to create a DRAFT version.
source
Main.Bedrock_Agent.start_ingestion_jobMethod
start_ingestion_job(data_source_id, knowledge_base_id)
start_ingestion_job(data_source_id, knowledge_base_id, params::Dict{String,<:Any})

Begins an ingestion job, in which a data source is added to a knowledge base.

Arguments

  • data_source_id: The unique identifier of the data source to ingest.
  • knowledge_base_id: The unique identifier of the knowledge base to which to add the data source.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "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.
  • "description": A description of the ingestion job.
source
Main.Bedrock_Agent.tag_resourceMethod
tag_resource(resource_arn, tags)
tag_resource(resource_arn, tags, params::Dict{String,<:Any})

Associate tags with a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.

Arguments

  • resource_arn: The Amazon Resource Name (ARN) of the resource to tag.
  • tags: An object containing key-value pairs that define the tags to attach to the resource.
source
Main.Bedrock_Agent.untag_resourceMethod
untag_resource(resource_arn, tag_keys)
untag_resource(resource_arn, tag_keys, params::Dict{String,<:Any})

Remove tags from a resource.

Arguments

  • resource_arn: The Amazon Resource Name (ARN) of the resource from which to remove tags.
  • tag_keys: A list of keys of the tags to remove from the resource.
source
Main.Bedrock_Agent.update_agentMethod
update_agent(agent_id, agent_name, agent_resource_role_arn, foundation_model)
update_agent(agent_id, agent_name, agent_resource_role_arn, foundation_model, params::Dict{String,<:Any})

Updates the configuration of an agent.

Arguments

  • agent_id: The unique identifier of the agent.
  • agent_name: Specifies a new name for the agent.
  • agent_resource_role_arn: The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent.
  • foundation_model: Specifies a new foundation model to be used for orchestration by the agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "customerEncryptionKeyArn": The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent.
  • "description": Specifies a new description of the agent.
  • "guardrailConfiguration": The unique Guardrail configuration assigned to the agent when it is updated.
  • "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.
  • "instruction": Specifies new instructions that tell the agent what it should do and how it should interact with users.
  • "promptOverrideConfiguration": Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.
source
Main.Bedrock_Agent.update_agent_action_groupMethod
update_agent_action_group(action_group_id, action_group_name, agent_id, agent_version)
update_agent_action_group(action_group_id, action_group_name, agent_id, agent_version, params::Dict{String,<:Any})

Updates the configuration for an action group for an agent.

Arguments

  • action_group_id: The unique identifier of the action group.
  • action_group_name: Specifies a new name for the action group.
  • agent_id: The unique identifier of the agent for which to update the action group.
  • agent_version: The unique identifier of the agent version for which to update the action group.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "actionGroupExecutor": The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action.
  • "actionGroupState": Specifies whether the action group is available for the agent to invoke or not when sending an InvokeAgent request.
  • "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.
  • "description": Specifies a new name for the action group.
  • "functionSchema": Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
  • "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.
source
Main.Bedrock_Agent.update_agent_aliasMethod
update_agent_alias(agent_alias_id, agent_alias_name, agent_id)
update_agent_alias(agent_alias_id, agent_alias_name, agent_id, params::Dict{String,<:Any})

Updates configurations for an alias of an agent.

Arguments

  • agent_alias_id: The unique identifier of the alias.
  • agent_alias_name: Specifies a new name for the alias.
  • agent_id: The unique identifier of the agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "description": Specifies a new description for the alias.
  • "routingConfiguration": Contains details about the routing configuration of the alias.
source
Main.Bedrock_Agent.update_agent_knowledge_baseMethod
update_agent_knowledge_base(agent_id, agent_version, knowledge_base_id)
update_agent_knowledge_base(agent_id, agent_version, knowledge_base_id, params::Dict{String,<:Any})

Updates the configuration for a knowledge base that has been associated with an agent.

Arguments

  • agent_id: The unique identifier of the agent associated with the knowledge base that you want to update.
  • agent_version: The version of the agent associated with the knowledge base that you want to update.
  • knowledge_base_id: The unique identifier of the knowledge base that has been associated with an agent.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "description": Specifies a new description for the knowledge base associated with an agent.
  • "knowledgeBaseState": Specifies whether the agent uses the knowledge base or not when sending an InvokeAgent request.
source
Main.Bedrock_Agent.update_data_sourceMethod
update_data_source(data_source_configuration, data_source_id, knowledge_base_id, name)
update_data_source(data_source_configuration, data_source_id, knowledge_base_id, name, params::Dict{String,<:Any})

Updates configurations for a data source. You can't change the chunkingConfiguration after you create the data source. Specify the existing chunkingConfiguration.

Arguments

  • data_source_configuration: Contains details about the storage configuration of the data source.
  • data_source_id: The unique identifier of the data source.
  • knowledge_base_id: The unique identifier of the knowledge base to which the data source belongs.
  • name: Specifies a new name for the data source.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "dataDeletionPolicy": The data deletion policy of the updated data source.
  • "description": Specifies a new description for the data source.
  • "serverSideEncryptionConfiguration": Contains details about server-side encryption of the data source.
  • "vectorIngestionConfiguration": Contains details about how to ingest the documents in the data source.
source
Main.Bedrock_Agent.update_knowledge_baseMethod
update_knowledge_base(knowledge_base_configuration, knowledge_base_id, name, role_arn, storage_configuration)
update_knowledge_base(knowledge_base_configuration, knowledge_base_id, name, role_arn, storage_configuration, params::Dict{String,<:Any})

Updates the configuration of a knowledge base with the fields that you specify. Because all fields will be overwritten, you must include the same values for fields that you want to keep the same. You can change the following fields: name description roleArn You can't change the knowledgeBaseConfiguration or storageConfiguration fields, so you must specify the same configurations as when you created the knowledge base. You can send a GetKnowledgeBase request and copy the same configurations.

Arguments

  • knowledge_base_configuration: 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.
  • knowledge_base_id: The unique identifier of the knowledge base to update.
  • name: Specifies a new name for the knowledge base.
  • role_arn: Specifies a different Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the knowledge base.
  • storage_configuration: 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.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

  • "description": Specifies a new description for the knowledge base.
source