Update Agent
bedrockagent_update_agent | R Documentation |
Updates the configuration of an agent¶
Description¶
Updates the configuration of an agent.
Usage¶
bedrockagent_update_agent(agentCollaboration, agentId, agentName,
agentResourceRoleArn, customOrchestration, customerEncryptionKeyArn,
description, foundationModel, guardrailConfiguration,
idleSessionTTLInSeconds, instruction, memoryConfiguration,
orchestrationType, promptOverrideConfiguration)
Arguments¶
agentCollaboration |
The agent's collaboration role. |
agentId |
[required] The unique identifier of the agent. |
agentName |
[required] Specifies a new name for the agent. |
agentResourceRoleArn |
[required] The Amazon Resource Name (ARN) of the IAM role with permissions to invoke API operations on the agent. |
customOrchestration |
Contains details of the custom orchestration configured for the agent. |
customerEncryptionKeyArn |
The Amazon Resource Name (ARN) of the KMS key with which to encrypt the agent. |
description |
Specifies a new description of the agent. |
foundationModel |
[required] The identifier for the model that you want to be used for orchestration by the agent you create. The
|
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. |
memoryConfiguration |
Specifies the new memory configuration for the agent. |
orchestrationType |
Specifies the type of orchestration strategy for the agent. This
is set to |
promptOverrideConfiguration |
Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts. |
Value¶
A list with the following syntax:
list(
agent = list(
agentArn = "string",
agentCollaboration = "SUPERVISOR"|"SUPERVISOR_ROUTER"|"DISABLED",
agentId = "string",
agentName = "string",
agentResourceRoleArn = "string",
agentStatus = "CREATING"|"PREPARING"|"PREPARED"|"NOT_PREPARED"|"DELETING"|"FAILED"|"VERSIONING"|"UPDATING",
agentVersion = "string",
clientToken = "string",
createdAt = as.POSIXct(
"2015-01-01"
),
customOrchestration = list(
executor = list(
lambda = "string"
)
),
customerEncryptionKeyArn = "string",
description = "string",
failureReasons = list(
"string"
),
foundationModel = "string",
guardrailConfiguration = list(
guardrailIdentifier = "string",
guardrailVersion = "string"
),
idleSessionTTLInSeconds = 123,
instruction = "string",
memoryConfiguration = list(
enabledMemoryTypes = list(
"SESSION_SUMMARY"
),
sessionSummaryConfiguration = list(
maxRecentSessions = 123
),
storageDays = 123
),
orchestrationType = "DEFAULT"|"CUSTOM_ORCHESTRATION",
preparedAt = as.POSIXct(
"2015-01-01"
),
promptOverrideConfiguration = list(
overrideLambda = "string",
promptConfigurations = list(
list(
additionalModelRequestFields = list(),
basePromptTemplate = "string",
foundationModel = "string",
inferenceConfiguration = list(
maximumLength = 123,
stopSequences = list(
"string"
),
temperature = 123.0,
topK = 123,
topP = 123.0
),
parserMode = "DEFAULT"|"OVERRIDDEN",
promptCreationMode = "DEFAULT"|"OVERRIDDEN",
promptState = "ENABLED"|"DISABLED",
promptType = "PRE_PROCESSING"|"ORCHESTRATION"|"POST_PROCESSING"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"MEMORY_SUMMARIZATION"
)
)
),
recommendedActions = list(
"string"
),
updatedAt = as.POSIXct(
"2015-01-01"
)
)
)
Request syntax¶
svc$update_agent(
agentCollaboration = "SUPERVISOR"|"SUPERVISOR_ROUTER"|"DISABLED",
agentId = "string",
agentName = "string",
agentResourceRoleArn = "string",
customOrchestration = list(
executor = list(
lambda = "string"
)
),
customerEncryptionKeyArn = "string",
description = "string",
foundationModel = "string",
guardrailConfiguration = list(
guardrailIdentifier = "string",
guardrailVersion = "string"
),
idleSessionTTLInSeconds = 123,
instruction = "string",
memoryConfiguration = list(
enabledMemoryTypes = list(
"SESSION_SUMMARY"
),
sessionSummaryConfiguration = list(
maxRecentSessions = 123
),
storageDays = 123
),
orchestrationType = "DEFAULT"|"CUSTOM_ORCHESTRATION",
promptOverrideConfiguration = list(
overrideLambda = "string",
promptConfigurations = list(
list(
additionalModelRequestFields = list(),
basePromptTemplate = "string",
foundationModel = "string",
inferenceConfiguration = list(
maximumLength = 123,
stopSequences = list(
"string"
),
temperature = 123.0,
topK = 123,
topP = 123.0
),
parserMode = "DEFAULT"|"OVERRIDDEN",
promptCreationMode = "DEFAULT"|"OVERRIDDEN",
promptState = "ENABLED"|"DISABLED",
promptType = "PRE_PROCESSING"|"ORCHESTRATION"|"POST_PROCESSING"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"MEMORY_SUMMARIZATION"
)
)
)
)