Invoke Inline Agent
| bedrockagentruntime_invoke_inline_agent | R Documentation |
Invokes an inline Amazon Bedrock agent using the configurations you provide with the request¶
Description¶
Invokes an inline Amazon Bedrock agent using the configurations you provide with the request.
-
Specify the following fields for security purposes.
-
(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 subsequentinvoke_inline_agentrequest begins a new session.
-
-
To override the default prompt behavior for agent orchestration and to use advanced prompts, include a
promptOverrideConfigurationobject. For more information, see Advanced prompts. -
The agent instructions will not be honored if your agent has only one knowledge base, uses default prompts, has no action group, and user input is disabled.
Usage¶
bedrockagentruntime_invoke_inline_agent(actionGroups,
agentCollaboration, agentName, bedrockModelConfigurations,
collaboratorConfigurations, collaborators, customOrchestration,
customerEncryptionKeyArn, enableTrace, endSession, foundationModel,
guardrailConfiguration, idleSessionTTLInSeconds, inlineSessionState,
inputText, instruction, knowledgeBases, orchestrationType,
promptOverrideConfiguration, sessionId, streamingConfigurations)
Arguments¶
actionGroups |
A list of action groups with each action group defining the action the inline agent needs to carry out. |
agentCollaboration |
Defines how the inline collaborator agent handles information across multiple collaborator agents to coordinate a final response. The inline collaborator agent can also be the supervisor. |
agentName |
The name for the agent. |
bedrockModelConfigurations |
Model settings for the request. |
collaboratorConfigurations |
Settings for an inline agent collaborator called with
|
collaborators |
List of collaborator inline agents. |
customOrchestration |
Contains details of the custom orchestration configured for the agent. |
customerEncryptionKeyArn |
The Amazon Resource Name (ARN) of the Amazon Web Services KMS key to use to encrypt your inline agent. |
enableTrace |
Specifies whether to turn on the trace or not to track the agent's reasoning process. For more information, see Using trace. |
endSession |
Specifies whether to end the session with the inline agent or not. |
foundationModel |
[required] The model
identifier (ID) of the model to use for orchestration by the inline
agent. For example, |
guardrailConfiguration |
The guardrails to assign to the inline agent. |
idleSessionTTLInSeconds |
The number of seconds for which the inline agent should maintain
session information. After this time expires, the subsequent
A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and the data provided before the timeout is deleted. |
inlineSessionState |
Parameters that specify the various attributes of a sessions. You can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group. For more information, see Control session context. If you include |
inputText |
The prompt text to send to the agent. If you include |
instruction |
[required] The instructions that tell the inline agent what it should do and how it should interact with users. |
knowledgeBases |
Contains information of the knowledge bases to associate with. |
orchestrationType |
Specifies the type of orchestration strategy for the agent. This is set to DEFAULT orchestration type, by default. |
promptOverrideConfiguration |
Configurations for advanced prompts used to override the default prompts to enhance the accuracy of the inline agent. |
sessionId |
[required] The unique identifier of the session. Use the same value across requests to continue the same conversation. |
streamingConfigurations |
Specifies the configurations for streaming. To use agent streaming, you need permissions to perform the
|
Value¶
A list with the following syntax:
list(
completion = list(
accessDeniedException = list(
message = "string"
),
badGatewayException = list(
message = "string",
resourceName = "string"
),
chunk = list(
attribution = list(
citations = list(
list(
generatedResponsePart = list(
textResponsePart = list(
span = list(
end = 123,
start = 123
),
text = "string"
)
),
retrievedReferences = list(
list(
content = list(
byteContent = "string",
row = list(
list(
columnName = "string",
columnValue = "string",
type = "BLOB"|"BOOLEAN"|"DOUBLE"|"NULL"|"LONG"|"STRING"
)
),
text = "string",
type = "TEXT"|"IMAGE"|"ROW"
),
location = list(
confluenceLocation = list(
url = "string"
),
customDocumentLocation = list(
id = "string"
),
kendraDocumentLocation = list(
uri = "string"
),
s3Location = list(
uri = "string"
),
salesforceLocation = list(
url = "string"
),
sharePointLocation = list(
url = "string"
),
sqlLocation = list(
query = "string"
),
type = "S3"|"WEB"|"CONFLUENCE"|"SALESFORCE"|"SHAREPOINT"|"CUSTOM"|"KENDRA"|"SQL",
webLocation = list(
url = "string"
)
),
metadata = list(
list()
)
)
)
)
)
),
bytes = raw
),
conflictException = list(
message = "string"
),
dependencyFailedException = list(
message = "string",
resourceName = "string"
),
files = list(
files = list(
list(
bytes = raw,
name = "string",
type = "string"
)
)
),
internalServerException = list(
message = "string",
reason = "string"
),
resourceNotFoundException = list(
message = "string"
),
returnControl = list(
invocationId = "string",
invocationInputs = list(
list(
apiInvocationInput = list(
actionGroup = "string",
actionInvocationType = "RESULT"|"USER_CONFIRMATION"|"USER_CONFIRMATION_AND_RESULT",
agentId = "string",
apiPath = "string",
collaboratorName = "string",
httpMethod = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
),
requestBody = list(
content = list(
list(
properties = list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
)
)
),
functionInvocationInput = list(
actionGroup = "string",
actionInvocationType = "RESULT"|"USER_CONFIRMATION"|"USER_CONFIRMATION_AND_RESULT",
agentId = "string",
collaboratorName = "string",
function = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
)
)
),
serviceQuotaExceededException = list(
message = "string"
),
throttlingException = list(
message = "string"
),
trace = list(
callerChain = list(
list(
agentAliasArn = "string"
)
),
collaboratorName = "string",
eventTime = as.POSIXct(
"2015-01-01"
),
sessionId = "string",
trace = list(
customOrchestrationTrace = list(
event = list(
text = "string"
),
traceId = "string"
),
failureTrace = list(
failureCode = 123,
failureReason = "string",
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
traceId = "string"
),
guardrailTrace = list(
action = "INTERVENED"|"NONE",
inputAssessments = list(
list(
contentPolicy = list(
filters = list(
list(
action = "BLOCKED",
confidence = "NONE"|"LOW"|"MEDIUM"|"HIGH",
type = "INSULTS"|"HATE"|"SEXUAL"|"VIOLENCE"|"MISCONDUCT"|"PROMPT_ATTACK"
)
)
),
sensitiveInformationPolicy = list(
piiEntities = list(
list(
action = "BLOCKED"|"ANONYMIZED",
match = "string",
type = "ADDRESS"|"AGE"|"AWS_ACCESS_KEY"|"AWS_SECRET_KEY"|"CA_HEALTH_NUMBER"|"CA_SOCIAL_INSURANCE_NUMBER"|"CREDIT_DEBIT_CARD_CVV"|"CREDIT_DEBIT_CARD_EXPIRY"|"CREDIT_DEBIT_CARD_NUMBER"|"DRIVER_ID"|"EMAIL"|"INTERNATIONAL_BANK_ACCOUNT_NUMBER"|"IP_ADDRESS"|"LICENSE_PLATE"|"MAC_ADDRESS"|"NAME"|"PASSWORD"|"PHONE"|"PIN"|"SWIFT_CODE"|"UK_NATIONAL_HEALTH_SERVICE_NUMBER"|"UK_NATIONAL_INSURANCE_NUMBER"|"UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER"|"URL"|"USERNAME"|"US_BANK_ACCOUNT_NUMBER"|"US_BANK_ROUTING_NUMBER"|"US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER"|"US_PASSPORT_NUMBER"|"US_SOCIAL_SECURITY_NUMBER"|"VEHICLE_IDENTIFICATION_NUMBER"
)
),
regexes = list(
list(
action = "BLOCKED"|"ANONYMIZED",
match = "string",
name = "string",
regex = "string"
)
)
),
topicPolicy = list(
topics = list(
list(
action = "BLOCKED",
name = "string",
type = "DENY"
)
)
),
wordPolicy = list(
customWords = list(
list(
action = "BLOCKED",
match = "string"
)
),
managedWordLists = list(
list(
action = "BLOCKED",
match = "string",
type = "PROFANITY"
)
)
)
)
),
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
outputAssessments = list(
list(
contentPolicy = list(
filters = list(
list(
action = "BLOCKED",
confidence = "NONE"|"LOW"|"MEDIUM"|"HIGH",
type = "INSULTS"|"HATE"|"SEXUAL"|"VIOLENCE"|"MISCONDUCT"|"PROMPT_ATTACK"
)
)
),
sensitiveInformationPolicy = list(
piiEntities = list(
list(
action = "BLOCKED"|"ANONYMIZED",
match = "string",
type = "ADDRESS"|"AGE"|"AWS_ACCESS_KEY"|"AWS_SECRET_KEY"|"CA_HEALTH_NUMBER"|"CA_SOCIAL_INSURANCE_NUMBER"|"CREDIT_DEBIT_CARD_CVV"|"CREDIT_DEBIT_CARD_EXPIRY"|"CREDIT_DEBIT_CARD_NUMBER"|"DRIVER_ID"|"EMAIL"|"INTERNATIONAL_BANK_ACCOUNT_NUMBER"|"IP_ADDRESS"|"LICENSE_PLATE"|"MAC_ADDRESS"|"NAME"|"PASSWORD"|"PHONE"|"PIN"|"SWIFT_CODE"|"UK_NATIONAL_HEALTH_SERVICE_NUMBER"|"UK_NATIONAL_INSURANCE_NUMBER"|"UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER"|"URL"|"USERNAME"|"US_BANK_ACCOUNT_NUMBER"|"US_BANK_ROUTING_NUMBER"|"US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER"|"US_PASSPORT_NUMBER"|"US_SOCIAL_SECURITY_NUMBER"|"VEHICLE_IDENTIFICATION_NUMBER"
)
),
regexes = list(
list(
action = "BLOCKED"|"ANONYMIZED",
match = "string",
name = "string",
regex = "string"
)
)
),
topicPolicy = list(
topics = list(
list(
action = "BLOCKED",
name = "string",
type = "DENY"
)
)
),
wordPolicy = list(
customWords = list(
list(
action = "BLOCKED",
match = "string"
)
),
managedWordLists = list(
list(
action = "BLOCKED",
match = "string",
type = "PROFANITY"
)
)
)
)
),
traceId = "string"
),
orchestrationTrace = list(
invocationInput = list(
actionGroupInvocationInput = list(
actionGroupName = "string",
apiPath = "string",
executionType = "LAMBDA"|"RETURN_CONTROL",
function = "string",
invocationId = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
),
requestBody = list(
content = list(
list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
),
verb = "string"
),
agentCollaboratorInvocationInput = list(
agentCollaboratorAliasArn = "string",
agentCollaboratorName = "string",
input = list(
returnControlResults = list(
invocationId = "string",
returnControlInvocationResults = list(
list(
apiResult = list(
actionGroup = "string",
agentId = "string",
apiPath = "string",
confirmationState = "CONFIRM"|"DENY",
httpMethod = "string",
httpStatusCode = 123,
responseBody = list(
list(
body = "string",
images = list(
list(
format = "png"|"jpeg"|"gif"|"webp",
source = list(
bytes = raw
)
)
)
)
),
responseState = "FAILURE"|"REPROMPT"
),
functionResult = list(
actionGroup = "string",
agentId = "string",
confirmationState = "CONFIRM"|"DENY",
function = "string",
responseBody = list(
list(
body = "string",
images = list(
list(
format = "png"|"jpeg"|"gif"|"webp",
source = list(
bytes = raw
)
)
)
)
),
responseState = "FAILURE"|"REPROMPT"
)
)
)
),
text = "string",
type = "TEXT"|"RETURN_CONTROL"
)
),
codeInterpreterInvocationInput = list(
code = "string",
files = list(
"string"
)
),
invocationType = "ACTION_GROUP"|"KNOWLEDGE_BASE"|"FINISH"|"ACTION_GROUP_CODE_INTERPRETER"|"AGENT_COLLABORATOR",
knowledgeBaseLookupInput = list(
knowledgeBaseId = "string",
text = "string"
),
traceId = "string"
),
modelInvocationInput = list(
foundationModel = "string",
inferenceConfiguration = list(
maximumLength = 123,
stopSequences = list(
"string"
),
temperature = 123.0,
topK = 123,
topP = 123.0
),
overrideLambda = "string",
parserMode = "DEFAULT"|"OVERRIDDEN",
promptCreationMode = "DEFAULT"|"OVERRIDDEN",
text = "string",
traceId = "string",
type = "PRE_PROCESSING"|"ORCHESTRATION"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"POST_PROCESSING"|"ROUTING_CLASSIFIER"
),
modelInvocationOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
rawResponse = list(
content = "string"
),
reasoningContent = list(
reasoningText = list(
signature = "string",
text = "string"
),
redactedContent = raw
),
traceId = "string"
),
observation = list(
actionGroupInvocationOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
text = "string"
),
agentCollaboratorInvocationOutput = list(
agentCollaboratorAliasArn = "string",
agentCollaboratorName = "string",
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
output = list(
returnControlPayload = list(
invocationId = "string",
invocationInputs = list(
list(
apiInvocationInput = list(
actionGroup = "string",
actionInvocationType = "RESULT"|"USER_CONFIRMATION"|"USER_CONFIRMATION_AND_RESULT",
agentId = "string",
apiPath = "string",
collaboratorName = "string",
httpMethod = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
),
requestBody = list(
content = list(
list(
properties = list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
)
)
),
functionInvocationInput = list(
actionGroup = "string",
actionInvocationType = "RESULT"|"USER_CONFIRMATION"|"USER_CONFIRMATION_AND_RESULT",
agentId = "string",
collaboratorName = "string",
function = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
)
)
),
text = "string",
type = "TEXT"|"RETURN_CONTROL"
)
),
codeInterpreterInvocationOutput = list(
executionError = "string",
executionOutput = "string",
executionTimeout = TRUE|FALSE,
files = list(
"string"
),
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
)
),
finalResponse = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
text = "string"
),
knowledgeBaseLookupOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
retrievedReferences = list(
list(
content = list(
byteContent = "string",
row = list(
list(
columnName = "string",
columnValue = "string",
type = "BLOB"|"BOOLEAN"|"DOUBLE"|"NULL"|"LONG"|"STRING"
)
),
text = "string",
type = "TEXT"|"IMAGE"|"ROW"
),
location = list(
confluenceLocation = list(
url = "string"
),
customDocumentLocation = list(
id = "string"
),
kendraDocumentLocation = list(
uri = "string"
),
s3Location = list(
uri = "string"
),
salesforceLocation = list(
url = "string"
),
sharePointLocation = list(
url = "string"
),
sqlLocation = list(
query = "string"
),
type = "S3"|"WEB"|"CONFLUENCE"|"SALESFORCE"|"SHAREPOINT"|"CUSTOM"|"KENDRA"|"SQL",
webLocation = list(
url = "string"
)
),
metadata = list(
list()
)
)
)
),
repromptResponse = list(
source = "ACTION_GROUP"|"KNOWLEDGE_BASE"|"PARSER",
text = "string"
),
traceId = "string",
type = "ACTION_GROUP"|"AGENT_COLLABORATOR"|"KNOWLEDGE_BASE"|"FINISH"|"ASK_USER"|"REPROMPT"
),
rationale = list(
text = "string",
traceId = "string"
)
),
postProcessingTrace = list(
modelInvocationInput = list(
foundationModel = "string",
inferenceConfiguration = list(
maximumLength = 123,
stopSequences = list(
"string"
),
temperature = 123.0,
topK = 123,
topP = 123.0
),
overrideLambda = "string",
parserMode = "DEFAULT"|"OVERRIDDEN",
promptCreationMode = "DEFAULT"|"OVERRIDDEN",
text = "string",
traceId = "string",
type = "PRE_PROCESSING"|"ORCHESTRATION"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"POST_PROCESSING"|"ROUTING_CLASSIFIER"
),
modelInvocationOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
parsedResponse = list(
text = "string"
),
rawResponse = list(
content = "string"
),
reasoningContent = list(
reasoningText = list(
signature = "string",
text = "string"
),
redactedContent = raw
),
traceId = "string"
)
),
preProcessingTrace = list(
modelInvocationInput = list(
foundationModel = "string",
inferenceConfiguration = list(
maximumLength = 123,
stopSequences = list(
"string"
),
temperature = 123.0,
topK = 123,
topP = 123.0
),
overrideLambda = "string",
parserMode = "DEFAULT"|"OVERRIDDEN",
promptCreationMode = "DEFAULT"|"OVERRIDDEN",
text = "string",
traceId = "string",
type = "PRE_PROCESSING"|"ORCHESTRATION"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"POST_PROCESSING"|"ROUTING_CLASSIFIER"
),
modelInvocationOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
parsedResponse = list(
isValid = TRUE|FALSE,
rationale = "string"
),
rawResponse = list(
content = "string"
),
reasoningContent = list(
reasoningText = list(
signature = "string",
text = "string"
),
redactedContent = raw
),
traceId = "string"
)
),
routingClassifierTrace = list(
invocationInput = list(
actionGroupInvocationInput = list(
actionGroupName = "string",
apiPath = "string",
executionType = "LAMBDA"|"RETURN_CONTROL",
function = "string",
invocationId = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
),
requestBody = list(
content = list(
list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
),
verb = "string"
),
agentCollaboratorInvocationInput = list(
agentCollaboratorAliasArn = "string",
agentCollaboratorName = "string",
input = list(
returnControlResults = list(
invocationId = "string",
returnControlInvocationResults = list(
list(
apiResult = list(
actionGroup = "string",
agentId = "string",
apiPath = "string",
confirmationState = "CONFIRM"|"DENY",
httpMethod = "string",
httpStatusCode = 123,
responseBody = list(
list(
body = "string",
images = list(
list(
format = "png"|"jpeg"|"gif"|"webp",
source = list(
bytes = raw
)
)
)
)
),
responseState = "FAILURE"|"REPROMPT"
),
functionResult = list(
actionGroup = "string",
agentId = "string",
confirmationState = "CONFIRM"|"DENY",
function = "string",
responseBody = list(
list(
body = "string",
images = list(
list(
format = "png"|"jpeg"|"gif"|"webp",
source = list(
bytes = raw
)
)
)
)
),
responseState = "FAILURE"|"REPROMPT"
)
)
)
),
text = "string",
type = "TEXT"|"RETURN_CONTROL"
)
),
codeInterpreterInvocationInput = list(
code = "string",
files = list(
"string"
)
),
invocationType = "ACTION_GROUP"|"KNOWLEDGE_BASE"|"FINISH"|"ACTION_GROUP_CODE_INTERPRETER"|"AGENT_COLLABORATOR",
knowledgeBaseLookupInput = list(
knowledgeBaseId = "string",
text = "string"
),
traceId = "string"
),
modelInvocationInput = list(
foundationModel = "string",
inferenceConfiguration = list(
maximumLength = 123,
stopSequences = list(
"string"
),
temperature = 123.0,
topK = 123,
topP = 123.0
),
overrideLambda = "string",
parserMode = "DEFAULT"|"OVERRIDDEN",
promptCreationMode = "DEFAULT"|"OVERRIDDEN",
text = "string",
traceId = "string",
type = "PRE_PROCESSING"|"ORCHESTRATION"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"POST_PROCESSING"|"ROUTING_CLASSIFIER"
),
modelInvocationOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
rawResponse = list(
content = "string"
),
traceId = "string"
),
observation = list(
actionGroupInvocationOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
text = "string"
),
agentCollaboratorInvocationOutput = list(
agentCollaboratorAliasArn = "string",
agentCollaboratorName = "string",
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
output = list(
returnControlPayload = list(
invocationId = "string",
invocationInputs = list(
list(
apiInvocationInput = list(
actionGroup = "string",
actionInvocationType = "RESULT"|"USER_CONFIRMATION"|"USER_CONFIRMATION_AND_RESULT",
agentId = "string",
apiPath = "string",
collaboratorName = "string",
httpMethod = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
),
requestBody = list(
content = list(
list(
properties = list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
)
)
),
functionInvocationInput = list(
actionGroup = "string",
actionInvocationType = "RESULT"|"USER_CONFIRMATION"|"USER_CONFIRMATION_AND_RESULT",
agentId = "string",
collaboratorName = "string",
function = "string",
parameters = list(
list(
name = "string",
type = "string",
value = "string"
)
)
)
)
)
),
text = "string",
type = "TEXT"|"RETURN_CONTROL"
)
),
codeInterpreterInvocationOutput = list(
executionError = "string",
executionOutput = "string",
executionTimeout = TRUE|FALSE,
files = list(
"string"
),
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
)
),
finalResponse = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
text = "string"
),
knowledgeBaseLookupOutput = list(
metadata = list(
clientRequestId = "string",
endTime = as.POSIXct(
"2015-01-01"
),
operationTotalTimeMs = 123,
startTime = as.POSIXct(
"2015-01-01"
),
totalTimeMs = 123,
usage = list(
inputTokens = 123,
outputTokens = 123
)
),
retrievedReferences = list(
list(
content = list(
byteContent = "string",
row = list(
list(
columnName = "string",
columnValue = "string",
type = "BLOB"|"BOOLEAN"|"DOUBLE"|"NULL"|"LONG"|"STRING"
)
),
text = "string",
type = "TEXT"|"IMAGE"|"ROW"
),
location = list(
confluenceLocation = list(
url = "string"
),
customDocumentLocation = list(
id = "string"
),
kendraDocumentLocation = list(
uri = "string"
),
s3Location = list(
uri = "string"
),
salesforceLocation = list(
url = "string"
),
sharePointLocation = list(
url = "string"
),
sqlLocation = list(
query = "string"
),
type = "S3"|"WEB"|"CONFLUENCE"|"SALESFORCE"|"SHAREPOINT"|"CUSTOM"|"KENDRA"|"SQL",
webLocation = list(
url = "string"
)
),
metadata = list(
list()
)
)
)
),
repromptResponse = list(
source = "ACTION_GROUP"|"KNOWLEDGE_BASE"|"PARSER",
text = "string"
),
traceId = "string",
type = "ACTION_GROUP"|"AGENT_COLLABORATOR"|"KNOWLEDGE_BASE"|"FINISH"|"ASK_USER"|"REPROMPT"
)
)
)
),
validationException = list(
message = "string"
)
),
contentType = "string",
sessionId = "string"
)
Request syntax¶
svc$invoke_inline_agent(
actionGroups = list(
list(
actionGroupExecutor = list(
customControl = "RETURN_CONTROL",
lambda = "string"
),
actionGroupName = "string",
apiSchema = list(
payload = "string",
s3 = list(
s3BucketName = "string",
s3ObjectKey = "string"
)
),
description = "string",
functionSchema = list(
functions = list(
list(
description = "string",
name = "string",
parameters = list(
list(
description = "string",
required = TRUE|FALSE,
type = "string"|"number"|"integer"|"boolean"|"array"
)
),
requireConfirmation = "ENABLED"|"DISABLED"
)
)
),
parentActionGroupSignature = "AMAZON.UserInput"|"AMAZON.CodeInterpreter"|"ANTHROPIC.Computer"|"ANTHROPIC.Bash"|"ANTHROPIC.TextEditor",
parentActionGroupSignatureParams = list(
"string"
)
)
),
agentCollaboration = "SUPERVISOR"|"SUPERVISOR_ROUTER"|"DISABLED",
agentName = "string",
bedrockModelConfigurations = list(
performanceConfig = list(
latency = "standard"|"optimized"
)
),
collaboratorConfigurations = list(
list(
agentAliasArn = "string",
collaboratorInstruction = "string",
collaboratorName = "string",
relayConversationHistory = "TO_COLLABORATOR"|"DISABLED"
)
),
collaborators = list(
list(
actionGroups = list(
list(
actionGroupExecutor = list(
customControl = "RETURN_CONTROL",
lambda = "string"
),
actionGroupName = "string",
apiSchema = list(
payload = "string",
s3 = list(
s3BucketName = "string",
s3ObjectKey = "string"
)
),
description = "string",
functionSchema = list(
functions = list(
list(
description = "string",
name = "string",
parameters = list(
list(
description = "string",
required = TRUE|FALSE,
type = "string"|"number"|"integer"|"boolean"|"array"
)
),
requireConfirmation = "ENABLED"|"DISABLED"
)
)
),
parentActionGroupSignature = "AMAZON.UserInput"|"AMAZON.CodeInterpreter"|"ANTHROPIC.Computer"|"ANTHROPIC.Bash"|"ANTHROPIC.TextEditor",
parentActionGroupSignatureParams = list(
"string"
)
)
),
agentCollaboration = "SUPERVISOR"|"SUPERVISOR_ROUTER"|"DISABLED",
agentName = "string",
collaboratorConfigurations = list(
list(
agentAliasArn = "string",
collaboratorInstruction = "string",
collaboratorName = "string",
relayConversationHistory = "TO_COLLABORATOR"|"DISABLED"
)
),
customerEncryptionKeyArn = "string",
foundationModel = "string",
guardrailConfiguration = list(
guardrailIdentifier = "string",
guardrailVersion = "string"
),
idleSessionTTLInSeconds = 123,
instruction = "string",
knowledgeBases = list(
list(
description = "string",
knowledgeBaseId = "string",
retrievalConfiguration = list(
vectorSearchConfiguration = list(
filter = list(
andAll = list(
list()
),
equals = list(
key = "string",
value = list()
),
greaterThan = list(
key = "string",
value = list()
),
greaterThanOrEquals = list(
key = "string",
value = list()
),
in = list(
key = "string",
value = list()
),
lessThan = list(
key = "string",
value = list()
),
lessThanOrEquals = list(
key = "string",
value = list()
),
listContains = list(
key = "string",
value = list()
),
notEquals = list(
key = "string",
value = list()
),
notIn = list(
key = "string",
value = list()
),
orAll = list(
list()
),
startsWith = list(
key = "string",
value = list()
),
stringContains = list(
key = "string",
value = list()
)
),
implicitFilterConfiguration = list(
metadataAttributes = list(
list(
description = "string",
key = "string",
type = "STRING"|"NUMBER"|"BOOLEAN"|"STRING_LIST"
)
),
modelArn = "string"
),
numberOfResults = 123,
overrideSearchType = "HYBRID"|"SEMANTIC",
rerankingConfiguration = list(
bedrockRerankingConfiguration = list(
metadataConfiguration = list(
selectionMode = "SELECTIVE"|"ALL",
selectiveModeConfiguration = list(
fieldsToExclude = list(
list(
fieldName = "string"
)
),
fieldsToInclude = list(
list(
fieldName = "string"
)
)
)
),
modelConfiguration = list(
additionalModelRequestFields = list(
list()
),
modelArn = "string"
),
numberOfRerankedResults = 123
),
type = "BEDROCK_RERANKING_MODEL"
)
)
)
)
),
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"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"POST_PROCESSING"|"ROUTING_CLASSIFIER"
)
)
)
)
),
customOrchestration = list(
executor = list(
lambda = "string"
)
),
customerEncryptionKeyArn = "string",
enableTrace = TRUE|FALSE,
endSession = TRUE|FALSE,
foundationModel = "string",
guardrailConfiguration = list(
guardrailIdentifier = "string",
guardrailVersion = "string"
),
idleSessionTTLInSeconds = 123,
inlineSessionState = list(
conversationHistory = list(
messages = list(
list(
content = list(
list(
text = "string"
)
),
role = "user"|"assistant"
)
)
),
files = list(
list(
name = "string",
source = list(
byteContent = list(
data = raw,
mediaType = "string"
),
s3Location = list(
uri = "string"
),
sourceType = "S3"|"BYTE_CONTENT"
),
useCase = "CODE_INTERPRETER"|"CHAT"
)
),
invocationId = "string",
promptSessionAttributes = list(
"string"
),
returnControlInvocationResults = list(
list(
apiResult = list(
actionGroup = "string",
agentId = "string",
apiPath = "string",
confirmationState = "CONFIRM"|"DENY",
httpMethod = "string",
httpStatusCode = 123,
responseBody = list(
list(
body = "string",
images = list(
list(
format = "png"|"jpeg"|"gif"|"webp",
source = list(
bytes = raw
)
)
)
)
),
responseState = "FAILURE"|"REPROMPT"
),
functionResult = list(
actionGroup = "string",
agentId = "string",
confirmationState = "CONFIRM"|"DENY",
function = "string",
responseBody = list(
list(
body = "string",
images = list(
list(
format = "png"|"jpeg"|"gif"|"webp",
source = list(
bytes = raw
)
)
)
)
),
responseState = "FAILURE"|"REPROMPT"
)
)
),
sessionAttributes = list(
"string"
)
),
inputText = "string",
instruction = "string",
knowledgeBases = list(
list(
description = "string",
knowledgeBaseId = "string",
retrievalConfiguration = list(
vectorSearchConfiguration = list(
filter = list(
andAll = list(
list()
),
equals = list(
key = "string",
value = list()
),
greaterThan = list(
key = "string",
value = list()
),
greaterThanOrEquals = list(
key = "string",
value = list()
),
in = list(
key = "string",
value = list()
),
lessThan = list(
key = "string",
value = list()
),
lessThanOrEquals = list(
key = "string",
value = list()
),
listContains = list(
key = "string",
value = list()
),
notEquals = list(
key = "string",
value = list()
),
notIn = list(
key = "string",
value = list()
),
orAll = list(
list()
),
startsWith = list(
key = "string",
value = list()
),
stringContains = list(
key = "string",
value = list()
)
),
implicitFilterConfiguration = list(
metadataAttributes = list(
list(
description = "string",
key = "string",
type = "STRING"|"NUMBER"|"BOOLEAN"|"STRING_LIST"
)
),
modelArn = "string"
),
numberOfResults = 123,
overrideSearchType = "HYBRID"|"SEMANTIC",
rerankingConfiguration = list(
bedrockRerankingConfiguration = list(
metadataConfiguration = list(
selectionMode = "SELECTIVE"|"ALL",
selectiveModeConfiguration = list(
fieldsToExclude = list(
list(
fieldName = "string"
)
),
fieldsToInclude = list(
list(
fieldName = "string"
)
)
)
),
modelConfiguration = list(
additionalModelRequestFields = list(
list()
),
modelArn = "string"
),
numberOfRerankedResults = 123
),
type = "BEDROCK_RERANKING_MODEL"
)
)
)
)
),
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"|"KNOWLEDGE_BASE_RESPONSE_GENERATION"|"POST_PROCESSING"|"ROUTING_CLASSIFIER"
)
)
),
sessionId = "string",
streamingConfigurations = list(
applyGuardrailInterval = 123,
streamFinalResponse = TRUE|FALSE
)
)