2024/08/06 - Agents for Amazon Bedrock Runtime - 1 updated api methods
Changes Introduce model invocation output traces for orchestration traces, which contain the model's raw response and usage.
{'completion': {'trace': {'trace': {'orchestrationTrace': {'modelInvocationOutput': {'metadata': {'usage': {'inputTokens': 'integer', 'outputTokens': 'integer'}}, 'rawResponse': {'content': 'string'}, 'traceId': 'string'}}}}}}
Note
The CLI doesn't support streaming operations in Amazon Bedrock, including InvokeAgent .
Sends a prompt for the agent to process and respond to. Note the following fields for the request:
To continue the same conversation with an agent, use the same sessionId value in the request.
To activate trace enablement, turn enableTrace to true . Trace enablement helps you follow the agent's reasoning process that led it to the information it processed, the actions it took, and the final result it yielded. For more information, see Trace enablement.
End a conversation by setting endSession to true .
In the sessionState object, 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.
The response is returned in the bytes field of the chunk object.
The attribution object contains citations for parts of the response.
If you set enableTrace to true in the request, you can trace the agent's steps and reasoning process that led it to the response.
If the action predicted was configured to return control, the response returns parameters for the action, elicited from the user, in the returnControl field.
Errors are also surfaced in the response.
See also: AWS API Documentation
Request Syntax
client.invoke_agent( agentAliasId='string', agentId='string', enableTrace=True|False, endSession=True|False, inputText='string', memoryId='string', sessionId='string', sessionState={ 'files': [ { 'name': 'string', 'source': { 'byteContent': { 'data': b'bytes', 'mediaType': 'string' }, 's3Location': { 'uri': 'string' }, 'sourceType': 'S3'|'BYTE_CONTENT' }, 'useCase': 'CODE_INTERPRETER'|'CHAT' }, ], 'invocationId': 'string', 'knowledgeBaseConfigurations': [ { 'knowledgeBaseId': 'string', 'retrievalConfiguration': { 'vectorSearchConfiguration': { 'filter': { 'andAll': [ {'... recursive ...'}, ], 'equals': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'greaterThan': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'greaterThanOrEquals': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'in': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'lessThan': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'lessThanOrEquals': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'listContains': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'notEquals': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'notIn': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'orAll': [ {'... recursive ...'}, ], 'startsWith': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None }, 'stringContains': { 'key': 'string', 'value': {...}|[...]|123|123.4|'string'|True|None } }, 'numberOfResults': 123, 'overrideSearchType': 'HYBRID'|'SEMANTIC' } } }, ], 'promptSessionAttributes': { 'string': 'string' }, 'returnControlInvocationResults': [ { 'apiResult': { 'actionGroup': 'string', 'apiPath': 'string', 'httpMethod': 'string', 'httpStatusCode': 123, 'responseBody': { 'string': { 'body': 'string' } }, 'responseState': 'FAILURE'|'REPROMPT' }, 'functionResult': { 'actionGroup': 'string', 'function': 'string', 'responseBody': { 'string': { 'body': 'string' } }, 'responseState': 'FAILURE'|'REPROMPT' } }, ], 'sessionAttributes': { 'string': 'string' } } )
string
[REQUIRED]
The alias of the agent to use.
string
[REQUIRED]
The unique identifier of the agent to use.
boolean
Specifies whether to turn on the trace or not to track the agent's reasoning process. For more information, see Trace enablement.
boolean
Specifies whether to end the session with the agent or not.
string
The prompt text to send the agent.
Note
If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.
string
The unique identifier of the agent memory.
string
[REQUIRED]
The unique identifier of the session. Use the same value across requests to continue the same conversation.
dict
Contains parameters that specify various attributes of the session. For more information, see Control session context.
Note
If you include returnControlInvocationResults in the sessionState field, the inputText field will be ignored.
files (list) --
Contains information about the files used by code interpreter.
(dict) --
Contains details of the source files.
name (string) -- [REQUIRED]
The name of the source file.
source (dict) -- [REQUIRED]
Specifies where the files are located.
byteContent (dict) --
The data and the text of the attached files.
data (bytes) -- [REQUIRED]
The byte value of the file to attach, encoded as Base-64 string. The maximum size of all files that is attached is 10MB. You can attach a maximum of 5 files.
mediaType (string) -- [REQUIRED]
The MIME type of data contained in the file used for chat.
s3Location (dict) --
The s3 location of the files to attach.
uri (string) -- [REQUIRED]
The uri of the s3 object.
sourceType (string) -- [REQUIRED]
The source type of the files to attach.
useCase (string) -- [REQUIRED]
Specifies how the source files will be used by the code interpreter.
invocationId (string) --
The identifier of the invocation of an action. This value must match the invocationId returned in the InvokeAgent response for the action whose results are provided in the returnControlInvocationResults field. For more information, see Return control to the agent developer and Control session context.
knowledgeBaseConfigurations (list) --
An array of configurations, each of which applies to a knowledge base attached to the agent.
(dict) --
Configurations to apply to a knowledge base attached to the agent during query. For more information, see Knowledge base retrieval configurations.
knowledgeBaseId (string) -- [REQUIRED]
The unique identifier for a knowledge base attached to the agent.
retrievalConfiguration (dict) -- [REQUIRED]
The configurations to apply to the knowledge base during query. For more information, see Query configurations.
vectorSearchConfiguration (dict) -- [REQUIRED]
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
filter (dict) --
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
Note
This is a Tagged Union structure. Only one of the following top level keys can be set: andAll, equals, greaterThan, greaterThanOrEquals, in, lessThan, lessThanOrEquals, listContains, notEquals, notIn, orAll, startsWith, stringContains.
andAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
Note
This is a Tagged Union structure. Only one of the following top level keys can be set: andAll, equals, greaterThan, greaterThanOrEquals, in, lessThan, lessThanOrEquals, listContains, notEquals, notIn, orAll, startsWith, stringContains.
equals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is cat :
"equals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than 1989 :
"greaterThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989 :
"greaterThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
in (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either cat or dog :
"in": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to 1989 .
"lessThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to 1989 .
"lessThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
listContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"] ).
"listContains": { "key": "animals", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notEquals (dict) --
Knowledge base data sources that contain a metadata attribute whose name matches the key and whose value doesn't match the value in this object are returned.
The following example would return data sources that don't contain an animal attribute whose value is cat .
"notEquals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notIn (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither cat nor dog .
"notIn": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
orAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
Note
This is a Tagged Union structure. Only one of the following top level keys can be set: andAll, equals, greaterThan, greaterThanOrEquals, in, lessThan, lessThanOrEquals, listContains, notEquals, notIn, orAll, startsWith, stringContains.
startsWith (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel ).
"startsWith": { "key": "animal", "value": "ca" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
stringContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat ). "stringContains": { "key": "animal", "value": "at" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"] ). "stringContains": { "key": "animals", "value": "at" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
numberOfResults (integer) --
The number of source chunks to retrieve.
overrideSearchType (string) --
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
promptSessionAttributes (dict) --
Contains attributes that persist across a prompt and the values of those attributes. These attributes replace the $prompt_session_attributes$ placeholder variable in the orchestration prompt template. For more information, see Prompt template placeholder variables.
(string) --
(string) --
returnControlInvocationResults (list) --
Contains information about the results from the action group invocation. For more information, see Return control to the agent developer and Control session context.
Note
If you include this field, the inputText field will be ignored.
(dict) --
A result from the invocation of an action. For more information, see Return control to the agent developer and Control session context.
This data type is used in the following API operations:
Note
This is a Tagged Union structure. Only one of the following top level keys can be set: apiResult, functionResult.
apiResult (dict) --
The result from the API response from the action group invocation.
actionGroup (string) -- [REQUIRED]
The action group that the API operation belongs to.
apiPath (string) --
The path to the API operation.
httpMethod (string) --
The HTTP method for the API operation.
httpStatusCode (integer) --
http status code from API execution response (for example: 200, 400, 500).
responseBody (dict) --
The response body from the API operation. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.
(string) --
(dict) --
Contains the body of the API response.
This data type is used in the following API operations:
In the returnControlInvocationResults field of the InvokeAgent request
body (string) --
The body of the API response.
responseState (string) --
Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
functionResult (dict) --
The result from the function from the action group invocation.
actionGroup (string) -- [REQUIRED]
The action group that the function belongs to.
function (string) --
The name of the function that was called.
responseBody (dict) --
The response from the function call using the parameters. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.
(string) --
(dict) --
Contains the body of the API response.
This data type is used in the following API operations:
In the returnControlInvocationResults field of the InvokeAgent request
body (string) --
The body of the API response.
responseState (string) --
Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
sessionAttributes (dict) --
Contains attributes that persist across a session and the values of those attributes.
(string) --
(string) --
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{ 'completion': EventStream({ 'accessDeniedException': { 'message': 'string' }, 'badGatewayException': { 'message': 'string', 'resourceName': 'string' }, 'chunk': { 'attribution': { 'citations': [ { 'generatedResponsePart': { 'textResponsePart': { 'span': { 'end': 123, 'start': 123 }, 'text': 'string' } }, 'retrievedReferences': [ { 'content': { 'text': 'string' }, 'location': { 'confluenceLocation': { 'url': 'string' }, 's3Location': { 'uri': 'string' }, 'salesforceLocation': { 'url': 'string' }, 'sharePointLocation': { 'url': 'string' }, 'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT', 'webLocation': { 'url': 'string' } }, 'metadata': { 'string': {...}|[...]|123|123.4|'string'|True|None } }, ] }, ] }, 'bytes': b'bytes' }, 'conflictException': { 'message': 'string' }, 'dependencyFailedException': { 'message': 'string', 'resourceName': 'string' }, 'files': { 'files': [ { 'bytes': b'bytes', 'name': 'string', 'type': 'string' }, ] }, 'internalServerException': { 'message': 'string' }, 'resourceNotFoundException': { 'message': 'string' }, 'returnControl': { 'invocationId': 'string', 'invocationInputs': [ { 'apiInvocationInput': { 'actionGroup': 'string', 'apiPath': 'string', 'httpMethod': 'string', 'parameters': [ { 'name': 'string', 'type': 'string', 'value': 'string' }, ], 'requestBody': { 'content': { 'string': { 'properties': [ { 'name': 'string', 'type': 'string', 'value': 'string' }, ] } } } }, 'functionInvocationInput': { 'actionGroup': 'string', 'function': 'string', 'parameters': [ { 'name': 'string', 'type': 'string', 'value': 'string' }, ] } }, ] }, 'serviceQuotaExceededException': { 'message': 'string' }, 'throttlingException': { 'message': 'string' }, 'trace': { 'agentAliasId': 'string', 'agentId': 'string', 'agentVersion': 'string', 'sessionId': 'string', 'trace': { 'failureTrace': { 'failureReason': 'string', 'traceId': 'string' }, 'guardrailTrace': { 'action': 'INTERVENED'|'NONE', 'inputAssessments': [ { 'contentPolicy': { 'filters': [ { 'action': 'BLOCKED', 'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH', 'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK' }, ] }, 'sensitiveInformationPolicy': { 'piiEntities': [ { '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': [ { 'action': 'BLOCKED'|'ANONYMIZED', 'match': 'string', 'name': 'string', 'regex': 'string' }, ] }, 'topicPolicy': { 'topics': [ { 'action': 'BLOCKED', 'name': 'string', 'type': 'DENY' }, ] }, 'wordPolicy': { 'customWords': [ { 'action': 'BLOCKED', 'match': 'string' }, ], 'managedWordLists': [ { 'action': 'BLOCKED', 'match': 'string', 'type': 'PROFANITY' }, ] } }, ], 'outputAssessments': [ { 'contentPolicy': { 'filters': [ { 'action': 'BLOCKED', 'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH', 'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK' }, ] }, 'sensitiveInformationPolicy': { 'piiEntities': [ { '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': [ { 'action': 'BLOCKED'|'ANONYMIZED', 'match': 'string', 'name': 'string', 'regex': 'string' }, ] }, 'topicPolicy': { 'topics': [ { 'action': 'BLOCKED', 'name': 'string', 'type': 'DENY' }, ] }, 'wordPolicy': { 'customWords': [ { 'action': 'BLOCKED', 'match': 'string' }, ], 'managedWordLists': [ { 'action': 'BLOCKED', 'match': 'string', 'type': 'PROFANITY' }, ] } }, ], 'traceId': 'string' }, 'orchestrationTrace': { 'invocationInput': { 'actionGroupInvocationInput': { 'actionGroupName': 'string', 'apiPath': 'string', 'executionType': 'LAMBDA'|'RETURN_CONTROL', 'function': 'string', 'invocationId': 'string', 'parameters': [ { 'name': 'string', 'type': 'string', 'value': 'string' }, ], 'requestBody': { 'content': { 'string': [ { 'name': 'string', 'type': 'string', 'value': 'string' }, ] } }, 'verb': 'string' }, 'codeInterpreterInvocationInput': { 'code': 'string', 'files': [ 'string', ] }, 'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER', 'knowledgeBaseLookupInput': { 'knowledgeBaseId': 'string', 'text': 'string' }, 'traceId': 'string' }, 'modelInvocationInput': { 'inferenceConfiguration': { 'maximumLength': 123, 'stopSequences': [ 'string', ], 'temperature': ..., 'topK': 123, 'topP': ... }, 'overrideLambda': 'string', 'parserMode': 'DEFAULT'|'OVERRIDDEN', 'promptCreationMode': 'DEFAULT'|'OVERRIDDEN', 'text': 'string', 'traceId': 'string', 'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING' }, 'modelInvocationOutput': { 'metadata': { 'usage': { 'inputTokens': 123, 'outputTokens': 123 } }, 'rawResponse': { 'content': 'string' }, 'traceId': 'string' }, 'observation': { 'actionGroupInvocationOutput': { 'text': 'string' }, 'codeInterpreterInvocationOutput': { 'executionError': 'string', 'executionOutput': 'string', 'executionTimeout': True|False, 'files': [ 'string', ] }, 'finalResponse': { 'text': 'string' }, 'knowledgeBaseLookupOutput': { 'retrievedReferences': [ { 'content': { 'text': 'string' }, 'location': { 'confluenceLocation': { 'url': 'string' }, 's3Location': { 'uri': 'string' }, 'salesforceLocation': { 'url': 'string' }, 'sharePointLocation': { 'url': 'string' }, 'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT', 'webLocation': { 'url': 'string' } }, 'metadata': { 'string': {...}|[...]|123|123.4|'string'|True|None } }, ] }, 'repromptResponse': { 'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER', 'text': 'string' }, 'traceId': 'string', 'type': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT' }, 'rationale': { 'text': 'string', 'traceId': 'string' } }, 'postProcessingTrace': { 'modelInvocationInput': { 'inferenceConfiguration': { 'maximumLength': 123, 'stopSequences': [ 'string', ], 'temperature': ..., 'topK': 123, 'topP': ... }, 'overrideLambda': 'string', 'parserMode': 'DEFAULT'|'OVERRIDDEN', 'promptCreationMode': 'DEFAULT'|'OVERRIDDEN', 'text': 'string', 'traceId': 'string', 'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING' }, 'modelInvocationOutput': { 'parsedResponse': { 'text': 'string' }, 'traceId': 'string' } }, 'preProcessingTrace': { 'modelInvocationInput': { 'inferenceConfiguration': { 'maximumLength': 123, 'stopSequences': [ 'string', ], 'temperature': ..., 'topK': 123, 'topP': ... }, 'overrideLambda': 'string', 'parserMode': 'DEFAULT'|'OVERRIDDEN', 'promptCreationMode': 'DEFAULT'|'OVERRIDDEN', 'text': 'string', 'traceId': 'string', 'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING' }, 'modelInvocationOutput': { 'parsedResponse': { 'isValid': True|False, 'rationale': 'string' }, 'traceId': 'string' } } } }, 'validationException': { 'message': 'string' } }), 'contentType': 'string', 'memoryId': 'string', 'sessionId': 'string' }
Response Structure
(dict) --
completion (:class:`.EventStream`) --
The agent's response to the user prompt.
accessDeniedException (dict) --
The request is denied because of missing access permissions. Check your permissions and retry your request.
message (string) --
badGatewayException (dict) --
There was an issue with a dependency due to a server issue. Retry your request.
message (string) --
resourceName (string) --
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
chunk (dict) --
Contains a part of an agent response and citations for it.
attribution (dict) --
Contains citations for a part of an agent response.
citations (list) --
A list of citations and related information for a part of an agent response.
(dict) --
An object containing a segment of the generated response that is based on a source in the knowledge base, alongside information about the source.
This data type is used in the following API operations:
InvokeAgent response – in the citations field
RetrieveAndGenerate response – in the citations field
generatedResponsePart (dict) --
Contains the generated response and metadata
textResponsePart (dict) --
Contains metadata about a textual part of the generated response that is accompanied by a citation.
span (dict) --
Contains information about where the text with a citation begins and ends in the generated output.
end (integer) --
Where the text with a citation ends in the generated output.
start (integer) --
Where the text with a citation starts in the generated output.
text (string) --
The part of the generated text that contains a citation.
retrievedReferences (list) --
Contains metadata about the sources cited for the generated response.
(dict) --
Contains metadata about a source cited for the generated response.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the retrievedReferences field
InvokeAgent response – in the retrievedReferences field
content (dict) --
Contains the cited text from the data source.
text (string) --
The cited text from the data source.
location (dict) --
Contains information about the location of the data source.
confluenceLocation (dict) --
The Confluence data source location.
url (string) --
The Confluence host URL for the data source location.
s3Location (dict) --
The S3 data source location.
uri (string) --
The S3 URI for the data source location.
salesforceLocation (dict) --
The Salesforce data source location.
url (string) --
The Salesforce host URL for the data source location.
sharePointLocation (dict) --
The SharePoint data source location.
url (string) --
The SharePoint site URL for the data source location.
type (string) --
The type of data source location.
webLocation (dict) --
The web URL/URLs data source location.
url (string) --
The web URL/URLs for the data source location.
metadata (dict) --
Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
(string) --
bytes (bytes) --
A part of the agent response in bytes.
conflictException (dict) --
There was a conflict performing an operation. Resolve the conflict and retry your request.
message (string) --
dependencyFailedException (dict) --
There was an issue with a dependency. Check the resource configurations and retry the request.
message (string) --
resourceName (string) --
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
files (dict) --
Contains intermediate response for code interpreter if any files have been generated.
files (list) --
Files containing intermediate response for the user.
(dict) --
Contains details of the response from code interpreter.
bytes (bytes) --
The byte count of files that contains response from code interpreter.
name (string) --
The name of the file containing response from code interpreter.
type (string) --
The type of file that contains response from the code interpreter.
internalServerException (dict) --
An internal server error occurred. Retry your request.
message (string) --
resourceNotFoundException (dict) --
The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.
message (string) --
returnControl (dict) --
Contains the parameters and information that the agent elicited from the customer to carry out an action. This information is returned to the system and can be used in your own setup for fulfilling the action.
invocationId (string) --
The identifier of the action group invocation.
invocationInputs (list) --
A list of objects that contain information about the parameters and inputs that need to be sent into the API operation or function, based on what the agent determines from its session with the user.
(dict) --
Contains details about the API operation or function that the agent predicts should be called.
This data type is used in the following API operations:
In the returnControl field of the InvokeAgent response
Note
This is a Tagged Union structure. Only one of the following top level keys will be set: apiInvocationInput, functionInvocationInput. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:
'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}
apiInvocationInput (dict) --
Contains information about the API operation that the agent predicts should be called.
actionGroup (string) --
The action group that the API operation belongs to.
apiPath (string) --
The path to the API operation.
httpMethod (string) --
The HTTP method of the API operation.
parameters (list) --
The parameters to provide for the API request, as the agent elicited from the user.
(dict) --
Information about a parameter to provide to the API request.
This data type is used in the following API operations:
name (string) --
The name of the parameter.
type (string) --
The data type for the parameter.
value (string) --
The value of the parameter.
requestBody (dict) --
The request body to provide for the API request, as the agent elicited from the user.
content (dict) --
The content of the request body. The key of the object in this field is a media type defining the format of the request body.
(string) --
(dict) --
Contains the parameters in the request body.
properties (list) --
A list of parameters in the request body.
(dict) --
A parameter for the API request or function.
name (string) --
The name of the parameter.
type (string) --
The type of the parameter.
value (string) --
The value of the parameter.
functionInvocationInput (dict) --
Contains information about the function that the agent predicts should be called.
actionGroup (string) --
The action group that the function belongs to.
function (string) --
The name of the function.
parameters (list) --
A list of parameters of the function.
(dict) --
Contains information about a parameter of the function.
This data type is used in the following API operations:
In the returnControl field of the InvokeAgent response
name (string) --
The name of the parameter.
type (string) --
The data type of the parameter.
value (string) --
The value of the parameter.
serviceQuotaExceededException (dict) --
The number of requests exceeds the service quota. Resubmit your request later.
message (string) --
throttlingException (dict) --
The number of requests exceeds the limit. Resubmit your request later.
message (string) --
trace (dict) --
Contains information about the agent and session, alongside the agent's reasoning process and results from calling actions and querying knowledge bases and metadata about the trace. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace events.
agentAliasId (string) --
The unique identifier of the alias of the agent.
agentId (string) --
The unique identifier of the agent.
agentVersion (string) --
The version of the agent.
sessionId (string) --
The unique identifier of the session with the agent.
trace (dict) --
Contains one part of the agent's reasoning process and results from calling API actions and querying knowledge bases. You can use the trace to understand how the agent arrived at the response it provided the customer. For more information, see Trace enablement.
Note
This is a Tagged Union structure. Only one of the following top level keys will be set: failureTrace, guardrailTrace, orchestrationTrace, postProcessingTrace, preProcessingTrace. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:
'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}
failureTrace (dict) --
Contains information about the failure of the interaction.
failureReason (string) --
The reason the interaction failed.
traceId (string) --
The unique identifier of the trace.
guardrailTrace (dict) --
The trace details for a trace defined in the Guardrail filter.
action (string) --
The trace action details used with the Guardrail.
inputAssessments (list) --
The details of the input assessments used in the Guardrail Trace.
(dict) --
Assessment details of the content analyzed by Guardrails.
contentPolicy (dict) --
Content policy details of the Guardrail.
filters (list) --
The filter details of the policy assessment used in the Guardrails filter.
(dict) --
Details of the content filter used in the Guardrail.
action (string) --
The action placed on the content by the Guardrail filter.
confidence (string) --
The confidence level regarding the content detected in the filter by the Guardrail.
type (string) --
The type of content detected in the filter by the Guardrail.
sensitiveInformationPolicy (dict) --
Sensitive Information policy details of Guardrail.
piiEntities (list) --
The details of the PII entities used in the sensitive policy assessment for the Guardrail.
(dict) --
The Guardrail filter to identify and remove personally identifiable information (PII).
action (string) --
The action of the Guardrail filter to identify and remove PII.
match (string) --
The match to settings in the Guardrail filter to identify and remove PII.
type (string) --
The type of PII the Guardrail filter has identified and removed.
regexes (list) --
The details of the regexes used in the sensitive policy assessment for the Guardrail.
(dict) --
The details for the regex filter used in the Guardrail.
action (string) --
The action details for the regex filter used in the Guardrail.
match (string) --
The match details for the regex filter used in the Guardrail.
name (string) --
The name details for the regex filter used in the Guardrail.
regex (string) --
The regex details for the regex filter used in the Guardrail.
topicPolicy (dict) --
Topic policy details of the Guardrail.
topics (list) --
The topic details of the policy assessment used in the Guardrail.
(dict) --
The details for a specific topic defined in the Guardrail.
action (string) --
The action details on a specific topic in the Guardrail.
name (string) --
The name details on a specific topic in the Guardrail.
type (string) --
The type details on a specific topic in the Guardrail.
wordPolicy (dict) --
Word policy details of the Guardrail.
customWords (list) --
The custom word details for words defined in the Guardrail filter.
(dict) --
The custom word details for the filter in the Guardrail.
action (string) --
The action details for the custom word filter in the Guardrail.
match (string) --
The match details for the custom word filter in the Guardrail.
managedWordLists (list) --
The managed word lists for words defined in the Guardrail filter.
(dict) --
The managed word details for the filter in the Guardrail.
action (string) --
The action details for the managed word filter in the Guardrail.
match (string) --
The match details for the managed word filter in the Guardrail.
type (string) --
The type details for the managed word filter in the Guardrail.
outputAssessments (list) --
The details of the output assessments used in the Guardrail Trace.
(dict) --
Assessment details of the content analyzed by Guardrails.
contentPolicy (dict) --
Content policy details of the Guardrail.
filters (list) --
The filter details of the policy assessment used in the Guardrails filter.
(dict) --
Details of the content filter used in the Guardrail.
action (string) --
The action placed on the content by the Guardrail filter.
confidence (string) --
The confidence level regarding the content detected in the filter by the Guardrail.
type (string) --
The type of content detected in the filter by the Guardrail.
sensitiveInformationPolicy (dict) --
Sensitive Information policy details of Guardrail.
piiEntities (list) --
The details of the PII entities used in the sensitive policy assessment for the Guardrail.
(dict) --
The Guardrail filter to identify and remove personally identifiable information (PII).
action (string) --
The action of the Guardrail filter to identify and remove PII.
match (string) --
The match to settings in the Guardrail filter to identify and remove PII.
type (string) --
The type of PII the Guardrail filter has identified and removed.
regexes (list) --
The details of the regexes used in the sensitive policy assessment for the Guardrail.
(dict) --
The details for the regex filter used in the Guardrail.
action (string) --
The action details for the regex filter used in the Guardrail.
match (string) --
The match details for the regex filter used in the Guardrail.
name (string) --
The name details for the regex filter used in the Guardrail.
regex (string) --
The regex details for the regex filter used in the Guardrail.
topicPolicy (dict) --
Topic policy details of the Guardrail.
topics (list) --
The topic details of the policy assessment used in the Guardrail.
(dict) --
The details for a specific topic defined in the Guardrail.
action (string) --
The action details on a specific topic in the Guardrail.
name (string) --
The name details on a specific topic in the Guardrail.
type (string) --
The type details on a specific topic in the Guardrail.
wordPolicy (dict) --
Word policy details of the Guardrail.
customWords (list) --
The custom word details for words defined in the Guardrail filter.
(dict) --
The custom word details for the filter in the Guardrail.
action (string) --
The action details for the custom word filter in the Guardrail.
match (string) --
The match details for the custom word filter in the Guardrail.
managedWordLists (list) --
The managed word lists for words defined in the Guardrail filter.
(dict) --
The managed word details for the filter in the Guardrail.
action (string) --
The action details for the managed word filter in the Guardrail.
match (string) --
The match details for the managed word filter in the Guardrail.
type (string) --
The type details for the managed word filter in the Guardrail.
traceId (string) --
The details of the trace Id used in the Guardrail Trace.
orchestrationTrace (dict) --
Details about the orchestration step, in which the agent determines the order in which actions are executed and which knowledge bases are retrieved.
Note
This is a Tagged Union structure. Only one of the following top level keys will be set: invocationInput, modelInvocationInput, modelInvocationOutput, observation, rationale. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:
'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}
invocationInput (dict) --
Contains information pertaining to the action group or knowledge base that is being invoked.
actionGroupInvocationInput (dict) --
Contains information about the action group to be invoked.
actionGroupName (string) --
The name of the action group.
apiPath (string) --
The path to the API to call, based off the action group.
executionType (string) --
How fulfillment of the action is handled. For more information, see Handling fulfillment of the action.
function (string) --
The function in the action group to call.
invocationId (string) --
The unique identifier of the invocation. Only returned if the executionType is RETURN_CONTROL .
parameters (list) --
The parameters in the Lambda input event.
(dict) --
A parameter for the API request or function.
name (string) --
The name of the parameter.
type (string) --
The type of the parameter.
value (string) --
The value of the parameter.
requestBody (dict) --
The parameters in the request body for the Lambda input event.
content (dict) --
The content in the request body.
(string) --
(list) --
(dict) --
A parameter for the API request or function.
name (string) --
The name of the parameter.
type (string) --
The type of the parameter.
value (string) --
The value of the parameter.
verb (string) --
The API method being used, based off the action group.
codeInterpreterInvocationInput (dict) --
Contains information about the code interpreter to be invoked.
code (string) --
The code for the code interpreter to use.
files (list) --
Files that are uploaded for code interpreter to use.
(string) --
invocationType (string) --
Specifies whether the agent is invoking an action group or a knowledge base.
knowledgeBaseLookupInput (dict) --
Contains details about the knowledge base to look up and the query to be made.
knowledgeBaseId (string) --
The unique identifier of the knowledge base to look up.
text (string) --
The query made to the knowledge base.
traceId (string) --
The unique identifier of the trace.
modelInvocationInput (dict) --
The input for the orchestration step.
The type is ORCHESTRATION .
The text contains the prompt.
The inferenceConfiguration , parserMode , and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
inferenceConfiguration (dict) --
Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.
maximumLength (integer) --
The maximum number of tokens allowed in the generated response.
stopSequences (list) --
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
(string) --
temperature (float) --
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.
topK (integer) --
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.
topP (float) --
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 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.
overrideLambda (string) --
The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.
parserMode (string) --
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 .
promptCreationMode (string) --
Specifies whether the default prompt template was OVERRIDDEN . If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.
text (string) --
The text that prompted the agent at this step.
traceId (string) --
The unique identifier of the trace.
type (string) --
The step in the agent sequence.
modelInvocationOutput (dict) --
Contains information pertaining to the output from the foundation model that is being invoked.
metadata (dict) --
Contains information about the foundation model output.
usage (dict) --
Contains details of the foundation model usage.
inputTokens (integer) --
Contains information about the input tokens from the foundation model usage.
outputTokens (integer) --
Contains information about the output tokens from the foundation model usage.
rawResponse (dict) --
Contains details of the raw response from the foundation model output.
content (string) --
The foundation model's raw output content.
traceId (string) --
The unique identifier of the trace.
observation (dict) --
Details about the observation (the output of the action group Lambda or knowledge base) made by the agent.
actionGroupInvocationOutput (dict) --
Contains the JSON-formatted string returned by the API invoked by the action group.
text (string) --
The JSON-formatted string returned by the API invoked by the action group.
codeInterpreterInvocationOutput (dict) --
Contains the JSON-formatted string returned by the API invoked by the code interpreter.
executionError (string) --
Contains the error returned from code execution.
executionOutput (string) --
Contains the successful output returned from code execution
executionTimeout (boolean) --
Indicates if the execution of the code timed out.
files (list) --
Contains output files, if generated by code execution.
(string) --
finalResponse (dict) --
Contains details about the response to the user.
text (string) --
The text in the response to the user.
knowledgeBaseLookupOutput (dict) --
Contains details about the results from looking up the knowledge base.
retrievedReferences (list) --
Contains metadata about the sources cited for the generated response.
(dict) --
Contains metadata about a source cited for the generated response.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the retrievedReferences field
InvokeAgent response – in the retrievedReferences field
content (dict) --
Contains the cited text from the data source.
text (string) --
The cited text from the data source.
location (dict) --
Contains information about the location of the data source.
confluenceLocation (dict) --
The Confluence data source location.
url (string) --
The Confluence host URL for the data source location.
s3Location (dict) --
The S3 data source location.
uri (string) --
The S3 URI for the data source location.
salesforceLocation (dict) --
The Salesforce data source location.
url (string) --
The Salesforce host URL for the data source location.
sharePointLocation (dict) --
The SharePoint data source location.
url (string) --
The SharePoint site URL for the data source location.
type (string) --
The type of data source location.
webLocation (dict) --
The web URL/URLs data source location.
url (string) --
The web URL/URLs for the data source location.
metadata (dict) --
Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
(string) --
repromptResponse (dict) --
Contains details about the response to reprompt the input.
source (string) --
Specifies what output is prompting the agent to reprompt the input.
text (string) --
The text reprompting the input.
traceId (string) --
The unique identifier of the trace.
type (string) --
Specifies what kind of information the agent returns in the observation. The following values are possible.
ACTION_GROUP – The agent returns the result of an action group.
KNOWLEDGE_BASE – The agent returns information from a knowledge base.
FINISH – The agent returns a final response to the user with no follow-up.
ASK_USER – The agent asks the user a question.
REPROMPT – The agent prompts the user again for the same information.
rationale (dict) --
Details about the reasoning, based on the input, that the agent uses to justify carrying out an action group or getting information from a knowledge base.
text (string) --
The reasoning or thought process of the agent, based on the input.
traceId (string) --
The unique identifier of the trace step.
postProcessingTrace (dict) --
Details about the post-processing step, in which the agent shapes the response..
Note
This is a Tagged Union structure. Only one of the following top level keys will be set: modelInvocationInput, modelInvocationOutput. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:
'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}
modelInvocationInput (dict) --
The input for the post-processing step.
The type is POST_PROCESSING .
The text contains the prompt.
The inferenceConfiguration , parserMode , and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
inferenceConfiguration (dict) --
Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.
maximumLength (integer) --
The maximum number of tokens allowed in the generated response.
stopSequences (list) --
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
(string) --
temperature (float) --
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.
topK (integer) --
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.
topP (float) --
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 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.
overrideLambda (string) --
The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.
parserMode (string) --
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 .
promptCreationMode (string) --
Specifies whether the default prompt template was OVERRIDDEN . If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.
text (string) --
The text that prompted the agent at this step.
traceId (string) --
The unique identifier of the trace.
type (string) --
The step in the agent sequence.
modelInvocationOutput (dict) --
The foundation model output from the post-processing step.
parsedResponse (dict) --
Details about the response from the Lambda parsing of the output of the post-processing step.
text (string) --
The text returned by the parser.
traceId (string) --
The unique identifier of the trace.
preProcessingTrace (dict) --
Details about the pre-processing step, in which the agent contextualizes and categorizes user inputs.
Note
This is a Tagged Union structure. Only one of the following top level keys will be set: modelInvocationInput, modelInvocationOutput. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:
'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}
modelInvocationInput (dict) --
The input for the pre-processing step.
The type is PRE_PROCESSING .
The text contains the prompt.
The inferenceConfiguration , parserMode , and overrideLambda values are set in the PromptOverrideConfiguration object that was set when the agent was created or updated.
inferenceConfiguration (dict) --
Specifications about the inference parameters that were provided alongside the prompt. These are specified in the PromptOverrideConfiguration object that was set when the agent was created or updated. For more information, see Inference parameters for foundation models.
maximumLength (integer) --
The maximum number of tokens allowed in the generated response.
stopSequences (list) --
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
(string) --
temperature (float) --
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.
topK (integer) --
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.
topP (float) --
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 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.
overrideLambda (string) --
The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence.
parserMode (string) --
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 .
promptCreationMode (string) --
Specifies whether the default prompt template was OVERRIDDEN . If it was, the basePromptTemplate that was set in the PromptOverrideConfiguration object when the agent was created or updated is used instead.
text (string) --
The text that prompted the agent at this step.
traceId (string) --
The unique identifier of the trace.
type (string) --
The step in the agent sequence.
modelInvocationOutput (dict) --
The foundation model output from the pre-processing step.
parsedResponse (dict) --
Details about the response from the Lambda parsing of the output of the pre-processing step.
isValid (boolean) --
Whether the user input is valid or not. If false , the agent doesn't proceed to orchestration.
rationale (string) --
The text returned by the parsing of the pre-processing step, explaining the steps that the agent plans to take in orchestration, if the user input is valid.
traceId (string) --
The unique identifier of the trace.
validationException (dict) --
Input validation failed. Check your request parameters and retry the request.
message (string) --
contentType (string) --
The MIME type of the input data in the request. The default value is application/json .
memoryId (string) --
The unique identifier of the agent memory.
sessionId (string) --
The unique identifier of the session with the agent.