2026/11/05 - Amazon Q Connect - 2 new41 updated api methods
Changes Adds support for real-time agent assistance and self-service with Amazon Connect Global Resiliency, including cross-Region replication of supported AI agent resources and configurations.
Registers a replica Region KMS key for an Amazon Q in Connect knowledge base. To use this operation, you must have kms:GenerateDataKey permission on the replica key. You must also have kms:CreateGrant permission on the primary key.
See also: AWS API Documentation
Request Syntax
client.register_knowledge_base_replica_key(
knowledgeBaseId='string',
replicaKmsKey={
'arn': 'string'
},
clientToken='string'
)
string
[REQUIRED]
The identifier of the knowledge base.
dict
[REQUIRED]
The replica Region KMS key to register for the knowledge base.
arn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
dict
Response Syntax
{
'knowledgeBase': {
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string',
'name': 'string',
'knowledgeBaseType': 'EXTERNAL'|'CUSTOM'|'QUICK_RESPONSES'|'MESSAGE_TEMPLATES'|'MANAGED',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'lastContentModificationTime': datetime(2015, 1, 1),
'vectorIngestionConfiguration': {
'chunkingConfiguration': {
'chunkingStrategy': 'FIXED_SIZE'|'NONE'|'HIERARCHICAL'|'SEMANTIC',
'fixedSizeChunkingConfiguration': {
'maxTokens': 123,
'overlapPercentage': 123
},
'hierarchicalChunkingConfiguration': {
'levelConfigurations': [
{
'maxTokens': 123
},
],
'overlapTokens': 123
},
'semanticChunkingConfiguration': {
'maxTokens': 123,
'bufferSize': 123,
'breakpointPercentileThreshold': 123
}
},
'parsingConfiguration': {
'parsingStrategy': 'BEDROCK_FOUNDATION_MODEL',
'bedrockFoundationModelConfiguration': {
'modelArn': 'string',
'parsingPrompt': {
'parsingPromptText': 'string'
}
}
}
},
'sourceConfiguration': {
'appIntegrations': {
'appIntegrationArn': 'string',
'objectFields': [
'string',
]
},
'managedSourceConfiguration': {
'webCrawlerConfiguration': {
'urlConfiguration': {
'seedUrls': [
{
'url': 'string'
},
]
},
'crawlerLimits': {
'rateLimit': 123
},
'inclusionFilters': [
'string',
],
'exclusionFilters': [
'string',
],
'scope': 'HOST_ONLY'|'SUBDOMAINS'
}
}
},
'renderingConfiguration': {
'templateUri': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'description': 'string',
'tags': {
'string': 'string'
},
'ingestionStatus': 'SYNC_FAILED'|'SYNCING_IN_PROGRESS'|'SYNC_SUCCESS'|'CREATE_IN_PROGRESS',
'ingestionFailureReasons': [
'string',
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
knowledgeBase (dict) --
Information about the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
name (string) --
The name of the knowledge base.
knowledgeBaseType (string) --
The type of knowledge base.
status (string) --
The status of the knowledge base.
lastContentModificationTime (datetime) --
An epoch timestamp indicating the most recent content modification inside the knowledge base. If no content exists in a knowledge base, this value is unset.
vectorIngestionConfiguration (dict) --
Contains details about how to ingest the documents in a data source.
chunkingConfiguration (dict) --
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
chunkingStrategy (string) --
Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
fixedSizeChunkingConfiguration (dict) --
Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as NONE, exclude this field.
maxTokens (integer) --
The maximum number of tokens to include in a chunk.
overlapPercentage (integer) --
The percentage of overlap between adjacent chunks of a data source.
hierarchicalChunkingConfiguration (dict) --
Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
levelConfigurations (list) --
Token settings for each layer.
(dict) --
Token settings for each layer.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain in this layer.
overlapTokens (integer) --
The number of tokens to repeat across chunks in the same layer.
semanticChunkingConfiguration (dict) --
Settings for semantic document chunking for a data source. Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain.
bufferSize (integer) --
The buffer size.
breakpointPercentileThreshold (integer) --
The dissimilarity threshold for splitting chunks.
parsingConfiguration (dict) --
A custom parser for data source documents.
parsingStrategy (string) --
The parsing strategy for the data source.
bedrockFoundationModelConfiguration (dict) --
Settings for a foundation model used to parse documents for a data source.
modelArn (string) --
The ARN of the foundation model.
parsingPrompt (dict) --
Instructions for interpreting the contents of a document.
parsingPromptText (string) --
Instructions for interpreting the contents of a document.
sourceConfiguration (dict) --
Source configuration information about the knowledge base.
appIntegrations (dict) --
Configuration information for Amazon AppIntegrations to automatically ingest content.
appIntegrationArn (string) --
The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content.
For Salesforce, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted as source fields.
For ServiceNow, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least number, short_description, sys_mod_count, workflow_state, and active as source fields.
For Zendesk, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least id, title, updated_at, and draft as source fields.
For SharePoint, your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are among docx, pdf, html, htm, and txt.
For Amazon S3, the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. The SourceURI of your DataIntegration must use the following format: s3://your_s3_bucket_name.
objectFields (list) --
The fields from the source that are made available to your agents in Amazon Q in Connect. Optional if ObjectConfiguration is included in the provided DataIntegration.
For Salesforce, you must include at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted.
For ServiceNow, you must include at least number, short_description, sys_mod_count, workflow_state, and active.
For Zendesk, you must include at least id, title, updated_at, and draft.
Make sure to include additional fields. These fields are indexed and used to source recommendations.
(string) --
managedSourceConfiguration (dict) --
Source configuration for managed resources.
webCrawlerConfiguration (dict) --
Configuration data for web crawler data source.
urlConfiguration (dict) --
The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.
seedUrls (list) --
List of URLs for crawling.
(dict) --
A URL for crawling.
url (string) --
URL for crawling
crawlerLimits (dict) --
The configuration of crawl limits for the web URLs.
rateLimit (integer) --
Rate of web URLs retrieved per minute.
inclusionFilters (list) --
A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
exclusionFilters (list) --
A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
scope (string) --
The scope of what is crawled for your URLs. You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL https://docs.aws.amazon.com/bedrock/latest/userguide/ and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain aws.amazon.com can also include sub domain docs.aws.amazon.com.
renderingConfiguration (dict) --
Information about how to render the content.
templateUri (string) --
A URI template containing exactly one variable in ${variableName} ``format. This can only be set for ``EXTERNAL knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following:
Salesforce: Id, ArticleNumber, VersionNumber, Title, PublishStatus, or IsDeleted
ServiceNow: number, short_description, sys_mod_count, workflow_state, or active
Zendesk: id, title, updated_at, or draft
The variable is replaced with the actual value for a piece of content when calling GetContent.
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
ingestionStatus (string) --
Status of ingestion on data source.
ingestionFailureReasons (list) --
List of failure reasons on ingestion per file.
(string) --
lastModifiedTime (datetime) --
The timestamp when the knowledge base was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the knowledge base was last modified.
Registers a replica Region KMS key for an Amazon Q in Connect assistant. To use this operation, you must have kms:GenerateDataKey permission on the replica key.
See also: AWS API Documentation
Request Syntax
client.register_assistant_replica_key(
assistantId='string',
replicaKmsKey={
'arn': 'string'
},
clientToken='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant.
dict
[REQUIRED]
The replica Region KMS key to register for the assistant.
arn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
dict
Response Syntax
{
'assistant': {
'assistantId': 'string',
'assistantArn': 'string',
'name': 'string',
'type': 'AGENT',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'description': 'string',
'tags': {
'string': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'integrationConfiguration': {
'topicIntegrationArn': 'string'
},
'capabilityConfiguration': {
'type': 'V1'|'V2'
},
'aiAgentConfiguration': {
'string': {
'aiAgentId': 'string',
'enabled': True|False
}
},
'orchestratorConfigurationList': [
{
'aiAgentId': 'string',
'orchestratorUseCase': 'string'
},
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'assistantGlobalResiliencyStatus': 'ENABLED'|'DISABLED'
}
}
Response Structure
(dict) --
assistant (dict) --
The assistant data.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
name (string) --
The name.
type (string) --
The type of assistant.
status (string) --
The status of the assistant.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect. To use Amazon Q in Connect with chat, the key policy must also allow kms:Decrypt, kms:GenerateDataKey*, and kms:DescribeKey permissions to the connect.amazonaws.com service principal.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
integrationConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant integration.
topicIntegrationArn (string) --
The Amazon Resource Name (ARN) of the integrated Amazon SNS topic used for streaming chat messages.
capabilityConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant capability.
type (string) --
The type of Amazon Q in Connect assistant capability.
aiAgentConfiguration (dict) --
The configuration of the AI Agents (mapped by AI Agent Type to AI Agent version) that is set on the Amazon Q in Connect Assistant.
(string) --
(dict) --
A type that specifies the AI Agent ID configuration data when mapping an AI Agents to be used for an AI Agent type on a session or assistant.
aiAgentId (string) --
The ID of the AI Agent to be configured.
enabled (boolean) --
Indicates whether the AI Agent configured for this AI Agent type is enabled. When this value is omitted or set to true, the configured AI Agent runs; when set to false, the AI Agent ID is retained but no AI Agent runs for the AI Agent type. Setting this value to false is currently supported only for the ANSWER_RECOMMENDATION AI Agent type; other requests to set it to false are rejected with a validation error.
orchestratorConfigurationList (list) --
The list of orchestrator configurations for the assistant.
(dict) --
An entry in the orchestrator configuration list.
aiAgentId (string) --
The identifier of the AI Agent in the orchestrator configuration.
orchestratorUseCase (string) --
The use case for the orchestrator configuration. (for example Connect.SelfService, Connect.AgentAssistance)
lastModifiedTime (datetime) --
The timestamp when the assistant was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant was last modified.
assistantGlobalResiliencyStatus (string) --
Whether Amazon Connect Global Resiliency replicates the Connect instance this assistant is associated with, and so whether resources created under this assistant must satisfy the replication group's model parity constraint. Answered from the ACGR side per request rather than stored, so it reflects the customer's replication state now.
Absent means "not applicable or not known" - never read an absent field as DISABLED. It is absent on the operations that return an assistant which is not yet associated with a Connect instance, because replication cannot be established until it is.
{'aiAgent': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Creates an Amazon Q in Connect AI Agent.
See also: AWS API Documentation
Request Syntax
client.create_ai_agent(
clientToken='string',
assistantId='string',
name='string',
type='MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
configuration={
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
visibilityStatus='SAVED'|'PUBLISHED',
tags={
'string': 'string'
},
description='string'
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The name of the AI Agent.
string
[REQUIRED]
The type of the AI Agent.
dict
[REQUIRED]
The configuration of the AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) -- [REQUIRED]
The name of the tool.
toolType (string) -- [REQUIRED]
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) -- [REQUIRED]
The JSON path for the input value override.
value (dict) -- [REQUIRED]
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) -- [REQUIRED]
Override tool input value with constant values
value (string) -- [REQUIRED]
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) -- [REQUIRED]
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) -- [REQUIRED]
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) -- [REQUIRED]
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
string
[REQUIRED]
The visibility status of the AI Agent.
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
string
The description of the AI Agent.
dict
Response Syntax
{
'aiAgent': {
'assistantId': 'string',
'assistantArn': 'string',
'aiAgentId': 'string',
'aiAgentArn': 'string',
'name': 'string',
'type': 'MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'configuration': {
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
}
}
Response Structure
(dict) --
aiAgent (dict) --
The data of the created AI Agent.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiAgentId (string) --
The identifier of the AI Agent.
aiAgentArn (string) --
The Amazon Resource Name (ARN) of the AI agent.
name (string) --
The name of the AI Agent.
type (string) --
The type of the AI Agent.
configuration (dict) --
Configuration for the AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) --
The name of the tool.
toolType (string) --
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) --
The JSON path for the input value override.
value (dict) --
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) --
Override tool input value with constant values
value (string) --
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) --
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) --
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) --
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
modifiedTime (datetime) --
The time the AI Agent was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Agent was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Agent was last modified.
description (string) --
The description of the AI Agent.
visibilityStatus (string) --
The visibility status of the AI Agent.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
Specifies the origin of the AI Agent. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
status (string) --
The status of the AI Agent.
{'aiAgent': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Creates and Amazon Q in Connect AI Agent version.
See also: AWS API Documentation
Request Syntax
client.create_ai_agent_version(
assistantId='string',
aiAgentId='string',
modifiedTime=datetime(2015, 1, 1),
clientToken='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Agent.
datetime
The modification time of the AI Agent should be tracked for version creation. This field should be specified to avoid version creation when simultaneous update to the underlying AI Agent are possible. The value should be the modifiedTime returned from the request to create or update an AI Agent so that version creation can fail if an update to the AI Agent post the specified modification time has been made.
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
dict
Response Syntax
{
'aiAgent': {
'assistantId': 'string',
'assistantArn': 'string',
'aiAgentId': 'string',
'aiAgentArn': 'string',
'name': 'string',
'type': 'MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'configuration': {
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
},
'versionNumber': 123
}
Response Structure
(dict) --
aiAgent (dict) --
The data of the AI Agent version.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiAgentId (string) --
The identifier of the AI Agent.
aiAgentArn (string) --
The Amazon Resource Name (ARN) of the AI agent.
name (string) --
The name of the AI Agent.
type (string) --
The type of the AI Agent.
configuration (dict) --
Configuration for the AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) --
The name of the tool.
toolType (string) --
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) --
The JSON path for the input value override.
value (dict) --
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) --
Override tool input value with constant values
value (string) --
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) --
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) --
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) --
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
modifiedTime (datetime) --
The time the AI Agent was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Agent was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Agent was last modified.
description (string) --
The description of the AI Agent.
visibilityStatus (string) --
The visibility status of the AI Agent.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
Specifies the origin of the AI Agent. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
status (string) --
The status of the AI Agent.
versionNumber (integer) --
The version number of the AI Agent version.
{'aiGuardrail': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Creates an Amazon Q in Connect AI Guardrail.
See also: AWS API Documentation
Request Syntax
client.create_ai_guardrail(
clientToken='string',
assistantId='string',
name='string',
blockedInputMessaging='string',
blockedOutputsMessaging='string',
visibilityStatus='SAVED'|'PUBLISHED',
description='string',
topicPolicyConfig={
'topicsConfig': [
{
'name': 'string',
'definition': 'string',
'examples': [
'string',
],
'type': 'DENY'
},
]
},
contentPolicyConfig={
'filtersConfig': [
{
'type': 'SEXUAL'|'VIOLENCE'|'HATE'|'INSULTS'|'MISCONDUCT'|'PROMPT_ATTACK',
'inputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'outputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH'
},
]
},
wordPolicyConfig={
'wordsConfig': [
{
'text': 'string'
},
],
'managedWordListsConfig': [
{
'type': 'PROFANITY'
},
]
},
sensitiveInformationPolicyConfig={
'piiEntitiesConfig': [
{
'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',
'action': 'BLOCK'|'ANONYMIZE'
},
],
'regexesConfig': [
{
'name': 'string',
'description': 'string',
'pattern': 'string',
'action': 'BLOCK'|'ANONYMIZE'
},
]
},
contextualGroundingPolicyConfig={
'filtersConfig': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0
},
]
},
tags={
'string': 'string'
}
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The name of the AI Guardrail.
string
[REQUIRED]
The message to return when the AI Guardrail blocks a prompt.
string
[REQUIRED]
The message to return when the AI Guardrail blocks a model response.
string
[REQUIRED]
The visibility status of the AI Guardrail.
string
A description of the AI Guardrail.
dict
The topic policies to configure for the AI Guardrail.
topicsConfig (list) -- [REQUIRED]
A list of policies related to topics that the AI Guardrail should deny.
(dict) --
Details about topics for the AI Guardrail to identify and deny.
name (string) -- [REQUIRED]
The name of the topic to deny.
definition (string) -- [REQUIRED]
A definition of the topic to deny.
examples (list) --
A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
(string) --
Text example in topic policy
type (string) -- [REQUIRED]
Specifies to deny the topic.
dict
The content filter policies to configure for the AI Guardrail.
filtersConfig (list) -- [REQUIRED]
Contains the type of the content filter and how strongly it should apply to prompts and model responses.
(dict) --
Contains filter strengths for harmful content. AI Guardrail's support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate: Describes input prompts and model responses that discriminate, criticize, insult, denounce, or dehumanize a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults: Describes input prompts and model responses that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual: Describes input prompts and model responses that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence: Describes input prompts and model responses that includes glorification of, or threats to inflict physical pain, hurt, or injury toward a person, group, or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
type (string) -- [REQUIRED]
The harmful category that the content filter is applied to.
inputStrength (string) -- [REQUIRED]
The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
outputStrength (string) -- [REQUIRED]
The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
dict
The word policy you configure for the AI Guardrail.
wordsConfig (list) --
A list of words to configure for the AI Guardrail.
(dict) --
A word to configure for the AI Guardrail.
text (string) -- [REQUIRED]
Text of the word configured for the AI Guardrail to block.
managedWordListsConfig (list) --
A list of managed words to configure for the AI Guardrail.
(dict) --
The managed word list to configure for the AI Guardrail.
type (string) -- [REQUIRED]
The managed word type to configure for the AI Guardrail.
dict
The sensitive information policy to configure for the AI Guardrail.
piiEntitiesConfig (list) --
A list of PII entities to configure to the AI Guardrail.
(dict) --
The PII entity to configure for the AI Guardrail.
type (string) -- [REQUIRED]
Configure AI Guardrail type when the PII entity is detected.
The following PIIs are used to block or mask sensitive information:
General
ADDRESS A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.
AGE An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guarrails recognizes "40 years" as an age.
NAME An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. AI Guardrail doesn't apply this entity type to names that are part of organizations or addresses. For example, AI Guardrail recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.
EMAIL An email address, such as marymajor@email.com.
PHONE A phone number. This entity type also includes fax and pager numbers.
USERNAME A user name that identifies an account, such as a login name, screen name, nick name, or handle.
PASSWORD An alphanumeric string that is used as a password, such as "** very20special#pass**".
DRIVER_ID The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.
LICENSE_PLATE A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.
VEHICLE_IDENTIFICATION_NUMBER A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.
Finance
CREDIT_DEBIT_CARD_CVV A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.
CREDIT_DEBIT_CARD_EXPIRY The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY. AI Guardrail recognizes expiration dates such as 01/21, 01/2021, and Jan 2021.
CREDIT_DEBIT_CARD_NUMBER The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.
PIN A four-digit personal identification number (PIN) with which you can access your bank account.
INTERNATIONAL_BANK_ACCOUNT_NUMBER An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure.
SWIFT_CODE A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers. SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.
IT
IP_ADDRESS An IPv4 address, such as 198.51.100.0.
MAC_ADDRESS A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).
URL A web address, such as www.example.com.
AWS_ACCESS_KEY A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
AWS_SECRET_KEY A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
USA specific
US_BANK_ACCOUNT_NUMBER A US bank account number, which is typically 10 to 12 digits long.
US_BANK_ROUTING_NUMBER A US bank account routing number. These are typically nine digits long,
US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.
US_PASSPORT_NUMBER A US passport number. Passport numbers range from six to nine alphanumeric characters.
US_SOCIAL_SECURITY_NUMBER A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.
Canada specific
CA_HEALTH_NUMBER A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.
CA_SOCIAL_INSURANCE_NUMBER A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits. The SIN is formatted as three groups of three digits, such as 123-456-789. A SIN can be validated through a simple check-digit process called the Luhn algorithm. For more information, see Luhn algorithm on the Wikipedia website.
UK Specific
UK_NATIONAL_HEALTH_SERVICE_NUMBER A UK National Health Service Number is a 10-17 digit number, such as 485 555 3456. The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.
UK_NATIONAL_INSURANCE_NUMBER A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system. The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.
UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.
Custom
Regex filter - You can use a regular expressions to define patterns for an AI Guardrail to recognize and act upon such as serial number, booking ID etc..
action (string) -- [REQUIRED]
Configure AI Guardrail's action when the PII entity is detected.
regexesConfig (list) --
A list of regular expressions to configure to the AI Guardrail.
(dict) --
The regular expression to configure for the AI Guardrail.
name (string) -- [REQUIRED]
The name of the regular expression to configure for the AI Guardrail.
description (string) --
The description of the regular expression to configure for the AI Guardrail.
pattern (string) -- [REQUIRED]
The regular expression pattern to configure for the AI Guardrail.
action (string) -- [REQUIRED]
The AI Guardrail action to configure when matching regular expression is detected.
dict
The contextual grounding policy configuration used to create an AI Guardrail.
filtersConfig (list) -- [REQUIRED]
The filter configuration details for the AI Guardrails contextual grounding policy.
(dict) --
The filter configuration details for the AI Guardrail's contextual grounding filter.
type (string) -- [REQUIRED]
The filter type for the AI Guardrail's contextual grounding filter.
threshold (float) -- [REQUIRED]
The threshold details for the AI Guardrail's contextual grounding filter.
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
dict
Response Syntax
{
'aiGuardrail': {
'assistantId': 'string',
'assistantArn': 'string',
'aiGuardrailArn': 'string',
'aiGuardrailId': 'string',
'name': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'blockedInputMessaging': 'string',
'blockedOutputsMessaging': 'string',
'description': 'string',
'topicPolicyConfig': {
'topicsConfig': [
{
'name': 'string',
'definition': 'string',
'examples': [
'string',
],
'type': 'DENY'
},
]
},
'contentPolicyConfig': {
'filtersConfig': [
{
'type': 'SEXUAL'|'VIOLENCE'|'HATE'|'INSULTS'|'MISCONDUCT'|'PROMPT_ATTACK',
'inputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'outputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH'
},
]
},
'wordPolicyConfig': {
'wordsConfig': [
{
'text': 'string'
},
],
'managedWordListsConfig': [
{
'type': 'PROFANITY'
},
]
},
'sensitiveInformationPolicyConfig': {
'piiEntitiesConfig': [
{
'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',
'action': 'BLOCK'|'ANONYMIZE'
},
],
'regexesConfig': [
{
'name': 'string',
'description': 'string',
'pattern': 'string',
'action': 'BLOCK'|'ANONYMIZE'
},
]
},
'contextualGroundingPolicyConfig': {
'filtersConfig': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0
},
]
},
'tags': {
'string': 'string'
},
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
aiGuardrail (dict) --
The data of the AI Guardrail.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiGuardrailArn (string) --
The Amazon Resource Name (ARN) of the AI Guardrail.
aiGuardrailId (string) --
The identifier of the Amazon Q in Connect AI Guardrail.
name (string) --
The name of the AI Guardrail.
visibilityStatus (string) --
The visibility status of the AI Guardrail.
blockedInputMessaging (string) --
The message to return when the AI Guardrail blocks a prompt.
blockedOutputsMessaging (string) --
The message to return when the AI Guardrail blocks a model response.
description (string) --
A description of the AI Guardrail.
topicPolicyConfig (dict) --
Contains details about topics that the AI Guardrail should identify and deny.
topicsConfig (list) --
A list of policies related to topics that the AI Guardrail should deny.
(dict) --
Details about topics for the AI Guardrail to identify and deny.
name (string) --
The name of the topic to deny.
definition (string) --
A definition of the topic to deny.
examples (list) --
A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
(string) --
Text example in topic policy
type (string) --
Specifies to deny the topic.
contentPolicyConfig (dict) --
Contains details about how to handle harmful content.
filtersConfig (list) --
Contains the type of the content filter and how strongly it should apply to prompts and model responses.
(dict) --
Contains filter strengths for harmful content. AI Guardrail's support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate: Describes input prompts and model responses that discriminate, criticize, insult, denounce, or dehumanize a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults: Describes input prompts and model responses that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual: Describes input prompts and model responses that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence: Describes input prompts and model responses that includes glorification of, or threats to inflict physical pain, hurt, or injury toward a person, group, or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
type (string) --
The harmful category that the content filter is applied to.
inputStrength (string) --
The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
outputStrength (string) --
The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
wordPolicyConfig (dict) --
Contains details about the word policy to configured for the AI Guardrail.
wordsConfig (list) --
A list of words to configure for the AI Guardrail.
(dict) --
A word to configure for the AI Guardrail.
text (string) --
Text of the word configured for the AI Guardrail to block.
managedWordListsConfig (list) --
A list of managed words to configure for the AI Guardrail.
(dict) --
The managed word list to configure for the AI Guardrail.
type (string) --
The managed word type to configure for the AI Guardrail.
sensitiveInformationPolicyConfig (dict) --
Contains details about PII entities and regular expressions to configure for the AI Guardrail.
piiEntitiesConfig (list) --
A list of PII entities to configure to the AI Guardrail.
(dict) --
The PII entity to configure for the AI Guardrail.
type (string) --
Configure AI Guardrail type when the PII entity is detected.
The following PIIs are used to block or mask sensitive information:
General
ADDRESS A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.
AGE An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guarrails recognizes "40 years" as an age.
NAME An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. AI Guardrail doesn't apply this entity type to names that are part of organizations or addresses. For example, AI Guardrail recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.
EMAIL An email address, such as marymajor@email.com.
PHONE A phone number. This entity type also includes fax and pager numbers.
USERNAME A user name that identifies an account, such as a login name, screen name, nick name, or handle.
PASSWORD An alphanumeric string that is used as a password, such as "** very20special#pass**".
DRIVER_ID The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.
LICENSE_PLATE A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.
VEHICLE_IDENTIFICATION_NUMBER A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.
Finance
CREDIT_DEBIT_CARD_CVV A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.
CREDIT_DEBIT_CARD_EXPIRY The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY. AI Guardrail recognizes expiration dates such as 01/21, 01/2021, and Jan 2021.
CREDIT_DEBIT_CARD_NUMBER The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.
PIN A four-digit personal identification number (PIN) with which you can access your bank account.
INTERNATIONAL_BANK_ACCOUNT_NUMBER An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure.
SWIFT_CODE A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers. SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.
IT
IP_ADDRESS An IPv4 address, such as 198.51.100.0.
MAC_ADDRESS A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).
URL A web address, such as www.example.com.
AWS_ACCESS_KEY A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
AWS_SECRET_KEY A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
USA specific
US_BANK_ACCOUNT_NUMBER A US bank account number, which is typically 10 to 12 digits long.
US_BANK_ROUTING_NUMBER A US bank account routing number. These are typically nine digits long,
US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.
US_PASSPORT_NUMBER A US passport number. Passport numbers range from six to nine alphanumeric characters.
US_SOCIAL_SECURITY_NUMBER A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.
Canada specific
CA_HEALTH_NUMBER A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.
CA_SOCIAL_INSURANCE_NUMBER A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits. The SIN is formatted as three groups of three digits, such as 123-456-789. A SIN can be validated through a simple check-digit process called the Luhn algorithm. For more information, see Luhn algorithm on the Wikipedia website.
UK Specific
UK_NATIONAL_HEALTH_SERVICE_NUMBER A UK National Health Service Number is a 10-17 digit number, such as 485 555 3456. The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.
UK_NATIONAL_INSURANCE_NUMBER A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system. The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.
UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.
Custom
Regex filter - You can use a regular expressions to define patterns for an AI Guardrail to recognize and act upon such as serial number, booking ID etc..
action (string) --
Configure AI Guardrail's action when the PII entity is detected.
regexesConfig (list) --
A list of regular expressions to configure to the AI Guardrail.
(dict) --
The regular expression to configure for the AI Guardrail.
name (string) --
The name of the regular expression to configure for the AI Guardrail.
description (string) --
The description of the regular expression to configure for the AI Guardrail.
pattern (string) --
The regular expression pattern to configure for the AI Guardrail.
action (string) --
The AI Guardrail action to configure when matching regular expression is detected.
contextualGroundingPolicyConfig (dict) --
The policy configuration details for the AI Guardrail's contextual grounding policy.
filtersConfig (list) --
The filter configuration details for the AI Guardrails contextual grounding policy.
(dict) --
The filter configuration details for the AI Guardrail's contextual grounding filter.
type (string) --
The filter type for the AI Guardrail's contextual grounding filter.
threshold (float) --
The threshold details for the AI Guardrail's contextual grounding filter.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
status (string) --
The status of the AI Guardrail.
modifiedTime (datetime) --
The time the AI Guardrail was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Guardrail was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Guardrail was last modified.
{'aiGuardrail': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Creates an Amazon Q in Connect AI Guardrail version.
See also: AWS API Documentation
Request Syntax
client.create_ai_guardrail_version(
assistantId='string',
aiGuardrailId='string',
modifiedTime=datetime(2015, 1, 1),
clientToken='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Guardrail.
datetime
The time the AI Guardrail was last modified.
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
dict
Response Syntax
{
'aiGuardrail': {
'assistantId': 'string',
'assistantArn': 'string',
'aiGuardrailArn': 'string',
'aiGuardrailId': 'string',
'name': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'blockedInputMessaging': 'string',
'blockedOutputsMessaging': 'string',
'description': 'string',
'topicPolicyConfig': {
'topicsConfig': [
{
'name': 'string',
'definition': 'string',
'examples': [
'string',
],
'type': 'DENY'
},
]
},
'contentPolicyConfig': {
'filtersConfig': [
{
'type': 'SEXUAL'|'VIOLENCE'|'HATE'|'INSULTS'|'MISCONDUCT'|'PROMPT_ATTACK',
'inputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'outputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH'
},
]
},
'wordPolicyConfig': {
'wordsConfig': [
{
'text': 'string'
},
],
'managedWordListsConfig': [
{
'type': 'PROFANITY'
},
]
},
'sensitiveInformationPolicyConfig': {
'piiEntitiesConfig': [
{
'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',
'action': 'BLOCK'|'ANONYMIZE'
},
],
'regexesConfig': [
{
'name': 'string',
'description': 'string',
'pattern': 'string',
'action': 'BLOCK'|'ANONYMIZE'
},
]
},
'contextualGroundingPolicyConfig': {
'filtersConfig': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0
},
]
},
'tags': {
'string': 'string'
},
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
},
'versionNumber': 123
}
Response Structure
(dict) --
aiGuardrail (dict) --
The data of the AI Guardrail version.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiGuardrailArn (string) --
The Amazon Resource Name (ARN) of the AI Guardrail.
aiGuardrailId (string) --
The identifier of the Amazon Q in Connect AI Guardrail.
name (string) --
The name of the AI Guardrail.
visibilityStatus (string) --
The visibility status of the AI Guardrail.
blockedInputMessaging (string) --
The message to return when the AI Guardrail blocks a prompt.
blockedOutputsMessaging (string) --
The message to return when the AI Guardrail blocks a model response.
description (string) --
A description of the AI Guardrail.
topicPolicyConfig (dict) --
Contains details about topics that the AI Guardrail should identify and deny.
topicsConfig (list) --
A list of policies related to topics that the AI Guardrail should deny.
(dict) --
Details about topics for the AI Guardrail to identify and deny.
name (string) --
The name of the topic to deny.
definition (string) --
A definition of the topic to deny.
examples (list) --
A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
(string) --
Text example in topic policy
type (string) --
Specifies to deny the topic.
contentPolicyConfig (dict) --
Contains details about how to handle harmful content.
filtersConfig (list) --
Contains the type of the content filter and how strongly it should apply to prompts and model responses.
(dict) --
Contains filter strengths for harmful content. AI Guardrail's support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate: Describes input prompts and model responses that discriminate, criticize, insult, denounce, or dehumanize a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults: Describes input prompts and model responses that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual: Describes input prompts and model responses that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence: Describes input prompts and model responses that includes glorification of, or threats to inflict physical pain, hurt, or injury toward a person, group, or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
type (string) --
The harmful category that the content filter is applied to.
inputStrength (string) --
The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
outputStrength (string) --
The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
wordPolicyConfig (dict) --
Contains details about the word policy to configured for the AI Guardrail.
wordsConfig (list) --
A list of words to configure for the AI Guardrail.
(dict) --
A word to configure for the AI Guardrail.
text (string) --
Text of the word configured for the AI Guardrail to block.
managedWordListsConfig (list) --
A list of managed words to configure for the AI Guardrail.
(dict) --
The managed word list to configure for the AI Guardrail.
type (string) --
The managed word type to configure for the AI Guardrail.
sensitiveInformationPolicyConfig (dict) --
Contains details about PII entities and regular expressions to configure for the AI Guardrail.
piiEntitiesConfig (list) --
A list of PII entities to configure to the AI Guardrail.
(dict) --
The PII entity to configure for the AI Guardrail.
type (string) --
Configure AI Guardrail type when the PII entity is detected.
The following PIIs are used to block or mask sensitive information:
General
ADDRESS A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.
AGE An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guarrails recognizes "40 years" as an age.
NAME An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. AI Guardrail doesn't apply this entity type to names that are part of organizations or addresses. For example, AI Guardrail recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.
EMAIL An email address, such as marymajor@email.com.
PHONE A phone number. This entity type also includes fax and pager numbers.
USERNAME A user name that identifies an account, such as a login name, screen name, nick name, or handle.
PASSWORD An alphanumeric string that is used as a password, such as "** very20special#pass**".
DRIVER_ID The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.
LICENSE_PLATE A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.
VEHICLE_IDENTIFICATION_NUMBER A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.
Finance
CREDIT_DEBIT_CARD_CVV A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.
CREDIT_DEBIT_CARD_EXPIRY The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY. AI Guardrail recognizes expiration dates such as 01/21, 01/2021, and Jan 2021.
CREDIT_DEBIT_CARD_NUMBER The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.
PIN A four-digit personal identification number (PIN) with which you can access your bank account.
INTERNATIONAL_BANK_ACCOUNT_NUMBER An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure.
SWIFT_CODE A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers. SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.
IT
IP_ADDRESS An IPv4 address, such as 198.51.100.0.
MAC_ADDRESS A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).
URL A web address, such as www.example.com.
AWS_ACCESS_KEY A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
AWS_SECRET_KEY A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
USA specific
US_BANK_ACCOUNT_NUMBER A US bank account number, which is typically 10 to 12 digits long.
US_BANK_ROUTING_NUMBER A US bank account routing number. These are typically nine digits long,
US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.
US_PASSPORT_NUMBER A US passport number. Passport numbers range from six to nine alphanumeric characters.
US_SOCIAL_SECURITY_NUMBER A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.
Canada specific
CA_HEALTH_NUMBER A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.
CA_SOCIAL_INSURANCE_NUMBER A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits. The SIN is formatted as three groups of three digits, such as 123-456-789. A SIN can be validated through a simple check-digit process called the Luhn algorithm. For more information, see Luhn algorithm on the Wikipedia website.
UK Specific
UK_NATIONAL_HEALTH_SERVICE_NUMBER A UK National Health Service Number is a 10-17 digit number, such as 485 555 3456. The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.
UK_NATIONAL_INSURANCE_NUMBER A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system. The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.
UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.
Custom
Regex filter - You can use a regular expressions to define patterns for an AI Guardrail to recognize and act upon such as serial number, booking ID etc..
action (string) --
Configure AI Guardrail's action when the PII entity is detected.
regexesConfig (list) --
A list of regular expressions to configure to the AI Guardrail.
(dict) --
The regular expression to configure for the AI Guardrail.
name (string) --
The name of the regular expression to configure for the AI Guardrail.
description (string) --
The description of the regular expression to configure for the AI Guardrail.
pattern (string) --
The regular expression pattern to configure for the AI Guardrail.
action (string) --
The AI Guardrail action to configure when matching regular expression is detected.
contextualGroundingPolicyConfig (dict) --
The policy configuration details for the AI Guardrail's contextual grounding policy.
filtersConfig (list) --
The filter configuration details for the AI Guardrails contextual grounding policy.
(dict) --
The filter configuration details for the AI Guardrail's contextual grounding filter.
type (string) --
The filter type for the AI Guardrail's contextual grounding filter.
threshold (float) --
The threshold details for the AI Guardrail's contextual grounding filter.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
status (string) --
The status of the AI Guardrail.
modifiedTime (datetime) --
The time the AI Guardrail was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Guardrail was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Guardrail was last modified.
versionNumber (integer) --
The version number of the AI Guardrail version.
{'aiPrompt': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Creates an Amazon Q in Connect AI Prompt.
See also: AWS API Documentation
Request Syntax
client.create_ai_prompt(
clientToken='string',
assistantId='string',
name='string',
type='ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
templateConfiguration={
'textFullAIPromptEditTemplateConfiguration': {
'text': 'string'
}
},
visibilityStatus='SAVED'|'PUBLISHED',
templateType='TEXT',
modelId='string',
apiFormat='ANTHROPIC_CLAUDE_MESSAGES'|'ANTHROPIC_CLAUDE_TEXT_COMPLETIONS'|'MESSAGES'|'TEXT_COMPLETIONS',
tags={
'string': 'string'
},
description='string',
inferenceConfiguration={
'temperature': ...,
'topP': ...,
'topK': 123,
'maxTokensToSample': 123
}
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The name of the AI Prompt.
string
[REQUIRED]
The type of this AI Prompt.
dict
[REQUIRED]
The configuration of the prompt template for this AI Prompt.
textFullAIPromptEditTemplateConfiguration (dict) --
The configuration for a prompt template that supports full textual prompt configuration using a YAML prompt.
text (string) -- [REQUIRED]
The YAML text for the AI Prompt template.
string
[REQUIRED]
The visibility status of the AI Prompt.
string
[REQUIRED]
The type of the prompt template for this AI Prompt.
string
[REQUIRED]
The identifier of the model used for this AI Prompt.
string
[REQUIRED]
The API Format of the AI Prompt.
Recommended values: MESSAGES | TEXT_COMPLETIONS
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
string
The description of the AI Prompt.
dict
The inference configuration for the AI Prompt being created.
temperature (float) --
The temperature setting for controlling randomness in the generated response.
topP (float) --
The top-P sampling parameter for nucleus sampling.
topK (integer) --
The top-K sampling parameter for token selection.
maxTokensToSample (integer) --
The maximum number of tokens to generate in the response.
dict
Response Syntax
{
'aiPrompt': {
'assistantId': 'string',
'assistantArn': 'string',
'aiPromptId': 'string',
'aiPromptArn': 'string',
'name': 'string',
'type': 'ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'templateType': 'TEXT',
'modelId': 'string',
'apiFormat': 'ANTHROPIC_CLAUDE_MESSAGES'|'ANTHROPIC_CLAUDE_TEXT_COMPLETIONS'|'MESSAGES'|'TEXT_COMPLETIONS',
'templateConfiguration': {
'textFullAIPromptEditTemplateConfiguration': {
'text': 'string'
}
},
'inferenceConfiguration': {
'temperature': ...,
'topP': ...,
'topK': 123,
'maxTokensToSample': 123
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
}
}
Response Structure
(dict) --
aiPrompt (dict) --
The data of the AI Prompt.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiPromptId (string) --
The identifier of the Amazon Q in Connect AI prompt.
aiPromptArn (string) --
The Amazon Resource Name (ARN) of the AI Prompt.
name (string) --
The name of the AI Prompt
type (string) --
The type of this AI Prompt.
templateType (string) --
The type of the prompt template for this AI Prompt.
modelId (string) --
The identifier of the model used for this AI Prompt. The following model Ids are supported:
anthropic.claude-3-haiku--v1:0
apac.amazon.nova-lite-v1:0
apac.amazon.nova-micro-v1:0
apac.amazon.nova-pro-v1:0
apac.anthropic.claude-3-5-sonnet--v2:0
apac.anthropic.claude-3-haiku-20240307-v1:0
eu.amazon.nova-lite-v1:0
eu.amazon.nova-micro-v1:0
eu.amazon.nova-pro-v1:0
eu.anthropic.claude-3-7-sonnet-20250219-v1:0
eu.anthropic.claude-3-haiku-20240307-v1:0
us.amazon.nova-lite-v1:0
us.amazon.nova-micro-v1:0
us.amazon.nova-pro-v1:0
us.anthropic.claude-3-5-haiku-20241022-v1:0
us.anthropic.claude-3-7-sonnet-20250219-v1:0
us.anthropic.claude-3-haiku-20240307-v1:0
apiFormat (string) --
The API format used for this AI Prompt.
templateConfiguration (dict) --
The configuration of the prompt template for this AI Prompt.
textFullAIPromptEditTemplateConfiguration (dict) --
The configuration for a prompt template that supports full textual prompt configuration using a YAML prompt.
text (string) --
The YAML text for the AI Prompt template.
inferenceConfiguration (dict) --
The configuration for inference parameters when using the AI Prompt.
temperature (float) --
The temperature setting for controlling randomness in the generated response.
topP (float) --
The top-P sampling parameter for nucleus sampling.
topK (integer) --
The top-K sampling parameter for token selection.
maxTokensToSample (integer) --
The maximum number of tokens to generate in the response.
modifiedTime (datetime) --
The time the AI Prompt was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Prompt was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Prompt was last modified.
description (string) --
The description of the AI Prompt.
visibilityStatus (string) --
The visibility status of the AI Prompt.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
The origin of the AI Prompt. SYSTEM for a default AI Prompt created by Q in Connect or CUSTOMER for an AI Prompt created by calling AI Prompt creation APIs.
status (string) --
The status of the AI Prompt.
{'aiPrompt': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Creates an Amazon Q in Connect AI Prompt version.
See also: AWS API Documentation
Request Syntax
client.create_ai_prompt_version(
assistantId='string',
aiPromptId='string',
modifiedTime=datetime(2015, 1, 1),
clientToken='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI prompt.
datetime
The time the AI Prompt was last modified.
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
dict
Response Syntax
{
'aiPrompt': {
'assistantId': 'string',
'assistantArn': 'string',
'aiPromptId': 'string',
'aiPromptArn': 'string',
'name': 'string',
'type': 'ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'templateType': 'TEXT',
'modelId': 'string',
'apiFormat': 'ANTHROPIC_CLAUDE_MESSAGES'|'ANTHROPIC_CLAUDE_TEXT_COMPLETIONS'|'MESSAGES'|'TEXT_COMPLETIONS',
'templateConfiguration': {
'textFullAIPromptEditTemplateConfiguration': {
'text': 'string'
}
},
'inferenceConfiguration': {
'temperature': ...,
'topP': ...,
'topK': 123,
'maxTokensToSample': 123
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
},
'versionNumber': 123
}
Response Structure
(dict) --
aiPrompt (dict) --
The data of the AI Prompt version.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiPromptId (string) --
The identifier of the Amazon Q in Connect AI prompt.
aiPromptArn (string) --
The Amazon Resource Name (ARN) of the AI Prompt.
name (string) --
The name of the AI Prompt
type (string) --
The type of this AI Prompt.
templateType (string) --
The type of the prompt template for this AI Prompt.
modelId (string) --
The identifier of the model used for this AI Prompt. The following model Ids are supported:
anthropic.claude-3-haiku--v1:0
apac.amazon.nova-lite-v1:0
apac.amazon.nova-micro-v1:0
apac.amazon.nova-pro-v1:0
apac.anthropic.claude-3-5-sonnet--v2:0
apac.anthropic.claude-3-haiku-20240307-v1:0
eu.amazon.nova-lite-v1:0
eu.amazon.nova-micro-v1:0
eu.amazon.nova-pro-v1:0
eu.anthropic.claude-3-7-sonnet-20250219-v1:0
eu.anthropic.claude-3-haiku-20240307-v1:0
us.amazon.nova-lite-v1:0
us.amazon.nova-micro-v1:0
us.amazon.nova-pro-v1:0
us.anthropic.claude-3-5-haiku-20241022-v1:0
us.anthropic.claude-3-7-sonnet-20250219-v1:0
us.anthropic.claude-3-haiku-20240307-v1:0
apiFormat (string) --
The API format used for this AI Prompt.
templateConfiguration (dict) --
The configuration of the prompt template for this AI Prompt.
textFullAIPromptEditTemplateConfiguration (dict) --
The configuration for a prompt template that supports full textual prompt configuration using a YAML prompt.
text (string) --
The YAML text for the AI Prompt template.
inferenceConfiguration (dict) --
The configuration for inference parameters when using the AI Prompt.
temperature (float) --
The temperature setting for controlling randomness in the generated response.
topP (float) --
The top-P sampling parameter for nucleus sampling.
topK (integer) --
The top-K sampling parameter for token selection.
maxTokensToSample (integer) --
The maximum number of tokens to generate in the response.
modifiedTime (datetime) --
The time the AI Prompt was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Prompt was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Prompt was last modified.
description (string) --
The description of the AI Prompt.
visibilityStatus (string) --
The visibility status of the AI Prompt.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
The origin of the AI Prompt. SYSTEM for a default AI Prompt created by Q in Connect or CUSTOMER for an AI Prompt created by calling AI Prompt creation APIs.
status (string) --
The status of the AI Prompt.
versionNumber (integer) --
The version number of the AI Prompt version.
{'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}
Response {'assistant': {'assistantGlobalResiliencyStatus': 'ENABLED | DISABLED',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Creates an Amazon Q in Connect assistant.
See also: AWS API Documentation
Request Syntax
client.create_assistant(
clientToken='string',
name='string',
type='AGENT',
description='string',
tags={
'string': 'string'
},
serverSideEncryptionConfiguration={
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
}
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs.
This field is autopopulated if not provided.
string
[REQUIRED]
The name of the assistant.
string
[REQUIRED]
The type of assistant.
string
The description of the assistant.
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
dict
The configuration information for the customer managed key used for encryption.
The customer managed key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect. To use Amazon Q in Connect with chat, the key policy must also allow kms:Decrypt, kms:GenerateDataKey*, and kms:DescribeKey permissions to the connect.amazonaws.com service principal.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
dict
Response Syntax
{
'assistant': {
'assistantId': 'string',
'assistantArn': 'string',
'name': 'string',
'type': 'AGENT',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'description': 'string',
'tags': {
'string': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'integrationConfiguration': {
'topicIntegrationArn': 'string'
},
'capabilityConfiguration': {
'type': 'V1'|'V2'
},
'aiAgentConfiguration': {
'string': {
'aiAgentId': 'string',
'enabled': True|False
}
},
'orchestratorConfigurationList': [
{
'aiAgentId': 'string',
'orchestratorUseCase': 'string'
},
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'assistantGlobalResiliencyStatus': 'ENABLED'|'DISABLED'
}
}
Response Structure
(dict) --
assistant (dict) --
Information about the assistant.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
name (string) --
The name.
type (string) --
The type of assistant.
status (string) --
The status of the assistant.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect. To use Amazon Q in Connect with chat, the key policy must also allow kms:Decrypt, kms:GenerateDataKey*, and kms:DescribeKey permissions to the connect.amazonaws.com service principal.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
integrationConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant integration.
topicIntegrationArn (string) --
The Amazon Resource Name (ARN) of the integrated Amazon SNS topic used for streaming chat messages.
capabilityConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant capability.
type (string) --
The type of Amazon Q in Connect assistant capability.
aiAgentConfiguration (dict) --
The configuration of the AI Agents (mapped by AI Agent Type to AI Agent version) that is set on the Amazon Q in Connect Assistant.
(string) --
(dict) --
A type that specifies the AI Agent ID configuration data when mapping an AI Agents to be used for an AI Agent type on a session or assistant.
aiAgentId (string) --
The ID of the AI Agent to be configured.
enabled (boolean) --
Indicates whether the AI Agent configured for this AI Agent type is enabled. When this value is omitted or set to true, the configured AI Agent runs; when set to false, the AI Agent ID is retained but no AI Agent runs for the AI Agent type. Setting this value to false is currently supported only for the ANSWER_RECOMMENDATION AI Agent type; other requests to set it to false are rejected with a validation error.
orchestratorConfigurationList (list) --
The list of orchestrator configurations for the assistant.
(dict) --
An entry in the orchestrator configuration list.
aiAgentId (string) --
The identifier of the AI Agent in the orchestrator configuration.
orchestratorUseCase (string) --
The use case for the orchestrator configuration. (for example Connect.SelfService, Connect.AgentAssistance)
lastModifiedTime (datetime) --
The timestamp when the assistant was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant was last modified.
assistantGlobalResiliencyStatus (string) --
Whether Amazon Connect Global Resiliency replicates the Connect instance this assistant is associated with, and so whether resources created under this assistant must satisfy the replication group's model parity constraint. Answered from the ACGR side per request rather than stored, so it reflects the customer's replication state now.
Absent means "not applicable or not known" - never read an absent field as DISABLED. It is absent on the operations that return an assistant which is not yet associated with a Connect instance, because replication cannot be established until it is.
{'assistantAssociation': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Creates an association between an Amazon Q in Connect assistant and another resource. Currently, the only supported association is with a knowledge base. An assistant can have only a single association.
See also: AWS API Documentation
Request Syntax
client.create_assistant_association(
assistantId='string',
associationType='KNOWLEDGE_BASE'|'EXTERNAL_BEDROCK_KNOWLEDGE_BASE',
association={
'knowledgeBaseId': 'string',
'externalBedrockKnowledgeBaseConfig': {
'bedrockKnowledgeBaseArn': 'string',
'accessRoleArn': 'string'
}
},
clientToken='string',
tags={
'string': 'string'
}
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The type of association.
dict
[REQUIRED]
The identifier of the associated resource.
knowledgeBaseId (string) --
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base.
externalBedrockKnowledgeBaseConfig (dict) --
The configuration for an external Bedrock knowledge base association.
bedrockKnowledgeBaseArn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the external Bedrock knowledge base.
accessRoleArn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the IAM role used to access the external Bedrock knowledge base.
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs.
This field is autopopulated if not provided.
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
dict
Response Syntax
{
'assistantAssociation': {
'assistantAssociationId': 'string',
'assistantAssociationArn': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'associationType': 'KNOWLEDGE_BASE'|'EXTERNAL_BEDROCK_KNOWLEDGE_BASE',
'associationData': {
'knowledgeBaseAssociation': {
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string'
},
'externalBedrockKnowledgeBaseConfig': {
'bedrockKnowledgeBaseArn': 'string',
'accessRoleArn': 'string'
}
},
'tags': {
'string': 'string'
},
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
assistantAssociation (dict) --
The assistant association.
assistantAssociationId (string) --
The identifier of the assistant association.
assistantAssociationArn (string) --
The Amazon Resource Name (ARN) of the assistant association.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
associationType (string) --
The type of association.
associationData (dict) --
A union type that currently has a single argument, the knowledge base ID.
knowledgeBaseAssociation (dict) --
The knowledge base where output data is sent.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
externalBedrockKnowledgeBaseConfig (dict) --
The configuration for an external Bedrock knowledge base association in the output data.
bedrockKnowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the external Bedrock knowledge base.
accessRoleArn (string) --
The Amazon Resource Name (ARN) of the IAM role used to access the external Bedrock knowledge base.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
lastModifiedTime (datetime) --
The timestamp when the assistant association was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant association was last modified.
{'content': {'fileHash': 'string',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Creates Amazon Q in Connect content. Before to calling this API, use StartContentUpload to upload an asset.
See also: AWS API Documentation
Request Syntax
client.create_content(
knowledgeBaseId='string',
name='string',
title='string',
overrideLinkOutUri='string',
metadata={
'string': 'string'
},
uploadId='string',
clientToken='string',
tags={
'string': 'string'
}
)
string
[REQUIRED]
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The name of the content. Each piece of content in a knowledge base must have a unique name. You can retrieve a piece of content using only its knowledge base and its name with the SearchContent API.
string
The title of the content. If not set, the title is equal to the name.
string
The URI you want to use for the article. If the knowledge base has a templateUri, setting this argument overrides it for this piece of content.
dict
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
string
[REQUIRED]
A pointer to the uploaded asset. This value is returned by StartContentUpload.
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs.
This field is autopopulated if not provided.
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
dict
Response Syntax
{
'content': {
'contentArn': 'string',
'contentId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'revisionId': 'string',
'title': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_FAILED',
'metadata': {
'string': 'string'
},
'tags': {
'string': 'string'
},
'linkOutUri': 'string',
'url': 'string',
'urlExpiry': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'fileHash': 'string'
}
}
Response Structure
(dict) --
content (dict) --
The content.
contentArn (string) --
The Amazon Resource Name (ARN) of the content.
contentId (string) --
The identifier of the content.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
name (string) --
The name of the content.
revisionId (string) --
The identifier of the content revision.
title (string) --
The title of the content.
contentType (string) --
The media type of the content.
status (string) --
The status of the content.
metadata (dict) --
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
linkOutUri (string) --
The URI of the content.
url (string) --
The URL of the content.
urlExpiry (datetime) --
The expiration time of the URL as an epoch timestamp.
lastModifiedTime (datetime) --
The timestamp when the content was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the content was last modified.
fileHash (string) --
The Base64-encoded SHA-256 hash of the content file. Amazon Connect Global Resiliency returns this field only for replicated content.
{'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}
Response {'knowledgeBase': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Creates a knowledge base.
See also: AWS API Documentation
Request Syntax
client.create_knowledge_base(
clientToken='string',
name='string',
knowledgeBaseType='EXTERNAL'|'CUSTOM'|'QUICK_RESPONSES'|'MESSAGE_TEMPLATES'|'MANAGED',
sourceConfiguration={
'appIntegrations': {
'appIntegrationArn': 'string',
'objectFields': [
'string',
]
},
'managedSourceConfiguration': {
'webCrawlerConfiguration': {
'urlConfiguration': {
'seedUrls': [
{
'url': 'string'
},
]
},
'crawlerLimits': {
'rateLimit': 123
},
'inclusionFilters': [
'string',
],
'exclusionFilters': [
'string',
],
'scope': 'HOST_ONLY'|'SUBDOMAINS'
}
}
},
renderingConfiguration={
'templateUri': 'string'
},
vectorIngestionConfiguration={
'chunkingConfiguration': {
'chunkingStrategy': 'FIXED_SIZE'|'NONE'|'HIERARCHICAL'|'SEMANTIC',
'fixedSizeChunkingConfiguration': {
'maxTokens': 123,
'overlapPercentage': 123
},
'hierarchicalChunkingConfiguration': {
'levelConfigurations': [
{
'maxTokens': 123
},
],
'overlapTokens': 123
},
'semanticChunkingConfiguration': {
'maxTokens': 123,
'bufferSize': 123,
'breakpointPercentileThreshold': 123
}
},
'parsingConfiguration': {
'parsingStrategy': 'BEDROCK_FOUNDATION_MODEL',
'bedrockFoundationModelConfiguration': {
'modelArn': 'string',
'parsingPrompt': {
'parsingPromptText': 'string'
}
}
}
},
serverSideEncryptionConfiguration={
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
description='string',
tags={
'string': 'string'
}
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs.
This field is autopopulated if not provided.
string
[REQUIRED]
The name of the knowledge base.
string
[REQUIRED]
The type of knowledge base. Only CUSTOM knowledge bases allow you to upload your own content. EXTERNAL knowledge bases support integrations with third-party systems whose content is synchronized automatically.
dict
The source of the knowledge base content. Only set this argument for EXTERNAL or Managed knowledge bases.
appIntegrations (dict) --
Configuration information for Amazon AppIntegrations to automatically ingest content.
appIntegrationArn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content.
For Salesforce, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted as source fields.
For ServiceNow, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least number, short_description, sys_mod_count, workflow_state, and active as source fields.
For Zendesk, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least id, title, updated_at, and draft as source fields.
For SharePoint, your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are among docx, pdf, html, htm, and txt.
For Amazon S3, the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. The SourceURI of your DataIntegration must use the following format: s3://your_s3_bucket_name.
objectFields (list) --
The fields from the source that are made available to your agents in Amazon Q in Connect. Optional if ObjectConfiguration is included in the provided DataIntegration.
For Salesforce, you must include at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted.
For ServiceNow, you must include at least number, short_description, sys_mod_count, workflow_state, and active.
For Zendesk, you must include at least id, title, updated_at, and draft.
Make sure to include additional fields. These fields are indexed and used to source recommendations.
(string) --
managedSourceConfiguration (dict) --
Source configuration for managed resources.
webCrawlerConfiguration (dict) --
Configuration data for web crawler data source.
urlConfiguration (dict) -- [REQUIRED]
The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.
seedUrls (list) --
List of URLs for crawling.
(dict) --
A URL for crawling.
url (string) --
URL for crawling
crawlerLimits (dict) --
The configuration of crawl limits for the web URLs.
rateLimit (integer) --
Rate of web URLs retrieved per minute.
inclusionFilters (list) --
A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
exclusionFilters (list) --
A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
scope (string) --
The scope of what is crawled for your URLs. You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL https://docs.aws.amazon.com/bedrock/latest/userguide/ and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain aws.amazon.com can also include sub domain docs.aws.amazon.com.
dict
Information about how to render the content.
templateUri (string) --
A URI template containing exactly one variable in ${variableName} ``format. This can only be set for ``EXTERNAL knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following:
Salesforce: Id, ArticleNumber, VersionNumber, Title, PublishStatus, or IsDeleted
ServiceNow: number, short_description, sys_mod_count, workflow_state, or active
Zendesk: id, title, updated_at, or draft
The variable is replaced with the actual value for a piece of content when calling GetContent.
dict
Contains details about how to ingest the documents in a data source.
chunkingConfiguration (dict) --
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
chunkingStrategy (string) -- [REQUIRED]
Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
fixedSizeChunkingConfiguration (dict) --
Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as NONE, exclude this field.
maxTokens (integer) -- [REQUIRED]
The maximum number of tokens to include in a chunk.
overlapPercentage (integer) -- [REQUIRED]
The percentage of overlap between adjacent chunks of a data source.
hierarchicalChunkingConfiguration (dict) --
Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
levelConfigurations (list) -- [REQUIRED]
Token settings for each layer.
(dict) --
Token settings for each layer.
maxTokens (integer) -- [REQUIRED]
The maximum number of tokens that a chunk can contain in this layer.
overlapTokens (integer) -- [REQUIRED]
The number of tokens to repeat across chunks in the same layer.
semanticChunkingConfiguration (dict) --
Settings for semantic document chunking for a data source. Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
maxTokens (integer) -- [REQUIRED]
The maximum number of tokens that a chunk can contain.
bufferSize (integer) -- [REQUIRED]
The buffer size.
breakpointPercentileThreshold (integer) -- [REQUIRED]
The dissimilarity threshold for splitting chunks.
parsingConfiguration (dict) --
A custom parser for data source documents.
parsingStrategy (string) -- [REQUIRED]
The parsing strategy for the data source.
bedrockFoundationModelConfiguration (dict) --
Settings for a foundation model used to parse documents for a data source.
modelArn (string) -- [REQUIRED]
The ARN of the foundation model.
parsingPrompt (dict) --
Instructions for interpreting the contents of a document.
parsingPromptText (string) -- [REQUIRED]
Instructions for interpreting the contents of a document.
dict
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
string
The description.
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
dict
Response Syntax
{
'knowledgeBase': {
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string',
'name': 'string',
'knowledgeBaseType': 'EXTERNAL'|'CUSTOM'|'QUICK_RESPONSES'|'MESSAGE_TEMPLATES'|'MANAGED',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'lastContentModificationTime': datetime(2015, 1, 1),
'vectorIngestionConfiguration': {
'chunkingConfiguration': {
'chunkingStrategy': 'FIXED_SIZE'|'NONE'|'HIERARCHICAL'|'SEMANTIC',
'fixedSizeChunkingConfiguration': {
'maxTokens': 123,
'overlapPercentage': 123
},
'hierarchicalChunkingConfiguration': {
'levelConfigurations': [
{
'maxTokens': 123
},
],
'overlapTokens': 123
},
'semanticChunkingConfiguration': {
'maxTokens': 123,
'bufferSize': 123,
'breakpointPercentileThreshold': 123
}
},
'parsingConfiguration': {
'parsingStrategy': 'BEDROCK_FOUNDATION_MODEL',
'bedrockFoundationModelConfiguration': {
'modelArn': 'string',
'parsingPrompt': {
'parsingPromptText': 'string'
}
}
}
},
'sourceConfiguration': {
'appIntegrations': {
'appIntegrationArn': 'string',
'objectFields': [
'string',
]
},
'managedSourceConfiguration': {
'webCrawlerConfiguration': {
'urlConfiguration': {
'seedUrls': [
{
'url': 'string'
},
]
},
'crawlerLimits': {
'rateLimit': 123
},
'inclusionFilters': [
'string',
],
'exclusionFilters': [
'string',
],
'scope': 'HOST_ONLY'|'SUBDOMAINS'
}
}
},
'renderingConfiguration': {
'templateUri': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'description': 'string',
'tags': {
'string': 'string'
},
'ingestionStatus': 'SYNC_FAILED'|'SYNCING_IN_PROGRESS'|'SYNC_SUCCESS'|'CREATE_IN_PROGRESS',
'ingestionFailureReasons': [
'string',
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
knowledgeBase (dict) --
The knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
name (string) --
The name of the knowledge base.
knowledgeBaseType (string) --
The type of knowledge base.
status (string) --
The status of the knowledge base.
lastContentModificationTime (datetime) --
An epoch timestamp indicating the most recent content modification inside the knowledge base. If no content exists in a knowledge base, this value is unset.
vectorIngestionConfiguration (dict) --
Contains details about how to ingest the documents in a data source.
chunkingConfiguration (dict) --
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
chunkingStrategy (string) --
Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
fixedSizeChunkingConfiguration (dict) --
Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as NONE, exclude this field.
maxTokens (integer) --
The maximum number of tokens to include in a chunk.
overlapPercentage (integer) --
The percentage of overlap between adjacent chunks of a data source.
hierarchicalChunkingConfiguration (dict) --
Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
levelConfigurations (list) --
Token settings for each layer.
(dict) --
Token settings for each layer.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain in this layer.
overlapTokens (integer) --
The number of tokens to repeat across chunks in the same layer.
semanticChunkingConfiguration (dict) --
Settings for semantic document chunking for a data source. Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain.
bufferSize (integer) --
The buffer size.
breakpointPercentileThreshold (integer) --
The dissimilarity threshold for splitting chunks.
parsingConfiguration (dict) --
A custom parser for data source documents.
parsingStrategy (string) --
The parsing strategy for the data source.
bedrockFoundationModelConfiguration (dict) --
Settings for a foundation model used to parse documents for a data source.
modelArn (string) --
The ARN of the foundation model.
parsingPrompt (dict) --
Instructions for interpreting the contents of a document.
parsingPromptText (string) --
Instructions for interpreting the contents of a document.
sourceConfiguration (dict) --
Source configuration information about the knowledge base.
appIntegrations (dict) --
Configuration information for Amazon AppIntegrations to automatically ingest content.
appIntegrationArn (string) --
The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content.
For Salesforce, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted as source fields.
For ServiceNow, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least number, short_description, sys_mod_count, workflow_state, and active as source fields.
For Zendesk, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least id, title, updated_at, and draft as source fields.
For SharePoint, your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are among docx, pdf, html, htm, and txt.
For Amazon S3, the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. The SourceURI of your DataIntegration must use the following format: s3://your_s3_bucket_name.
objectFields (list) --
The fields from the source that are made available to your agents in Amazon Q in Connect. Optional if ObjectConfiguration is included in the provided DataIntegration.
For Salesforce, you must include at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted.
For ServiceNow, you must include at least number, short_description, sys_mod_count, workflow_state, and active.
For Zendesk, you must include at least id, title, updated_at, and draft.
Make sure to include additional fields. These fields are indexed and used to source recommendations.
(string) --
managedSourceConfiguration (dict) --
Source configuration for managed resources.
webCrawlerConfiguration (dict) --
Configuration data for web crawler data source.
urlConfiguration (dict) --
The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.
seedUrls (list) --
List of URLs for crawling.
(dict) --
A URL for crawling.
url (string) --
URL for crawling
crawlerLimits (dict) --
The configuration of crawl limits for the web URLs.
rateLimit (integer) --
Rate of web URLs retrieved per minute.
inclusionFilters (list) --
A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
exclusionFilters (list) --
A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
scope (string) --
The scope of what is crawled for your URLs. You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL https://docs.aws.amazon.com/bedrock/latest/userguide/ and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain aws.amazon.com can also include sub domain docs.aws.amazon.com.
renderingConfiguration (dict) --
Information about how to render the content.
templateUri (string) --
A URI template containing exactly one variable in ${variableName} ``format. This can only be set for ``EXTERNAL knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following:
Salesforce: Id, ArticleNumber, VersionNumber, Title, PublishStatus, or IsDeleted
ServiceNow: number, short_description, sys_mod_count, workflow_state, or active
Zendesk: id, title, updated_at, or draft
The variable is replaced with the actual value for a piece of content when calling GetContent.
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
ingestionStatus (string) --
Status of ingestion on data source.
ingestionFailureReasons (list) --
List of failure reasons on ingestion per file.
(string) --
lastModifiedTime (datetime) --
The timestamp when the knowledge base was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the knowledge base was last modified.
{'quickResponse': {'lastModifiedRegion': 'string'}}
Creates an Amazon Q in Connect quick response.
See also: AWS API Documentation
Request Syntax
client.create_quick_response(
knowledgeBaseId='string',
name='string',
content={
'content': 'string'
},
contentType='string',
groupingConfiguration={
'criteria': 'string',
'values': [
'string',
]
},
description='string',
shortcutKey='string',
isActive=True|False,
channels=[
'string',
],
language='string',
clientToken='string',
tags={
'string': 'string'
}
)
string
[REQUIRED]
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The name of the quick response.
dict
[REQUIRED]
The content of the quick response.
content (string) --
The content of the quick response.
string
The media type of the quick response content.
Use application/x.quickresponse;format=plain for a quick response written in plain text.
Use application/x.quickresponse;format=markdown for a quick response written in richtext.
dict
The configuration information of the user groups that the quick response is accessible to.
criteria (string) --
The criteria used for grouping Amazon Q in Connect users.
The following is the list of supported criteria values.
RoutingProfileArn: Grouping the users by their Amazon Connect routing profile ARN. User should have SearchRoutingProfile and DescribeRoutingProfile permissions when setting criteria to this value.
values (list) --
The list of values that define different groups of Amazon Q in Connect users.
When setting criteria to RoutingProfileArn, you need to provide a list of ARNs of Connect Customer routing profiles as values of this parameter.
(string) --
string
The description of the quick response.
string
The shortcut key of the quick response. The value should be unique across the knowledge base.
boolean
Whether the quick response is active.
list
The Connect Customer channels this quick response applies to.
(string) --
string
The language code value for the language in which the quick response is written. The supported language codes include de_DE, en_US, es_ES, fr_FR, id_ID, it_IT, ja_JP, ko_KR, pt_BR, zh_CN, zh_TW
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs.
This field is autopopulated if not provided.
dict
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
dict
Response Syntax
{
'quickResponse': {
'quickResponseArn': 'string',
'quickResponseId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'CREATED'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_IN_PROGRESS'|'UPDATE_FAILED',
'createdTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'contents': {
'plainText': {
'content': 'string'
},
'markdown': {
'content': 'string'
}
},
'description': 'string',
'groupingConfiguration': {
'criteria': 'string',
'values': [
'string',
]
},
'shortcutKey': 'string',
'lastModifiedBy': 'string',
'isActive': True|False,
'channels': [
'string',
],
'language': 'string',
'tags': {
'string': 'string'
}
}
}
Response Structure
(dict) --
quickResponse (dict) --
The quick response.
quickResponseArn (string) --
The Amazon Resource Name (ARN) of the quick response.
quickResponseId (string) --
The identifier of the quick response.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
name (string) --
The name of the quick response.
contentType (string) --
The media type of the quick response content.
Use application/x.quickresponse;format=plain for quick response written in plain text.
Use application/x.quickresponse;format=markdown for quick response written in richtext.
status (string) --
The status of the quick response data.
createdTime (datetime) --
The timestamp when the quick response was created.
lastModifiedTime (datetime) --
The timestamp when the quick response data was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the quick response was last modified.
contents (dict) --
The contents of the quick response.
plainText (dict) --
The container quick response content.
content (string) --
The content of the quick response.
markdown (dict) --
The container quick response content.
content (string) --
The content of the quick response.
description (string) --
The description of the quick response.
groupingConfiguration (dict) --
The configuration information of the user groups that the quick response is accessible to.
criteria (string) --
The criteria used for grouping Amazon Q in Connect users.
The following is the list of supported criteria values.
RoutingProfileArn: Grouping the users by their Amazon Connect routing profile ARN. User should have SearchRoutingProfile and DescribeRoutingProfile permissions when setting criteria to this value.
values (list) --
The list of values that define different groups of Amazon Q in Connect users.
When setting criteria to RoutingProfileArn, you need to provide a list of ARNs of Connect Customer routing profiles as values of this parameter.
(string) --
shortcutKey (string) --
The shortcut key of the quick response. The value should be unique across the knowledge base.
lastModifiedBy (string) --
The Amazon Resource Name (ARN) of the user who last updated the quick response data.
isActive (boolean) --
Whether the quick response is active.
channels (list) --
The Connect Customer contact channels this quick response applies to. The supported contact channel types include Chat.
(string) --
language (string) --
The language code value for the language in which the quick response is written. The supported language codes include de_DE, en_US, es_ES, fr_FR, id_ID, it_IT, ja_JP, ko_KR, pt_BR, zh_CN, zh_TW
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
{'aiAgent': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Gets an Amazon Q in Connect AI Agent.
See also: AWS API Documentation
Request Syntax
client.get_ai_agent(
assistantId='string',
aiAgentId='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Agent (with or without a version qualifier). Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'aiAgent': {
'assistantId': 'string',
'assistantArn': 'string',
'aiAgentId': 'string',
'aiAgentArn': 'string',
'name': 'string',
'type': 'MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'configuration': {
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
},
'versionNumber': 123
}
Response Structure
(dict) --
aiAgent (dict) --
The data of the AI Agent.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiAgentId (string) --
The identifier of the AI Agent.
aiAgentArn (string) --
The Amazon Resource Name (ARN) of the AI agent.
name (string) --
The name of the AI Agent.
type (string) --
The type of the AI Agent.
configuration (dict) --
Configuration for the AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) --
The name of the tool.
toolType (string) --
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) --
The JSON path for the input value override.
value (dict) --
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) --
Override tool input value with constant values
value (string) --
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) --
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) --
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) --
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
modifiedTime (datetime) --
The time the AI Agent was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Agent was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Agent was last modified.
description (string) --
The description of the AI Agent.
visibilityStatus (string) --
The visibility status of the AI Agent.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
Specifies the origin of the AI Agent. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
status (string) --
The status of the AI Agent.
versionNumber (integer) --
The version number of the AI Agent version (returned if an AI Agent version was specified via use of a qualifier for the aiAgentId on the request).
{'aiGuardrail': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Gets the Amazon Q in Connect AI Guardrail.
See also: AWS API Documentation
Request Syntax
client.get_ai_guardrail(
assistantId='string',
aiGuardrailId='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Guardrail.
dict
Response Syntax
{
'aiGuardrail': {
'assistantId': 'string',
'assistantArn': 'string',
'aiGuardrailArn': 'string',
'aiGuardrailId': 'string',
'name': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'blockedInputMessaging': 'string',
'blockedOutputsMessaging': 'string',
'description': 'string',
'topicPolicyConfig': {
'topicsConfig': [
{
'name': 'string',
'definition': 'string',
'examples': [
'string',
],
'type': 'DENY'
},
]
},
'contentPolicyConfig': {
'filtersConfig': [
{
'type': 'SEXUAL'|'VIOLENCE'|'HATE'|'INSULTS'|'MISCONDUCT'|'PROMPT_ATTACK',
'inputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'outputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH'
},
]
},
'wordPolicyConfig': {
'wordsConfig': [
{
'text': 'string'
},
],
'managedWordListsConfig': [
{
'type': 'PROFANITY'
},
]
},
'sensitiveInformationPolicyConfig': {
'piiEntitiesConfig': [
{
'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',
'action': 'BLOCK'|'ANONYMIZE'
},
],
'regexesConfig': [
{
'name': 'string',
'description': 'string',
'pattern': 'string',
'action': 'BLOCK'|'ANONYMIZE'
},
]
},
'contextualGroundingPolicyConfig': {
'filtersConfig': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0
},
]
},
'tags': {
'string': 'string'
},
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
},
'versionNumber': 123
}
Response Structure
(dict) --
aiGuardrail (dict) --
The data of the AI Guardrail.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiGuardrailArn (string) --
The Amazon Resource Name (ARN) of the AI Guardrail.
aiGuardrailId (string) --
The identifier of the Amazon Q in Connect AI Guardrail.
name (string) --
The name of the AI Guardrail.
visibilityStatus (string) --
The visibility status of the AI Guardrail.
blockedInputMessaging (string) --
The message to return when the AI Guardrail blocks a prompt.
blockedOutputsMessaging (string) --
The message to return when the AI Guardrail blocks a model response.
description (string) --
A description of the AI Guardrail.
topicPolicyConfig (dict) --
Contains details about topics that the AI Guardrail should identify and deny.
topicsConfig (list) --
A list of policies related to topics that the AI Guardrail should deny.
(dict) --
Details about topics for the AI Guardrail to identify and deny.
name (string) --
The name of the topic to deny.
definition (string) --
A definition of the topic to deny.
examples (list) --
A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
(string) --
Text example in topic policy
type (string) --
Specifies to deny the topic.
contentPolicyConfig (dict) --
Contains details about how to handle harmful content.
filtersConfig (list) --
Contains the type of the content filter and how strongly it should apply to prompts and model responses.
(dict) --
Contains filter strengths for harmful content. AI Guardrail's support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate: Describes input prompts and model responses that discriminate, criticize, insult, denounce, or dehumanize a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults: Describes input prompts and model responses that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual: Describes input prompts and model responses that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence: Describes input prompts and model responses that includes glorification of, or threats to inflict physical pain, hurt, or injury toward a person, group, or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
type (string) --
The harmful category that the content filter is applied to.
inputStrength (string) --
The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
outputStrength (string) --
The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
wordPolicyConfig (dict) --
Contains details about the word policy to configured for the AI Guardrail.
wordsConfig (list) --
A list of words to configure for the AI Guardrail.
(dict) --
A word to configure for the AI Guardrail.
text (string) --
Text of the word configured for the AI Guardrail to block.
managedWordListsConfig (list) --
A list of managed words to configure for the AI Guardrail.
(dict) --
The managed word list to configure for the AI Guardrail.
type (string) --
The managed word type to configure for the AI Guardrail.
sensitiveInformationPolicyConfig (dict) --
Contains details about PII entities and regular expressions to configure for the AI Guardrail.
piiEntitiesConfig (list) --
A list of PII entities to configure to the AI Guardrail.
(dict) --
The PII entity to configure for the AI Guardrail.
type (string) --
Configure AI Guardrail type when the PII entity is detected.
The following PIIs are used to block or mask sensitive information:
General
ADDRESS A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.
AGE An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guarrails recognizes "40 years" as an age.
NAME An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. AI Guardrail doesn't apply this entity type to names that are part of organizations or addresses. For example, AI Guardrail recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.
EMAIL An email address, such as marymajor@email.com.
PHONE A phone number. This entity type also includes fax and pager numbers.
USERNAME A user name that identifies an account, such as a login name, screen name, nick name, or handle.
PASSWORD An alphanumeric string that is used as a password, such as "** very20special#pass**".
DRIVER_ID The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.
LICENSE_PLATE A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.
VEHICLE_IDENTIFICATION_NUMBER A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.
Finance
CREDIT_DEBIT_CARD_CVV A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.
CREDIT_DEBIT_CARD_EXPIRY The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY. AI Guardrail recognizes expiration dates such as 01/21, 01/2021, and Jan 2021.
CREDIT_DEBIT_CARD_NUMBER The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.
PIN A four-digit personal identification number (PIN) with which you can access your bank account.
INTERNATIONAL_BANK_ACCOUNT_NUMBER An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure.
SWIFT_CODE A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers. SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.
IT
IP_ADDRESS An IPv4 address, such as 198.51.100.0.
MAC_ADDRESS A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).
URL A web address, such as www.example.com.
AWS_ACCESS_KEY A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
AWS_SECRET_KEY A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
USA specific
US_BANK_ACCOUNT_NUMBER A US bank account number, which is typically 10 to 12 digits long.
US_BANK_ROUTING_NUMBER A US bank account routing number. These are typically nine digits long,
US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.
US_PASSPORT_NUMBER A US passport number. Passport numbers range from six to nine alphanumeric characters.
US_SOCIAL_SECURITY_NUMBER A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.
Canada specific
CA_HEALTH_NUMBER A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.
CA_SOCIAL_INSURANCE_NUMBER A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits. The SIN is formatted as three groups of three digits, such as 123-456-789. A SIN can be validated through a simple check-digit process called the Luhn algorithm. For more information, see Luhn algorithm on the Wikipedia website.
UK Specific
UK_NATIONAL_HEALTH_SERVICE_NUMBER A UK National Health Service Number is a 10-17 digit number, such as 485 555 3456. The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.
UK_NATIONAL_INSURANCE_NUMBER A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system. The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.
UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.
Custom
Regex filter - You can use a regular expressions to define patterns for an AI Guardrail to recognize and act upon such as serial number, booking ID etc..
action (string) --
Configure AI Guardrail's action when the PII entity is detected.
regexesConfig (list) --
A list of regular expressions to configure to the AI Guardrail.
(dict) --
The regular expression to configure for the AI Guardrail.
name (string) --
The name of the regular expression to configure for the AI Guardrail.
description (string) --
The description of the regular expression to configure for the AI Guardrail.
pattern (string) --
The regular expression pattern to configure for the AI Guardrail.
action (string) --
The AI Guardrail action to configure when matching regular expression is detected.
contextualGroundingPolicyConfig (dict) --
The policy configuration details for the AI Guardrail's contextual grounding policy.
filtersConfig (list) --
The filter configuration details for the AI Guardrails contextual grounding policy.
(dict) --
The filter configuration details for the AI Guardrail's contextual grounding filter.
type (string) --
The filter type for the AI Guardrail's contextual grounding filter.
threshold (float) --
The threshold details for the AI Guardrail's contextual grounding filter.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
status (string) --
The status of the AI Guardrail.
modifiedTime (datetime) --
The time the AI Guardrail was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Guardrail was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Guardrail was last modified.
versionNumber (integer) --
The version number of the AI Guardrail version (returned if an AI Guardrail version was specified via use of a qualifier for the aiGuardrailId on the request).
{'aiPrompt': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Gets and Amazon Q in Connect AI Prompt.
See also: AWS API Documentation
Request Syntax
client.get_ai_prompt(
assistantId='string',
aiPromptId='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI prompt.
dict
Response Syntax
{
'aiPrompt': {
'assistantId': 'string',
'assistantArn': 'string',
'aiPromptId': 'string',
'aiPromptArn': 'string',
'name': 'string',
'type': 'ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'templateType': 'TEXT',
'modelId': 'string',
'apiFormat': 'ANTHROPIC_CLAUDE_MESSAGES'|'ANTHROPIC_CLAUDE_TEXT_COMPLETIONS'|'MESSAGES'|'TEXT_COMPLETIONS',
'templateConfiguration': {
'textFullAIPromptEditTemplateConfiguration': {
'text': 'string'
}
},
'inferenceConfiguration': {
'temperature': ...,
'topP': ...,
'topK': 123,
'maxTokensToSample': 123
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
},
'versionNumber': 123
}
Response Structure
(dict) --
aiPrompt (dict) --
The data of the AI Prompt.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiPromptId (string) --
The identifier of the Amazon Q in Connect AI prompt.
aiPromptArn (string) --
The Amazon Resource Name (ARN) of the AI Prompt.
name (string) --
The name of the AI Prompt
type (string) --
The type of this AI Prompt.
templateType (string) --
The type of the prompt template for this AI Prompt.
modelId (string) --
The identifier of the model used for this AI Prompt. The following model Ids are supported:
anthropic.claude-3-haiku--v1:0
apac.amazon.nova-lite-v1:0
apac.amazon.nova-micro-v1:0
apac.amazon.nova-pro-v1:0
apac.anthropic.claude-3-5-sonnet--v2:0
apac.anthropic.claude-3-haiku-20240307-v1:0
eu.amazon.nova-lite-v1:0
eu.amazon.nova-micro-v1:0
eu.amazon.nova-pro-v1:0
eu.anthropic.claude-3-7-sonnet-20250219-v1:0
eu.anthropic.claude-3-haiku-20240307-v1:0
us.amazon.nova-lite-v1:0
us.amazon.nova-micro-v1:0
us.amazon.nova-pro-v1:0
us.anthropic.claude-3-5-haiku-20241022-v1:0
us.anthropic.claude-3-7-sonnet-20250219-v1:0
us.anthropic.claude-3-haiku-20240307-v1:0
apiFormat (string) --
The API format used for this AI Prompt.
templateConfiguration (dict) --
The configuration of the prompt template for this AI Prompt.
textFullAIPromptEditTemplateConfiguration (dict) --
The configuration for a prompt template that supports full textual prompt configuration using a YAML prompt.
text (string) --
The YAML text for the AI Prompt template.
inferenceConfiguration (dict) --
The configuration for inference parameters when using the AI Prompt.
temperature (float) --
The temperature setting for controlling randomness in the generated response.
topP (float) --
The top-P sampling parameter for nucleus sampling.
topK (integer) --
The top-K sampling parameter for token selection.
maxTokensToSample (integer) --
The maximum number of tokens to generate in the response.
modifiedTime (datetime) --
The time the AI Prompt was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Prompt was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Prompt was last modified.
description (string) --
The description of the AI Prompt.
visibilityStatus (string) --
The visibility status of the AI Prompt.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
The origin of the AI Prompt. SYSTEM for a default AI Prompt created by Q in Connect or CUSTOMER for an AI Prompt created by calling AI Prompt creation APIs.
status (string) --
The status of the AI Prompt.
versionNumber (integer) --
The version number of the AI Prompt version (returned if an AI Prompt version was specified via use of a qualifier for the aiPromptId on the request).
{'assistant': {'assistantGlobalResiliencyStatus': 'ENABLED | DISABLED',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Retrieves information about an assistant.
See also: AWS API Documentation
Request Syntax
client.get_assistant(
assistantId='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'assistant': {
'assistantId': 'string',
'assistantArn': 'string',
'name': 'string',
'type': 'AGENT',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'description': 'string',
'tags': {
'string': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'integrationConfiguration': {
'topicIntegrationArn': 'string'
},
'capabilityConfiguration': {
'type': 'V1'|'V2'
},
'aiAgentConfiguration': {
'string': {
'aiAgentId': 'string',
'enabled': True|False
}
},
'orchestratorConfigurationList': [
{
'aiAgentId': 'string',
'orchestratorUseCase': 'string'
},
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'assistantGlobalResiliencyStatus': 'ENABLED'|'DISABLED'
}
}
Response Structure
(dict) --
assistant (dict) --
Information about the assistant.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
name (string) --
The name.
type (string) --
The type of assistant.
status (string) --
The status of the assistant.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect. To use Amazon Q in Connect with chat, the key policy must also allow kms:Decrypt, kms:GenerateDataKey*, and kms:DescribeKey permissions to the connect.amazonaws.com service principal.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
integrationConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant integration.
topicIntegrationArn (string) --
The Amazon Resource Name (ARN) of the integrated Amazon SNS topic used for streaming chat messages.
capabilityConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant capability.
type (string) --
The type of Amazon Q in Connect assistant capability.
aiAgentConfiguration (dict) --
The configuration of the AI Agents (mapped by AI Agent Type to AI Agent version) that is set on the Amazon Q in Connect Assistant.
(string) --
(dict) --
A type that specifies the AI Agent ID configuration data when mapping an AI Agents to be used for an AI Agent type on a session or assistant.
aiAgentId (string) --
The ID of the AI Agent to be configured.
enabled (boolean) --
Indicates whether the AI Agent configured for this AI Agent type is enabled. When this value is omitted or set to true, the configured AI Agent runs; when set to false, the AI Agent ID is retained but no AI Agent runs for the AI Agent type. Setting this value to false is currently supported only for the ANSWER_RECOMMENDATION AI Agent type; other requests to set it to false are rejected with a validation error.
orchestratorConfigurationList (list) --
The list of orchestrator configurations for the assistant.
(dict) --
An entry in the orchestrator configuration list.
aiAgentId (string) --
The identifier of the AI Agent in the orchestrator configuration.
orchestratorUseCase (string) --
The use case for the orchestrator configuration. (for example Connect.SelfService, Connect.AgentAssistance)
lastModifiedTime (datetime) --
The timestamp when the assistant was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant was last modified.
assistantGlobalResiliencyStatus (string) --
Whether Amazon Connect Global Resiliency replicates the Connect instance this assistant is associated with, and so whether resources created under this assistant must satisfy the replication group's model parity constraint. Answered from the ACGR side per request rather than stored, so it reflects the customer's replication state now.
Absent means "not applicable or not known" - never read an absent field as DISABLED. It is absent on the operations that return an assistant which is not yet associated with a Connect instance, because replication cannot be established until it is.
{'assistantAssociation': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Retrieves information about an assistant association.
See also: AWS API Documentation
Request Syntax
client.get_assistant_association(
assistantAssociationId='string',
assistantId='string'
)
string
[REQUIRED]
The identifier of the assistant association. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'assistantAssociation': {
'assistantAssociationId': 'string',
'assistantAssociationArn': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'associationType': 'KNOWLEDGE_BASE'|'EXTERNAL_BEDROCK_KNOWLEDGE_BASE',
'associationData': {
'knowledgeBaseAssociation': {
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string'
},
'externalBedrockKnowledgeBaseConfig': {
'bedrockKnowledgeBaseArn': 'string',
'accessRoleArn': 'string'
}
},
'tags': {
'string': 'string'
},
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
assistantAssociation (dict) --
The assistant association.
assistantAssociationId (string) --
The identifier of the assistant association.
assistantAssociationArn (string) --
The Amazon Resource Name (ARN) of the assistant association.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
associationType (string) --
The type of association.
associationData (dict) --
A union type that currently has a single argument, the knowledge base ID.
knowledgeBaseAssociation (dict) --
The knowledge base where output data is sent.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
externalBedrockKnowledgeBaseConfig (dict) --
The configuration for an external Bedrock knowledge base association in the output data.
bedrockKnowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the external Bedrock knowledge base.
accessRoleArn (string) --
The Amazon Resource Name (ARN) of the IAM role used to access the external Bedrock knowledge base.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
lastModifiedTime (datetime) --
The timestamp when the assistant association was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant association was last modified.
{'content': {'fileHash': 'string',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Retrieves content, including a pre-signed URL to download the content.
See also: AWS API Documentation
Request Syntax
client.get_content(
contentId='string',
knowledgeBaseId='string'
)
string
[REQUIRED]
The identifier of the content. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'content': {
'contentArn': 'string',
'contentId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'revisionId': 'string',
'title': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_FAILED',
'metadata': {
'string': 'string'
},
'tags': {
'string': 'string'
},
'linkOutUri': 'string',
'url': 'string',
'urlExpiry': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'fileHash': 'string'
}
}
Response Structure
(dict) --
content (dict) --
The content.
contentArn (string) --
The Amazon Resource Name (ARN) of the content.
contentId (string) --
The identifier of the content.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
name (string) --
The name of the content.
revisionId (string) --
The identifier of the content revision.
title (string) --
The title of the content.
contentType (string) --
The media type of the content.
status (string) --
The status of the content.
metadata (dict) --
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
linkOutUri (string) --
The URI of the content.
url (string) --
The URL of the content.
urlExpiry (datetime) --
The expiration time of the URL as an epoch timestamp.
lastModifiedTime (datetime) --
The timestamp when the content was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the content was last modified.
fileHash (string) --
The Base64-encoded SHA-256 hash of the content file. Amazon Connect Global Resiliency returns this field only for replicated content.
{'contentSummary': {'fileHash': 'string',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Retrieves summary information about the content.
See also: AWS API Documentation
Request Syntax
client.get_content_summary(
contentId='string',
knowledgeBaseId='string'
)
string
[REQUIRED]
The identifier of the content. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'contentSummary': {
'contentArn': 'string',
'contentId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'revisionId': 'string',
'title': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_FAILED',
'metadata': {
'string': 'string'
},
'tags': {
'string': 'string'
},
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'fileHash': 'string'
}
}
Response Structure
(dict) --
contentSummary (dict) --
The content summary.
contentArn (string) --
The Amazon Resource Name (ARN) of the content.
contentId (string) --
The identifier of the content.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base.
name (string) --
The name of the content.
revisionId (string) --
The identifier of the revision of the content.
title (string) --
The title of the content.
contentType (string) --
The media type of the content.
status (string) --
The status of the content.
metadata (dict) --
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
lastModifiedTime (datetime) --
The timestamp when the content was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the content was last modified.
fileHash (string) --
The Base64-encoded SHA-256 hash of the content file. Amazon Connect Global Resiliency returns this field only for replicated content.
{'knowledgeBase': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Retrieves information about the knowledge base.
See also: AWS API Documentation
Request Syntax
client.get_knowledge_base(
knowledgeBaseId='string'
)
string
[REQUIRED]
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'knowledgeBase': {
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string',
'name': 'string',
'knowledgeBaseType': 'EXTERNAL'|'CUSTOM'|'QUICK_RESPONSES'|'MESSAGE_TEMPLATES'|'MANAGED',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'lastContentModificationTime': datetime(2015, 1, 1),
'vectorIngestionConfiguration': {
'chunkingConfiguration': {
'chunkingStrategy': 'FIXED_SIZE'|'NONE'|'HIERARCHICAL'|'SEMANTIC',
'fixedSizeChunkingConfiguration': {
'maxTokens': 123,
'overlapPercentage': 123
},
'hierarchicalChunkingConfiguration': {
'levelConfigurations': [
{
'maxTokens': 123
},
],
'overlapTokens': 123
},
'semanticChunkingConfiguration': {
'maxTokens': 123,
'bufferSize': 123,
'breakpointPercentileThreshold': 123
}
},
'parsingConfiguration': {
'parsingStrategy': 'BEDROCK_FOUNDATION_MODEL',
'bedrockFoundationModelConfiguration': {
'modelArn': 'string',
'parsingPrompt': {
'parsingPromptText': 'string'
}
}
}
},
'sourceConfiguration': {
'appIntegrations': {
'appIntegrationArn': 'string',
'objectFields': [
'string',
]
},
'managedSourceConfiguration': {
'webCrawlerConfiguration': {
'urlConfiguration': {
'seedUrls': [
{
'url': 'string'
},
]
},
'crawlerLimits': {
'rateLimit': 123
},
'inclusionFilters': [
'string',
],
'exclusionFilters': [
'string',
],
'scope': 'HOST_ONLY'|'SUBDOMAINS'
}
}
},
'renderingConfiguration': {
'templateUri': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'description': 'string',
'tags': {
'string': 'string'
},
'ingestionStatus': 'SYNC_FAILED'|'SYNCING_IN_PROGRESS'|'SYNC_SUCCESS'|'CREATE_IN_PROGRESS',
'ingestionFailureReasons': [
'string',
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
knowledgeBase (dict) --
The knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
name (string) --
The name of the knowledge base.
knowledgeBaseType (string) --
The type of knowledge base.
status (string) --
The status of the knowledge base.
lastContentModificationTime (datetime) --
An epoch timestamp indicating the most recent content modification inside the knowledge base. If no content exists in a knowledge base, this value is unset.
vectorIngestionConfiguration (dict) --
Contains details about how to ingest the documents in a data source.
chunkingConfiguration (dict) --
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
chunkingStrategy (string) --
Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
fixedSizeChunkingConfiguration (dict) --
Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as NONE, exclude this field.
maxTokens (integer) --
The maximum number of tokens to include in a chunk.
overlapPercentage (integer) --
The percentage of overlap between adjacent chunks of a data source.
hierarchicalChunkingConfiguration (dict) --
Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
levelConfigurations (list) --
Token settings for each layer.
(dict) --
Token settings for each layer.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain in this layer.
overlapTokens (integer) --
The number of tokens to repeat across chunks in the same layer.
semanticChunkingConfiguration (dict) --
Settings for semantic document chunking for a data source. Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain.
bufferSize (integer) --
The buffer size.
breakpointPercentileThreshold (integer) --
The dissimilarity threshold for splitting chunks.
parsingConfiguration (dict) --
A custom parser for data source documents.
parsingStrategy (string) --
The parsing strategy for the data source.
bedrockFoundationModelConfiguration (dict) --
Settings for a foundation model used to parse documents for a data source.
modelArn (string) --
The ARN of the foundation model.
parsingPrompt (dict) --
Instructions for interpreting the contents of a document.
parsingPromptText (string) --
Instructions for interpreting the contents of a document.
sourceConfiguration (dict) --
Source configuration information about the knowledge base.
appIntegrations (dict) --
Configuration information for Amazon AppIntegrations to automatically ingest content.
appIntegrationArn (string) --
The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content.
For Salesforce, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted as source fields.
For ServiceNow, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least number, short_description, sys_mod_count, workflow_state, and active as source fields.
For Zendesk, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least id, title, updated_at, and draft as source fields.
For SharePoint, your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are among docx, pdf, html, htm, and txt.
For Amazon S3, the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. The SourceURI of your DataIntegration must use the following format: s3://your_s3_bucket_name.
objectFields (list) --
The fields from the source that are made available to your agents in Amazon Q in Connect. Optional if ObjectConfiguration is included in the provided DataIntegration.
For Salesforce, you must include at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted.
For ServiceNow, you must include at least number, short_description, sys_mod_count, workflow_state, and active.
For Zendesk, you must include at least id, title, updated_at, and draft.
Make sure to include additional fields. These fields are indexed and used to source recommendations.
(string) --
managedSourceConfiguration (dict) --
Source configuration for managed resources.
webCrawlerConfiguration (dict) --
Configuration data for web crawler data source.
urlConfiguration (dict) --
The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.
seedUrls (list) --
List of URLs for crawling.
(dict) --
A URL for crawling.
url (string) --
URL for crawling
crawlerLimits (dict) --
The configuration of crawl limits for the web URLs.
rateLimit (integer) --
Rate of web URLs retrieved per minute.
inclusionFilters (list) --
A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
exclusionFilters (list) --
A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
scope (string) --
The scope of what is crawled for your URLs. You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL https://docs.aws.amazon.com/bedrock/latest/userguide/ and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain aws.amazon.com can also include sub domain docs.aws.amazon.com.
renderingConfiguration (dict) --
Information about how to render the content.
templateUri (string) --
A URI template containing exactly one variable in ${variableName} ``format. This can only be set for ``EXTERNAL knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following:
Salesforce: Id, ArticleNumber, VersionNumber, Title, PublishStatus, or IsDeleted
ServiceNow: number, short_description, sys_mod_count, workflow_state, or active
Zendesk: id, title, updated_at, or draft
The variable is replaced with the actual value for a piece of content when calling GetContent.
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
ingestionStatus (string) --
Status of ingestion on data source.
ingestionFailureReasons (list) --
List of failure reasons on ingestion per file.
(string) --
lastModifiedTime (datetime) --
The timestamp when the knowledge base was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the knowledge base was last modified.
{'quickResponse': {'lastModifiedRegion': 'string'}}
Retrieves the quick response.
See also: AWS API Documentation
Request Syntax
client.get_quick_response(
quickResponseId='string',
knowledgeBaseId='string'
)
string
[REQUIRED]
The identifier of the quick response.
string
[REQUIRED]
The identifier of the knowledge base. This should be a QUICK_RESPONSES type knowledge base.
dict
Response Syntax
{
'quickResponse': {
'quickResponseArn': 'string',
'quickResponseId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'CREATED'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_IN_PROGRESS'|'UPDATE_FAILED',
'createdTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'contents': {
'plainText': {
'content': 'string'
},
'markdown': {
'content': 'string'
}
},
'description': 'string',
'groupingConfiguration': {
'criteria': 'string',
'values': [
'string',
]
},
'shortcutKey': 'string',
'lastModifiedBy': 'string',
'isActive': True|False,
'channels': [
'string',
],
'language': 'string',
'tags': {
'string': 'string'
}
}
}
Response Structure
(dict) --
quickResponse (dict) --
The quick response.
quickResponseArn (string) --
The Amazon Resource Name (ARN) of the quick response.
quickResponseId (string) --
The identifier of the quick response.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
name (string) --
The name of the quick response.
contentType (string) --
The media type of the quick response content.
Use application/x.quickresponse;format=plain for quick response written in plain text.
Use application/x.quickresponse;format=markdown for quick response written in richtext.
status (string) --
The status of the quick response data.
createdTime (datetime) --
The timestamp when the quick response was created.
lastModifiedTime (datetime) --
The timestamp when the quick response data was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the quick response was last modified.
contents (dict) --
The contents of the quick response.
plainText (dict) --
The container quick response content.
content (string) --
The content of the quick response.
markdown (dict) --
The container quick response content.
content (string) --
The content of the quick response.
description (string) --
The description of the quick response.
groupingConfiguration (dict) --
The configuration information of the user groups that the quick response is accessible to.
criteria (string) --
The criteria used for grouping Amazon Q in Connect users.
The following is the list of supported criteria values.
RoutingProfileArn: Grouping the users by their Amazon Connect routing profile ARN. User should have SearchRoutingProfile and DescribeRoutingProfile permissions when setting criteria to this value.
values (list) --
The list of values that define different groups of Amazon Q in Connect users.
When setting criteria to RoutingProfileArn, you need to provide a list of ARNs of Connect Customer routing profiles as values of this parameter.
(string) --
shortcutKey (string) --
The shortcut key of the quick response. The value should be unique across the knowledge base.
lastModifiedBy (string) --
The Amazon Resource Name (ARN) of the user who last updated the quick response data.
isActive (boolean) --
Whether the quick response is active.
channels (list) --
The Connect Customer contact channels this quick response applies to. The supported contact channel types include Chat.
(string) --
language (string) --
The language code value for the language in which the quick response is written. The supported language codes include de_DE, en_US, es_ES, fr_FR, id_ID, it_IT, ja_JP, ko_KR, pt_BR, zh_CN, zh_TW
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
{'aiAgentVersionSummaries': {'aiAgentSummary': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}}
List AI Agent versions.
See also: AWS API Documentation
Request Syntax
client.list_ai_agent_versions(
assistantId='string',
aiAgentId='string',
nextToken='string',
maxResults=123,
origin='SYSTEM'|'CUSTOMER'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Agent for which versions are to be listed.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
The origin of the AI Agent versions to be listed. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
dict
Response Syntax
{
'aiAgentVersionSummaries': [
{
'aiAgentSummary': {
'name': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'aiAgentId': 'string',
'type': 'MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'aiAgentArn': 'string',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'configuration': {
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
'origin': 'SYSTEM'|'CUSTOMER',
'description': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'tags': {
'string': 'string'
}
},
'versionNumber': 123
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
aiAgentVersionSummaries (list) --
The summaries of AI Agent versions.
(dict) --
The summary of the AI Agent version.
aiAgentSummary (dict) --
The data for the summary of the AI Agent version.
name (string) --
The name of the AI Agent.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiAgentId (string) --
The identifier of the AI Agent.
type (string) --
The type of the AI Agent.
aiAgentArn (string) --
The Amazon Resource Name (ARN) of the AI agent.
modifiedTime (datetime) --
The time the AI Agent was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Agent was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Agent was last modified.
visibilityStatus (string) --
The visibility status of the AI Agent.
configuration (dict) --
The configuration for the AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) --
The name of the tool.
toolType (string) --
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) --
The JSON path for the input value override.
value (dict) --
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) --
Override tool input value with constant values
value (string) --
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) --
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) --
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) --
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
origin (string) --
The origin of the AI Agent. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
description (string) --
The description of the AI Agent.
status (string) --
The status of the AI Agent.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
versionNumber (integer) --
The version number for this AI Agent version.
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'aiAgentSummaries': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Lists AI Agents.
See also: AWS API Documentation
Request Syntax
client.list_ai_agents(
assistantId='string',
nextToken='string',
maxResults=123,
origin='SYSTEM'|'CUSTOMER'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
The origin of the AI Agents to be listed. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
dict
Response Syntax
{
'aiAgentSummaries': [
{
'name': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'aiAgentId': 'string',
'type': 'MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'aiAgentArn': 'string',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'configuration': {
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
'origin': 'SYSTEM'|'CUSTOMER',
'description': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'tags': {
'string': 'string'
}
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
aiAgentSummaries (list) --
The summaries of AI Agents.
(dict) --
The summary of the AI Agent.
name (string) --
The name of the AI Agent.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiAgentId (string) --
The identifier of the AI Agent.
type (string) --
The type of the AI Agent.
aiAgentArn (string) --
The Amazon Resource Name (ARN) of the AI agent.
modifiedTime (datetime) --
The time the AI Agent was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Agent was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Agent was last modified.
visibilityStatus (string) --
The visibility status of the AI Agent.
configuration (dict) --
The configuration for the AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) --
The name of the tool.
toolType (string) --
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) --
The JSON path for the input value override.
value (dict) --
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) --
Override tool input value with constant values
value (string) --
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) --
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) --
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) --
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
origin (string) --
The origin of the AI Agent. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
description (string) --
The description of the AI Agent.
status (string) --
The status of the AI Agent.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'aiGuardrailVersionSummaries': {'aiGuardrailSummary': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}}
Lists AI Guardrail versions.
See also: AWS API Documentation
Request Syntax
client.list_ai_guardrail_versions(
assistantId='string',
aiGuardrailId='string',
nextToken='string',
maxResults=123
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Guardrail for which versions are to be listed.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
dict
Response Syntax
{
'aiGuardrailVersionSummaries': [
{
'aiGuardrailSummary': {
'name': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'aiGuardrailId': 'string',
'aiGuardrailArn': 'string',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'description': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'tags': {
'string': 'string'
}
},
'versionNumber': 123
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
aiGuardrailVersionSummaries (list) --
The summaries of the AI Guardrail versions.
(dict) --
The summary of the AI Guardrail version.
aiGuardrailSummary (dict) --
The data for the summary of the AI Guardrail version.
name (string) --
The name of the AI Guardrail.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiGuardrailId (string) --
The identifier of the Amazon Q in Connect AI Guardrail.
aiGuardrailArn (string) --
The Amazon Resource Name (ARN) of the AI Guardrail.
modifiedTime (datetime) --
The time the AI Guardrail was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Guardrail was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Guardrail was last modified.
visibilityStatus (string) --
The visibility status of the AI Guardrail.
description (string) --
A description of the AI Guardrail.
status (string) --
The status of the AI Guardrail.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
versionNumber (integer) --
The version number for this AI Guardrail version.
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'aiGuardrailSummaries': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Lists the AI Guardrails available on the Amazon Q in Connect assistant.
See also: AWS API Documentation
Request Syntax
client.list_ai_guardrails(
assistantId='string',
nextToken='string',
maxResults=123
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
dict
Response Syntax
{
'aiGuardrailSummaries': [
{
'name': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'aiGuardrailId': 'string',
'aiGuardrailArn': 'string',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'description': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'tags': {
'string': 'string'
}
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
aiGuardrailSummaries (list) --
The summaries of the AI Guardrails.
(dict) --
The summary of the AI Guardrail.
name (string) --
The name of the AI Guardrail.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiGuardrailId (string) --
The identifier of the Amazon Q in Connect AI Guardrail.
aiGuardrailArn (string) --
The Amazon Resource Name (ARN) of the AI Guardrail.
modifiedTime (datetime) --
The time the AI Guardrail was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Guardrail was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Guardrail was last modified.
visibilityStatus (string) --
The visibility status of the AI Guardrail.
description (string) --
A description of the AI Guardrail.
status (string) --
The status of the AI Guardrail.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'aiPromptVersionSummaries': {'aiPromptSummary': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}}
Lists AI Prompt versions.
See also: AWS API Documentation
Request Syntax
client.list_ai_prompt_versions(
assistantId='string',
aiPromptId='string',
nextToken='string',
maxResults=123,
origin='SYSTEM'|'CUSTOMER'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI prompt for which versions are to be listed.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
The origin of the AI Prompt versions to be listed. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
dict
Response Syntax
{
'aiPromptVersionSummaries': [
{
'aiPromptSummary': {
'name': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'aiPromptId': 'string',
'type': 'ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'aiPromptArn': 'string',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'templateType': 'TEXT',
'modelId': 'string',
'apiFormat': 'ANTHROPIC_CLAUDE_MESSAGES'|'ANTHROPIC_CLAUDE_TEXT_COMPLETIONS'|'MESSAGES'|'TEXT_COMPLETIONS',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'origin': 'SYSTEM'|'CUSTOMER',
'description': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'tags': {
'string': 'string'
}
},
'versionNumber': 123
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
aiPromptVersionSummaries (list) --
The summaries of the AI Prompt versions.
(dict) --
The summary of the AI Prompt version.
aiPromptSummary (dict) --
The date for the summary of the AI Prompt version.
name (string) --
The name of the AI Prompt.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiPromptId (string) --
The identifier of the Amazon Q in Connect AI prompt.
type (string) --
The type of this AI Prompt.
aiPromptArn (string) --
The Amazon Resource Name (ARN) of the AI Prompt.
modifiedTime (datetime) --
The time the AI Prompt was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Prompt was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Prompt was last modified.
templateType (string) --
The type of the prompt template for this AI Prompt.
modelId (string) --
The identifier of the model used for this AI Prompt. Model Ids supported are: anthropic.claude-3-haiku-20240307-v1:0.
apiFormat (string) --
The API format used for this AI Prompt.
visibilityStatus (string) --
The visibility status of the AI Prompt.
origin (string) --
The origin of the AI Prompt. SYSTEM for a default AI Prompt created by Q in Connect or CUSTOMER for an AI Prompt created by calling AI Prompt creation APIs.
description (string) --
The description of the AI Prompt.
status (string) --
The status of the AI Prompt.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
versionNumber (integer) --
The version number for this AI Prompt version.
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'aiPromptSummaries': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Lists the AI Prompts available on the Amazon Q in Connect assistant.
See also: AWS API Documentation
Request Syntax
client.list_ai_prompts(
assistantId='string',
nextToken='string',
maxResults=123,
origin='SYSTEM'|'CUSTOMER'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
The origin of the AI Prompts to be listed. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
dict
Response Syntax
{
'aiPromptSummaries': [
{
'name': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'aiPromptId': 'string',
'type': 'ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'aiPromptArn': 'string',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'templateType': 'TEXT',
'modelId': 'string',
'apiFormat': 'ANTHROPIC_CLAUDE_MESSAGES'|'ANTHROPIC_CLAUDE_TEXT_COMPLETIONS'|'MESSAGES'|'TEXT_COMPLETIONS',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'origin': 'SYSTEM'|'CUSTOMER',
'description': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'tags': {
'string': 'string'
}
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
aiPromptSummaries (list) --
The summaries of the AI Prompts.
(dict) --
The summary of the AI Prompt.
name (string) --
The name of the AI Prompt.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiPromptId (string) --
The identifier of the Amazon Q in Connect AI prompt.
type (string) --
The type of this AI Prompt.
aiPromptArn (string) --
The Amazon Resource Name (ARN) of the AI Prompt.
modifiedTime (datetime) --
The time the AI Prompt was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Prompt was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Prompt was last modified.
templateType (string) --
The type of the prompt template for this AI Prompt.
modelId (string) --
The identifier of the model used for this AI Prompt. Model Ids supported are: anthropic.claude-3-haiku-20240307-v1:0.
apiFormat (string) --
The API format used for this AI Prompt.
visibilityStatus (string) --
The visibility status of the AI Prompt.
origin (string) --
The origin of the AI Prompt. SYSTEM for a default AI Prompt created by Q in Connect or CUSTOMER for an AI Prompt created by calling AI Prompt creation APIs.
description (string) --
The description of the AI Prompt.
status (string) --
The status of the AI Prompt.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'assistantAssociationSummaries': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Lists information about assistant associations.
See also: AWS API Documentation
Request Syntax
client.list_assistant_associations(
nextToken='string',
maxResults=123,
assistantId='string'
)
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'assistantAssociationSummaries': [
{
'assistantAssociationId': 'string',
'assistantAssociationArn': 'string',
'assistantId': 'string',
'assistantArn': 'string',
'associationType': 'KNOWLEDGE_BASE'|'EXTERNAL_BEDROCK_KNOWLEDGE_BASE',
'associationData': {
'knowledgeBaseAssociation': {
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string'
},
'externalBedrockKnowledgeBaseConfig': {
'bedrockKnowledgeBaseArn': 'string',
'accessRoleArn': 'string'
}
},
'tags': {
'string': 'string'
},
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
assistantAssociationSummaries (list) --
Summary information about assistant associations.
(dict) --
Summary information about the assistant association.
assistantAssociationId (string) --
The identifier of the assistant association.
assistantAssociationArn (string) --
The Amazon Resource Name (ARN) of the assistant association.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
associationType (string) --
The type of association.
associationData (dict) --
The association data.
knowledgeBaseAssociation (dict) --
The knowledge base where output data is sent.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
externalBedrockKnowledgeBaseConfig (dict) --
The configuration for an external Bedrock knowledge base association in the output data.
bedrockKnowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the external Bedrock knowledge base.
accessRoleArn (string) --
The Amazon Resource Name (ARN) of the IAM role used to access the external Bedrock knowledge base.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
lastModifiedTime (datetime) --
The timestamp when the assistant association was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant association was last modified.
nextToken (string) --
If there are additional results, this is the token for the next set of results.
{'assistantSummaries': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Lists information about assistants.
See also: AWS API Documentation
Request Syntax
client.list_assistants(
nextToken='string',
maxResults=123
)
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
dict
Response Syntax
{
'assistantSummaries': [
{
'assistantId': 'string',
'assistantArn': 'string',
'name': 'string',
'type': 'AGENT',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'description': 'string',
'tags': {
'string': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'integrationConfiguration': {
'topicIntegrationArn': 'string'
},
'capabilityConfiguration': {
'type': 'V1'|'V2'
},
'aiAgentConfiguration': {
'string': {
'aiAgentId': 'string',
'enabled': True|False
}
},
'orchestratorConfigurationList': [
{
'aiAgentId': 'string',
'orchestratorUseCase': 'string'
},
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
assistantSummaries (list) --
Information about the assistants.
(dict) --
Summary information about the assistant.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
name (string) --
The name of the assistant.
type (string) --
The type of the assistant.
status (string) --
The status of the assistant.
description (string) --
The description of the assistant.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect. To use Amazon Q in Connect with chat, the key policy must also allow kms:Decrypt, kms:GenerateDataKey*, and kms:DescribeKey permissions to the connect.amazonaws.com service principal.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
integrationConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant integration.
topicIntegrationArn (string) --
The Amazon Resource Name (ARN) of the integrated Amazon SNS topic used for streaming chat messages.
capabilityConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant capability.
type (string) --
The type of Amazon Q in Connect assistant capability.
aiAgentConfiguration (dict) --
The configuration of the AI Agents (mapped by AI Agent Type to AI Agent version) that is set on the Amazon Q in Connect Assistant.
(string) --
(dict) --
A type that specifies the AI Agent ID configuration data when mapping an AI Agents to be used for an AI Agent type on a session or assistant.
aiAgentId (string) --
The ID of the AI Agent to be configured.
enabled (boolean) --
Indicates whether the AI Agent configured for this AI Agent type is enabled. When this value is omitted or set to true, the configured AI Agent runs; when set to false, the AI Agent ID is retained but no AI Agent runs for the AI Agent type. Setting this value to false is currently supported only for the ANSWER_RECOMMENDATION AI Agent type; other requests to set it to false are rejected with a validation error.
orchestratorConfigurationList (list) --
The list of orchestrator configurations for the assistant.
(dict) --
An entry in the orchestrator configuration list.
aiAgentId (string) --
The identifier of the AI Agent in the orchestrator configuration.
orchestratorUseCase (string) --
The use case for the orchestrator configuration. (for example Connect.SelfService, Connect.AgentAssistance)
lastModifiedTime (datetime) --
The timestamp when the assistant was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant was last modified.
nextToken (string) --
If there are additional results, this is the token for the next set of results.
{'contentSummaries': {'fileHash': 'string',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Lists the content.
See also: AWS API Documentation
Request Syntax
client.list_contents(
nextToken='string',
maxResults=123,
knowledgeBaseId='string'
)
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
[REQUIRED]
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'contentSummaries': [
{
'contentArn': 'string',
'contentId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'revisionId': 'string',
'title': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_FAILED',
'metadata': {
'string': 'string'
},
'tags': {
'string': 'string'
},
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'fileHash': 'string'
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
contentSummaries (list) --
Information about the content.
(dict) --
Summary information about the content.
contentArn (string) --
The Amazon Resource Name (ARN) of the content.
contentId (string) --
The identifier of the content.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base.
name (string) --
The name of the content.
revisionId (string) --
The identifier of the revision of the content.
title (string) --
The title of the content.
contentType (string) --
The media type of the content.
status (string) --
The status of the content.
metadata (dict) --
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
lastModifiedTime (datetime) --
The timestamp when the content was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the content was last modified.
fileHash (string) --
The Base64-encoded SHA-256 hash of the content file. Amazon Connect Global Resiliency returns this field only for replicated content.
nextToken (string) --
If there are additional results, this is the token for the next set of results.
{'knowledgeBaseSummaries': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Lists the knowledge bases.
See also: AWS API Documentation
Request Syntax
client.list_knowledge_bases(
nextToken='string',
maxResults=123
)
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
dict
Response Syntax
{
'knowledgeBaseSummaries': [
{
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string',
'name': 'string',
'knowledgeBaseType': 'EXTERNAL'|'CUSTOM'|'QUICK_RESPONSES'|'MESSAGE_TEMPLATES'|'MANAGED',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'sourceConfiguration': {
'appIntegrations': {
'appIntegrationArn': 'string',
'objectFields': [
'string',
]
},
'managedSourceConfiguration': {
'webCrawlerConfiguration': {
'urlConfiguration': {
'seedUrls': [
{
'url': 'string'
},
]
},
'crawlerLimits': {
'rateLimit': 123
},
'inclusionFilters': [
'string',
],
'exclusionFilters': [
'string',
],
'scope': 'HOST_ONLY'|'SUBDOMAINS'
}
}
},
'vectorIngestionConfiguration': {
'chunkingConfiguration': {
'chunkingStrategy': 'FIXED_SIZE'|'NONE'|'HIERARCHICAL'|'SEMANTIC',
'fixedSizeChunkingConfiguration': {
'maxTokens': 123,
'overlapPercentage': 123
},
'hierarchicalChunkingConfiguration': {
'levelConfigurations': [
{
'maxTokens': 123
},
],
'overlapTokens': 123
},
'semanticChunkingConfiguration': {
'maxTokens': 123,
'bufferSize': 123,
'breakpointPercentileThreshold': 123
}
},
'parsingConfiguration': {
'parsingStrategy': 'BEDROCK_FOUNDATION_MODEL',
'bedrockFoundationModelConfiguration': {
'modelArn': 'string',
'parsingPrompt': {
'parsingPromptText': 'string'
}
}
}
},
'renderingConfiguration': {
'templateUri': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'description': 'string',
'tags': {
'string': 'string'
},
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
knowledgeBaseSummaries (list) --
Information about the knowledge bases.
(dict) --
Summary information about the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
name (string) --
The name of the knowledge base.
knowledgeBaseType (string) --
The type of knowledge base.
status (string) --
The status of the knowledge base summary.
sourceConfiguration (dict) --
Configuration information about the external data source.
appIntegrations (dict) --
Configuration information for Amazon AppIntegrations to automatically ingest content.
appIntegrationArn (string) --
The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content.
For Salesforce, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted as source fields.
For ServiceNow, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least number, short_description, sys_mod_count, workflow_state, and active as source fields.
For Zendesk, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least id, title, updated_at, and draft as source fields.
For SharePoint, your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are among docx, pdf, html, htm, and txt.
For Amazon S3, the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. The SourceURI of your DataIntegration must use the following format: s3://your_s3_bucket_name.
objectFields (list) --
The fields from the source that are made available to your agents in Amazon Q in Connect. Optional if ObjectConfiguration is included in the provided DataIntegration.
For Salesforce, you must include at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted.
For ServiceNow, you must include at least number, short_description, sys_mod_count, workflow_state, and active.
For Zendesk, you must include at least id, title, updated_at, and draft.
Make sure to include additional fields. These fields are indexed and used to source recommendations.
(string) --
managedSourceConfiguration (dict) --
Source configuration for managed resources.
webCrawlerConfiguration (dict) --
Configuration data for web crawler data source.
urlConfiguration (dict) --
The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.
seedUrls (list) --
List of URLs for crawling.
(dict) --
A URL for crawling.
url (string) --
URL for crawling
crawlerLimits (dict) --
The configuration of crawl limits for the web URLs.
rateLimit (integer) --
Rate of web URLs retrieved per minute.
inclusionFilters (list) --
A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
exclusionFilters (list) --
A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
scope (string) --
The scope of what is crawled for your URLs. You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL https://docs.aws.amazon.com/bedrock/latest/userguide/ and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain aws.amazon.com can also include sub domain docs.aws.amazon.com.
vectorIngestionConfiguration (dict) --
Contains details about how to ingest the documents in a data source.
chunkingConfiguration (dict) --
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
chunkingStrategy (string) --
Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
fixedSizeChunkingConfiguration (dict) --
Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as NONE, exclude this field.
maxTokens (integer) --
The maximum number of tokens to include in a chunk.
overlapPercentage (integer) --
The percentage of overlap between adjacent chunks of a data source.
hierarchicalChunkingConfiguration (dict) --
Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
levelConfigurations (list) --
Token settings for each layer.
(dict) --
Token settings for each layer.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain in this layer.
overlapTokens (integer) --
The number of tokens to repeat across chunks in the same layer.
semanticChunkingConfiguration (dict) --
Settings for semantic document chunking for a data source. Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain.
bufferSize (integer) --
The buffer size.
breakpointPercentileThreshold (integer) --
The dissimilarity threshold for splitting chunks.
parsingConfiguration (dict) --
A custom parser for data source documents.
parsingStrategy (string) --
The parsing strategy for the data source.
bedrockFoundationModelConfiguration (dict) --
Settings for a foundation model used to parse documents for a data source.
modelArn (string) --
The ARN of the foundation model.
parsingPrompt (dict) --
Instructions for interpreting the contents of a document.
parsingPromptText (string) --
Instructions for interpreting the contents of a document.
renderingConfiguration (dict) --
Information about how to render the content.
templateUri (string) --
A URI template containing exactly one variable in ${variableName} ``format. This can only be set for ``EXTERNAL knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following:
Salesforce: Id, ArticleNumber, VersionNumber, Title, PublishStatus, or IsDeleted
ServiceNow: number, short_description, sys_mod_count, workflow_state, or active
Zendesk: id, title, updated_at, or draft
The variable is replaced with the actual value for a piece of content when calling GetContent.
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
description (string) --
The description of the knowledge base.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
lastModifiedTime (datetime) --
The timestamp when the knowledge base was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the knowledge base was last modified.
nextToken (string) --
If there are additional results, this is the token for the next set of results.
{'modelSummaries': {'globalResiliencyStatus': 'SUPPORTED | UNSUPPORTED'}}
Lists the models available to an Amazon Q in Connect assistant in the assistant's Amazon Web Services Region. The available models are determined by the region of the specified assistant.
See also: AWS API Documentation
Request Syntax
client.list_models(
assistantId='string',
aiPromptType='ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
modelLifecycle='ACTIVE'|'LEGACY',
nextToken='string',
maxResults=123
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN. The assistant's region determines which models are available.
string
The type of the AI Prompt to filter models by. When specified, only models that support the given AI Prompt type are returned.
string
The lifecycle status of models to filter by. When specified, only models with the given lifecycle status are returned.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
dict
Response Syntax
{
'modelSummaries': [
{
'modelId': 'string',
'displayName': 'string',
'crossRegionStatus': 'NONE'|'REGIONAL'|'GLOBAL',
'supportsPromptCaching': True|False,
'supportedAIPromptTypes': [
'ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
],
'modelLifecycle': 'ACTIVE'|'LEGACY',
'legacyTimestamp': datetime(2015, 1, 1),
'endOfLifeTimestamp': datetime(2015, 1, 1),
'globalResiliencyStatus': 'SUPPORTED'|'UNSUPPORTED'
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
modelSummaries (list) --
The summaries of the models available to the assistant.
(dict) --
The summary of a model available to an Amazon Q in Connect assistant.
modelId (string) --
The identifier of the model.
displayName (string) --
The display name of the model.
crossRegionStatus (string) --
The cross-region availability status of the model. NONE indicates the model is only available in a single region, REGIONAL indicates the model is available through regional inference, and GLOBAL indicates the model is available through global cross-region inference.
supportsPromptCaching (boolean) --
Whether the model supports prompt caching.
supportedAIPromptTypes (list) --
The list of AI Prompt types that the model supports.
(string) --
modelLifecycle (string) --
The current lifecycle of the model. ACTIVE indicates the model is recommended for use and LEGACY indicates the model is still usable but is deprecated.
legacyTimestamp (datetime) --
The timestamp when the model lifecycle will transition from ACTIVE to LEGACY.
endOfLifeTimestamp (datetime) --
The timestamp when the model will reach end of life and no longer be available for use.
globalResiliencyStatus (string) --
Whether this model is published in every Region of the caller's Amazon Connect Global Resiliency replication group, and so can be referenced by an AI Prompt that replicates. Present only for callers to which global resiliency applies.
nextToken (string) --
If there are additional results, this is the token for the next set of results.
{'quickResponseSummaries': {'lastModifiedRegion': 'string'}}
Lists information about quick response.
See also: AWS API Documentation
Request Syntax
client.list_quick_responses(
nextToken='string',
maxResults=123,
knowledgeBaseId='string'
)
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
[REQUIRED]
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
Response Syntax
{
'quickResponseSummaries': [
{
'quickResponseArn': 'string',
'quickResponseId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'CREATED'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_IN_PROGRESS'|'UPDATE_FAILED',
'createdTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'lastModifiedBy': 'string',
'isActive': True|False,
'channels': [
'string',
],
'tags': {
'string': 'string'
}
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
quickResponseSummaries (list) --
Summary information about the quick responses.
(dict) --
The summary information about the quick response.
quickResponseArn (string) --
The Amazon Resource Name (ARN) of the quick response.
quickResponseId (string) --
The identifier of the quick response.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
name (string) --
The name of the quick response.
contentType (string) --
The media type of the quick response content.
Use application/x.quickresponse;format=plain for quick response written in plain text.
Use application/x.quickresponse;format=markdown for quick response written in richtext.
status (string) --
The resource status of the quick response.
createdTime (datetime) --
The timestamp when the quick response was created.
lastModifiedTime (datetime) --
The timestamp when the quick response summary was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the quick response was last modified.
description (string) --
The description of the quick response.
lastModifiedBy (string) --
The Amazon Resource Name (ARN) of the user who last updated the quick response data.
isActive (boolean) --
Whether the quick response is active.
channels (list) --
The Connect Customer contact channels this quick response applies to. The supported contact channel types include Chat.
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'contentSummaries': {'fileHash': 'string',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Searches for content in a specified knowledge base. Can be used to get a specific content resource by its name.
See also: AWS API Documentation
Request Syntax
client.search_content(
nextToken='string',
maxResults=123,
knowledgeBaseId='string',
searchExpression={
'filters': [
{
'field': 'NAME',
'operator': 'EQUALS',
'value': 'string'
},
]
}
)
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
string
[REQUIRED]
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
[REQUIRED]
The search expression to filter results.
filters (list) -- [REQUIRED]
The search expression filters.
(dict) --
A search filter.
field (string) -- [REQUIRED]
The field on which to filter.
operator (string) -- [REQUIRED]
The operator to use for comparing the field’s value with the provided value.
value (string) -- [REQUIRED]
The desired field value on which to filter.
dict
Response Syntax
{
'contentSummaries': [
{
'contentArn': 'string',
'contentId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'revisionId': 'string',
'title': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_FAILED',
'metadata': {
'string': 'string'
},
'tags': {
'string': 'string'
},
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'fileHash': 'string'
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
contentSummaries (list) --
Summary information about the content.
(dict) --
Summary information about the content.
contentArn (string) --
The Amazon Resource Name (ARN) of the content.
contentId (string) --
The identifier of the content.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base.
name (string) --
The name of the content.
revisionId (string) --
The identifier of the revision of the content.
title (string) --
The title of the content.
contentType (string) --
The media type of the content.
status (string) --
The status of the content.
metadata (dict) --
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
lastModifiedTime (datetime) --
The timestamp when the content was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the content was last modified.
fileHash (string) --
The Base64-encoded SHA-256 hash of the content file. Amazon Connect Global Resiliency returns this field only for replicated content.
nextToken (string) --
If there are additional results, this is the token for the next set of results.
{'results': {'lastModifiedRegion': 'string'}}
Searches existing Amazon Q in Connect quick responses in an Amazon Q in Connect knowledge base.
See also: AWS API Documentation
Request Syntax
client.search_quick_responses(
knowledgeBaseId='string',
searchExpression={
'queries': [
{
'name': 'string',
'values': [
'string',
],
'operator': 'CONTAINS'|'CONTAINS_AND_PREFIX',
'allowFuzziness': True|False,
'priority': 'HIGH'|'MEDIUM'|'LOW'
},
],
'filters': [
{
'name': 'string',
'values': [
'string',
],
'operator': 'EQUALS'|'PREFIX',
'includeNoExistence': True|False
},
],
'orderOnField': {
'name': 'string',
'order': 'ASC'|'DESC'
}
},
nextToken='string',
maxResults=123,
attributes={
'string': 'string'
}
)
string
[REQUIRED]
The identifier of the knowledge base. This should be a QUICK_RESPONSES type knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
dict
[REQUIRED]
The search expression for querying the quick response.
queries (list) --
The quick response query expressions.
(dict) --
The quick response fields to query quick responses by.
The following is the list of supported field names.
content
name
description
shortcutKey
name (string) -- [REQUIRED]
The name of the attribute to query the quick responses by.
values (list) -- [REQUIRED]
The values of the attribute to query the quick responses by.
(string) --
operator (string) -- [REQUIRED]
The operator to use for matching attribute field values in the query.
allowFuzziness (boolean) --
Whether the query expects only exact matches on the attribute field values. The results of the query will only include exact matches if this parameter is set to false.
priority (string) --
The importance of the attribute field when calculating query result relevancy scores. The value set for this parameter affects the ordering of search results.
filters (list) --
The configuration of filtering rules applied to quick response query results.
(dict) --
The quick response fields to filter the quick response query results by.
The following is the list of supported field names.
name
description
shortcutKey
isActive
channels
language
contentType
createdTime
lastModifiedTime
lastModifiedBy
groupingConfiguration.criteria
groupingConfiguration.values
name (string) -- [REQUIRED]
The name of the attribute field to filter the quick responses by.
values (list) --
The values of attribute field to filter the quick response by.
(string) --
operator (string) -- [REQUIRED]
The operator to use for filtering.
includeNoExistence (boolean) --
Whether to treat null value as a match for the attribute field.
orderOnField (dict) --
The quick response attribute fields on which the query results are ordered.
name (string) -- [REQUIRED]
The name of the attribute to order the quick response query results by.
order (string) --
The order at which the quick responses are sorted by.
string
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
integer
The maximum number of results to return per page.
dict
The user-defined Connect Customer contact attributes to be resolved when search results are returned.
(string) --
(string) --
dict
Response Syntax
{
'results': [
{
'quickResponseArn': 'string',
'quickResponseId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'CREATED'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_IN_PROGRESS'|'UPDATE_FAILED',
'contents': {
'plainText': {
'content': 'string'
},
'markdown': {
'content': 'string'
}
},
'createdTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'isActive': True|False,
'description': 'string',
'groupingConfiguration': {
'criteria': 'string',
'values': [
'string',
]
},
'shortcutKey': 'string',
'lastModifiedBy': 'string',
'channels': [
'string',
],
'language': 'string',
'attributesNotInterpolated': [
'string',
],
'attributesInterpolated': [
'string',
],
'tags': {
'string': 'string'
}
},
],
'nextToken': 'string'
}
Response Structure
(dict) --
results (list) --
The results of the quick response search.
(dict) --
The result of quick response search.
quickResponseArn (string) --
The Amazon Resource Name (ARN) of the quick response.
quickResponseId (string) --
The identifier of the quick response.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
name (string) --
The name of the quick response.
contentType (string) --
The media type of the quick response content.
Use application/x.quickresponse;format=plain for quick response written in plain text.
Use application/x.quickresponse;format=markdown for quick response written in richtext.
status (string) --
The resource status of the quick response.
contents (dict) --
The contents of the quick response.
plainText (dict) --
The container quick response content.
content (string) --
The content of the quick response.
markdown (dict) --
The container quick response content.
content (string) --
The content of the quick response.
createdTime (datetime) --
The timestamp when the quick response was created.
lastModifiedTime (datetime) --
The timestamp when the quick response search result data was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the quick response was last modified.
isActive (boolean) --
Whether the quick response is active.
description (string) --
The description of the quick response.
groupingConfiguration (dict) --
The configuration information of the user groups that the quick response is accessible to.
criteria (string) --
The criteria used for grouping Amazon Q in Connect users.
The following is the list of supported criteria values.
RoutingProfileArn: Grouping the users by their Amazon Connect routing profile ARN. User should have SearchRoutingProfile and DescribeRoutingProfile permissions when setting criteria to this value.
values (list) --
The list of values that define different groups of Amazon Q in Connect users.
When setting criteria to RoutingProfileArn, you need to provide a list of ARNs of Connect Customer routing profiles as values of this parameter.
(string) --
shortcutKey (string) --
The shortcut key of the quick response. The value should be unique across the knowledge base.
lastModifiedBy (string) --
The Amazon Resource Name (ARN) of the user who last updated the quick response search result data.
channels (list) --
The Connect Customer contact channels this quick response applies to. The supported contact channel types include Chat.
(string) --
language (string) --
The language code value for the language in which the quick response is written.
attributesNotInterpolated (list) --
The user defined contact attributes that are not resolved when the search result is returned.
(string) --
attributesInterpolated (list) --
The user defined contact attributes that are resolved when the search result is returned.
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
nextToken (string) --
The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.
{'aiAgent': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Updates an AI Agent.
See also: AWS API Documentation
Request Syntax
client.update_ai_agent(
clientToken='string',
assistantId='string',
aiAgentId='string',
visibilityStatus='SAVED'|'PUBLISHED',
configuration={
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
description='string'
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Agent.
string
[REQUIRED]
The visbility status of the Amazon Q in Connect AI Agent.
dict
The configuration of the Amazon Q in Connect AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) -- [REQUIRED]
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) -- [REQUIRED]
The name of the tool.
toolType (string) -- [REQUIRED]
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) -- [REQUIRED]
The JSON path for the input value override.
value (dict) -- [REQUIRED]
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) -- [REQUIRED]
Override tool input value with constant values
value (string) -- [REQUIRED]
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) -- [REQUIRED]
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) -- [REQUIRED]
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) -- [REQUIRED]
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
string
The description of the Amazon Q in Connect AI Agent.
dict
Response Syntax
{
'aiAgent': {
'assistantId': 'string',
'assistantArn': 'string',
'aiAgentId': 'string',
'aiAgentArn': 'string',
'name': 'string',
'type': 'MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'configuration': {
'manualSearchAIAgentConfiguration': {
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string'
},
'answerRecommendationAIAgentConfiguration': {
'intentLabelingGenerationAIPromptId': 'string',
'queryReformulationAIPromptId': 'string',
'answerGenerationAIPromptId': 'string',
'answerGenerationAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
],
'locale': 'string',
'suggestedMessages': [
'string',
]
},
'selfServiceAIAgentConfiguration': {
'selfServicePreProcessingAIPromptId': 'string',
'selfServiceAnswerGenerationAIPromptId': 'string',
'selfServiceAIGuardrailId': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailResponseAIAgentConfiguration': {
'emailResponseAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'emailOverviewAIAgentConfiguration': {
'emailOverviewAIPromptId': 'string',
'locale': 'string'
},
'emailGenerativeAnswerAIAgentConfiguration': {
'emailGenerativeAnswerAIPromptId': 'string',
'emailQueryReformulationAIPromptId': 'string',
'locale': 'string',
'associationConfigurations': [
{
'associationId': 'string',
'associationType': 'KNOWLEDGE_BASE',
'associationConfigurationData': {
'knowledgeBaseAssociationConfigurationData': {
'contentTagFilter': {
'tagCondition': {
'key': 'string',
'value': 'string'
},
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'orConditions': [
{
'andConditions': [
{
'key': 'string',
'value': 'string'
},
],
'tagCondition': {
'key': 'string',
'value': 'string'
}
},
]
},
'maxResults': 123,
'overrideKnowledgeBaseSearchType': 'HYBRID'|'SEMANTIC'
}
}
},
]
},
'orchestrationAIAgentConfiguration': {
'orchestrationAIPromptId': 'string',
'orchestrationAIGuardrailId': 'string',
'toolConfigurations': [
{
'toolName': 'string',
'toolType': 'MODEL_CONTEXT_PROTOCOL'|'RETURN_TO_CONTROL'|'CONSTANT',
'title': 'string',
'toolId': 'string',
'description': 'string',
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'overrideInputValues': [
{
'jsonPath': 'string',
'value': {
'constant': {
'type': 'STRING'|'NUMBER'|'JSON_STRING',
'value': 'string'
}
}
},
],
'outputFilters': [
{
'jsonPath': 'string',
'outputConfiguration': {
'outputVariableNameOverride': 'string',
'sessionDataNamespace': 'string'
}
},
],
'inputSchema': {...}|[...]|123|123.4|'string'|True|None,
'outputSchema': {...}|[...]|123|123.4|'string'|True|None,
'annotations': {
'title': 'string',
'destructiveHint': True|False
},
'userInteractionConfiguration': {
'isUserConfirmationRequired': True|False
}
},
],
'multiAgentConfigurations': [
{
'delegateAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
}
},
'handoffAgentConfiguration': {
'agentTarget': {
'aiAgentId': 'string',
'applicationId': 'string'
},
'instruction': {
'instruction': 'string',
'examples': [
'string',
]
},
'audioStreamingEnabled': True|False,
'immediateHandoff': True|False
}
},
],
'connectInstanceArn': 'string',
'locale': 'string',
'inputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
],
'outputSchemas': [
{...}|[...]|123|123.4|'string'|True|None,
]
},
'noteTakingAIAgentConfiguration': {
'noteTakingAIPromptId': 'string',
'noteTakingAIGuardrailId': 'string',
'locale': 'string'
},
'caseSummarizationAIAgentConfiguration': {
'caseSummarizationAIPromptId': 'string',
'caseSummarizationAIGuardrailId': 'string',
'locale': 'string'
}
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
}
}
Response Structure
(dict) --
aiAgent (dict) --
The data of the updated Amazon Q in Connect AI Agent.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiAgentId (string) --
The identifier of the AI Agent.
aiAgentArn (string) --
The Amazon Resource Name (ARN) of the AI agent.
name (string) --
The name of the AI Agent.
type (string) --
The type of the AI Agent.
configuration (dict) --
Configuration for the AI Agent.
manualSearchAIAgentConfiguration (dict) --
The configuration for AI Agents of type MANUAL_SEARCH.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the MANUAL_SEARCH AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation guardrail used by the MANUAL_SEARCH AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
answerRecommendationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ANSWER_RECOMMENDATION.
intentLabelingGenerationAIPromptId (string) --
The AI Prompt identifier for the Intent Labeling prompt used by the ANSWER_RECOMMENDATION AI Agent.
queryReformulationAIPromptId (string) --
The AI Prompt identifier for the Query Reformulation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIPromptId (string) --
The AI Prompt identifier for the Answer Generation prompt used by the ANSWER_RECOMMENDATION AI Agent.
answerGenerationAIGuardrailId (string) --
The AI Guardrail identifier for the Answer Generation Guardrail used by the ANSWER_RECOMMENDATION AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
locale (string) --
The locale to which specifies the language and region settings that determine the response language for QueryAssistant.
suggestedMessages (list) --
The suggested messages configuration for the Answer Recommendation AI Agent.
(string) --
selfServiceAIAgentConfiguration (dict) --
The configuration for AI Agents of type SELF_SERVICE.
selfServicePreProcessingAIPromptId (string) --
The AI Prompt identifier for the Self Service Pre-Processing prompt used by the SELF_SERVICE AI Agent
selfServiceAnswerGenerationAIPromptId (string) --
The AI Prompt identifier for the Self Service Answer Generation prompt used by the SELF_SERVICE AI Agent
selfServiceAIGuardrailId (string) --
The AI Guardrail identifier used by the SELF_SERVICE AI Agent.
associationConfigurations (list) --
The association configurations for overriding behavior on this AI Agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailResponseAIAgentConfiguration (dict) --
Configuration for the EMAIL_RESPONSE AI agent that generates professional email responses using knowledge base content.
emailResponseAIPromptId (string) --
The ID of the System AI prompt used for generating professional email responses based on knowledge base content.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search for response generation.
locale (string) --
The locale setting for language-specific email response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email response agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
emailOverviewAIAgentConfiguration (dict) --
Configuration for the EMAIL_OVERVIEW AI agent that generates structured overview of email conversations.
emailOverviewAIPromptId (string) --
The ID of the System AI prompt used for generating structured email conversation summaries.
locale (string) --
The locale setting for language-specific email overview processing (for example, en_US, es_ES).
emailGenerativeAnswerAIAgentConfiguration (dict) --
Configuration for the EMAIL_GENERATIVE_ANSWER AI agent that provides comprehensive knowledge-based answers for customer queries.
emailGenerativeAnswerAIPromptId (string) --
The ID of the System AI prompt used for generating comprehensive knowledge-based answers from email queries.
emailQueryReformulationAIPromptId (string) --
The ID of the System AI prompt used for reformulating email queries to optimize knowledge base search results.
locale (string) --
The locale setting for language-specific email processing and response generation (for example, en_US, es_ES).
associationConfigurations (list) --
Configuration settings for knowledge base associations used by the email generative answer agent.
(dict) --
The configuration for an Amazon Q in Connect Assistant Association.
associationId (string) --
The identifier of the association for this Association Configuration.
associationType (string) --
The type of the association for this Association Configuration.
associationConfigurationData (dict) --
The data of the configuration for an Amazon Q in Connect Assistant Association.
knowledgeBaseAssociationConfigurationData (dict) --
The data of the configuration for a KNOWLEDGE_BASE type Amazon Q in Connect Assistant Association.
contentTagFilter (dict) --
An object that can be used to specify Tag conditions.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
orConditions (list) --
A list of conditions which would be applied together with an OR condition.
(dict) --
A list of conditions which would be applied together with an OR condition.
andConditions (list) --
A list of conditions which would be applied together with an AND condition.
(dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
tagCondition (dict) --
A leaf node condition which can be used to specify a tag condition.
key (string) --
The tag key in the tag condition.
value (string) --
The tag value in the tag condition.
maxResults (integer) --
The maximum number of results to return per page.
overrideKnowledgeBaseSearchType (string) --
The search type to be used against the Knowledge Base for this request. The values can be SEMANTIC which uses vector embeddings or HYBRID which use vector embeddings and raw text
orchestrationAIAgentConfiguration (dict) --
The configuration for AI Agents of type ORCHESTRATION.
orchestrationAIPromptId (string) --
The AI Prompt identifier used by the Orchestration AI Agent.
orchestrationAIGuardrailId (string) --
The AI Guardrail identifier used by the Orchestration AI Agent.
toolConfigurations (list) --
The tool configurations used by the Orchestration AI Agent.
(dict) --
Configuration settings for a tool used by AI Agents.
toolName (string) --
The name of the tool.
toolType (string) --
The type of the tool.
title (string) --
The title of the tool configuration.
toolId (string) --
The identifier of the tool, for example toolName from Model Context Provider server.
description (string) --
The description of the tool configuration.
instruction (dict) --
Instructions for using the tool.
instruction (string) --
The instruction text for the tool.
examples (list) --
Examples for using the tool.
(string) --
overrideInputValues (list) --
Override input values for the tool configuration.
(dict) --
An input value override for tools.
jsonPath (string) --
The JSON path for the input value override.
value (dict) --
The override input value.
constant (dict) --
Constant input value configuration for tool override.
type (string) --
Override tool input value with constant values
value (string) --
The constant input override value.
outputFilters (list) --
Output filters applies to the tool result.
(dict) --
Filter configuration for tool output.
jsonPath (string) --
The JSON path for filtering tool output.
outputConfiguration (dict) --
The output configuration for the filter.
outputVariableNameOverride (string) --
Override the tool output results to different variable name.
sessionDataNamespace (string) --
The session data namespace for tool output.
inputSchema (:ref:`document<document>`) --
The input schema for the tool configuration.
outputSchema (:ref:`document<document>`) --
The output schema for the tool configuration.
annotations (dict) --
Annotations for the tool configuration.
title (string) --
The title of the annotation.
destructiveHint (boolean) --
A hint indicating that the annotation contains potentially destructive content.
userInteractionConfiguration (dict) --
Configuration for user interaction with the tool.
isUserConfirmationRequired (boolean) --
Indicates whether user confirmation is required for the interaction.
multiAgentConfigurations (list) --
The collaborator agents that the Orchestration AI Agent can work with. Each entry defines another agent that the orchestrator either delegates to or hands the conversation off to.
(dict) --
A union that configures a single collaborator agent for an Orchestration AI Agent, as either a delegate or a handoff.
delegateAgentConfiguration (dict) --
Configures the collaborator agent as a delegate that the Orchestration AI Agent invokes while retaining control of the conversation.
agentTarget (dict) --
The collaborator agent to delegate to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to delegate to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
handoffAgentConfiguration (dict) --
Configures the collaborator agent as a handoff target that the Orchestration AI Agent transfers control of the conversation to.
agentTarget (dict) --
The collaborator agent to hand off to.
aiAgentId (string) --
The identifier of an Amazon Connect AI Agent to use as the collaborator agent.
applicationId (string) --
The identifier of a third-party agent to use as the collaborator agent.
instruction (dict) --
The instruction that tells the Orchestration AI Agent when and how to hand off to this collaborator agent.
instruction (string) --
The natural-language instruction that tells the Orchestration AI Agent when and how to engage the collaborator agent.
examples (list) --
Example interactions that illustrate when the Orchestration AI Agent should engage the collaborator agent.
(string) --
audioStreamingEnabled (boolean) --
Specifies whether the caller's audio is streamed directly to the collaborator agent and the collaborator's audio response is played back during the handoff. This applies only to voice handoffs.
immediateHandoff (boolean) --
Specifies whether the conversation is handed off to this collaborator agent immediately on the first turn, without any orchestration reasoning. At most one handoff in an AI Agent's configuration can set this to true.
connectInstanceArn (string) --
The Amazon Resource Name (ARN) of the Amazon Connect instance used by the Orchestration AI Agent.
locale (string) --
The locale setting for the Orchestration AI Agent.
inputSchemas (list) --
The JSON schemas that define the structure of the structured data input accepted by the Orchestration AI Agent. The data in a DATA message sent to the agent is validated against these schemas. You can specify at most one schema.
(:ref:`document<document>`) --
outputSchemas (list) --
The JSON schemas that define the structure of the structured output generated by the Orchestration AI Agent. You can specify at most one schema.
(:ref:`document<document>`) --
noteTakingAIAgentConfiguration (dict) --
The configuration for AI Agents of type NOTE_TAKING.
noteTakingAIPromptId (string) --
The AI Prompt identifier used by the Note Taking AI Agent.
noteTakingAIGuardrailId (string) --
The AI Guardrail identifier used by the Note Taking AI Agent.
locale (string) --
The locale setting for language-specific case summarization generation (for example, en_US, es_ES).
caseSummarizationAIAgentConfiguration (dict) --
The configuration for AI Agents of type CASE_SUMMARIZATION.
caseSummarizationAIPromptId (string) --
The AI Prompt identifier used by the Case Summarization AI Agent.
caseSummarizationAIGuardrailId (string) --
The AI Guardrail identifier used by the Case Summarization AI Agent.
locale (string) --
The locale setting for the Case Summarization AI Agent.
modifiedTime (datetime) --
The time the AI Agent was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Agent was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Agent was last modified.
description (string) --
The description of the AI Agent.
visibilityStatus (string) --
The visibility status of the AI Agent.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
Specifies the origin of the AI Agent. SYSTEM for a default AI Agent created by Q in Connect or CUSTOMER for an AI Agent created by calling AI Agent creation APIs.
status (string) --
The status of the AI Agent.
{'aiGuardrail': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Updates an AI Guardrail.
See also: AWS API Documentation
Request Syntax
client.update_ai_guardrail(
clientToken='string',
assistantId='string',
aiGuardrailId='string',
visibilityStatus='SAVED'|'PUBLISHED',
blockedInputMessaging='string',
blockedOutputsMessaging='string',
description='string',
topicPolicyConfig={
'topicsConfig': [
{
'name': 'string',
'definition': 'string',
'examples': [
'string',
],
'type': 'DENY'
},
]
},
contentPolicyConfig={
'filtersConfig': [
{
'type': 'SEXUAL'|'VIOLENCE'|'HATE'|'INSULTS'|'MISCONDUCT'|'PROMPT_ATTACK',
'inputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'outputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH'
},
]
},
wordPolicyConfig={
'wordsConfig': [
{
'text': 'string'
},
],
'managedWordListsConfig': [
{
'type': 'PROFANITY'
},
]
},
sensitiveInformationPolicyConfig={
'piiEntitiesConfig': [
{
'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',
'action': 'BLOCK'|'ANONYMIZE'
},
],
'regexesConfig': [
{
'name': 'string',
'description': 'string',
'pattern': 'string',
'action': 'BLOCK'|'ANONYMIZE'
},
]
},
contextualGroundingPolicyConfig={
'filtersConfig': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0
},
]
}
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Guardrail.
string
[REQUIRED]
The visibility status of the Amazon Q in Connect AI Guardrail.
string
[REQUIRED]
The message to return when the AI Guardrail blocks a prompt.
string
[REQUIRED]
The message to return when the AI Guardrail blocks a model response.
string
A description of the AI Guardrail.
dict
The topic policies to configure for the AI Guardrail.
topicsConfig (list) -- [REQUIRED]
A list of policies related to topics that the AI Guardrail should deny.
(dict) --
Details about topics for the AI Guardrail to identify and deny.
name (string) -- [REQUIRED]
The name of the topic to deny.
definition (string) -- [REQUIRED]
A definition of the topic to deny.
examples (list) --
A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
(string) --
Text example in topic policy
type (string) -- [REQUIRED]
Specifies to deny the topic.
dict
The content filter policies to configure for the AI Guardrail.
filtersConfig (list) -- [REQUIRED]
Contains the type of the content filter and how strongly it should apply to prompts and model responses.
(dict) --
Contains filter strengths for harmful content. AI Guardrail's support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate: Describes input prompts and model responses that discriminate, criticize, insult, denounce, or dehumanize a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults: Describes input prompts and model responses that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual: Describes input prompts and model responses that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence: Describes input prompts and model responses that includes glorification of, or threats to inflict physical pain, hurt, or injury toward a person, group, or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
type (string) -- [REQUIRED]
The harmful category that the content filter is applied to.
inputStrength (string) -- [REQUIRED]
The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
outputStrength (string) -- [REQUIRED]
The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
dict
The word policy you configure for the AI Guardrail.
wordsConfig (list) --
A list of words to configure for the AI Guardrail.
(dict) --
A word to configure for the AI Guardrail.
text (string) -- [REQUIRED]
Text of the word configured for the AI Guardrail to block.
managedWordListsConfig (list) --
A list of managed words to configure for the AI Guardrail.
(dict) --
The managed word list to configure for the AI Guardrail.
type (string) -- [REQUIRED]
The managed word type to configure for the AI Guardrail.
dict
The sensitive information policy to configure for the AI Guardrail.
piiEntitiesConfig (list) --
A list of PII entities to configure to the AI Guardrail.
(dict) --
The PII entity to configure for the AI Guardrail.
type (string) -- [REQUIRED]
Configure AI Guardrail type when the PII entity is detected.
The following PIIs are used to block or mask sensitive information:
General
ADDRESS A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.
AGE An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guarrails recognizes "40 years" as an age.
NAME An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. AI Guardrail doesn't apply this entity type to names that are part of organizations or addresses. For example, AI Guardrail recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.
EMAIL An email address, such as marymajor@email.com.
PHONE A phone number. This entity type also includes fax and pager numbers.
USERNAME A user name that identifies an account, such as a login name, screen name, nick name, or handle.
PASSWORD An alphanumeric string that is used as a password, such as "** very20special#pass**".
DRIVER_ID The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.
LICENSE_PLATE A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.
VEHICLE_IDENTIFICATION_NUMBER A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.
Finance
CREDIT_DEBIT_CARD_CVV A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.
CREDIT_DEBIT_CARD_EXPIRY The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY. AI Guardrail recognizes expiration dates such as 01/21, 01/2021, and Jan 2021.
CREDIT_DEBIT_CARD_NUMBER The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.
PIN A four-digit personal identification number (PIN) with which you can access your bank account.
INTERNATIONAL_BANK_ACCOUNT_NUMBER An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure.
SWIFT_CODE A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers. SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.
IT
IP_ADDRESS An IPv4 address, such as 198.51.100.0.
MAC_ADDRESS A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).
URL A web address, such as www.example.com.
AWS_ACCESS_KEY A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
AWS_SECRET_KEY A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
USA specific
US_BANK_ACCOUNT_NUMBER A US bank account number, which is typically 10 to 12 digits long.
US_BANK_ROUTING_NUMBER A US bank account routing number. These are typically nine digits long,
US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.
US_PASSPORT_NUMBER A US passport number. Passport numbers range from six to nine alphanumeric characters.
US_SOCIAL_SECURITY_NUMBER A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.
Canada specific
CA_HEALTH_NUMBER A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.
CA_SOCIAL_INSURANCE_NUMBER A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits. The SIN is formatted as three groups of three digits, such as 123-456-789. A SIN can be validated through a simple check-digit process called the Luhn algorithm. For more information, see Luhn algorithm on the Wikipedia website.
UK Specific
UK_NATIONAL_HEALTH_SERVICE_NUMBER A UK National Health Service Number is a 10-17 digit number, such as 485 555 3456. The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.
UK_NATIONAL_INSURANCE_NUMBER A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system. The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.
UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.
Custom
Regex filter - You can use a regular expressions to define patterns for an AI Guardrail to recognize and act upon such as serial number, booking ID etc..
action (string) -- [REQUIRED]
Configure AI Guardrail's action when the PII entity is detected.
regexesConfig (list) --
A list of regular expressions to configure to the AI Guardrail.
(dict) --
The regular expression to configure for the AI Guardrail.
name (string) -- [REQUIRED]
The name of the regular expression to configure for the AI Guardrail.
description (string) --
The description of the regular expression to configure for the AI Guardrail.
pattern (string) -- [REQUIRED]
The regular expression pattern to configure for the AI Guardrail.
action (string) -- [REQUIRED]
The AI Guardrail action to configure when matching regular expression is detected.
dict
The contextual grounding policy configuration used to create an AI Guardrail.
filtersConfig (list) -- [REQUIRED]
The filter configuration details for the AI Guardrails contextual grounding policy.
(dict) --
The filter configuration details for the AI Guardrail's contextual grounding filter.
type (string) -- [REQUIRED]
The filter type for the AI Guardrail's contextual grounding filter.
threshold (float) -- [REQUIRED]
The threshold details for the AI Guardrail's contextual grounding filter.
dict
Response Syntax
{
'aiGuardrail': {
'assistantId': 'string',
'assistantArn': 'string',
'aiGuardrailArn': 'string',
'aiGuardrailId': 'string',
'name': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'blockedInputMessaging': 'string',
'blockedOutputsMessaging': 'string',
'description': 'string',
'topicPolicyConfig': {
'topicsConfig': [
{
'name': 'string',
'definition': 'string',
'examples': [
'string',
],
'type': 'DENY'
},
]
},
'contentPolicyConfig': {
'filtersConfig': [
{
'type': 'SEXUAL'|'VIOLENCE'|'HATE'|'INSULTS'|'MISCONDUCT'|'PROMPT_ATTACK',
'inputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'outputStrength': 'NONE'|'LOW'|'MEDIUM'|'HIGH'
},
]
},
'wordPolicyConfig': {
'wordsConfig': [
{
'text': 'string'
},
],
'managedWordListsConfig': [
{
'type': 'PROFANITY'
},
]
},
'sensitiveInformationPolicyConfig': {
'piiEntitiesConfig': [
{
'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',
'action': 'BLOCK'|'ANONYMIZE'
},
],
'regexesConfig': [
{
'name': 'string',
'description': 'string',
'pattern': 'string',
'action': 'BLOCK'|'ANONYMIZE'
},
]
},
'contextualGroundingPolicyConfig': {
'filtersConfig': [
{
'type': 'GROUNDING'|'RELEVANCE',
'threshold': 123.0
},
]
},
'tags': {
'string': 'string'
},
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
aiGuardrail (dict) --
The data of the updated Amazon Q in Connect AI Guardrail.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiGuardrailArn (string) --
The Amazon Resource Name (ARN) of the AI Guardrail.
aiGuardrailId (string) --
The identifier of the Amazon Q in Connect AI Guardrail.
name (string) --
The name of the AI Guardrail.
visibilityStatus (string) --
The visibility status of the AI Guardrail.
blockedInputMessaging (string) --
The message to return when the AI Guardrail blocks a prompt.
blockedOutputsMessaging (string) --
The message to return when the AI Guardrail blocks a model response.
description (string) --
A description of the AI Guardrail.
topicPolicyConfig (dict) --
Contains details about topics that the AI Guardrail should identify and deny.
topicsConfig (list) --
A list of policies related to topics that the AI Guardrail should deny.
(dict) --
Details about topics for the AI Guardrail to identify and deny.
name (string) --
The name of the topic to deny.
definition (string) --
A definition of the topic to deny.
examples (list) --
A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
(string) --
Text example in topic policy
type (string) --
Specifies to deny the topic.
contentPolicyConfig (dict) --
Contains details about how to handle harmful content.
filtersConfig (list) --
Contains the type of the content filter and how strongly it should apply to prompts and model responses.
(dict) --
Contains filter strengths for harmful content. AI Guardrail's support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate: Describes input prompts and model responses that discriminate, criticize, insult, denounce, or dehumanize a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults: Describes input prompts and model responses that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual: Describes input prompts and model responses that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence: Describes input prompts and model responses that includes glorification of, or threats to inflict physical pain, hurt, or injury toward a person, group, or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
type (string) --
The harmful category that the content filter is applied to.
inputStrength (string) --
The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
outputStrength (string) --
The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
wordPolicyConfig (dict) --
Contains details about the word policy to configured for the AI Guardrail.
wordsConfig (list) --
A list of words to configure for the AI Guardrail.
(dict) --
A word to configure for the AI Guardrail.
text (string) --
Text of the word configured for the AI Guardrail to block.
managedWordListsConfig (list) --
A list of managed words to configure for the AI Guardrail.
(dict) --
The managed word list to configure for the AI Guardrail.
type (string) --
The managed word type to configure for the AI Guardrail.
sensitiveInformationPolicyConfig (dict) --
Contains details about PII entities and regular expressions to configure for the AI Guardrail.
piiEntitiesConfig (list) --
A list of PII entities to configure to the AI Guardrail.
(dict) --
The PII entity to configure for the AI Guardrail.
type (string) --
Configure AI Guardrail type when the PII entity is detected.
The following PIIs are used to block or mask sensitive information:
General
ADDRESS A physical address, such as "100 Main Street, Anytown, USA" or "Suite #12, Building 123". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.
AGE An individual's age, including the quantity and unit of time. For example, in the phrase "I am 40 years old," Guarrails recognizes "40 years" as an age.
NAME An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. AI Guardrail doesn't apply this entity type to names that are part of organizations or addresses. For example, AI Guardrail recognizes the "John Doe Organization" as an organization, and it recognizes "Jane Doe Street" as an address.
EMAIL An email address, such as marymajor@email.com.
PHONE A phone number. This entity type also includes fax and pager numbers.
USERNAME A user name that identifies an account, such as a login name, screen name, nick name, or handle.
PASSWORD An alphanumeric string that is used as a password, such as "** very20special#pass**".
DRIVER_ID The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.
LICENSE_PLATE A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.
VEHICLE_IDENTIFICATION_NUMBER A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.
Finance
CREDIT_DEBIT_CARD_CVV A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.
CREDIT_DEBIT_CARD_EXPIRY The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY. AI Guardrail recognizes expiration dates such as 01/21, 01/2021, and Jan 2021.
CREDIT_DEBIT_CARD_NUMBER The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.
PIN A four-digit personal identification number (PIN) with which you can access your bank account.
INTERNATIONAL_BANK_ACCOUNT_NUMBER An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure.
SWIFT_CODE A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers. SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.
IT
IP_ADDRESS An IPv4 address, such as 198.51.100.0.
MAC_ADDRESS A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).
URL A web address, such as www.example.com.
AWS_ACCESS_KEY A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
AWS_SECRET_KEY A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
USA specific
US_BANK_ACCOUNT_NUMBER A US bank account number, which is typically 10 to 12 digits long.
US_BANK_ROUTING_NUMBER A US bank account routing number. These are typically nine digits long,
US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a "9" and contain a "7" or "8" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.
US_PASSPORT_NUMBER A US passport number. Passport numbers range from six to nine alphanumeric characters.
US_SOCIAL_SECURITY_NUMBER A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.
Canada specific
CA_HEALTH_NUMBER A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.
CA_SOCIAL_INSURANCE_NUMBER A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits. The SIN is formatted as three groups of three digits, such as 123-456-789. A SIN can be validated through a simple check-digit process called the Luhn algorithm. For more information, see Luhn algorithm on the Wikipedia website.
UK Specific
UK_NATIONAL_HEALTH_SERVICE_NUMBER A UK National Health Service Number is a 10-17 digit number, such as 485 555 3456. The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.
UK_NATIONAL_INSURANCE_NUMBER A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system. The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.
UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.
Custom
Regex filter - You can use a regular expressions to define patterns for an AI Guardrail to recognize and act upon such as serial number, booking ID etc..
action (string) --
Configure AI Guardrail's action when the PII entity is detected.
regexesConfig (list) --
A list of regular expressions to configure to the AI Guardrail.
(dict) --
The regular expression to configure for the AI Guardrail.
name (string) --
The name of the regular expression to configure for the AI Guardrail.
description (string) --
The description of the regular expression to configure for the AI Guardrail.
pattern (string) --
The regular expression pattern to configure for the AI Guardrail.
action (string) --
The AI Guardrail action to configure when matching regular expression is detected.
contextualGroundingPolicyConfig (dict) --
The policy configuration details for the AI Guardrail's contextual grounding policy.
filtersConfig (list) --
The filter configuration details for the AI Guardrails contextual grounding policy.
(dict) --
The filter configuration details for the AI Guardrail's contextual grounding filter.
type (string) --
The filter type for the AI Guardrail's contextual grounding filter.
threshold (float) --
The threshold details for the AI Guardrail's contextual grounding filter.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
status (string) --
The status of the AI Guardrail.
modifiedTime (datetime) --
The time the AI Guardrail was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Guardrail was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Guardrail was last modified.
{'aiPrompt': {'lastModifiedRegion': 'string', 'lastModifiedTime': 'timestamp'}}
Updates an AI Prompt.
See also: AWS API Documentation
Request Syntax
client.update_ai_prompt(
clientToken='string',
assistantId='string',
aiPromptId='string',
visibilityStatus='SAVED'|'PUBLISHED',
templateConfiguration={
'textFullAIPromptEditTemplateConfiguration': {
'text': 'string'
}
},
description='string',
modelId='string',
inferenceConfiguration={
'temperature': ...,
'topP': ...,
'topK': 123,
'maxTokensToSample': 123
}
)
string
A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the Amazon Web Services SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..
This field is autopopulated if not provided.
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the Amazon Q in Connect AI Prompt.
string
[REQUIRED]
The visibility status of the Amazon Q in Connect AI prompt.
dict
The configuration of the prompt template for this AI Prompt.
textFullAIPromptEditTemplateConfiguration (dict) --
The configuration for a prompt template that supports full textual prompt configuration using a YAML prompt.
text (string) -- [REQUIRED]
The YAML text for the AI Prompt template.
string
The description of the Amazon Q in Connect AI Prompt.
string
The identifier of the model used for this AI Prompt.
dict
The updated inference configuration for the AI Prompt.
temperature (float) --
The temperature setting for controlling randomness in the generated response.
topP (float) --
The top-P sampling parameter for nucleus sampling.
topK (integer) --
The top-K sampling parameter for token selection.
maxTokensToSample (integer) --
The maximum number of tokens to generate in the response.
dict
Response Syntax
{
'aiPrompt': {
'assistantId': 'string',
'assistantArn': 'string',
'aiPromptId': 'string',
'aiPromptArn': 'string',
'name': 'string',
'type': 'ANSWER_GENERATION'|'INTENT_LABELING_GENERATION'|'QUERY_REFORMULATION'|'SELF_SERVICE_PRE_PROCESSING'|'SELF_SERVICE_ANSWER_GENERATION'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'EMAIL_QUERY_REFORMULATION'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
'templateType': 'TEXT',
'modelId': 'string',
'apiFormat': 'ANTHROPIC_CLAUDE_MESSAGES'|'ANTHROPIC_CLAUDE_TEXT_COMPLETIONS'|'MESSAGES'|'TEXT_COMPLETIONS',
'templateConfiguration': {
'textFullAIPromptEditTemplateConfiguration': {
'text': 'string'
}
},
'inferenceConfiguration': {
'temperature': ...,
'topP': ...,
'topK': 123,
'maxTokensToSample': 123
},
'modifiedTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'description': 'string',
'visibilityStatus': 'SAVED'|'PUBLISHED',
'tags': {
'string': 'string'
},
'origin': 'SYSTEM'|'CUSTOMER',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'
}
}
Response Structure
(dict) --
aiPrompt (dict) --
The data of the updated Amazon Q in Connect AI Prompt.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
aiPromptId (string) --
The identifier of the Amazon Q in Connect AI prompt.
aiPromptArn (string) --
The Amazon Resource Name (ARN) of the AI Prompt.
name (string) --
The name of the AI Prompt
type (string) --
The type of this AI Prompt.
templateType (string) --
The type of the prompt template for this AI Prompt.
modelId (string) --
The identifier of the model used for this AI Prompt. The following model Ids are supported:
anthropic.claude-3-haiku--v1:0
apac.amazon.nova-lite-v1:0
apac.amazon.nova-micro-v1:0
apac.amazon.nova-pro-v1:0
apac.anthropic.claude-3-5-sonnet--v2:0
apac.anthropic.claude-3-haiku-20240307-v1:0
eu.amazon.nova-lite-v1:0
eu.amazon.nova-micro-v1:0
eu.amazon.nova-pro-v1:0
eu.anthropic.claude-3-7-sonnet-20250219-v1:0
eu.anthropic.claude-3-haiku-20240307-v1:0
us.amazon.nova-lite-v1:0
us.amazon.nova-micro-v1:0
us.amazon.nova-pro-v1:0
us.anthropic.claude-3-5-haiku-20241022-v1:0
us.anthropic.claude-3-7-sonnet-20250219-v1:0
us.anthropic.claude-3-haiku-20240307-v1:0
apiFormat (string) --
The API format used for this AI Prompt.
templateConfiguration (dict) --
The configuration of the prompt template for this AI Prompt.
textFullAIPromptEditTemplateConfiguration (dict) --
The configuration for a prompt template that supports full textual prompt configuration using a YAML prompt.
text (string) --
The YAML text for the AI Prompt template.
inferenceConfiguration (dict) --
The configuration for inference parameters when using the AI Prompt.
temperature (float) --
The temperature setting for controlling randomness in the generated response.
topP (float) --
The top-P sampling parameter for nucleus sampling.
topK (integer) --
The top-K sampling parameter for token selection.
maxTokensToSample (integer) --
The maximum number of tokens to generate in the response.
modifiedTime (datetime) --
The time the AI Prompt was last modified.
lastModifiedTime (datetime) --
The timestamp when the AI Prompt was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the AI Prompt was last modified.
description (string) --
The description of the AI Prompt.
visibilityStatus (string) --
The visibility status of the AI Prompt.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
origin (string) --
The origin of the AI Prompt. SYSTEM for a default AI Prompt created by Q in Connect or CUSTOMER for an AI Prompt created by calling AI Prompt creation APIs.
status (string) --
The status of the AI Prompt.
{'assistant': {'assistantGlobalResiliencyStatus': 'ENABLED | DISABLED',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Updates the AI Agent that is set for use by default on an Amazon Q in Connect Assistant.
See also: AWS API Documentation
Request Syntax
client.update_assistant_ai_agent(
assistantId='string',
aiAgentType='MANUAL_SEARCH'|'ANSWER_RECOMMENDATION'|'SELF_SERVICE'|'EMAIL_RESPONSE'|'EMAIL_OVERVIEW'|'EMAIL_GENERATIVE_ANSWER'|'ORCHESTRATION'|'NOTE_TAKING'|'CASE_SUMMARIZATION',
configuration={
'aiAgentId': 'string',
'enabled': True|False
},
orchestratorUseCase='string'
)
string
[REQUIRED]
The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The type of the AI Agent being updated for use by default on the Amazon Q in Connect Assistant.
dict
[REQUIRED]
The configuration of the AI Agent being updated for use by default on the Amazon Q in Connect Assistant.
aiAgentId (string) -- [REQUIRED]
The ID of the AI Agent to be configured.
enabled (boolean) --
Indicates whether the AI Agent configured for this AI Agent type is enabled. When this value is omitted or set to true, the configured AI Agent runs; when set to false, the AI Agent ID is retained but no AI Agent runs for the AI Agent type. Setting this value to false is currently supported only for the ANSWER_RECOMMENDATION AI Agent type; other requests to set it to false are rejected with a validation error.
string
The orchestrator use case for the AI Agent being added.
dict
Response Syntax
{
'assistant': {
'assistantId': 'string',
'assistantArn': 'string',
'name': 'string',
'type': 'AGENT',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'description': 'string',
'tags': {
'string': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'integrationConfiguration': {
'topicIntegrationArn': 'string'
},
'capabilityConfiguration': {
'type': 'V1'|'V2'
},
'aiAgentConfiguration': {
'string': {
'aiAgentId': 'string',
'enabled': True|False
}
},
'orchestratorConfigurationList': [
{
'aiAgentId': 'string',
'orchestratorUseCase': 'string'
},
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'assistantGlobalResiliencyStatus': 'ENABLED'|'DISABLED'
}
}
Response Structure
(dict) --
assistant (dict) --
The assistant data.
assistantId (string) --
The identifier of the Amazon Q in Connect assistant.
assistantArn (string) --
The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant.
name (string) --
The name.
type (string) --
The type of assistant.
status (string) --
The status of the assistant.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect. To use Amazon Q in Connect with chat, the key policy must also allow kms:Decrypt, kms:GenerateDataKey*, and kms:DescribeKey permissions to the connect.amazonaws.com service principal.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
integrationConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant integration.
topicIntegrationArn (string) --
The Amazon Resource Name (ARN) of the integrated Amazon SNS topic used for streaming chat messages.
capabilityConfiguration (dict) --
The configuration information for the Amazon Q in Connect assistant capability.
type (string) --
The type of Amazon Q in Connect assistant capability.
aiAgentConfiguration (dict) --
The configuration of the AI Agents (mapped by AI Agent Type to AI Agent version) that is set on the Amazon Q in Connect Assistant.
(string) --
(dict) --
A type that specifies the AI Agent ID configuration data when mapping an AI Agents to be used for an AI Agent type on a session or assistant.
aiAgentId (string) --
The ID of the AI Agent to be configured.
enabled (boolean) --
Indicates whether the AI Agent configured for this AI Agent type is enabled. When this value is omitted or set to true, the configured AI Agent runs; when set to false, the AI Agent ID is retained but no AI Agent runs for the AI Agent type. Setting this value to false is currently supported only for the ANSWER_RECOMMENDATION AI Agent type; other requests to set it to false are rejected with a validation error.
orchestratorConfigurationList (list) --
The list of orchestrator configurations for the assistant.
(dict) --
An entry in the orchestrator configuration list.
aiAgentId (string) --
The identifier of the AI Agent in the orchestrator configuration.
orchestratorUseCase (string) --
The use case for the orchestrator configuration. (for example Connect.SelfService, Connect.AgentAssistance)
lastModifiedTime (datetime) --
The timestamp when the assistant was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the assistant was last modified.
assistantGlobalResiliencyStatus (string) --
Whether Amazon Connect Global Resiliency replicates the Connect instance this assistant is associated with, and so whether resources created under this assistant must satisfy the replication group's model parity constraint. Answered from the ACGR side per request rather than stored, so it reflects the customer's replication state now.
Absent means "not applicable or not known" - never read an absent field as DISABLED. It is absent on the operations that return an assistant which is not yet associated with a Connect instance, because replication cannot be established until it is.
{'content': {'fileHash': 'string',
'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp'}}
Updates information about the content.
See also: AWS API Documentation
Request Syntax
client.update_content(
knowledgeBaseId='string',
contentId='string',
revisionId='string',
title='string',
overrideLinkOutUri='string',
removeOverrideLinkOutUri=True|False,
metadata={
'string': 'string'
},
uploadId='string'
)
string
[REQUIRED]
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base. Can be either the ID or the ARN
string
[REQUIRED]
The identifier of the content. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
The revisionId of the content resource to update, taken from an earlier call to GetContent, GetContentSummary, SearchContent, or ListContents. If included, this argument acts as an optimistic lock to ensure content was not modified since it was last read. If it has been modified, this API throws a PreconditionFailedException.
string
The title of the content.
string
The URI for the article. If the knowledge base has a templateUri, setting this argument overrides it for this piece of content. To remove an existing overrideLinkOurUri, exclude this argument and set removeOverrideLinkOutUri to true.
boolean
Unset the existing overrideLinkOutUri if it exists.
dict
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
string
A pointer to the uploaded asset. This value is returned by StartContentUpload.
dict
Response Syntax
{
'content': {
'contentArn': 'string',
'contentId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'revisionId': 'string',
'title': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_FAILED',
'metadata': {
'string': 'string'
},
'tags': {
'string': 'string'
},
'linkOutUri': 'string',
'url': 'string',
'urlExpiry': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'fileHash': 'string'
}
}
Response Structure
(dict) --
content (dict) --
The content.
contentArn (string) --
The Amazon Resource Name (ARN) of the content.
contentId (string) --
The identifier of the content.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base.
name (string) --
The name of the content.
revisionId (string) --
The identifier of the content revision.
title (string) --
The title of the content.
contentType (string) --
The media type of the content.
status (string) --
The status of the content.
metadata (dict) --
A key/value map to store attributes without affecting tagging or recommendations. For example, when synchronizing data between an external system and Amazon Q in Connect, you can store an external version identifier as metadata to utilize for determining drift.
(string) --
(string) --
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
linkOutUri (string) --
The URI of the content.
url (string) --
The URL of the content.
urlExpiry (datetime) --
The expiration time of the URL as an epoch timestamp.
lastModifiedTime (datetime) --
The timestamp when the content was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the content was last modified.
fileHash (string) --
The Base64-encoded SHA-256 hash of the content file. Amazon Connect Global Resiliency returns this field only for replicated content.
{'knowledgeBase': {'lastModifiedRegion': 'string',
'lastModifiedTime': 'timestamp',
'serverSideEncryptionConfiguration': {'replicaKmsKeys': [{'arn': 'string'}]}}}
Updates the template URI of a knowledge base. This is only supported for knowledge bases of type EXTERNAL. Include a single variable in ${variable} format; this interpolated by Amazon Q in Connect using ingested content. For example, if you ingest a Salesforce article, it has an Id value, and you can set the template URI to https://myInstanceName.lightning.force.com/lightning/r/Knowledge__kav/*${Id}*/view.
See also: AWS API Documentation
Request Syntax
client.update_knowledge_base_template_uri(
knowledgeBaseId='string',
templateUri='string'
)
string
[REQUIRED]
The identifier of the knowledge base. This should not be a QUICK_RESPONSES type knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The template URI to update.
dict
Response Syntax
{
'knowledgeBase': {
'knowledgeBaseId': 'string',
'knowledgeBaseArn': 'string',
'name': 'string',
'knowledgeBaseType': 'EXTERNAL'|'CUSTOM'|'QUICK_RESPONSES'|'MESSAGE_TEMPLATES'|'MANAGED',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'ACTIVE'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED',
'lastContentModificationTime': datetime(2015, 1, 1),
'vectorIngestionConfiguration': {
'chunkingConfiguration': {
'chunkingStrategy': 'FIXED_SIZE'|'NONE'|'HIERARCHICAL'|'SEMANTIC',
'fixedSizeChunkingConfiguration': {
'maxTokens': 123,
'overlapPercentage': 123
},
'hierarchicalChunkingConfiguration': {
'levelConfigurations': [
{
'maxTokens': 123
},
],
'overlapTokens': 123
},
'semanticChunkingConfiguration': {
'maxTokens': 123,
'bufferSize': 123,
'breakpointPercentileThreshold': 123
}
},
'parsingConfiguration': {
'parsingStrategy': 'BEDROCK_FOUNDATION_MODEL',
'bedrockFoundationModelConfiguration': {
'modelArn': 'string',
'parsingPrompt': {
'parsingPromptText': 'string'
}
}
}
},
'sourceConfiguration': {
'appIntegrations': {
'appIntegrationArn': 'string',
'objectFields': [
'string',
]
},
'managedSourceConfiguration': {
'webCrawlerConfiguration': {
'urlConfiguration': {
'seedUrls': [
{
'url': 'string'
},
]
},
'crawlerLimits': {
'rateLimit': 123
},
'inclusionFilters': [
'string',
],
'exclusionFilters': [
'string',
],
'scope': 'HOST_ONLY'|'SUBDOMAINS'
}
}
},
'renderingConfiguration': {
'templateUri': 'string'
},
'serverSideEncryptionConfiguration': {
'kmsKeyId': 'string',
'replicaKmsKeys': [
{
'arn': 'string'
},
]
},
'description': 'string',
'tags': {
'string': 'string'
},
'ingestionStatus': 'SYNC_FAILED'|'SYNCING_IN_PROGRESS'|'SYNC_SUCCESS'|'CREATE_IN_PROGRESS',
'ingestionFailureReasons': [
'string',
],
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string'
}
}
Response Structure
(dict) --
knowledgeBase (dict) --
The knowledge base to update.
knowledgeBaseId (string) --
The identifier of the knowledge base.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
name (string) --
The name of the knowledge base.
knowledgeBaseType (string) --
The type of knowledge base.
status (string) --
The status of the knowledge base.
lastContentModificationTime (datetime) --
An epoch timestamp indicating the most recent content modification inside the knowledge base. If no content exists in a knowledge base, this value is unset.
vectorIngestionConfiguration (dict) --
Contains details about how to ingest the documents in a data source.
chunkingConfiguration (dict) --
Details about how to chunk the documents in the data source. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
chunkingStrategy (string) --
Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
fixedSizeChunkingConfiguration (dict) --
Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as NONE, exclude this field.
maxTokens (integer) --
The maximum number of tokens to include in a chunk.
overlapPercentage (integer) --
The percentage of overlap between adjacent chunks of a data source.
hierarchicalChunkingConfiguration (dict) --
Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
levelConfigurations (list) --
Token settings for each layer.
(dict) --
Token settings for each layer.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain in this layer.
overlapTokens (integer) --
The number of tokens to repeat across chunks in the same layer.
semanticChunkingConfiguration (dict) --
Settings for semantic document chunking for a data source. Semantic chunking splits a document into smaller documents based on groups of similar content derived from the text with natural language processing.
maxTokens (integer) --
The maximum number of tokens that a chunk can contain.
bufferSize (integer) --
The buffer size.
breakpointPercentileThreshold (integer) --
The dissimilarity threshold for splitting chunks.
parsingConfiguration (dict) --
A custom parser for data source documents.
parsingStrategy (string) --
The parsing strategy for the data source.
bedrockFoundationModelConfiguration (dict) --
Settings for a foundation model used to parse documents for a data source.
modelArn (string) --
The ARN of the foundation model.
parsingPrompt (dict) --
Instructions for interpreting the contents of a document.
parsingPromptText (string) --
Instructions for interpreting the contents of a document.
sourceConfiguration (dict) --
Source configuration information about the knowledge base.
appIntegrations (dict) --
Configuration information for Amazon AppIntegrations to automatically ingest content.
appIntegrationArn (string) --
The Amazon Resource Name (ARN) of the AppIntegrations DataIntegration to use for ingesting content.
For Salesforce, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted as source fields.
For ServiceNow, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least number, short_description, sys_mod_count, workflow_state, and active as source fields.
For Zendesk, your AppIntegrations DataIntegration must have an ObjectConfiguration if objectFields is not provided, including at least id, title, updated_at, and draft as source fields.
For SharePoint, your AppIntegrations DataIntegration must have a FileConfiguration, including only file extensions that are among docx, pdf, html, htm, and txt.
For Amazon S3, the ObjectConfiguration and FileConfiguration of your AppIntegrations DataIntegration must be null. The SourceURI of your DataIntegration must use the following format: s3://your_s3_bucket_name.
objectFields (list) --
The fields from the source that are made available to your agents in Amazon Q in Connect. Optional if ObjectConfiguration is included in the provided DataIntegration.
For Salesforce, you must include at least Id, ArticleNumber, VersionNumber, Title, PublishStatus, and IsDeleted.
For ServiceNow, you must include at least number, short_description, sys_mod_count, workflow_state, and active.
For Zendesk, you must include at least id, title, updated_at, and draft.
Make sure to include additional fields. These fields are indexed and used to source recommendations.
(string) --
managedSourceConfiguration (dict) --
Source configuration for managed resources.
webCrawlerConfiguration (dict) --
Configuration data for web crawler data source.
urlConfiguration (dict) --
The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.
seedUrls (list) --
List of URLs for crawling.
(dict) --
A URL for crawling.
url (string) --
URL for crawling
crawlerLimits (dict) --
The configuration of crawl limits for the web URLs.
rateLimit (integer) --
Rate of web URLs retrieved per minute.
inclusionFilters (list) --
A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
exclusionFilters (list) --
A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
(string) --
scope (string) --
The scope of what is crawled for your URLs. You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL https://docs.aws.amazon.com/bedrock/latest/userguide/ and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain aws.amazon.com can also include sub domain docs.aws.amazon.com.
renderingConfiguration (dict) --
Information about how to render the content.
templateUri (string) --
A URI template containing exactly one variable in ${variableName} ``format. This can only be set for ``EXTERNAL knowledge bases. For Salesforce, ServiceNow, and Zendesk, the variable must be one of the following:
Salesforce: Id, ArticleNumber, VersionNumber, Title, PublishStatus, or IsDeleted
ServiceNow: number, short_description, sys_mod_count, workflow_state, or active
Zendesk: id, title, updated_at, or draft
The variable is replaced with the actual value for a piece of content when calling GetContent.
serverSideEncryptionConfiguration (dict) --
The configuration information for the customer managed key used for encryption.
This KMS key must have a policy that allows kms:CreateGrant, kms:DescribeKey, kms:Decrypt, and kms:GenerateDataKey* permissions to the IAM identity using the key to invoke Amazon Q in Connect.
For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance.
kmsKeyId (string) --
The customer managed key used for encryption. For more information about setting up a customer managed key for Amazon Q in Connect, see Enable Amazon Q in Connect for your instance. For information about valid ID values, see Key identifiers (KeyId).
replicaKmsKeys (list) --
The list of KMS keys used to encrypt data for this resource's replicas in other Amazon Web Services Regions. Each entry corresponds to a Region where a replica is configured.
(dict) --
Contains information about the KMS key used to encrypt data in a replica Amazon Web Services Region, including its Amazon Resource Name (ARN).
arn (string) --
The Amazon Resource Name (ARN) of the KMS key in the replica Region.
description (string) --
The description.
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --
ingestionStatus (string) --
Status of ingestion on data source.
ingestionFailureReasons (list) --
List of failure reasons on ingestion per file.
(string) --
lastModifiedTime (datetime) --
The timestamp when the knowledge base was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the knowledge base was last modified.
{'quickResponse': {'lastModifiedRegion': 'string'}}
Updates an existing Amazon Q in Connect quick response.
See also: AWS API Documentation
Request Syntax
client.update_quick_response(
knowledgeBaseId='string',
quickResponseId='string',
name='string',
content={
'content': 'string'
},
contentType='string',
groupingConfiguration={
'criteria': 'string',
'values': [
'string',
]
},
removeGroupingConfiguration=True|False,
description='string',
removeDescription=True|False,
shortcutKey='string',
removeShortcutKey=True|False,
isActive=True|False,
channels=[
'string',
],
language='string'
)
string
[REQUIRED]
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
string
[REQUIRED]
The identifier of the quick response.
string
The name of the quick response.
dict
The updated content of the quick response.
content (string) --
The content of the quick response.
string
The media type of the quick response content.
Use application/x.quickresponse;format=plain for quick response written in plain text.
Use application/x.quickresponse;format=markdown for quick response written in richtext.
dict
The updated grouping configuration of the quick response.
criteria (string) --
The criteria used for grouping Amazon Q in Connect users.
The following is the list of supported criteria values.
RoutingProfileArn: Grouping the users by their Amazon Connect routing profile ARN. User should have SearchRoutingProfile and DescribeRoutingProfile permissions when setting criteria to this value.
values (list) --
The list of values that define different groups of Amazon Q in Connect users.
When setting criteria to RoutingProfileArn, you need to provide a list of ARNs of Connect Customer routing profiles as values of this parameter.
(string) --
boolean
Whether to remove the grouping configuration of the quick response.
string
The updated description of the quick response.
boolean
Whether to remove the description from the quick response.
string
The shortcut key of the quick response. The value should be unique across the knowledge base.
boolean
Whether to remove the shortcut key of the quick response.
boolean
Whether the quick response is active.
list
The Connect Customer contact channels this quick response applies to. The supported contact channel types include Chat.
(string) --
string
The language code value for the language in which the quick response is written. The supported language codes include de_DE, en_US, es_ES, fr_FR, id_ID, it_IT, ja_JP, ko_KR, pt_BR, zh_CN, zh_TW
dict
Response Syntax
{
'quickResponse': {
'quickResponseArn': 'string',
'quickResponseId': 'string',
'knowledgeBaseArn': 'string',
'knowledgeBaseId': 'string',
'name': 'string',
'contentType': 'string',
'status': 'CREATE_IN_PROGRESS'|'CREATE_FAILED'|'CREATED'|'DELETE_IN_PROGRESS'|'DELETE_FAILED'|'DELETED'|'UPDATE_IN_PROGRESS'|'UPDATE_FAILED',
'createdTime': datetime(2015, 1, 1),
'lastModifiedTime': datetime(2015, 1, 1),
'lastModifiedRegion': 'string',
'contents': {
'plainText': {
'content': 'string'
},
'markdown': {
'content': 'string'
}
},
'description': 'string',
'groupingConfiguration': {
'criteria': 'string',
'values': [
'string',
]
},
'shortcutKey': 'string',
'lastModifiedBy': 'string',
'isActive': True|False,
'channels': [
'string',
],
'language': 'string',
'tags': {
'string': 'string'
}
}
}
Response Structure
(dict) --
quickResponse (dict) --
The quick response.
quickResponseArn (string) --
The Amazon Resource Name (ARN) of the quick response.
quickResponseId (string) --
The identifier of the quick response.
knowledgeBaseArn (string) --
The Amazon Resource Name (ARN) of the knowledge base.
knowledgeBaseId (string) --
The identifier of the knowledge base. Can be either the ID or the ARN. URLs cannot contain the ARN.
name (string) --
The name of the quick response.
contentType (string) --
The media type of the quick response content.
Use application/x.quickresponse;format=plain for quick response written in plain text.
Use application/x.quickresponse;format=markdown for quick response written in richtext.
status (string) --
The status of the quick response data.
createdTime (datetime) --
The timestamp when the quick response was created.
lastModifiedTime (datetime) --
The timestamp when the quick response data was last modified.
lastModifiedRegion (string) --
The Amazon Web Services Region where the quick response was last modified.
contents (dict) --
The contents of the quick response.
plainText (dict) --
The container quick response content.
content (string) --
The content of the quick response.
markdown (dict) --
The container quick response content.
content (string) --
The content of the quick response.
description (string) --
The description of the quick response.
groupingConfiguration (dict) --
The configuration information of the user groups that the quick response is accessible to.
criteria (string) --
The criteria used for grouping Amazon Q in Connect users.
The following is the list of supported criteria values.
RoutingProfileArn: Grouping the users by their Amazon Connect routing profile ARN. User should have SearchRoutingProfile and DescribeRoutingProfile permissions when setting criteria to this value.
values (list) --
The list of values that define different groups of Amazon Q in Connect users.
When setting criteria to RoutingProfileArn, you need to provide a list of ARNs of Connect Customer routing profiles as values of this parameter.
(string) --
shortcutKey (string) --
The shortcut key of the quick response. The value should be unique across the knowledge base.
lastModifiedBy (string) --
The Amazon Resource Name (ARN) of the user who last updated the quick response data.
isActive (boolean) --
Whether the quick response is active.
channels (list) --
The Connect Customer contact channels this quick response applies to. The supported contact channel types include Chat.
(string) --
language (string) --
The language code value for the language in which the quick response is written. The supported language codes include de_DE, en_US, es_ES, fr_FR, id_ID, it_IT, ja_JP, ko_KR, pt_BR, zh_CN, zh_TW
tags (dict) --
The tags used to organize, track, or control access for this resource.
(string) --
(string) --