ai_guardrails

Creates, updates, deletes, gets or lists an ai_guardrails resource.

Overview

Name	ai_guardrails
Type	Resource
Id	aws.qconnect.ai_guardrails

Fields

The following fields are returned by SELECT queries:

get_ai_guardrail

Name	Datatype	Description
ai_guardrail	object	The data of the AI Guardrail.
version_number	integer (int64)	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).

list_ai_guardrails

Name	Datatype	Description
name	string	The name of the AI Guardrail. (pattern: <code>[a-zA-Z0-9\s_.,-]+.*</code>)
ai_guardrail_arn	string	The Amazon Resource Name (ARN) of the AI Guardrail. (pattern: <code>arn:[a-z-]?:wisdom:[a-z0-9-]?:[0-9]{12}:[a-z-]*?/[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}(?:/[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}){0,2}</code>)
ai_guardrail_id	string	The identifier of the Amazon Q in Connect AI Guardrail. (pattern: <code>[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}</code>)
assistant_arn	string	The Amazon Resource Name (ARN) of the Amazon Q in Connect assistant. (pattern: <code>arn:[a-z-]?:wisdom:[a-z0-9-]?:[0-9]{12}:[a-z-]*?/[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}(?:/[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}){0,2}</code>)
assistant_id	string	The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN. (pattern: <code>[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}</code>)
description	string	Description of the guardrail or its version
modified_time	string (date-time)	The time the AI Guardrail was last modified.
status	string	The status of the AI Guardrail. (CREATE_IN_PROGRESS, CREATE_FAILED, ACTIVE, DELETE_IN_PROGRESS, DELETE_FAILED, DELETED)
tags	object	The tags used to organize, track, or control access for this resource.
visibility_status	string	The visibility status of the AI Guardrail. (SAVED, PUBLISHED)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
get_ai_guardrail	select	assistant_id, ai_guardrail_id, region		Gets the Amazon Q in Connect AI Guardrail.
list_ai_guardrails	select	assistant_id, region	nextToken, maxResults	Lists the AI Guardrails available on the Amazon Q in Connect assistant.
create_ai_guardrail	insert	assistant_id, region, name, blockedInputMessaging, blockedOutputsMessaging, visibilityStatus		Creates an Amazon Q in Connect AI Guardrail.
update_ai_guardrail	update	assistant_id, ai_guardrail_id, region, visibilityStatus, blockedInputMessaging, blockedOutputsMessaging		Updates an AI Guardrail.
delete_ai_guardrail	delete	assistant_id, ai_guardrail_id, region		Deletes an Amazon Q in Connect AI Guardrail.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
ai_guardrail_id	string	The identifier of the Amazon Q in Connect AI Guardrail. Can be either the ID or the ARN. URLs cannot contain the ARN.
assistant_id	string	The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.
region	string	AWS region (default: us-east-1)
maxResults	integer	The maximum number of results to return per page.
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.

SELECT examples

get_ai_guardrail

Gets the Amazon Q in Connect AI Guardrail.

SELECT
ai_guardrail,
version_number
FROM aws.qconnect.ai_guardrails
WHERE assistant_id = '{{ assistant_id }}' -- required
AND ai_guardrail_id = '{{ ai_guardrail_id }}' -- required
AND region = '{{ region }}' -- required
;

list_ai_guardrails

Lists the AI Guardrails available on the Amazon Q in Connect assistant.

SELECT
name,
ai_guardrail_arn,
ai_guardrail_id,
assistant_arn,
assistant_id,
description,
modified_time,
status,
tags,
visibility_status
FROM aws.qconnect.ai_guardrails
WHERE assistant_id = '{{ assistant_id }}' -- required
AND region = '{{ region }}' -- required
AND nextToken = '{{ nextToken }}'
AND maxResults = '{{ maxResults }}'
;

INSERT examples

create_ai_guardrail

Creates an Amazon Q in Connect AI Guardrail.

INSERT INTO aws.qconnect.ai_guardrails (
clientToken,
name,
blockedInputMessaging,
blockedOutputsMessaging,
visibilityStatus,
description,
topicPolicyConfig,
contentPolicyConfig,
wordPolicyConfig,
sensitiveInformationPolicyConfig,
contextualGroundingPolicyConfig,
tags,
assistant_id,
region
)
SELECT 
'{{ clientToken }}',
'{{ name }}' /* required */,
'{{ blockedInputMessaging }}' /* required */,
'{{ blockedOutputsMessaging }}' /* required */,
'{{ visibilityStatus }}' /* required */,
'{{ description }}',
'{{ topicPolicyConfig }}',
'{{ contentPolicyConfig }}',
'{{ wordPolicyConfig }}',
'{{ sensitiveInformationPolicyConfig }}',
'{{ contextualGroundingPolicyConfig }}',
'{{ tags }}',
'{{ assistant_id }}',
'{{ region }}'
RETURNING
ai_guardrail
;

Manifest

# Description fields are for documentation purposes
- name: ai_guardrails
props:
  - name: assistant_id
    value: "{{ assistant_id }}"
    description: Required parameter for the ai_guardrails resource.
  - name: region
    value: "{{ region }}"
    description: Required parameter for the ai_guardrails resource.
  - name: clientToken
    value: "{{ clientToken }}"
  - name: name
    value: "{{ name }}"
  - name: blockedInputMessaging
    value: "{{ blockedInputMessaging }}"
    description: |
      Messaging for when violations are detected in text
  - name: blockedOutputsMessaging
    value: "{{ blockedOutputsMessaging }}"
    description: |
      Messaging for when violations are detected in text
  - name: visibilityStatus
    value: "{{ visibilityStatus }}"
    valid_values: ['SAVED', 'PUBLISHED']
  - name: description
    value: "{{ description }}"
    description: |
      Description of the guardrail or its version
  - name: topicPolicyConfig
    description: |
      Contains details about topics that the AI Guardrail should identify and deny.
    value:
      topicsConfig:
        - name: "{{ name }}"
          definition: "{{ definition }}"
          examples: "{{ examples }}"
          type_: "{{ type_ }}"
  - name: contentPolicyConfig
    description: |
      Contains details about how to handle harmful content.
    value:
      filtersConfig:
        - type_: "{{ type_ }}"
          inputStrength: "{{ inputStrength }}"
          outputStrength: "{{ outputStrength }}"
  - name: wordPolicyConfig
    description: |
      Contains details about the word policy to configured for the AI Guardrail.
    value:
      wordsConfig:
        - text: "{{ text }}"
      managedWordListsConfig:
        - type_: "{{ type_ }}"
  - name: sensitiveInformationPolicyConfig
    description: |
      Contains details about PII entities and regular expressions to configure for the AI Guardrail.
    value:
      piiEntitiesConfig:
        - type_: "{{ type_ }}"
          action: "{{ action }}"
      regexesConfig:
        - name: "{{ name }}"
          description: "{{ description }}"
          pattern_: "{{ pattern_ }}"
          action: "{{ action }}"
  - name: contextualGroundingPolicyConfig
    description: |
      The policy configuration details for the AI Guardrail's contextual grounding policy.
    value:
      filtersConfig:
        - type_: "{{ type_ }}"
          threshold: {{ threshold }}
  - name: tags
    value: "{{ tags }}"

UPDATE examples

update_ai_guardrail

Updates an AI Guardrail.

UPDATE aws.qconnect.ai_guardrails
SET 
clientToken = '{{ clientToken }}',
visibilityStatus = '{{ visibilityStatus }}',
blockedInputMessaging = '{{ blockedInputMessaging }}',
blockedOutputsMessaging = '{{ blockedOutputsMessaging }}',
description = '{{ description }}',
topicPolicyConfig = '{{ topicPolicyConfig }}',
contentPolicyConfig = '{{ contentPolicyConfig }}',
wordPolicyConfig = '{{ wordPolicyConfig }}',
sensitiveInformationPolicyConfig = '{{ sensitiveInformationPolicyConfig }}',
contextualGroundingPolicyConfig = '{{ contextualGroundingPolicyConfig }}'
WHERE 
assistant_id = '{{ assistant_id }}' --required
AND ai_guardrail_id = '{{ ai_guardrail_id }}' --required
AND region = '{{ region }}' --required
AND visibilityStatus = '{{ visibilityStatus }}' --required
AND blockedInputMessaging = '{{ blockedInputMessaging }}' --required
AND blockedOutputsMessaging = '{{ blockedOutputsMessaging }}' --required
RETURNING
ai_guardrail;

DELETE examples

delete_ai_guardrail

Deletes an Amazon Q in Connect AI Guardrail.

DELETE FROM aws.qconnect.ai_guardrails
WHERE assistant_id = '{{ assistant_id }}' --required
AND ai_guardrail_id = '{{ ai_guardrail_id }}' --required
AND region = '{{ region }}' --required
;