Request Syntax URI Request Parameters Request Body Response Syntax Response Elements Errors See Also

CreateAIGuardrail

Creates an Amazon Q in Connect AI Guardrail.

Request Syntax


POST /assistants/assistantId/aiguardrails HTTP/1.1
Content-type: application/json

{
   "blockedInputMessaging": "string",
   "blockedOutputsMessaging": "string",
   "clientToken": "string",
   "contentPolicyConfig": { 
      "filtersConfig": [ 
         { 
            "inputStrength": "string",
            "outputStrength": "string",
            "type": "string"
         }
      ]
   },
   "contextualGroundingPolicyConfig": { 
      "filtersConfig": [ 
         { 
            "threshold": number,
            "type": "string"
         }
      ]
   },
   "description": "string",
   "name": "string",
   "sensitiveInformationPolicyConfig": { 
      "piiEntitiesConfig": [ 
         { 
            "action": "string",
            "type": "string"
         }
      ],
      "regexesConfig": [ 
         { 
            "action": "string",
            "description": "string",
            "name": "string",
            "pattern": "string"
         }
      ]
   },
   "tags": { 
      "string" : "string" 
   },
   "topicPolicyConfig": { 
      "topicsConfig": [ 
         { 
            "definition": "string",
            "examples": [ "string" ],
            "name": "string",
            "type": "string"
         }
      ]
   },
   "visibilityStatus": "string",
   "wordPolicyConfig": { 
      "managedWordListsConfig": [ 
         { 
            "type": "string"
         }
      ],
      "wordsConfig": [ 
         { 
            "text": "string"
         }
      ]
   }
}

URI Request Parameters

The request uses the following URI parameters.

assistantId

The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN.

Pattern: ^[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}$|^arn:[a-z-]*?:wisdom:[a-z0-9-]*?:[0-9]{12}:[a-z-]*?/[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}(?:/[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}){0,2}$

Required: Yes

Request Body

The request accepts the following data in JSON format.

blockedInputMessaging

The message to return when the AI Guardrail blocks a prompt.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 500.

Required: Yes

blockedOutputsMessaging

The message to return when the AI Guardrail blocks a model response.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 500.

Required: Yes

clientToken

A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. If not provided, the AWS SDK populates this field. For more information about idempotency, see Making retries safe with idempotent APIs..

Type: String

Length Constraints: Minimum length of 1. Maximum length of 4096.

Required: No

contentPolicyConfig

The content filter policies to configure for the AI Guardrail.

Type: AIGuardrailContentPolicyConfig object

Required: No

contextualGroundingPolicyConfig

The contextual grounding policy configuration used to create an AI Guardrail.

Type: AIGuardrailContextualGroundingPolicyConfig object

Required: No

description

A description of the AI Guardrail.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 200.

Required: No

name

The name of the AI Guardrail.

Type: String

Length Constraints: Minimum length of 1. Maximum length of 255.

Pattern: ^[a-zA-Z0-9\s_.,-]+

Required: Yes

sensitiveInformationPolicyConfig

The sensitive information policy to configure for the AI Guardrail.

Type: AIGuardrailSensitiveInformationPolicyConfig object

Required: No

tags

The tags used to organize, track, or control access for this resource.

Type: String to string map

Key Length Constraints: Minimum length of 1. Maximum length of 128.

Key Pattern: ^(?!aws:)[a-zA-Z+-=._:/]+$

Value Length Constraints: Minimum length of 1. Maximum length of 256.

Required: No

topicPolicyConfig

The topic policies to configure for the AI Guardrail.

Type: AIGuardrailTopicPolicyConfig object

Required: No

visibilityStatus

The visibility status of the AI Guardrail.

Type: String

Valid Values: SAVED | PUBLISHED

Required: Yes

wordPolicyConfig

The word policy you configure for the AI Guardrail.

Type: AIGuardrailWordPolicyConfig object

Required: No

Response Syntax


HTTP/1.1 200
Content-type: application/json

{
   "aiGuardrail": { 
      "aiGuardrailArn": "string",
      "aiGuardrailId": "string",
      "assistantArn": "string",
      "assistantId": "string",
      "blockedInputMessaging": "string",
      "blockedOutputsMessaging": "string",
      "contentPolicyConfig": { 
         "filtersConfig": [ 
            { 
               "inputStrength": "string",
               "outputStrength": "string",
               "type": "string"
            }
         ]
      },
      "contextualGroundingPolicyConfig": { 
         "filtersConfig": [ 
            { 
               "threshold": number,
               "type": "string"
            }
         ]
      },
      "description": "string",
      "modifiedTime": number,
      "name": "string",
      "sensitiveInformationPolicyConfig": { 
         "piiEntitiesConfig": [ 
            { 
               "action": "string",
               "type": "string"
            }
         ],
         "regexesConfig": [ 
            { 
               "action": "string",
               "description": "string",
               "name": "string",
               "pattern": "string"
            }
         ]
      },
      "status": "string",
      "tags": { 
         "string" : "string" 
      },
      "topicPolicyConfig": { 
         "topicsConfig": [ 
            { 
               "definition": "string",
               "examples": [ "string" ],
               "name": "string",
               "type": "string"
            }
         ]
      },
      "visibilityStatus": "string",
      "wordPolicyConfig": { 
         "managedWordListsConfig": [ 
            { 
               "type": "string"
            }
         ],
         "wordsConfig": [ 
            { 
               "text": "string"
            }
         ]
      }
   }
}

Response Elements

If the action is successful, the service sends back an HTTP 200 response.

The following data is returned in JSON format by the service.

aiGuardrail

The data of the AI Guardrail.

Type: AIGuardrailData object

Errors

For information about the errors that are common to all actions, see Common Errors.

AccessDeniedException

You do not have sufficient access to perform this action.

HTTP Status Code: 403

ConflictException

The request could not be processed because of conflict in the current state of the resource. For example, if you're using a Create API (such as CreateAssistant) that accepts name, a conflicting resource (usually with the same name) is being created or mutated.

HTTP Status Code: 409

ResourceNotFoundException

The specified resource does not exist.

HTTP Status Code: 404

ServiceQuotaExceededException

You've exceeded your service quota. To perform the requested action, remove some of the relevant resources, or use service quotas to request a service quota increase.

HTTP Status Code: 402

ThrottlingException

The throttling limit has been exceeded.

HTTP Status Code: 400

ValidationException

The input fails to satisfy the constraints specified by a service.

HTTP Status Code: 400