- Navigation GuideYou are on a Command (operation) page with structural examples. Use the navigation breadcrumb if you would like to return to the Client landing page.
CreateAIGuardrailCommand
Creates an Amazon Q in Connect AI Guardrail.
Example Syntax
Use a bare-bones client and the command you need to make an API call.
import { QConnectClient, CreateAIGuardrailCommand } from "@aws-sdk/client-qconnect"; // ES Modules import
// const { QConnectClient, CreateAIGuardrailCommand } = require("@aws-sdk/client-qconnect"); // CommonJS import
const client = new QConnectClient(config);
const input = { // CreateAIGuardrailRequest
clientToken: "STRING_VALUE",
assistantId: "STRING_VALUE", // required
name: "STRING_VALUE", // required
blockedInputMessaging: "STRING_VALUE", // required
blockedOutputsMessaging: "STRING_VALUE", // required
visibilityStatus: "STRING_VALUE", // required
description: "STRING_VALUE",
topicPolicyConfig: { // AIGuardrailTopicPolicyConfig
topicsConfig: [ // GuardrailTopicsConfig // required
{ // GuardrailTopicConfig
name: "STRING_VALUE", // required
definition: "STRING_VALUE", // required
examples: [ // GuardrailTopicExamples
"STRING_VALUE",
],
type: "STRING_VALUE", // required
},
],
},
contentPolicyConfig: { // AIGuardrailContentPolicyConfig
filtersConfig: [ // GuardrailContentFiltersConfig // required
{ // GuardrailContentFilterConfig
type: "STRING_VALUE", // required
inputStrength: "STRING_VALUE", // required
outputStrength: "STRING_VALUE", // required
},
],
},
wordPolicyConfig: { // AIGuardrailWordPolicyConfig
wordsConfig: [ // GuardrailWordsConfig
{ // GuardrailWordConfig
text: "STRING_VALUE", // required
},
],
managedWordListsConfig: [ // GuardrailManagedWordListsConfig
{ // GuardrailManagedWordsConfig
type: "STRING_VALUE", // required
},
],
},
sensitiveInformationPolicyConfig: { // AIGuardrailSensitiveInformationPolicyConfig
piiEntitiesConfig: [ // GuardrailPiiEntitiesConfig
{ // GuardrailPiiEntityConfig
type: "STRING_VALUE", // required
action: "STRING_VALUE", // required
},
],
regexesConfig: [ // GuardrailRegexesConfig
{ // GuardrailRegexConfig
name: "STRING_VALUE", // required
description: "STRING_VALUE",
pattern: "STRING_VALUE", // required
action: "STRING_VALUE", // required
},
],
},
contextualGroundingPolicyConfig: { // AIGuardrailContextualGroundingPolicyConfig
filtersConfig: [ // GuardrailContextualGroundingFiltersConfig // required
{ // GuardrailContextualGroundingFilterConfig
type: "STRING_VALUE", // required
threshold: Number("double"), // required
},
],
},
tags: { // Tags
"<keys>": "STRING_VALUE",
},
};
const command = new CreateAIGuardrailCommand(input);
const response = await client.send(command);
// { // CreateAIGuardrailResponse
// aiGuardrail: { // AIGuardrailData
// assistantId: "STRING_VALUE", // required
// assistantArn: "STRING_VALUE", // required
// aiGuardrailArn: "STRING_VALUE", // required
// aiGuardrailId: "STRING_VALUE", // required
// name: "STRING_VALUE", // required
// visibilityStatus: "STRING_VALUE", // required
// blockedInputMessaging: "STRING_VALUE", // required
// blockedOutputsMessaging: "STRING_VALUE", // required
// description: "STRING_VALUE",
// topicPolicyConfig: { // AIGuardrailTopicPolicyConfig
// topicsConfig: [ // GuardrailTopicsConfig // required
// { // GuardrailTopicConfig
// name: "STRING_VALUE", // required
// definition: "STRING_VALUE", // required
// examples: [ // GuardrailTopicExamples
// "STRING_VALUE",
// ],
// type: "STRING_VALUE", // required
// },
// ],
// },
// contentPolicyConfig: { // AIGuardrailContentPolicyConfig
// filtersConfig: [ // GuardrailContentFiltersConfig // required
// { // GuardrailContentFilterConfig
// type: "STRING_VALUE", // required
// inputStrength: "STRING_VALUE", // required
// outputStrength: "STRING_VALUE", // required
// },
// ],
// },
// wordPolicyConfig: { // AIGuardrailWordPolicyConfig
// wordsConfig: [ // GuardrailWordsConfig
// { // GuardrailWordConfig
// text: "STRING_VALUE", // required
// },
// ],
// managedWordListsConfig: [ // GuardrailManagedWordListsConfig
// { // GuardrailManagedWordsConfig
// type: "STRING_VALUE", // required
// },
// ],
// },
// sensitiveInformationPolicyConfig: { // AIGuardrailSensitiveInformationPolicyConfig
// piiEntitiesConfig: [ // GuardrailPiiEntitiesConfig
// { // GuardrailPiiEntityConfig
// type: "STRING_VALUE", // required
// action: "STRING_VALUE", // required
// },
// ],
// regexesConfig: [ // GuardrailRegexesConfig
// { // GuardrailRegexConfig
// name: "STRING_VALUE", // required
// description: "STRING_VALUE",
// pattern: "STRING_VALUE", // required
// action: "STRING_VALUE", // required
// },
// ],
// },
// contextualGroundingPolicyConfig: { // AIGuardrailContextualGroundingPolicyConfig
// filtersConfig: [ // GuardrailContextualGroundingFiltersConfig // required
// { // GuardrailContextualGroundingFilterConfig
// type: "STRING_VALUE", // required
// threshold: Number("double"), // required
// },
// ],
// },
// tags: { // Tags
// "<keys>": "STRING_VALUE",
// },
// status: "STRING_VALUE",
// modifiedTime: new Date("TIMESTAMP"),
// },
// };
CreateAIGuardrailCommand Input
Parameter | Type | Description |
---|
Parameter | Type | Description |
---|---|---|
assistantId Required | string | undefined | The identifier of the Amazon Q in Connect assistant. Can be either the ID or the ARN. URLs cannot contain the ARN. |
blockedInputMessaging Required | string | undefined | The message to return when the AI Guardrail blocks a prompt. |
blockedOutputsMessaging Required | string | undefined | The message to return when the AI Guardrail blocks a model response. |
name Required | string | undefined | The name of the AI Guardrail. |
visibilityStatus Required | VisibilityStatus | undefined | The visibility status of the AI Guardrail. |
clientToken | string | undefined | 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 .. |
contentPolicyConfig | AIGuardrailContentPolicyConfig | undefined | The content filter policies to configure for the AI Guardrail. |
contextualGroundingPolicyConfig | AIGuardrailContextualGroundingPolicyConfig | undefined | The contextual grounding policy configuration used to create an AI Guardrail. |
description | string | undefined | A description of the AI Guardrail. |
sensitiveInformationPolicyConfig | AIGuardrailSensitiveInformationPolicyConfig | undefined | The sensitive information policy to configure for the AI Guardrail. |
tags | Record<string, string> | undefined | The tags used to organize, track, or control access for this resource. |
topicPolicyConfig | AIGuardrailTopicPolicyConfig | undefined | The topic policies to configure for the AI Guardrail. |
wordPolicyConfig | AIGuardrailWordPolicyConfig | undefined | The word policy you configure for the AI Guardrail. |
CreateAIGuardrailCommand Output
Parameter | Type | Description |
---|
Parameter | Type | Description |
---|---|---|
$metadata Required | ResponseMetadata | Metadata pertaining to this request. |
aiGuardrail | AIGuardrailData | undefined | The data of the AI Guardrail. |
Throws
Name | Fault | Details |
---|
Name | Fault | Details |
---|---|---|
AccessDeniedException | client | You do not have sufficient access to perform this action. |
ConflictException | client | The request could not be processed because of conflict in the current state of the resource. For example, if you're using a |
ResourceNotFoundException | client | The specified resource does not exist. |
ServiceQuotaExceededException | client | 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. |
ThrottlingException | client | The throttling limit has been exceeded. |
ValidationException | client | The input fails to satisfy the constraints specified by a service. |
QConnectServiceException | Base exception class for all service exceptions from QConnect service. |