Amazon Lex Model Building V2

2023/11/27 - Amazon Lex Model Building V2 - 4 new 6 updated api methods

Changes  This release introduces new generative AI features in AWS Lex: Assisted Slot Resolution, Descriptive Bot Building, and Sample Utterance Generation. These features leverage large language models available through Amazon Bedrock to improve the bot builder and customer experiences.

GenerateBotElement (new) Link ¶

Generates sample utterances for an intent.

See also: AWS API Documentation

Request Syntax

client.generate_bot_element(
    intentId='string',
    botId='string',
    botVersion='string',
    localeId='string'
)
type intentId

string

param intentId

[REQUIRED]

The intent unique Id for the bot request to generate utterances.

type botId

string

param botId

[REQUIRED]

The bot unique Id for the bot request to generate utterances.

type botVersion

string

param botVersion

[REQUIRED]

The bot version for the bot request to generate utterances.

type localeId

string

param localeId

[REQUIRED]

The unique locale Id for the bot request to generate utterances.

rtype

dict

returns

Response Syntax

{
    'botId': 'string',
    'botVersion': 'string',
    'localeId': 'string',
    'intentId': 'string',
    'sampleUtterances': [
        {
            'utterance': 'string'
        },
    ]
}

Response Structure

  • (dict) --

    • botId (string) --

      The unique bot Id for the bot which received the response.

    • botVersion (string) --

      The unique bot version for the bot which received the response.

    • localeId (string) --

      The unique locale Id for the bot which received the response.

    • intentId (string) --

      The unique intent Id for the bot which received the response.

    • sampleUtterances (list) --

      The sample utterances for the bot which received the response.

      • (dict) --

        A sample utterance that invokes an intent or respond to a slot elicitation prompt.

        • utterance (string) --

          The sample utterance that Amazon Lex uses to build its machine-learning model to recognize intents.

ListBotResourceGenerations (new) Link ¶

Lists the generation requests made for a bot locale.

See also: AWS API Documentation

Request Syntax

client.list_bot_resource_generations(
    botId='string',
    botVersion='string',
    localeId='string',
    sortBy={
        'attribute': 'creationStartTime'|'lastUpdatedTime',
        'order': 'Ascending'|'Descending'
    },
    maxResults=123,
    nextToken='string'
)
type botId

string

param botId

[REQUIRED]

The unique identifier of the bot whose generation requests you want to view.

type botVersion

string

param botVersion

[REQUIRED]

The version of the bot whose generation requests you want to view.

type localeId

string

param localeId

[REQUIRED]

The locale of the bot whose generation requests you want to view.

type sortBy

dict

param sortBy

An object containing information about the attribute and the method by which to sort the results

  • attribute (string) -- [REQUIRED]

    The attribute by which to sort the generation request information. You can sort by the following attributes.

    • creationStartTime – The time at which the generation request was created.

    • lastUpdatedTime – The time at which the generation request was last updated.

  • order (string) -- [REQUIRED]

    The order by which to sort the generation request information.

type maxResults

integer

param maxResults

The maximum number of results to return in the response.

type nextToken

string

param nextToken

If the total number of results is greater than the number specified in the maxResults , the response returns a token in the nextToken field. Use this token when making a request to return the next batch of results.

rtype

dict

returns

Response Syntax

{
    'botId': 'string',
    'botVersion': 'string',
    'localeId': 'string',
    'generationSummaries': [
        {
            'generationId': 'string',
            'generationStatus': 'Failed'|'Complete'|'InProgress',
            'creationDateTime': datetime(2015, 1, 1),
            'lastUpdatedDateTime': datetime(2015, 1, 1)
        },
    ],
    'nextToken': 'string'
}

Response Structure

  • (dict) --

    • botId (string) --

      The unique identifier of the bot for which the generation requests were made.

    • botVersion (string) --

      The version of the bot for which the generation requests were made.

    • localeId (string) --

      The locale of the bot for which the generation requests were made.

    • generationSummaries (list) --

      A list of objects, each containing information about a generation request for the bot locale.

      • (dict) --

        Contains information about a generation request made for the bot locale.

        • generationId (string) --

          The unique identifier of the generation request.

        • generationStatus (string) --

          The status of the generation request.

        • creationDateTime (datetime) --

          The date and time at which the generation request was made.

        • lastUpdatedDateTime (datetime) --

          The date and time at which the generation request was last updated.

    • nextToken (string) --

      If the total number of results is greater than the number specified in the maxResults , the response returns a token in the nextToken field. Use this token when making a request to return the next batch of results.

DescribeBotResourceGeneration (new) Link ¶

Returns information about a request to generate a bot through natural language description, made through the StartBotResource API. Use the generatedBotLocaleUrl to retrieve the Amazon S3 object containing the bot locale configuration. You can then modify and import this configuration.

See also: AWS API Documentation

Request Syntax

client.describe_bot_resource_generation(
    botId='string',
    botVersion='string',
    localeId='string',
    generationId='string'
)
type botId

string

param botId

[REQUIRED]

The unique identifier of the bot for which to return the generation details.

type botVersion

string

param botVersion

[REQUIRED]

The version of the bot for which to return the generation details.

type localeId

string

param localeId

[REQUIRED]

The locale of the bot for which to return the generation details.

type generationId

string

param generationId

[REQUIRED]

The unique identifier of the generation request for which to return the generation details.

rtype

dict

returns

Response Syntax

{
    'botId': 'string',
    'botVersion': 'string',
    'localeId': 'string',
    'generationId': 'string',
    'failureReasons': [
        'string',
    ],
    'generationStatus': 'Failed'|'Complete'|'InProgress',
    'generationInputPrompt': 'string',
    'generatedBotLocaleUrl': 'string',
    'creationDateTime': datetime(2015, 1, 1),
    'modelArn': 'string',
    'lastUpdatedDateTime': datetime(2015, 1, 1)
}

Response Structure

  • (dict) --

    • botId (string) --

      The unique identifier of the bot for which the generation request was made.

    • botVersion (string) --

      The version of the bot for which the generation request was made.

    • localeId (string) --

      The locale of the bot for which the generation request was made.

    • generationId (string) --

      The generation ID for which to return the generation details.

    • failureReasons (list) --

      A list of reasons why the generation of bot resources through natural language description failed.

      • (string) --

    • generationStatus (string) --

      The status of the generation request.

    • generationInputPrompt (string) --

      The prompt used in the generation request.

    • generatedBotLocaleUrl (string) --

      The Amazon S3 location of the generated bot locale configuration.

    • creationDateTime (datetime) --

      The date and time at which the item was generated.

    • modelArn (string) --

      The ARN of the model used to generate the bot resources.

    • lastUpdatedDateTime (datetime) --

      The date and time at which the generated item was updated.

StartBotResourceGeneration (new) Link ¶

Starts a request for the descriptive bot builder to generate a bot locale configuration based on the prompt you provide it. After you make this call, use the DescribeBotResourceGeneration operation to check on the status of the generation and for the generatedBotLocaleUrl when the generation is complete. Use that value to retrieve the Amazon S3 object containing the bot locale configuration. You can then modify and import this configuration.

See also: AWS API Documentation

Request Syntax

client.start_bot_resource_generation(
    generationInputPrompt='string',
    botId='string',
    botVersion='string',
    localeId='string'
)
type generationInputPrompt

string

param generationInputPrompt

[REQUIRED]

The prompt to generate intents and slot types for the bot locale. Your description should be both detailed and precise to help generate appropriate and sufficient intents for your bot. Include a list of actions to improve the intent creation process.

type botId

string

param botId

[REQUIRED]

The unique identifier of the bot for which to generate intents and slot types.

type botVersion

string

param botVersion

[REQUIRED]

The version of the bot for which to generate intents and slot types.

type localeId

string

param localeId

[REQUIRED]

The locale of the bot for which to generate intents and slot types.

rtype

dict

returns

Response Syntax

{
    'generationInputPrompt': 'string',
    'generationId': 'string',
    'botId': 'string',
    'botVersion': 'string',
    'localeId': 'string',
    'generationStatus': 'Failed'|'Complete'|'InProgress',
    'creationDateTime': datetime(2015, 1, 1)
}

Response Structure

  • (dict) --

    • generationInputPrompt (string) --

      The prompt that was used generate intents and slot types for the bot locale.

    • generationId (string) --

      The unique identifier of the generation request.

    • botId (string) --

      The unique identifier of the bot for which the generation request was made.

    • botVersion (string) --

      The version of the bot for which the generation request was made.

    • localeId (string) --

      The locale of the bot for which the generation request was made.

    • generationStatus (string) --

      The status of the generation request.

    • creationDateTime (datetime) --

      The date and time at which the generation request was made.

CreateBotLocale (updated) Link ¶
Changes (both)
{'generativeAISettings': {'buildtimeSettings': {'descriptiveBotBuilder': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                          'enabled': 'boolean'},
                                                'sampleUtteranceGeneration': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                              'enabled': 'boolean'}},
                          'runtimeSettings': {'slotResolutionImprovement': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                            'enabled': 'boolean'}}}}

Creates a locale in the bot. The locale contains the intents and slot types that the bot uses in conversations with users in the specified language and locale. You must add a locale to a bot before you can add intents and slot types to the bot.

See also: AWS API Documentation

Request Syntax

client.create_bot_locale(
    botId='string',
    botVersion='string',
    localeId='string',
    description='string',
    nluIntentConfidenceThreshold=123.0,
    voiceSettings={
        'voiceId': 'string',
        'engine': 'standard'|'neural'
    },
    generativeAISettings={
        'runtimeSettings': {
            'slotResolutionImprovement': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        },
        'buildtimeSettings': {
            'descriptiveBotBuilder': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            },
            'sampleUtteranceGeneration': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        }
    }
)
type botId

string

param botId

[REQUIRED]

The identifier of the bot to create the locale for.

type botVersion

string

param botVersion

[REQUIRED]

The version of the bot to create the locale for. This can only be the draft version of the bot.

type localeId

string

param localeId

[REQUIRED]

The identifier of the language and locale that the bot will be used in. The string must match one of the supported locales. All of the intents, slot types, and slots used in the bot must have the same locale. For more information, see Supported languages.

type description

string

param description

A description of the bot locale. Use this to help identify the bot locale in lists.

type nluIntentConfidenceThreshold

float

param nluIntentConfidenceThreshold

[REQUIRED]

Determines the threshold where Amazon Lex will insert the AMAZON.FallbackIntent , AMAZON.KendraSearchIntent , or both when returning alternative intents. AMAZON.FallbackIntent and AMAZON.KendraSearchIntent are only inserted if they are configured for the bot.

For example, suppose a bot is configured with the confidence threshold of 0.80 and the AMAZON.FallbackIntent . Amazon Lex returns three alternative intents with the following confidence scores: IntentA (0.70), IntentB (0.60), IntentC (0.50). The response from the RecognizeText operation would be:

  • AMAZON.FallbackIntent

  • IntentA

  • IntentB

  • IntentC

type voiceSettings

dict

param voiceSettings

The Amazon Polly voice ID that Amazon Lex uses for voice interaction with the user.

  • voiceId (string) -- [REQUIRED]

    The identifier of the Amazon Polly voice to use.

  • engine (string) --

    Indicates the type of Amazon Polly voice that Amazon Lex should use for voice interaction with the user. For more information, see the engineparameter of the SynthesizeSpeechoperation in the Amazon Polly developer guide .

    If you do not specify a value, the default is standard .

type generativeAISettings

dict

param generativeAISettings

Contains specifications about the generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

  • runtimeSettings (dict) --

    Contains specifications about the Amazon Lex runtime generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

    • slotResolutionImprovement (dict) --

      An object containing specifications for the assisted slot resolution feature.

      • enabled (boolean) -- [REQUIRED]

        Specifies whether assisted slot resolution is turned on or off.

      • bedrockModelSpecification (dict) --

        An object containing information about the Amazon Bedrock model used to assist slot resolution.

        • modelArn (string) -- [REQUIRED]

          The ARN of the foundation model used in descriptive bot building.

  • buildtimeSettings (dict) --

    Contains specifications about the Amazon Lex build time generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

    • descriptiveBotBuilder (dict) --

      An object containing specifications for the descriptive bot building feature.

      • enabled (boolean) -- [REQUIRED]

        Specifies whether the descriptive bot building feature is activated or not.

      • bedrockModelSpecification (dict) --

        An object containing information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

        • modelArn (string) -- [REQUIRED]

          The ARN of the foundation model used in descriptive bot building.

    • sampleUtteranceGeneration (dict) --

      Contains specifications for the sample utterance generation feature.

      • enabled (boolean) -- [REQUIRED]

        Specifies whether to enable sample utterance generation or not.

      • bedrockModelSpecification (dict) --

        Contains information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

        • modelArn (string) -- [REQUIRED]

          The ARN of the foundation model used in descriptive bot building.

rtype

dict

returns

Response Syntax

{
    'botId': 'string',
    'botVersion': 'string',
    'localeName': 'string',
    'localeId': 'string',
    'description': 'string',
    'nluIntentConfidenceThreshold': 123.0,
    'voiceSettings': {
        'voiceId': 'string',
        'engine': 'standard'|'neural'
    },
    'botLocaleStatus': 'Creating'|'Building'|'Built'|'ReadyExpressTesting'|'Failed'|'Deleting'|'NotBuilt'|'Importing'|'Processing',
    'creationDateTime': datetime(2015, 1, 1),
    'generativeAISettings': {
        'runtimeSettings': {
            'slotResolutionImprovement': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        },
        'buildtimeSettings': {
            'descriptiveBotBuilder': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            },
            'sampleUtteranceGeneration': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        }
    }
}

Response Structure

  • (dict) --

    • botId (string) --

      The specified bot identifier.

    • botVersion (string) --

      The specified bot version.

    • localeName (string) --

      The specified locale name.

    • localeId (string) --

      The specified locale identifier.

    • description (string) --

      The specified description of the bot locale.

    • nluIntentConfidenceThreshold (float) --

      The specified confidence threshold for inserting the AMAZON.FallbackIntent and AMAZON.KendraSearchIntent intents.

    • voiceSettings (dict) --

      The Amazon Polly voice ID that Amazon Lex uses for voice interaction with the user.

      • voiceId (string) --

        The identifier of the Amazon Polly voice to use.

      • engine (string) --

        Indicates the type of Amazon Polly voice that Amazon Lex should use for voice interaction with the user. For more information, see the engineparameter of the SynthesizeSpeechoperation in the Amazon Polly developer guide .

        If you do not specify a value, the default is standard .

    • botLocaleStatus (string) --

      The status of the bot.

      When the status is Creating the bot locale is being configured. When the status is Building Amazon Lex is building the bot for testing and use.

      If the status of the bot is ReadyExpressTesting , you can test the bot using the exact utterances specified in the bots' intents. When the bot is ready for full testing or to run, the status is Built .

      If there was a problem with building the bot, the status is Failed . If the bot was saved but not built, the status is NotBuilt .

    • creationDateTime (datetime) --

      A timestamp specifying the date and time that the bot locale was created.

    • generativeAISettings (dict) --

      Contains specifications about the generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

      • runtimeSettings (dict) --

        Contains specifications about the Amazon Lex runtime generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

        • slotResolutionImprovement (dict) --

          An object containing specifications for the assisted slot resolution feature.

          • enabled (boolean) --

            Specifies whether assisted slot resolution is turned on or off.

          • bedrockModelSpecification (dict) --

            An object containing information about the Amazon Bedrock model used to assist slot resolution.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

      • buildtimeSettings (dict) --

        Contains specifications about the Amazon Lex build time generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

        • descriptiveBotBuilder (dict) --

          An object containing specifications for the descriptive bot building feature.

          • enabled (boolean) --

            Specifies whether the descriptive bot building feature is activated or not.

          • bedrockModelSpecification (dict) --

            An object containing information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

        • sampleUtteranceGeneration (dict) --

          Contains specifications for the sample utterance generation feature.

          • enabled (boolean) --

            Specifies whether to enable sample utterance generation or not.

          • bedrockModelSpecification (dict) --

            Contains information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

CreateSlot (updated) Link ¶
Changes (both)
{'valueElicitationSetting': {'slotResolutionSetting': {'slotResolutionStrategy': 'EnhancedFallback '
                                                                                 '| '
                                                                                 'Default'}}}

Creates a slot in an intent. A slot is a variable needed to fulfill an intent. For example, an OrderPizza intent might need slots for size, crust, and number of pizzas. For each slot, you define one or more utterances that Amazon Lex uses to elicit a response from the user.

See also: AWS API Documentation

Request Syntax

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

Parameters

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

rtype

dict

returns

Response Syntax

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

Response Structure

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

DescribeBotLocale (updated) Link ¶
Changes (response)
{'generativeAISettings': {'buildtimeSettings': {'descriptiveBotBuilder': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                          'enabled': 'boolean'},
                                                'sampleUtteranceGeneration': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                              'enabled': 'boolean'}},
                          'runtimeSettings': {'slotResolutionImprovement': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                            'enabled': 'boolean'}}}}

Describes the settings that a bot has for a specific locale.

See also: AWS API Documentation

Request Syntax

client.describe_bot_locale(
    botId='string',
    botVersion='string',
    localeId='string'
)
type botId

string

param botId

[REQUIRED]

The identifier of the bot associated with the locale.

type botVersion

string

param botVersion

[REQUIRED]

The version of the bot associated with the locale.

type localeId

string

param localeId

[REQUIRED]

The unique identifier of the locale to describe. The string must match one of the supported locales. For more information, see Supported languages.

rtype

dict

returns

Response Syntax

{
    'botId': 'string',
    'botVersion': 'string',
    'localeId': 'string',
    'localeName': 'string',
    'description': 'string',
    'nluIntentConfidenceThreshold': 123.0,
    'voiceSettings': {
        'voiceId': 'string',
        'engine': 'standard'|'neural'
    },
    'intentsCount': 123,
    'slotTypesCount': 123,
    'botLocaleStatus': 'Creating'|'Building'|'Built'|'ReadyExpressTesting'|'Failed'|'Deleting'|'NotBuilt'|'Importing'|'Processing',
    'failureReasons': [
        'string',
    ],
    'creationDateTime': datetime(2015, 1, 1),
    'lastUpdatedDateTime': datetime(2015, 1, 1),
    'lastBuildSubmittedDateTime': datetime(2015, 1, 1),
    'botLocaleHistoryEvents': [
        {
            'event': 'string',
            'eventDate': datetime(2015, 1, 1)
        },
    ],
    'recommendedActions': [
        'string',
    ],
    'generativeAISettings': {
        'runtimeSettings': {
            'slotResolutionImprovement': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        },
        'buildtimeSettings': {
            'descriptiveBotBuilder': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            },
            'sampleUtteranceGeneration': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        }
    }
}

Response Structure

  • (dict) --

    • botId (string) --

      The identifier of the bot associated with the locale.

    • botVersion (string) --

      The version of the bot associated with the locale.

    • localeId (string) --

      The unique identifier of the described locale.

    • localeName (string) --

      The name of the locale.

    • description (string) --

      The description of the locale.

    • nluIntentConfidenceThreshold (float) --

      The confidence threshold where Amazon Lex inserts the AMAZON.FallbackIntent and AMAZON.KendraSearchIntent intents in the list of possible intents for an utterance.

    • voiceSettings (dict) --

      The Amazon Polly voice Amazon Lex uses for voice interaction with the user.

      • voiceId (string) --

        The identifier of the Amazon Polly voice to use.

      • engine (string) --

        Indicates the type of Amazon Polly voice that Amazon Lex should use for voice interaction with the user. For more information, see the engineparameter of the SynthesizeSpeechoperation in the Amazon Polly developer guide .

        If you do not specify a value, the default is standard .

    • intentsCount (integer) --

      The number of intents defined for the locale.

    • slotTypesCount (integer) --

      The number of slot types defined for the locale.

    • botLocaleStatus (string) --

      The status of the bot. If the status is Failed , the reasons for the failure are listed in the failureReasons field.

    • failureReasons (list) --

      if botLocaleStatus is Failed , Amazon Lex explains why it failed to build the bot.

      • (string) --

    • creationDateTime (datetime) --

      The date and time that the locale was created.

    • lastUpdatedDateTime (datetime) --

      The date and time that the locale was last updated.

    • lastBuildSubmittedDateTime (datetime) --

      The date and time that the locale was last submitted for building.

    • botLocaleHistoryEvents (list) --

      History of changes, such as when a locale is used in an alias, that have taken place for the locale.

      • (dict) --

        Provides information about an event that occurred affecting the bot locale.

        • event (string) --

          A description of the event that occurred.

        • eventDate (datetime) --

          A timestamp of the date and time that the event occurred.

    • recommendedActions (list) --

      Recommended actions to take to resolve an error in the failureReasons field.

      • (string) --

    • generativeAISettings (dict) --

      Contains settings for Amazon Bedrock's generative AI features for your bot locale.

      • runtimeSettings (dict) --

        Contains specifications about the Amazon Lex runtime generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

        • slotResolutionImprovement (dict) --

          An object containing specifications for the assisted slot resolution feature.

          • enabled (boolean) --

            Specifies whether assisted slot resolution is turned on or off.

          • bedrockModelSpecification (dict) --

            An object containing information about the Amazon Bedrock model used to assist slot resolution.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

      • buildtimeSettings (dict) --

        Contains specifications about the Amazon Lex build time generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

        • descriptiveBotBuilder (dict) --

          An object containing specifications for the descriptive bot building feature.

          • enabled (boolean) --

            Specifies whether the descriptive bot building feature is activated or not.

          • bedrockModelSpecification (dict) --

            An object containing information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

        • sampleUtteranceGeneration (dict) --

          Contains specifications for the sample utterance generation feature.

          • enabled (boolean) --

            Specifies whether to enable sample utterance generation or not.

          • bedrockModelSpecification (dict) --

            Contains information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

DescribeSlot (updated) Link ¶
Changes (response)
{'valueElicitationSetting': {'slotResolutionSetting': {'slotResolutionStrategy': 'EnhancedFallback '
                                                                                 '| '
                                                                                 'Default'}}}

Gets metadata information about a slot.

See also: AWS API Documentation

Request Syntax

client.describe_slot(
    slotId='string',
    botId='string',
    botVersion='string',
    localeId='string',
    intentId='string'
)
type slotId

string

param slotId

[REQUIRED]

The unique identifier for the slot.

type botId

string

param botId

[REQUIRED]

The identifier of the bot associated with the slot.

type botVersion

string

param botVersion

[REQUIRED]

The version of the bot associated with the slot.

type localeId

string

param localeId

[REQUIRED]

The identifier of the language and locale of the slot to describe. The string must match one of the supported locales. For more information, see Supported languages.

type intentId

string

param intentId

[REQUIRED]

The identifier of the intent that contains the slot.

rtype

dict

returns

Response Syntax

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

Response Structure

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

UpdateBotLocale (updated) Link ¶
Changes (both)
{'generativeAISettings': {'buildtimeSettings': {'descriptiveBotBuilder': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                          'enabled': 'boolean'},
                                                'sampleUtteranceGeneration': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                              'enabled': 'boolean'}},
                          'runtimeSettings': {'slotResolutionImprovement': {'bedrockModelSpecification': {'modelArn': 'string'},
                                                                            'enabled': 'boolean'}}}}

Updates the settings that a bot has for a specific locale.

See also: AWS API Documentation

Request Syntax

client.update_bot_locale(
    botId='string',
    botVersion='string',
    localeId='string',
    description='string',
    nluIntentConfidenceThreshold=123.0,
    voiceSettings={
        'voiceId': 'string',
        'engine': 'standard'|'neural'
    },
    generativeAISettings={
        'runtimeSettings': {
            'slotResolutionImprovement': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        },
        'buildtimeSettings': {
            'descriptiveBotBuilder': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            },
            'sampleUtteranceGeneration': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        }
    }
)
type botId

string

param botId

[REQUIRED]

The unique identifier of the bot that contains the locale.

type botVersion

string

param botVersion

[REQUIRED]

The version of the bot that contains the locale to be updated. The version can only be the DRAFT version.

type localeId

string

param localeId

[REQUIRED]

The identifier of the language and locale to update. The string must match one of the supported locales. For more information, see Supported languages.

type description

string

param description

The new description of the locale.

type nluIntentConfidenceThreshold

float

param nluIntentConfidenceThreshold

[REQUIRED]

The new confidence threshold where Amazon Lex inserts the AMAZON.FallbackIntent and AMAZON.KendraSearchIntent intents in the list of possible intents for an utterance.

type voiceSettings

dict

param voiceSettings

The new Amazon Polly voice Amazon Lex should use for voice interaction with the user.

  • voiceId (string) -- [REQUIRED]

    The identifier of the Amazon Polly voice to use.

  • engine (string) --

    Indicates the type of Amazon Polly voice that Amazon Lex should use for voice interaction with the user. For more information, see the engineparameter of the SynthesizeSpeechoperation in the Amazon Polly developer guide .

    If you do not specify a value, the default is standard .

type generativeAISettings

dict

param generativeAISettings

Contains settings for generative AI features powered by Amazon Bedrock for your bot locale. Use this object to turn generative AI features on and off. Pricing may differ if you turn a feature on. For more information, see LINK.

  • runtimeSettings (dict) --

    Contains specifications about the Amazon Lex runtime generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

    • slotResolutionImprovement (dict) --

      An object containing specifications for the assisted slot resolution feature.

      • enabled (boolean) -- [REQUIRED]

        Specifies whether assisted slot resolution is turned on or off.

      • bedrockModelSpecification (dict) --

        An object containing information about the Amazon Bedrock model used to assist slot resolution.

        • modelArn (string) -- [REQUIRED]

          The ARN of the foundation model used in descriptive bot building.

  • buildtimeSettings (dict) --

    Contains specifications about the Amazon Lex build time generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

    • descriptiveBotBuilder (dict) --

      An object containing specifications for the descriptive bot building feature.

      • enabled (boolean) -- [REQUIRED]

        Specifies whether the descriptive bot building feature is activated or not.

      • bedrockModelSpecification (dict) --

        An object containing information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

        • modelArn (string) -- [REQUIRED]

          The ARN of the foundation model used in descriptive bot building.

    • sampleUtteranceGeneration (dict) --

      Contains specifications for the sample utterance generation feature.

      • enabled (boolean) -- [REQUIRED]

        Specifies whether to enable sample utterance generation or not.

      • bedrockModelSpecification (dict) --

        Contains information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

        • modelArn (string) -- [REQUIRED]

          The ARN of the foundation model used in descriptive bot building.

rtype

dict

returns

Response Syntax

{
    'botId': 'string',
    'botVersion': 'string',
    'localeId': 'string',
    'localeName': 'string',
    'description': 'string',
    'nluIntentConfidenceThreshold': 123.0,
    'voiceSettings': {
        'voiceId': 'string',
        'engine': 'standard'|'neural'
    },
    'botLocaleStatus': 'Creating'|'Building'|'Built'|'ReadyExpressTesting'|'Failed'|'Deleting'|'NotBuilt'|'Importing'|'Processing',
    'failureReasons': [
        'string',
    ],
    'creationDateTime': datetime(2015, 1, 1),
    'lastUpdatedDateTime': datetime(2015, 1, 1),
    'recommendedActions': [
        'string',
    ],
    'generativeAISettings': {
        'runtimeSettings': {
            'slotResolutionImprovement': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        },
        'buildtimeSettings': {
            'descriptiveBotBuilder': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            },
            'sampleUtteranceGeneration': {
                'enabled': True|False,
                'bedrockModelSpecification': {
                    'modelArn': 'string'
                }
            }
        }
    }
}

Response Structure

  • (dict) --

    • botId (string) --

      The identifier of the bot that contains the updated locale.

    • botVersion (string) --

      The version of the bot that contains the updated locale.

    • localeId (string) --

      The language and locale of the updated bot locale.

    • localeName (string) --

      The updated locale name for the locale.

    • description (string) --

      The updated description of the locale.

    • nluIntentConfidenceThreshold (float) --

      The updated confidence threshold for inserting the AMAZON.FallbackIntent and AMAZON.KendraSearchIntent intents in the list of possible intents for an utterance.

    • voiceSettings (dict) --

      The updated Amazon Polly voice to use for voice interaction with the user.

      • voiceId (string) --

        The identifier of the Amazon Polly voice to use.

      • engine (string) --

        Indicates the type of Amazon Polly voice that Amazon Lex should use for voice interaction with the user. For more information, see the engineparameter of the SynthesizeSpeechoperation in the Amazon Polly developer guide .

        If you do not specify a value, the default is standard .

    • botLocaleStatus (string) --

      The current status of the locale. When the bot status is Built the locale is ready for use.

    • failureReasons (list) --

      If the botLocaleStatus is Failed , the failureReasons field lists the errors that occurred while building the bot.

      • (string) --

    • creationDateTime (datetime) --

      A timestamp of the date and time that the locale was created.

    • lastUpdatedDateTime (datetime) --

      A timestamp of the date and time that the locale was last updated.

    • recommendedActions (list) --

      Recommended actions to take to resolve an error in the failureReasons field.

      • (string) --

    • generativeAISettings (dict) --

      Contains settings for generative AI features powered by Amazon Bedrock for your bot locale.

      • runtimeSettings (dict) --

        Contains specifications about the Amazon Lex runtime generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

        • slotResolutionImprovement (dict) --

          An object containing specifications for the assisted slot resolution feature.

          • enabled (boolean) --

            Specifies whether assisted slot resolution is turned on or off.

          • bedrockModelSpecification (dict) --

            An object containing information about the Amazon Bedrock model used to assist slot resolution.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

      • buildtimeSettings (dict) --

        Contains specifications about the Amazon Lex build time generative AI capabilities from Amazon Bedrock that you can turn on for your bot.

        • descriptiveBotBuilder (dict) --

          An object containing specifications for the descriptive bot building feature.

          • enabled (boolean) --

            Specifies whether the descriptive bot building feature is activated or not.

          • bedrockModelSpecification (dict) --

            An object containing information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

        • sampleUtteranceGeneration (dict) --

          Contains specifications for the sample utterance generation feature.

          • enabled (boolean) --

            Specifies whether to enable sample utterance generation or not.

          • bedrockModelSpecification (dict) --

            Contains information about the Amazon Bedrock model used to interpret the prompt used in descriptive bot building.

            • modelArn (string) --

              The ARN of the foundation model used in descriptive bot building.

UpdateSlot (updated) Link ¶
Changes (both)
{'valueElicitationSetting': {'slotResolutionSetting': {'slotResolutionStrategy': 'EnhancedFallback '
                                                                                 '| '
                                                                                 'Default'}}}

Updates the settings for a slot.

See also: AWS API Documentation

Request Syntax

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

Parameters

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

rtype

dict

returns

Response Syntax

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation

Response Structure

# This section is too large to render.
# Please see the AWS API Documentation linked below.

AWS API Documentation