2020/06/11 - Amazon Lex Model Building Service - 3 updated api methods
Changes This change adds the built-in AMAZON.KendraSearchIntent that enables integration with Amazon Kendra.
{'kendraConfiguration': {'kendraIndex': 'string',
'queryFilterString': 'string',
'role': 'string'}}
Creates a new version of an intent based on the $LATEST version of the intent. If the $LATEST version of this intent hasn't changed since you last updated it, Amazon Lex doesn't create a new version. It returns the last version you created.
Note
You can update only the $LATEST version of the intent. You can't update the numbered versions that you create with the CreateIntentVersion operation.
When you create a version of an intent, Amazon Lex sets the version to 1. Subsequent versions increment by 1. For more information, see versioning-intro .
This operation requires permissions to perform the lex:CreateIntentVersion action.
See also: AWS API Documentation
Request Syntax
client.create_intent_version(
name='string',
checksum='string'
)
string
[REQUIRED]
The name of the intent that you want to create a new version of. The name is case sensitive.
string
Checksum of the $LATEST version of the intent that should be used to create the new version. If you specify a checksum and the $LATEST version of the intent has a different checksum, Amazon Lex returns a PreconditionFailedException exception and doesn't publish a new version. If you don't specify a checksum, Amazon Lex publishes the $LATEST version.
dict
Response Syntax
{
'name': 'string',
'description': 'string',
'slots': [
{
'name': 'string',
'description': 'string',
'slotConstraint': 'Required'|'Optional',
'slotType': 'string',
'slotTypeVersion': 'string',
'valueElicitationPrompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'priority': 123,
'sampleUtterances': [
'string',
],
'responseCard': 'string',
'obfuscationSetting': 'NONE'|'DEFAULT_OBFUSCATION'
},
],
'sampleUtterances': [
'string',
],
'confirmationPrompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'rejectionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
'followUpPrompt': {
'prompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'rejectionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
}
},
'conclusionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
'dialogCodeHook': {
'uri': 'string',
'messageVersion': 'string'
},
'fulfillmentActivity': {
'type': 'ReturnIntent'|'CodeHook',
'codeHook': {
'uri': 'string',
'messageVersion': 'string'
}
},
'parentIntentSignature': 'string',
'lastUpdatedDate': datetime(2015, 1, 1),
'createdDate': datetime(2015, 1, 1),
'version': 'string',
'checksum': 'string',
'kendraConfiguration': {
'kendraIndex': 'string',
'queryFilterString': 'string',
'role': 'string'
}
}
Response Structure
(dict) --
name (string) --
The name of the intent.
description (string) --
A description of the intent.
slots (list) --
An array of slot types that defines the information required to fulfill the intent.
(dict) --
Identifies the version of a specific slot.
name (string) --
The name of the slot.
description (string) --
A description of the slot.
slotConstraint (string) --
Specifies whether the slot is required or optional.
slotType (string) --
The type of the slot, either a custom slot type that you defined or one of the built-in slot types.
slotTypeVersion (string) --
The version of the slot type.
valueElicitationPrompt (dict) --
The prompt that Amazon Lex uses to elicit the slot value from the user.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
priority (integer) --
Directs Amazon Lex the order in which to elicit this slot value from the user. For example, if the intent has two slots with priorities 1 and 2, AWS Amazon Lex first elicits a value for the slot with priority 1.
If multiple slots share the same priority, the order in which Amazon Lex elicits values is arbitrary.
sampleUtterances (list) --
If you know a specific pattern with which users might respond to an Amazon Lex request for a slot value, you can provide those utterances to improve accuracy. This is optional. In most cases, Amazon Lex is capable of understanding user utterances.
(string) --
responseCard (string) --
A set of possible responses for the slot type used by text-based clients. A user chooses an option from the response card, instead of using text to reply.
obfuscationSetting (string) --
Determines whether a slot is obfuscated in conversation logs and stored utterances. When you obfuscate a slot, the value is replaced by the slot name in curly braces ({}). For example, if the slot name is "full_name", obfuscated values are replaced with "{full_name}". For more information, see Slot Obfuscation .
sampleUtterances (list) --
An array of sample utterances configured for the intent.
(string) --
confirmationPrompt (dict) --
If defined, the prompt that Amazon Lex uses to confirm the user's intent before fulfilling it.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
rejectionStatement (dict) --
If the user answers "no" to the question defined in confirmationPrompt , Amazon Lex responds with this statement to acknowledge that the intent was canceled.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
followUpPrompt (dict) --
If defined, Amazon Lex uses this prompt to solicit additional user activity after the intent is fulfilled.
prompt (dict) --
Prompts for information from the user.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
rejectionStatement (dict) --
If the user answers "no" to the question defined in the prompt field, Amazon Lex responds with this statement to acknowledge that the intent was canceled.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
conclusionStatement (dict) --
After the Lambda function specified in the fulfillmentActivity field fulfills the intent, Amazon Lex conveys this statement to the user.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
dialogCodeHook (dict) --
If defined, Amazon Lex invokes this Lambda function for each user input.
uri (string) --
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) --
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
fulfillmentActivity (dict) --
Describes how the intent is fulfilled.
type (string) --
How the intent should be fulfilled, either by running a Lambda function or by returning the slot data to the client application.
codeHook (dict) --
A description of the Lambda function that is run to fulfill the intent.
uri (string) --
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) --
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
parentIntentSignature (string) --
A unique identifier for a built-in intent.
lastUpdatedDate (datetime) --
The date that the intent was updated.
createdDate (datetime) --
The date that the intent was created.
version (string) --
The version number assigned to the new version of the intent.
checksum (string) --
Checksum of the intent version created.
kendraConfiguration (dict) --
Configuration information, if any, for connectin an Amazon Kendra index with the AMAZON.KendraSearchIntent intent.
kendraIndex (string) --
The Amazon Resource Name (ARN) of the Amazon Kendra index that you want the AMAZON.KendraSearchIntent intent to search. The index must be in the same account and Region as the Amazon Lex bot. If the Amazon Kendra index does not exist, you get an exception when you call the PutIntent operation.
queryFilterString (string) --
A query filter that Amazon Lex sends to Amazon Kendra to filter the response from the query. The filter is in the format defined by Amazon Kendra. For more information, see Filtering queries .
You can override this filter string with a new filter string at runtime.
role (string) --
The Amazon Resource Name (ARN) of an IAM role that has permission to search the Amazon Kendra index. The role must be in the same account and Region as the Amazon Lex bot. If the role does not exist, you get an exception when you call the PutIntent operation.
{'kendraConfiguration': {'kendraIndex': 'string',
'queryFilterString': 'string',
'role': 'string'}}
Returns information about an intent. In addition to the intent name, you must specify the intent version.
This operation requires permissions to perform the lex:GetIntent action.
See also: AWS API Documentation
Request Syntax
client.get_intent(
name='string',
version='string'
)
string
[REQUIRED]
The name of the intent. The name is case sensitive.
string
[REQUIRED]
The version of the intent.
dict
Response Syntax
{
'name': 'string',
'description': 'string',
'slots': [
{
'name': 'string',
'description': 'string',
'slotConstraint': 'Required'|'Optional',
'slotType': 'string',
'slotTypeVersion': 'string',
'valueElicitationPrompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'priority': 123,
'sampleUtterances': [
'string',
],
'responseCard': 'string',
'obfuscationSetting': 'NONE'|'DEFAULT_OBFUSCATION'
},
],
'sampleUtterances': [
'string',
],
'confirmationPrompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'rejectionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
'followUpPrompt': {
'prompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'rejectionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
}
},
'conclusionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
'dialogCodeHook': {
'uri': 'string',
'messageVersion': 'string'
},
'fulfillmentActivity': {
'type': 'ReturnIntent'|'CodeHook',
'codeHook': {
'uri': 'string',
'messageVersion': 'string'
}
},
'parentIntentSignature': 'string',
'lastUpdatedDate': datetime(2015, 1, 1),
'createdDate': datetime(2015, 1, 1),
'version': 'string',
'checksum': 'string',
'kendraConfiguration': {
'kendraIndex': 'string',
'queryFilterString': 'string',
'role': 'string'
}
}
Response Structure
(dict) --
name (string) --
The name of the intent.
description (string) --
A description of the intent.
slots (list) --
An array of intent slots configured for the intent.
(dict) --
Identifies the version of a specific slot.
name (string) --
The name of the slot.
description (string) --
A description of the slot.
slotConstraint (string) --
Specifies whether the slot is required or optional.
slotType (string) --
The type of the slot, either a custom slot type that you defined or one of the built-in slot types.
slotTypeVersion (string) --
The version of the slot type.
valueElicitationPrompt (dict) --
The prompt that Amazon Lex uses to elicit the slot value from the user.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
priority (integer) --
Directs Amazon Lex the order in which to elicit this slot value from the user. For example, if the intent has two slots with priorities 1 and 2, AWS Amazon Lex first elicits a value for the slot with priority 1.
If multiple slots share the same priority, the order in which Amazon Lex elicits values is arbitrary.
sampleUtterances (list) --
If you know a specific pattern with which users might respond to an Amazon Lex request for a slot value, you can provide those utterances to improve accuracy. This is optional. In most cases, Amazon Lex is capable of understanding user utterances.
(string) --
responseCard (string) --
A set of possible responses for the slot type used by text-based clients. A user chooses an option from the response card, instead of using text to reply.
obfuscationSetting (string) --
Determines whether a slot is obfuscated in conversation logs and stored utterances. When you obfuscate a slot, the value is replaced by the slot name in curly braces ({}). For example, if the slot name is "full_name", obfuscated values are replaced with "{full_name}". For more information, see Slot Obfuscation .
sampleUtterances (list) --
An array of sample utterances configured for the intent.
(string) --
confirmationPrompt (dict) --
If defined in the bot, Amazon Lex uses prompt to confirm the intent before fulfilling the user's request. For more information, see PutIntent .
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
rejectionStatement (dict) --
If the user answers "no" to the question defined in confirmationPrompt , Amazon Lex responds with this statement to acknowledge that the intent was canceled.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
followUpPrompt (dict) --
If defined in the bot, Amazon Lex uses this prompt to solicit additional user activity after the intent is fulfilled. For more information, see PutIntent .
prompt (dict) --
Prompts for information from the user.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
rejectionStatement (dict) --
If the user answers "no" to the question defined in the prompt field, Amazon Lex responds with this statement to acknowledge that the intent was canceled.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
conclusionStatement (dict) --
After the Lambda function specified in the fulfillmentActivity element fulfills the intent, Amazon Lex conveys this statement to the user.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
dialogCodeHook (dict) --
If defined in the bot, Amazon Amazon Lex invokes this Lambda function for each user input. For more information, see PutIntent .
uri (string) --
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) --
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
fulfillmentActivity (dict) --
Describes how the intent is fulfilled. For more information, see PutIntent .
type (string) --
How the intent should be fulfilled, either by running a Lambda function or by returning the slot data to the client application.
codeHook (dict) --
A description of the Lambda function that is run to fulfill the intent.
uri (string) --
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) --
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
parentIntentSignature (string) --
A unique identifier for a built-in intent.
lastUpdatedDate (datetime) --
The date that the intent was updated. When you create a resource, the creation date and the last updated date are the same.
createdDate (datetime) --
The date that the intent was created.
version (string) --
The version of the intent.
checksum (string) --
Checksum of the intent.
kendraConfiguration (dict) --
Configuration information, if any, to connect to an Amazon Kendra index with the AMAZON.KendraSearchIntent intent.
kendraIndex (string) --
The Amazon Resource Name (ARN) of the Amazon Kendra index that you want the AMAZON.KendraSearchIntent intent to search. The index must be in the same account and Region as the Amazon Lex bot. If the Amazon Kendra index does not exist, you get an exception when you call the PutIntent operation.
queryFilterString (string) --
A query filter that Amazon Lex sends to Amazon Kendra to filter the response from the query. The filter is in the format defined by Amazon Kendra. For more information, see Filtering queries .
You can override this filter string with a new filter string at runtime.
role (string) --
The Amazon Resource Name (ARN) of an IAM role that has permission to search the Amazon Kendra index. The role must be in the same account and Region as the Amazon Lex bot. If the role does not exist, you get an exception when you call the PutIntent operation.
{'kendraConfiguration': {'kendraIndex': 'string',
'queryFilterString': 'string',
'role': 'string'}}
Creates an intent or replaces an existing intent.
To define the interaction between the user and your bot, you use one or more intents. For a pizza ordering bot, for example, you would create an OrderPizza intent.
To create an intent or replace an existing intent, you must provide the following:
Intent name. For example, OrderPizza .
Sample utterances. For example, "Can I order a pizza, please." and "I want to order a pizza."
Information to be gathered. You specify slot types for the information that your bot will request from the user. You can specify standard slot types, such as a date or a time, or custom slot types such as the size and crust of a pizza.
How the intent will be fulfilled. You can provide a Lambda function or configure the intent to return the intent information to the client application. If you use a Lambda function, when all of the intent information is available, Amazon Lex invokes your Lambda function. If you configure your intent to return the intent information to the client application.
You can specify other optional information in the request, such as:
A confirmation prompt to ask the user to confirm an intent. For example, "Shall I order your pizza?"
A conclusion statement to send to the user after the intent has been fulfilled. For example, "I placed your pizza order."
A follow-up prompt that asks the user for additional activity. For example, asking "Do you want to order a drink with your pizza?"
If you specify an existing intent name to update the intent, Amazon Lex replaces the values in the $LATEST version of the intent with the values in the request. Amazon Lex removes fields that you don't provide in the request. If you don't specify the required fields, Amazon Lex throws an exception. When you update the $LATEST version of an intent, the status field of any bot that uses the $LATEST version of the intent is set to NOT_BUILT .
For more information, see how-it-works .
This operation requires permissions for the lex:PutIntent action.
See also: AWS API Documentation
Request Syntax
client.put_intent(
name='string',
description='string',
slots=[
{
'name': 'string',
'description': 'string',
'slotConstraint': 'Required'|'Optional',
'slotType': 'string',
'slotTypeVersion': 'string',
'valueElicitationPrompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'priority': 123,
'sampleUtterances': [
'string',
],
'responseCard': 'string',
'obfuscationSetting': 'NONE'|'DEFAULT_OBFUSCATION'
},
],
sampleUtterances=[
'string',
],
confirmationPrompt={
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
rejectionStatement={
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
followUpPrompt={
'prompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'rejectionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
}
},
conclusionStatement={
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
dialogCodeHook={
'uri': 'string',
'messageVersion': 'string'
},
fulfillmentActivity={
'type': 'ReturnIntent'|'CodeHook',
'codeHook': {
'uri': 'string',
'messageVersion': 'string'
}
},
parentIntentSignature='string',
checksum='string',
createVersion=True|False,
kendraConfiguration={
'kendraIndex': 'string',
'queryFilterString': 'string',
'role': 'string'
}
)
string
[REQUIRED]
The name of the intent. The name is not case sensitive.
The name can't match a built-in intent name, or a built-in intent name with "AMAZON." removed. For example, because there is a built-in intent called AMAZON.HelpIntent , you can't create a custom intent called HelpIntent .
For a list of built-in intents, see Standard Built-in Intents in the Alexa Skills Kit .
string
A description of the intent.
list
An array of intent slots. At runtime, Amazon Lex elicits required slot values from the user using prompts defined in the slots. For more information, see how-it-works .
(dict) --
Identifies the version of a specific slot.
name (string) -- [REQUIRED]
The name of the slot.
description (string) --
A description of the slot.
slotConstraint (string) -- [REQUIRED]
Specifies whether the slot is required or optional.
slotType (string) --
The type of the slot, either a custom slot type that you defined or one of the built-in slot types.
slotTypeVersion (string) --
The version of the slot type.
valueElicitationPrompt (dict) --
The prompt that Amazon Lex uses to elicit the slot value from the user.
messages (list) -- [REQUIRED]
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) -- [REQUIRED]
The content type of the message string.
content (string) -- [REQUIRED]
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) -- [REQUIRED]
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
priority (integer) --
Directs Amazon Lex the order in which to elicit this slot value from the user. For example, if the intent has two slots with priorities 1 and 2, AWS Amazon Lex first elicits a value for the slot with priority 1.
If multiple slots share the same priority, the order in which Amazon Lex elicits values is arbitrary.
sampleUtterances (list) --
If you know a specific pattern with which users might respond to an Amazon Lex request for a slot value, you can provide those utterances to improve accuracy. This is optional. In most cases, Amazon Lex is capable of understanding user utterances.
(string) --
responseCard (string) --
A set of possible responses for the slot type used by text-based clients. A user chooses an option from the response card, instead of using text to reply.
obfuscationSetting (string) --
Determines whether a slot is obfuscated in conversation logs and stored utterances. When you obfuscate a slot, the value is replaced by the slot name in curly braces ({}). For example, if the slot name is "full_name", obfuscated values are replaced with "{full_name}". For more information, see Slot Obfuscation .
list
An array of utterances (strings) that a user might say to signal the intent. For example, "I want {PizzaSize} pizza", "Order {Quantity} {PizzaSize} pizzas".
In each utterance, a slot name is enclosed in curly braces.
(string) --
dict
Prompts the user to confirm the intent. This question should have a yes or no answer.
Amazon Lex uses this prompt to ensure that the user acknowledges that the intent is ready for fulfillment. For example, with the OrderPizza intent, you might want to confirm that the order is correct before placing it. For other intents, such as intents that simply respond to user questions, you might not need to ask the user for confirmation before providing the information.
Note
You you must provide both the rejectionStatement and the confirmationPrompt , or neither.
messages (list) -- [REQUIRED]
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) -- [REQUIRED]
The content type of the message string.
content (string) -- [REQUIRED]
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) -- [REQUIRED]
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
dict
When the user answers "no" to the question defined in confirmationPrompt , Amazon Lex responds with this statement to acknowledge that the intent was canceled.
Note
You must provide both the rejectionStatement and the confirmationPrompt , or neither.
messages (list) -- [REQUIRED]
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) -- [REQUIRED]
The content type of the message string.
content (string) -- [REQUIRED]
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
dict
Amazon Lex uses this prompt to solicit additional activity after fulfilling an intent. For example, after the OrderPizza intent is fulfilled, you might prompt the user to order a drink.
The action that Amazon Lex takes depends on the user's response, as follows:
If the user says "Yes" it responds with the clarification prompt that is configured for the bot.
if the user says "Yes" and continues with an utterance that triggers an intent it starts a conversation for the intent.
If the user says "No" it responds with the rejection statement configured for the the follow-up prompt.
If it doesn't recognize the utterance it repeats the follow-up prompt again.
The followUpPrompt field and the conclusionStatement field are mutually exclusive. You can specify only one.
prompt (dict) -- [REQUIRED]
Prompts for information from the user.
messages (list) -- [REQUIRED]
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) -- [REQUIRED]
The content type of the message string.
content (string) -- [REQUIRED]
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) -- [REQUIRED]
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
rejectionStatement (dict) -- [REQUIRED]
If the user answers "no" to the question defined in the prompt field, Amazon Lex responds with this statement to acknowledge that the intent was canceled.
messages (list) -- [REQUIRED]
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) -- [REQUIRED]
The content type of the message string.
content (string) -- [REQUIRED]
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
dict
The statement that you want Amazon Lex to convey to the user after the intent is successfully fulfilled by the Lambda function.
This element is relevant only if you provide a Lambda function in the fulfillmentActivity . If you return the intent to the client application, you can't specify this element.
Note
The followUpPrompt and conclusionStatement are mutually exclusive. You can specify only one.
messages (list) -- [REQUIRED]
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) -- [REQUIRED]
The content type of the message string.
content (string) -- [REQUIRED]
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
dict
Specifies a Lambda function to invoke for each user input. You can invoke this Lambda function to personalize user interaction.
For example, suppose your bot determines that the user is John. Your Lambda function might retrieve John's information from a backend database and prepopulate some of the values. For example, if you find that John is gluten intolerant, you might set the corresponding intent slot, GlutenIntolerant , to true. You might find John's phone number and set the corresponding session attribute.
uri (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) -- [REQUIRED]
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
dict
Required. Describes how the intent is fulfilled. For example, after a user provides all of the information for a pizza order, fulfillmentActivity defines how the bot places an order with a local pizza store.
You might configure Amazon Lex to return all of the intent information to the client application, or direct it to invoke a Lambda function that can process the intent (for example, place an order with a pizzeria).
type (string) -- [REQUIRED]
How the intent should be fulfilled, either by running a Lambda function or by returning the slot data to the client application.
codeHook (dict) --
A description of the Lambda function that is run to fulfill the intent.
uri (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) -- [REQUIRED]
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
string
A unique identifier for the built-in intent to base this intent on. To find the signature for an intent, see Standard Built-in Intents in the Alexa Skills Kit .
string
Identifies a specific revision of the $LATEST version.
When you create a new intent, leave the checksum field blank. If you specify a checksum you get a BadRequestException exception.
When you want to update a intent, set the checksum field to the checksum of the most recent revision of the $LATEST version. If you don't specify the checksum field, or if the checksum does not match the $LATEST version, you get a PreconditionFailedException exception.
boolean
When set to true a new numbered version of the intent is created. This is the same as calling the CreateIntentVersion operation. If you do not specify createVersion , the default is false .
dict
Configuration information required to use the AMAZON.KendraSearchIntent intent to connect to an Amazon Kendra index. For more information, see AMAZON.KendraSearchIntent .
kendraIndex (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of the Amazon Kendra index that you want the AMAZON.KendraSearchIntent intent to search. The index must be in the same account and Region as the Amazon Lex bot. If the Amazon Kendra index does not exist, you get an exception when you call the PutIntent operation.
queryFilterString (string) --
A query filter that Amazon Lex sends to Amazon Kendra to filter the response from the query. The filter is in the format defined by Amazon Kendra. For more information, see Filtering queries .
You can override this filter string with a new filter string at runtime.
role (string) -- [REQUIRED]
The Amazon Resource Name (ARN) of an IAM role that has permission to search the Amazon Kendra index. The role must be in the same account and Region as the Amazon Lex bot. If the role does not exist, you get an exception when you call the PutIntent operation.
dict
Response Syntax
{
'name': 'string',
'description': 'string',
'slots': [
{
'name': 'string',
'description': 'string',
'slotConstraint': 'Required'|'Optional',
'slotType': 'string',
'slotTypeVersion': 'string',
'valueElicitationPrompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'priority': 123,
'sampleUtterances': [
'string',
],
'responseCard': 'string',
'obfuscationSetting': 'NONE'|'DEFAULT_OBFUSCATION'
},
],
'sampleUtterances': [
'string',
],
'confirmationPrompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'rejectionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
'followUpPrompt': {
'prompt': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'maxAttempts': 123,
'responseCard': 'string'
},
'rejectionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
}
},
'conclusionStatement': {
'messages': [
{
'contentType': 'PlainText'|'SSML'|'CustomPayload',
'content': 'string',
'groupNumber': 123
},
],
'responseCard': 'string'
},
'dialogCodeHook': {
'uri': 'string',
'messageVersion': 'string'
},
'fulfillmentActivity': {
'type': 'ReturnIntent'|'CodeHook',
'codeHook': {
'uri': 'string',
'messageVersion': 'string'
}
},
'parentIntentSignature': 'string',
'lastUpdatedDate': datetime(2015, 1, 1),
'createdDate': datetime(2015, 1, 1),
'version': 'string',
'checksum': 'string',
'createVersion': True|False,
'kendraConfiguration': {
'kendraIndex': 'string',
'queryFilterString': 'string',
'role': 'string'
}
}
Response Structure
(dict) --
name (string) --
The name of the intent.
description (string) --
A description of the intent.
slots (list) --
An array of intent slots that are configured for the intent.
(dict) --
Identifies the version of a specific slot.
name (string) --
The name of the slot.
description (string) --
A description of the slot.
slotConstraint (string) --
Specifies whether the slot is required or optional.
slotType (string) --
The type of the slot, either a custom slot type that you defined or one of the built-in slot types.
slotTypeVersion (string) --
The version of the slot type.
valueElicitationPrompt (dict) --
The prompt that Amazon Lex uses to elicit the slot value from the user.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
priority (integer) --
Directs Amazon Lex the order in which to elicit this slot value from the user. For example, if the intent has two slots with priorities 1 and 2, AWS Amazon Lex first elicits a value for the slot with priority 1.
If multiple slots share the same priority, the order in which Amazon Lex elicits values is arbitrary.
sampleUtterances (list) --
If you know a specific pattern with which users might respond to an Amazon Lex request for a slot value, you can provide those utterances to improve accuracy. This is optional. In most cases, Amazon Lex is capable of understanding user utterances.
(string) --
responseCard (string) --
A set of possible responses for the slot type used by text-based clients. A user chooses an option from the response card, instead of using text to reply.
obfuscationSetting (string) --
Determines whether a slot is obfuscated in conversation logs and stored utterances. When you obfuscate a slot, the value is replaced by the slot name in curly braces ({}). For example, if the slot name is "full_name", obfuscated values are replaced with "{full_name}". For more information, see Slot Obfuscation .
sampleUtterances (list) --
An array of sample utterances that are configured for the intent.
(string) --
confirmationPrompt (dict) --
If defined in the intent, Amazon Lex prompts the user to confirm the intent before fulfilling it.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
rejectionStatement (dict) --
If the user answers "no" to the question defined in confirmationPrompt Amazon Lex responds with this statement to acknowledge that the intent was canceled.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
followUpPrompt (dict) --
If defined in the intent, Amazon Lex uses this prompt to solicit additional user activity after the intent is fulfilled.
prompt (dict) --
Prompts for information from the user.
messages (list) --
An array of objects, each of which provides a message string and its type. You can specify the message string in plain text or in Speech Synthesis Markup Language (SSML).
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
maxAttempts (integer) --
The number of times to prompt the user for information.
responseCard (string) --
A response card. Amazon Lex uses this prompt at runtime, in the PostText API response. It substitutes session attributes and slot values for placeholders in the response card. For more information, see ex-resp-card .
rejectionStatement (dict) --
If the user answers "no" to the question defined in the prompt field, Amazon Lex responds with this statement to acknowledge that the intent was canceled.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
conclusionStatement (dict) --
After the Lambda function specified in the``fulfillmentActivity`` intent fulfills the intent, Amazon Lex conveys this statement to the user.
messages (list) --
A collection of message objects.
(dict) --
The message object that provides the message text and its type.
contentType (string) --
The content type of the message string.
content (string) --
The text of the message.
groupNumber (integer) --
Identifies the message group that the message belongs to. When a group is assigned to a message, Amazon Lex returns one message from each group in the response.
responseCard (string) --
At runtime, if the client is using the PostText API, Amazon Lex includes the response card in the response. It substitutes all of the session attributes and slot values for placeholders in the response card.
dialogCodeHook (dict) --
If defined in the intent, Amazon Lex invokes this Lambda function for each user input.
uri (string) --
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) --
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
fulfillmentActivity (dict) --
If defined in the intent, Amazon Lex invokes this Lambda function to fulfill the intent after the user provides all of the information required by the intent.
type (string) --
How the intent should be fulfilled, either by running a Lambda function or by returning the slot data to the client application.
codeHook (dict) --
A description of the Lambda function that is run to fulfill the intent.
uri (string) --
The Amazon Resource Name (ARN) of the Lambda function.
messageVersion (string) --
The version of the request-response that you want Amazon Lex to use to invoke your Lambda function. For more information, see using-lambda .
parentIntentSignature (string) --
A unique identifier for the built-in intent that this intent is based on.
lastUpdatedDate (datetime) --
The date that the intent was updated. When you create a resource, the creation date and last update dates are the same.
createdDate (datetime) --
The date that the intent was created.
version (string) --
The version of the intent. For a new intent, the version is always $LATEST .
checksum (string) --
Checksum of the $LATEST version of the intent created or updated.
createVersion (boolean) --
True if a new version of the intent was created. If the createVersion field was not specified in the request, the createVersion field is set to false in the response.
kendraConfiguration (dict) --
Configuration information, if any, required to connect to an Amazon Kendra index and use the AMAZON.KendraSearchIntent intent.
kendraIndex (string) --
The Amazon Resource Name (ARN) of the Amazon Kendra index that you want the AMAZON.KendraSearchIntent intent to search. The index must be in the same account and Region as the Amazon Lex bot. If the Amazon Kendra index does not exist, you get an exception when you call the PutIntent operation.
queryFilterString (string) --
A query filter that Amazon Lex sends to Amazon Kendra to filter the response from the query. The filter is in the format defined by Amazon Kendra. For more information, see Filtering queries .
You can override this filter string with a new filter string at runtime.
role (string) --
The Amazon Resource Name (ARN) of an IAM role that has permission to search the Amazon Kendra index. The role must be in the same account and Region as the Amazon Lex bot. If the role does not exist, you get an exception when you call the PutIntent operation.