Table of Contents
A low-level client representing Amazon Lex Runtime Service
Amazon Lex provides both build and runtime endpoints. Each endpoint provides a set of operations (API). Your conversational bot uses the runtime API to understand user utterances (user input text or voice). For example, suppose a user says "I want pizza", your bot sends this input to Amazon Lex using the runtime API. Amazon Lex recognizes that the user request is for the OrderPizza intent (one of the intents defined in the bot). Then Amazon Lex engages in user conversation on behalf of the bot to elicit required information (slot values, such as pizza size and crust type), and then performs fulfillment activity (that you configured when you created the bot). You use the build-time API to create and manage your Amazon Lex bot. For a list of build-time operations, see the build-time API, .
import boto3
client = boto3.client('lex-runtime')
These are the available methods:
Check if an operation can be paginated.
Removes session information for a specified bot, alias, and user ID.
See also: AWS API Documentation
Request Syntax
response = client.delete_session(
botName='string',
botAlias='string',
userId='string'
)
[REQUIRED]
The name of the bot that contains the session data.
[REQUIRED]
The alias in use for the bot that contains the session data.
[REQUIRED]
The identifier of the user associated with the session data.
dict
Response Syntax
{
'botName': 'string',
'botAlias': 'string',
'userId': 'string',
'sessionId': 'string'
}
Response Structure
(dict) --
botName (string) --
The name of the bot associated with the session data.
botAlias (string) --
The alias in use for the bot associated with the session data.
userId (string) --
The ID of the client application user.
sessionId (string) --
The unique identifier for the session.
Exceptions
Create a paginator for an operation.
Returns session information for a specified bot, alias, and user ID.
See also: AWS API Documentation
Request Syntax
response = client.get_session(
botName='string',
botAlias='string',
userId='string',
checkpointLabelFilter='string'
)
[REQUIRED]
The name of the bot that contains the session data.
[REQUIRED]
The alias in use for the bot that contains the session data.
[REQUIRED]
The ID of the client application user. Amazon Lex uses this to identify a user's conversation with your bot.
A string used to filter the intents returned in the recentIntentSummaryView structure.
When you specify a filter, only intents with their checkpointLabel field set to that string are returned.
dict
Response Syntax
{
'recentIntentSummaryView': [
{
'intentName': 'string',
'checkpointLabel': 'string',
'slots': {
'string': 'string'
},
'confirmationStatus': 'None'|'Confirmed'|'Denied',
'dialogActionType': 'ElicitIntent'|'ConfirmIntent'|'ElicitSlot'|'Close'|'Delegate',
'fulfillmentState': 'Fulfilled'|'Failed'|'ReadyForFulfillment',
'slotToElicit': 'string'
},
],
'sessionAttributes': {
'string': 'string'
},
'sessionId': 'string',
'dialogAction': {
'type': 'ElicitIntent'|'ConfirmIntent'|'ElicitSlot'|'Close'|'Delegate',
'intentName': 'string',
'slots': {
'string': 'string'
},
'slotToElicit': 'string',
'fulfillmentState': 'Fulfilled'|'Failed'|'ReadyForFulfillment',
'message': 'string',
'messageFormat': 'PlainText'|'CustomPayload'|'SSML'|'Composite'
},
'activeContexts': [
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'parameters': {
'string': 'string'
}
},
]
}
Response Structure
(dict) --
recentIntentSummaryView (list) --
An array of information about the intents used in the session. The array can contain a maximum of three summaries. If more than three intents are used in the session, the recentIntentSummaryView operation contains information about the last three intents used.
If you set the checkpointLabelFilter parameter in the request, the array contains only the intents with the specified label.
(dict) --
Provides information about the state of an intent. You can use this information to get the current state of an intent so that you can process the intent, or so that you can return the intent to its previous state.
intentName (string) --
The name of the intent.
checkpointLabel (string) --
A user-defined label that identifies a particular intent. You can use this label to return to a previous intent.
Use the checkpointLabelFilter parameter of the GetSessionRequest operation to filter the intents returned by the operation to those with only the specified label.
slots (dict) --
Map of the slots that have been gathered and their values.
confirmationStatus (string) --
The status of the intent after the user responds to the confirmation prompt. If the user confirms the intent, Amazon Lex sets this field to Confirmed . If the user denies the intent, Amazon Lex sets this value to Denied . The possible values are:
dialogActionType (string) --
The next action that the bot should take in its interaction with the user. The possible values are:
fulfillmentState (string) --
The fulfillment state of the intent. The possible values are:
slotToElicit (string) --
The next slot to elicit from the user. If there is not slot to elicit, the field is blank.
sessionAttributes (dict) --
Map of key/value pairs representing the session-specific context information. It contains application information passed between Amazon Lex and a client application.
sessionId (string) --
A unique identifier for the session.
dialogAction (dict) --
Describes the current state of the bot.
type (string) --
The next action that the bot should take in its interaction with the user. The possible values are:
intentName (string) --
The name of the intent.
slots (dict) --
Map of the slots that have been gathered and their values.
slotToElicit (string) --
The name of the slot that should be elicited from the user.
fulfillmentState (string) --
The fulfillment state of the intent. The possible values are:
message (string) --
The message that should be shown to the user. If you don't specify a message, Amazon Lex will use the message configured for the intent.
messageFormat (string) --
activeContexts (list) --
A list of active contexts for the session. A context can be set when an intent is fulfilled or by calling the PostContent , PostText , or PutSession operation.
You can use a context to control the intents that can follow up an intent, or to modify the operation of your application.
(dict) --
A context is a variable that contains information about the current state of the conversation between a user and Amazon Lex. Context can be set automatically by Amazon Lex when an intent is fulfilled, or it can be set at runtime using the PutContent , PutText , or PutSession operation.
name (string) --
The name of the context.
timeToLive (dict) --
The length of time or number of turns that a context remains active.
timeToLiveInSeconds (integer) --
The number of seconds that the context should be active after it is first sent in a PostContent or PostText response. You can set the value between 5 and 86,400 seconds (24 hours).
turnsToLive (integer) --
The number of conversation turns that the context should be active. A conversation turn is one PostContent or PostText request and the corresponding response from Amazon Lex.
parameters (dict) --
State variables for the current context. You can use these values as default values for slots in subsequent events.
Exceptions
Returns an object that can wait for some condition.
Sends user input (text or speech) to Amazon Lex. Clients use this API to send text and audio requests to Amazon Lex at runtime. Amazon Lex interprets the user input using the machine learning model that it built for the bot.
The PostContent operation supports audio input at 8kHz and 16kHz. You can use 8kHz audio to achieve higher speech recognition accuracy in telephone audio applications.
In response, Amazon Lex returns the next message to convey to the user. Consider the following example messages:
Not all Amazon Lex messages require a response from the user. For example, conclusion statements do not require a response. Some messages require only a yes or no response. In addition to the message , Amazon Lex provides additional context about the message in the response that you can use to enhance client behavior, such as displaying the appropriate client user interface. Consider the following examples:
In addition, Amazon Lex also returns your application-specific sessionAttributes . For more information, see Managing Conversation Context .
See also: AWS API Documentation
Request Syntax
response = client.post_content(
botName='string',
botAlias='string',
userId='string',
sessionAttributes={...}|[...]|123|123.4|'string'|True|None,
requestAttributes={...}|[...]|123|123.4|'string'|True|None,
contentType='string',
accept='string',
inputStream=b'bytes'|file,
activeContexts={...}|[...]|123|123.4|'string'|True|None
)
[REQUIRED]
Name of the Amazon Lex bot.
[REQUIRED]
Alias of the Amazon Lex bot.
[REQUIRED]
The ID of the client application user. Amazon Lex uses this to identify a user's conversation with your bot. At runtime, each request must contain the userID field.
To decide the user ID to use for your application, consider the following factors.
You pass this value as the x-amz-lex-session-attributes HTTP header.
Application-specific information passed between Amazon Lex and a client application. The value must be a JSON serialized and base64 encoded map with string keys and values. The total size of the sessionAttributes and requestAttributes headers is limited to 12 KB.
For more information, see Setting Session Attributes .
You pass this value as the x-amz-lex-request-attributes HTTP header.
Request-specific information passed between Amazon Lex and a client application. The value must be a JSON serialized and base64 encoded map with string keys and values. The total size of the requestAttributes and sessionAttributes headers is limited to 12 KB.
The namespace x-amz-lex: is reserved for special attributes. Don't create any request attributes with the prefix x-amz-lex: .
For more information, see Setting Request Attributes .
[REQUIRED]
You pass this value as the Content-Type HTTP header.
Indicates the audio format or text. The header value must start with one of the following prefixes:
You pass this value as the Accept HTTP header.
The message Amazon Lex returns in the response can be either text or speech based on the Accept HTTP header value in the request.
[REQUIRED]
User input in PCM or Opus audio format or text format as described in the Content-Type HTTP header.
You can stream audio data to Amazon Lex or you can create a local buffer that captures all of the audio data before sending. In general, you get better performance if you stream audio data rather than buffering the data locally.
A list of contexts active for the request. A context can be activated when a previous intent is fulfilled, or by including the context in the request,
If you don't specify a list of contexts, Amazon Lex will use the current list of contexts for the session. If you specify an empty list, all contexts for the session are cleared.
dict
Response Syntax
{
'contentType': 'string',
'intentName': 'string',
'nluIntentConfidence': {...}|[...]|123|123.4|'string'|True|None,
'alternativeIntents': {...}|[...]|123|123.4|'string'|True|None,
'slots': {...}|[...]|123|123.4|'string'|True|None,
'sessionAttributes': {...}|[...]|123|123.4|'string'|True|None,
'sentimentResponse': 'string',
'message': 'string',
'encodedMessage': 'string',
'messageFormat': 'PlainText'|'CustomPayload'|'SSML'|'Composite',
'dialogState': 'ElicitIntent'|'ConfirmIntent'|'ElicitSlot'|'Fulfilled'|'ReadyForFulfillment'|'Failed',
'slotToElicit': 'string',
'inputTranscript': 'string',
'encodedInputTranscript': 'string',
'audioStream': StreamingBody(),
'botVersion': 'string',
'sessionId': 'string',
'activeContexts': {...}|[...]|123|123.4|'string'|True|None
}
Response Structure
(dict) --
contentType (string) --
Content type as specified in the Accept HTTP header in the request.
intentName (string) --
Current user intent that Amazon Lex is aware of.
nluIntentConfidence (JSON serializable) --
Provides a score that indicates how confident Amazon Lex is that the returned intent is the one that matches the user's intent. The score is between 0.0 and 1.0.
The score is a relative score, not an absolute score. The score may change based on improvements to Amazon Lex.
alternativeIntents (JSON serializable) --
One to four alternative intents that may be applicable to the user's intent.
Each alternative includes a score that indicates how confident Amazon Lex is that the intent matches the user's intent. The intents are sorted by the confidence score.
slots (JSON serializable) --
Map of zero or more intent slots (name/value pairs) Amazon Lex detected from the user input during the conversation. The field is base-64 encoded.
Amazon Lex creates a resolution list containing likely values for a slot. The value that it returns is determined by the valueSelectionStrategy selected when the slot type was created or updated. If valueSelectionStrategy is set to ORIGINAL_VALUE , the value provided by the user is returned, if the user value is similar to the slot values. If valueSelectionStrategy is set to TOP_RESOLUTION Amazon Lex returns the first value in the resolution list or, if there is no resolution list, null. If you don't specify a valueSelectionStrategy , the default is ORIGINAL_VALUE .
sessionAttributes (JSON serializable) --
Map of key/value pairs representing the session-specific context information.
sentimentResponse (string) --
The sentiment expressed in an utterance.
When the bot is configured to send utterances to Amazon Comprehend for sentiment analysis, this field contains the result of the analysis.
message (string) --
You can only use this field in the de-DE, en-AU, en-GB, en-US, es-419, es-ES, es-US, fr-CA, fr-FR, and it-IT locales. In all other locales, the message field is null. You should use the encodedMessage field instead.
The message to convey to the user. The message can come from the bot's configuration or from a Lambda function.
If the intent is not configured with a Lambda function, or if the Lambda function returned Delegate as the dialogAction.type in its response, Amazon Lex decides on the next course of action and selects an appropriate message from the bot's configuration based on the current interaction context. For example, if Amazon Lex isn't able to understand user input, it uses a clarification prompt message.
When you create an intent you can assign messages to groups. When messages are assigned to groups Amazon Lex returns one message from each group in the response. The message field is an escaped JSON string containing the messages. For more information about the structure of the JSON string returned, see msg-prompts-formats .
If the Lambda function returns a message, Amazon Lex passes it to the client in its response.
encodedMessage (string) --
The message to convey to the user. The message can come from the bot's configuration or from a Lambda function.
If the intent is not configured with a Lambda function, or if the Lambda function returned Delegate as the dialogAction.type in its response, Amazon Lex decides on the next course of action and selects an appropriate message from the bot's configuration based on the current interaction context. For example, if Amazon Lex isn't able to understand user input, it uses a clarification prompt message.
When you create an intent you can assign messages to groups. When messages are assigned to groups Amazon Lex returns one message from each group in the response. The message field is an escaped JSON string containing the messages. For more information about the structure of the JSON string returned, see msg-prompts-formats .
If the Lambda function returns a message, Amazon Lex passes it to the client in its response.
The encodedMessage field is base-64 encoded. You must decode the field before you can use the value.
messageFormat (string) --
The format of the response message. One of the following values:
dialogState (string) --
Identifies the current state of the user interaction. Amazon Lex returns one of the following values as dialogState . The client can optionally use this information to customize the user interface.
slotToElicit (string) --
If the dialogState value is ElicitSlot , returns the name of the slot for which Amazon Lex is eliciting a value.
inputTranscript (string) --
The text used to process the request.
You can use this field only in the de-DE, en-AU, en-GB, en-US, es-419, es-ES, es-US, fr-CA, fr-FR, and it-IT locales. In all other locales, the inputTranscript field is null. You should use the encodedInputTranscript field instead.
If the input was an audio stream, the inputTranscript field contains the text extracted from the audio stream. This is the text that is actually processed to recognize intents and slot values. You can use this information to determine if Amazon Lex is correctly processing the audio that you send.
encodedInputTranscript (string) --
The text used to process the request.
If the input was an audio stream, the encodedInputTranscript field contains the text extracted from the audio stream. This is the text that is actually processed to recognize intents and slot values. You can use this information to determine if Amazon Lex is correctly processing the audio that you send.
The encodedInputTranscript field is base-64 encoded. You must decode the field before you can use the value.
audioStream (StreamingBody) --
The prompt (or statement) to convey to the user. This is based on the bot configuration and context. For example, if Amazon Lex did not understand the user intent, it sends the clarificationPrompt configured for the bot. If the intent requires confirmation before taking the fulfillment action, it sends the confirmationPrompt . Another example: Suppose that the Lambda function successfully fulfilled the intent, and sent a message to convey to the user. Then Amazon Lex sends that message in the response.
botVersion (string) --
The version of the bot that responded to the conversation. You can use this information to help determine if one version of a bot is performing better than another version.
sessionId (string) --
The unique identifier for the session.
activeContexts (JSON serializable) --
A list of active contexts for the session. A context can be set when an intent is fulfilled or by calling the PostContent , PostText , or PutSession operation.
You can use a context to control the intents that can follow up an intent, or to modify the operation of your application.
Exceptions
Sends user input to Amazon Lex. Client applications can use this API to send requests to Amazon Lex at runtime. Amazon Lex then interprets the user input using the machine learning model it built for the bot.
In response, Amazon Lex returns the next message to convey to the user an optional responseCard to display. Consider the following example messages:
Not all Amazon Lex messages require a user response. For example, a conclusion statement does not require a response. Some messages require only a "yes" or "no" user response. In addition to the message , Amazon Lex provides additional context about the message in the response that you might use to enhance client behavior, for example, to display the appropriate client user interface. These are the slotToElicit , dialogState , intentName , and slots fields in the response. Consider the following examples:
In addition, Amazon Lex also returns your application-specific sessionAttributes . For more information, see Managing Conversation Context .
See also: AWS API Documentation
Request Syntax
response = client.post_text(
botName='string',
botAlias='string',
userId='string',
sessionAttributes={
'string': 'string'
},
requestAttributes={
'string': 'string'
},
inputText='string',
activeContexts=[
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'parameters': {
'string': 'string'
}
},
]
)
[REQUIRED]
The name of the Amazon Lex bot.
[REQUIRED]
The alias of the Amazon Lex bot.
[REQUIRED]
The ID of the client application user. Amazon Lex uses this to identify a user's conversation with your bot. At runtime, each request must contain the userID field.
To decide the user ID to use for your application, consider the following factors.
Application-specific information passed between Amazon Lex and a client application.
For more information, see Setting Session Attributes .
Request-specific information passed between Amazon Lex and a client application.
The namespace x-amz-lex: is reserved for special attributes. Don't create any request attributes with the prefix x-amz-lex: .
For more information, see Setting Request Attributes .
[REQUIRED]
The text that the user entered (Amazon Lex interprets this text).
A list of contexts active for the request. A context can be activated when a previous intent is fulfilled, or by including the context in the request,
If you don't specify a list of contexts, Amazon Lex will use the current list of contexts for the session. If you specify an empty list, all contexts for the session are cleared.
A context is a variable that contains information about the current state of the conversation between a user and Amazon Lex. Context can be set automatically by Amazon Lex when an intent is fulfilled, or it can be set at runtime using the PutContent , PutText , or PutSession operation.
The name of the context.
The length of time or number of turns that a context remains active.
The number of seconds that the context should be active after it is first sent in a PostContent or PostText response. You can set the value between 5 and 86,400 seconds (24 hours).
The number of conversation turns that the context should be active. A conversation turn is one PostContent or PostText request and the corresponding response from Amazon Lex.
State variables for the current context. You can use these values as default values for slots in subsequent events.
dict
Response Syntax
{
'intentName': 'string',
'nluIntentConfidence': {
'score': 123.0
},
'alternativeIntents': [
{
'intentName': 'string',
'nluIntentConfidence': {
'score': 123.0
},
'slots': {
'string': 'string'
}
},
],
'slots': {
'string': 'string'
},
'sessionAttributes': {
'string': 'string'
},
'message': 'string',
'sentimentResponse': {
'sentimentLabel': 'string',
'sentimentScore': 'string'
},
'messageFormat': 'PlainText'|'CustomPayload'|'SSML'|'Composite',
'dialogState': 'ElicitIntent'|'ConfirmIntent'|'ElicitSlot'|'Fulfilled'|'ReadyForFulfillment'|'Failed',
'slotToElicit': 'string',
'responseCard': {
'version': 'string',
'contentType': 'application/vnd.amazonaws.card.generic',
'genericAttachments': [
{
'title': 'string',
'subTitle': 'string',
'attachmentLinkUrl': 'string',
'imageUrl': 'string',
'buttons': [
{
'text': 'string',
'value': 'string'
},
]
},
]
},
'sessionId': 'string',
'botVersion': 'string',
'activeContexts': [
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'parameters': {
'string': 'string'
}
},
]
}
Response Structure
(dict) --
intentName (string) --
The current user intent that Amazon Lex is aware of.
nluIntentConfidence (dict) --
Provides a score that indicates how confident Amazon Lex is that the returned intent is the one that matches the user's intent. The score is between 0.0 and 1.0. For more information, see Confidence Scores .
The score is a relative score, not an absolute score. The score may change based on improvements to Amazon Lex.
score (float) --
A score that indicates how confident Amazon Lex is that an intent satisfies the user's intent. Ranges between 0.00 and 1.00. Higher scores indicate higher confidence.
alternativeIntents (list) --
One to four alternative intents that may be applicable to the user's intent.
Each alternative includes a score that indicates how confident Amazon Lex is that the intent matches the user's intent. The intents are sorted by the confidence score.
(dict) --
An intent that Amazon Lex suggests satisfies the user's intent. Includes the name of the intent, the confidence that Amazon Lex has that the user's intent is satisfied, and the slots defined for the intent.
intentName (string) --
The name of the intent that Amazon Lex suggests satisfies the user's intent.
nluIntentConfidence (dict) --
Indicates how confident Amazon Lex is that an intent satisfies the user's intent.
score (float) --
A score that indicates how confident Amazon Lex is that an intent satisfies the user's intent. Ranges between 0.00 and 1.00. Higher scores indicate higher confidence.
slots (dict) --
The slot and slot values associated with the predicted intent.
slots (dict) --
The intent slots that Amazon Lex detected from the user input in the conversation.
Amazon Lex creates a resolution list containing likely values for a slot. The value that it returns is determined by the valueSelectionStrategy selected when the slot type was created or updated. If valueSelectionStrategy is set to ORIGINAL_VALUE , the value provided by the user is returned, if the user value is similar to the slot values. If valueSelectionStrategy is set to TOP_RESOLUTION Amazon Lex returns the first value in the resolution list or, if there is no resolution list, null. If you don't specify a valueSelectionStrategy , the default is ORIGINAL_VALUE .
sessionAttributes (dict) --
A map of key-value pairs representing the session-specific context information.
message (string) --
The message to convey to the user. The message can come from the bot's configuration or from a Lambda function.
If the intent is not configured with a Lambda function, or if the Lambda function returned Delegate as the dialogAction.type its response, Amazon Lex decides on the next course of action and selects an appropriate message from the bot's configuration based on the current interaction context. For example, if Amazon Lex isn't able to understand user input, it uses a clarification prompt message.
When you create an intent you can assign messages to groups. When messages are assigned to groups Amazon Lex returns one message from each group in the response. The message field is an escaped JSON string containing the messages. For more information about the structure of the JSON string returned, see msg-prompts-formats .
If the Lambda function returns a message, Amazon Lex passes it to the client in its response.
sentimentResponse (dict) --
The sentiment expressed in and utterance.
When the bot is configured to send utterances to Amazon Comprehend for sentiment analysis, this field contains the result of the analysis.
sentimentLabel (string) --
The inferred sentiment that Amazon Comprehend has the highest confidence in.
sentimentScore (string) --
The likelihood that the sentiment was correctly inferred.
messageFormat (string) --
The format of the response message. One of the following values:
dialogState (string) --
Identifies the current state of the user interaction. Amazon Lex returns one of the following values as dialogState . The client can optionally use this information to customize the user interface.
slotToElicit (string) --
If the dialogState value is ElicitSlot , returns the name of the slot for which Amazon Lex is eliciting a value.
responseCard (dict) --
Represents the options that the user has to respond to the current prompt. Response Card can come from the bot configuration (in the Amazon Lex console, choose the settings button next to a slot) or from a code hook (Lambda function).
version (string) --
The version of the response card format.
contentType (string) --
The content type of the response.
genericAttachments (list) --
An array of attachment objects representing options.
(dict) --
Represents an option rendered to the user when a prompt is shown. It could be an image, a button, a link, or text.
title (string) --
The title of the option.
subTitle (string) --
The subtitle shown below the title.
attachmentLinkUrl (string) --
The URL of an attachment to the response card.
imageUrl (string) --
The URL of an image that is displayed to the user.
buttons (list) --
The list of options to show to the user.
(dict) --
Represents an option to be shown on the client platform (Facebook, Slack, etc.)
text (string) --
Text that is visible to the user on the button.
value (string) --
The value sent to Amazon Lex when a user chooses the button. For example, consider button text "NYC." When the user chooses the button, the value sent can be "New York City."
sessionId (string) --
A unique identifier for the session.
botVersion (string) --
The version of the bot that responded to the conversation. You can use this information to help determine if one version of a bot is performing better than another version.
activeContexts (list) --
A list of active contexts for the session. A context can be set when an intent is fulfilled or by calling the PostContent , PostText , or PutSession operation.
You can use a context to control the intents that can follow up an intent, or to modify the operation of your application.
(dict) --
A context is a variable that contains information about the current state of the conversation between a user and Amazon Lex. Context can be set automatically by Amazon Lex when an intent is fulfilled, or it can be set at runtime using the PutContent , PutText , or PutSession operation.
name (string) --
The name of the context.
timeToLive (dict) --
The length of time or number of turns that a context remains active.
timeToLiveInSeconds (integer) --
The number of seconds that the context should be active after it is first sent in a PostContent or PostText response. You can set the value between 5 and 86,400 seconds (24 hours).
turnsToLive (integer) --
The number of conversation turns that the context should be active. A conversation turn is one PostContent or PostText request and the corresponding response from Amazon Lex.
parameters (dict) --
State variables for the current context. You can use these values as default values for slots in subsequent events.
Exceptions
Creates a new session or modifies an existing session with an Amazon Lex bot. Use this operation to enable your application to set the state of the bot.
For more information, see Managing Sessions .
See also: AWS API Documentation
Request Syntax
response = client.put_session(
botName='string',
botAlias='string',
userId='string',
sessionAttributes={
'string': 'string'
},
dialogAction={
'type': 'ElicitIntent'|'ConfirmIntent'|'ElicitSlot'|'Close'|'Delegate',
'intentName': 'string',
'slots': {
'string': 'string'
},
'slotToElicit': 'string',
'fulfillmentState': 'Fulfilled'|'Failed'|'ReadyForFulfillment',
'message': 'string',
'messageFormat': 'PlainText'|'CustomPayload'|'SSML'|'Composite'
},
recentIntentSummaryView=[
{
'intentName': 'string',
'checkpointLabel': 'string',
'slots': {
'string': 'string'
},
'confirmationStatus': 'None'|'Confirmed'|'Denied',
'dialogActionType': 'ElicitIntent'|'ConfirmIntent'|'ElicitSlot'|'Close'|'Delegate',
'fulfillmentState': 'Fulfilled'|'Failed'|'ReadyForFulfillment',
'slotToElicit': 'string'
},
],
accept='string',
activeContexts=[
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'parameters': {
'string': 'string'
}
},
]
)
[REQUIRED]
The name of the bot that contains the session data.
[REQUIRED]
The alias in use for the bot that contains the session data.
[REQUIRED]
The ID of the client application user. Amazon Lex uses this to identify a user's conversation with your bot.
Map of key/value pairs representing the session-specific context information. It contains application information passed between Amazon Lex and a client application.
Sets the next action that the bot should take to fulfill the conversation.
The next action that the bot should take in its interaction with the user. The possible values are:
The name of the intent.
Map of the slots that have been gathered and their values.
The name of the slot that should be elicited from the user.
The fulfillment state of the intent. The possible values are:
The message that should be shown to the user. If you don't specify a message, Amazon Lex will use the message configured for the intent.
A summary of the recent intents for the bot. You can use the intent summary view to set a checkpoint label on an intent and modify attributes of intents. You can also use it to remove or add intent summary objects to the list.
An intent that you modify or add to the list must make sense for the bot. For example, the intent name must be valid for the bot. You must provide valid values for:
If you send the recentIntentSummaryView parameter in a PutSession request, the contents of the new summary view replaces the old summary view. For example, if a GetSession request returns three intents in the summary view and you call PutSession with one intent in the summary view, the next call to GetSession will only return one intent.
Provides information about the state of an intent. You can use this information to get the current state of an intent so that you can process the intent, or so that you can return the intent to its previous state.
The name of the intent.
A user-defined label that identifies a particular intent. You can use this label to return to a previous intent.
Use the checkpointLabelFilter parameter of the GetSessionRequest operation to filter the intents returned by the operation to those with only the specified label.
Map of the slots that have been gathered and their values.
The status of the intent after the user responds to the confirmation prompt. If the user confirms the intent, Amazon Lex sets this field to Confirmed . If the user denies the intent, Amazon Lex sets this value to Denied . The possible values are:
The next action that the bot should take in its interaction with the user. The possible values are:
The fulfillment state of the intent. The possible values are:
The next slot to elicit from the user. If there is not slot to elicit, the field is blank.
The message that Amazon Lex returns in the response can be either text or speech based depending on the value of this field.
A list of contexts active for the request. A context can be activated when a previous intent is fulfilled, or by including the context in the request,
If you don't specify a list of contexts, Amazon Lex will use the current list of contexts for the session. If you specify an empty list, all contexts for the session are cleared.
A context is a variable that contains information about the current state of the conversation between a user and Amazon Lex. Context can be set automatically by Amazon Lex when an intent is fulfilled, or it can be set at runtime using the PutContent , PutText , or PutSession operation.
The name of the context.
The length of time or number of turns that a context remains active.
The number of seconds that the context should be active after it is first sent in a PostContent or PostText response. You can set the value between 5 and 86,400 seconds (24 hours).
The number of conversation turns that the context should be active. A conversation turn is one PostContent or PostText request and the corresponding response from Amazon Lex.
State variables for the current context. You can use these values as default values for slots in subsequent events.
dict
Response Syntax
{
'contentType': 'string',
'intentName': 'string',
'slots': {...}|[...]|123|123.4|'string'|True|None,
'sessionAttributes': {...}|[...]|123|123.4|'string'|True|None,
'message': 'string',
'encodedMessage': 'string',
'messageFormat': 'PlainText'|'CustomPayload'|'SSML'|'Composite',
'dialogState': 'ElicitIntent'|'ConfirmIntent'|'ElicitSlot'|'Fulfilled'|'ReadyForFulfillment'|'Failed',
'slotToElicit': 'string',
'audioStream': StreamingBody(),
'sessionId': 'string',
'activeContexts': {...}|[...]|123|123.4|'string'|True|None
}
Response Structure
(dict) --
contentType (string) --
Content type as specified in the Accept HTTP header in the request.
intentName (string) --
The name of the current intent.
slots (JSON serializable) --
Map of zero or more intent slots Amazon Lex detected from the user input during the conversation.
Amazon Lex creates a resolution list containing likely values for a slot. The value that it returns is determined by the valueSelectionStrategy selected when the slot type was created or updated. If valueSelectionStrategy is set to ORIGINAL_VALUE , the value provided by the user is returned, if the user value is similar to the slot values. If valueSelectionStrategy is set to TOP_RESOLUTION Amazon Lex returns the first value in the resolution list or, if there is no resolution list, null. If you don't specify a valueSelectionStrategy the default is ORIGINAL_VALUE .
sessionAttributes (JSON serializable) --
Map of key/value pairs representing session-specific context information.
message (string) --
The next message that should be presented to the user.
You can only use this field in the de-DE, en-AU, en-GB, en-US, es-419, es-ES, es-US, fr-CA, fr-FR, and it-IT locales. In all other locales, the message field is null. You should use the encodedMessage field instead.
encodedMessage (string) --
The next message that should be presented to the user.
The encodedMessage field is base-64 encoded. You must decode the field before you can use the value.
messageFormat (string) --
The format of the response message. One of the following values:
dialogState (string) --
slotToElicit (string) --
If the dialogState is ElicitSlot , returns the name of the slot for which Amazon Lex is eliciting a value.
audioStream (StreamingBody) --
The audio version of the message to convey to the user.
sessionId (string) --
A unique identifier for the session.
activeContexts (JSON serializable) --
A list of active contexts for the session.
Exceptions
The available paginators are: