2021/01/22 - Amazon Lex Runtime V2 - 6 new api methods
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.
See also: AWS API Documentation
Request Syntax
client.put_session(
botId='string',
botAliasId='string',
localeId='string',
sessionId='string',
messages=[
{
'content': 'string',
'contentType': 'CustomPayload'|'ImageResponseCard'|'PlainText'|'SSML',
'imageResponseCard': {
'title': 'string',
'subtitle': 'string',
'imageUrl': 'string',
'buttons': [
{
'text': 'string',
'value': 'string'
},
]
}
},
],
sessionState={
'dialogAction': {
'type': 'Close'|'ConfirmIntent'|'Delegate'|'ElicitIntent'|'ElicitSlot',
'slotToElicit': 'string'
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
},
'activeContexts': [
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'contextAttributes': {
'string': 'string'
}
},
],
'sessionAttributes': {
'string': 'string'
},
'originatingRequestId': 'string'
},
requestAttributes={
'string': 'string'
},
responseContentType='string'
)
string
[REQUIRED]
The identifier of the bot that receives the session data.
string
[REQUIRED]
The alias identifier of the bot that receives the session data.
string
[REQUIRED]
The locale where the session is in use.
string
[REQUIRED]
The identifier of the session that receives the session data.
list
A list of messages to send to the user. Messages are sent in the order that they are defined in the list.
(dict) --
Container for text that is returned to the customer..
content (string) --
The text of the message.
contentType (string) --
Indicates the type of response.
imageResponseCard (dict) --
A card that is shown to the user by a messaging platform. You define the contents of the card, the card is displayed by the platform.
When you use a response card, the response from the user is constrained to the text associated with a button on the card.
title (string) -- [REQUIRED]
The title to display on the response card. The format of the title is determined by the platform displaying the response card.
subtitle (string) --
The subtitle to display on the response card. The format of the subtitle is determined by the platform displaying the response card.
imageUrl (string) --
The URL of an image to display on the response card. The image URL must be publicly available so that the platform displaying the response card has access to the image.
buttons (list) --
A list of buttons that should be displayed on the response card. The arrangement of the buttons is determined by the platform that displays the button.
(dict) --
A button that appears on a response card show to the user.
text (string) -- [REQUIRED]
The text that is displayed on the button.
value (string) -- [REQUIRED]
The value returned to Amazon Lex when a user chooses the button.
dict
[REQUIRED]
Sets the state of the session with the user. You can use this to set the current intent, attributes, context, and dialog action. Use the dialog action to determine the next step that Amazon Lex should use in the conversation with the user.
dialogAction (dict) --
The next step that Amazon Lex should take in the conversation with a user.
type (string) -- [REQUIRED]
The next action that the bot should take in its interaction with the user. The possible values are:
Close - Indicates that there will not be a response from the user. For example, the statement "Your order has been placed" does not require a response.
ConfirmIntent - The next action is asking the user if the intent is complete and ready to be fulfilled. This is a yes/no question such as "Place the order?"
Delegate - The next action is determined by Amazon Lex.
ElicitSlot - The next action is to elicit a slot value from the user.
slotToElicit (string) --
The name of the slot that should be elicited from the user.
intent (dict) --
The active intent that Amazon Lex is processing.
name (string) -- [REQUIRED]
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) -- [REQUIRED]
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
activeContexts (list) --
One or more contexts that indicate to Amazon Lex the context of a request. When a context is active, Amazon Lex considers intents with the matching context as a trigger as the next intent in a session.
(dict) --
Contains information about the contexts that a user is using in a session. You can configure Amazon Lex to set a context when an intent is fulfilled, or you can set a context using the , , or operations.
Use a context to indicate to Amazon Lex intents that should be used as follow-up intents. For example, if the active context is order-fulfilled, only intents that have order-fulfilled configured as a trigger are considered for follow up.
name (string) -- [REQUIRED]
The name of the context.
timeToLive (dict) -- [REQUIRED]
Indicates the number of turns or seconds that the context is active. Once the time to live expires, the context is no longer returned in a response.
timeToLiveInSeconds (integer) -- [REQUIRED]
The number of seconds that the context is active. You can specify between 5 and 86400 seconds (24 hours).
turnsToLive (integer) -- [REQUIRED]
The number of turns that the context is active. You can specify up to 20 turns. Each request and response from the bot is a turn.
contextAttributes (dict) --
A lis tof 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.
(string) --
(string) --
sessionAttributes (dict) --
Map of key/value pairs representing session-specific context information. It contains application information passed between Amazon Lex and a client application.
(string) --
(string) --
originatingRequestId (string) --
dict
Request-specific information passed between Amazon Lex and the client application.
The namespace x-amz-lex: is reserved for special attributes. Don't create any request attributes with the prefix x-amz-lex:.
(string) --
(string) --
string
The message that Amazon Lex returns in the response can be either text or speech depending on the value of this parameter.
If the value is text/plain; charset=utf-8, Amazon Lex returns text in the response.
dict
Response Syntax
{
'contentType': 'string',
'messages': 'string',
'sessionState': 'string',
'requestAttributes': 'string',
'sessionId': 'string',
'audioStream': StreamingBody()
}
Response Structure
(dict) --
contentType (string) --
The type of response. Same as the type specified in the responseContentType field in the request.
messages (string) --
A list of messages that were last sent to the user. The messages are ordered based on how you return the messages from you Lambda function or the order that the messages are defined in the bot.
sessionState (string) --
Represents the current state of the dialog between the user and the bot.
Use this to determine the progress of the conversation and what the next action may be.
requestAttributes (string) --
Request-specific information passed between the client application and Amazon Lex. These are the same as the requestAttribute parameter in the call to the PutSession operation.
sessionId (string) --
The identifier of the session that received the data.
audioStream (:class:`.StreamingBody`) --
If the requested content type was audio, the audio version of the message to convey to the user.
Sends user input to Amazon Lex. Client applications use this API to send requests to Amazon Lex at runtime. Amazon Lex then interprets the user input using the machine learning model that it build for the bot.
In response, Amazon Lex returns the next message to convey to the user and an optional response card to display.
See also: AWS API Documentation
Request Syntax
client.recognize_text(
botId='string',
botAliasId='string',
localeId='string',
sessionId='string',
text='string',
sessionState={
'dialogAction': {
'type': 'Close'|'ConfirmIntent'|'Delegate'|'ElicitIntent'|'ElicitSlot',
'slotToElicit': 'string'
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
},
'activeContexts': [
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'contextAttributes': {
'string': 'string'
}
},
],
'sessionAttributes': {
'string': 'string'
},
'originatingRequestId': 'string'
},
requestAttributes={
'string': 'string'
}
)
string
[REQUIRED]
The identifier of the bot that processes the request.
string
[REQUIRED]
The alias identifier in use for the bot that processes the request.
string
[REQUIRED]
The locale where the session is in use.
string
[REQUIRED]
The identifier of the user session that is having the conversation.
string
[REQUIRED]
The text that the user entered. Amazon Lex interprets this text.
dict
The current state of the dialog between the user and the bot.
dialogAction (dict) --
The next step that Amazon Lex should take in the conversation with a user.
type (string) -- [REQUIRED]
The next action that the bot should take in its interaction with the user. The possible values are:
Close - Indicates that there will not be a response from the user. For example, the statement "Your order has been placed" does not require a response.
ConfirmIntent - The next action is asking the user if the intent is complete and ready to be fulfilled. This is a yes/no question such as "Place the order?"
Delegate - The next action is determined by Amazon Lex.
ElicitSlot - The next action is to elicit a slot value from the user.
slotToElicit (string) --
The name of the slot that should be elicited from the user.
intent (dict) --
The active intent that Amazon Lex is processing.
name (string) -- [REQUIRED]
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) -- [REQUIRED]
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
activeContexts (list) --
One or more contexts that indicate to Amazon Lex the context of a request. When a context is active, Amazon Lex considers intents with the matching context as a trigger as the next intent in a session.
(dict) --
Contains information about the contexts that a user is using in a session. You can configure Amazon Lex to set a context when an intent is fulfilled, or you can set a context using the , , or operations.
Use a context to indicate to Amazon Lex intents that should be used as follow-up intents. For example, if the active context is order-fulfilled, only intents that have order-fulfilled configured as a trigger are considered for follow up.
name (string) -- [REQUIRED]
The name of the context.
timeToLive (dict) -- [REQUIRED]
Indicates the number of turns or seconds that the context is active. Once the time to live expires, the context is no longer returned in a response.
timeToLiveInSeconds (integer) -- [REQUIRED]
The number of seconds that the context is active. You can specify between 5 and 86400 seconds (24 hours).
turnsToLive (integer) -- [REQUIRED]
The number of turns that the context is active. You can specify up to 20 turns. Each request and response from the bot is a turn.
contextAttributes (dict) --
A lis tof 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.
(string) --
(string) --
sessionAttributes (dict) --
Map of key/value pairs representing session-specific context information. It contains application information passed between Amazon Lex and a client application.
(string) --
(string) --
originatingRequestId (string) --
dict
Request-specific information passed between the client application and Amazon Lex
The namespace x-amz-lex: is reserved for special attributes. Don't create any request attributes with the prefix x-amz-lex:.
(string) --
(string) --
dict
Response Syntax
{
'messages': [
{
'content': 'string',
'contentType': 'CustomPayload'|'ImageResponseCard'|'PlainText'|'SSML',
'imageResponseCard': {
'title': 'string',
'subtitle': 'string',
'imageUrl': 'string',
'buttons': [
{
'text': 'string',
'value': 'string'
},
]
}
},
],
'sessionState': {
'dialogAction': {
'type': 'Close'|'ConfirmIntent'|'Delegate'|'ElicitIntent'|'ElicitSlot',
'slotToElicit': 'string'
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
},
'activeContexts': [
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'contextAttributes': {
'string': 'string'
}
},
],
'sessionAttributes': {
'string': 'string'
},
'originatingRequestId': 'string'
},
'interpretations': [
{
'nluConfidence': {
'score': 123.0
},
'sentimentResponse': {
'sentiment': 'MIXED'|'NEGATIVE'|'NEUTRAL'|'POSITIVE',
'sentimentScore': {
'positive': 123.0,
'negative': 123.0,
'neutral': 123.0,
'mixed': 123.0
}
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
}
},
],
'requestAttributes': {
'string': 'string'
},
'sessionId': 'string'
}
Response Structure
(dict) --
messages (list) --
A list of messages last sent to the user. The messages are ordered based on the order that you returned the messages from your Lambda function or the order that the messages are defined in the bot.
(dict) --
Container for text that is returned to the customer..
content (string) --
The text of the message.
contentType (string) --
Indicates the type of response.
imageResponseCard (dict) --
A card that is shown to the user by a messaging platform. You define the contents of the card, the card is displayed by the platform.
When you use a response card, the response from the user is constrained to the text associated with a button on the card.
title (string) --
The title to display on the response card. The format of the title is determined by the platform displaying the response card.
subtitle (string) --
The subtitle to display on the response card. The format of the subtitle is determined by the platform displaying the response card.
imageUrl (string) --
The URL of an image to display on the response card. The image URL must be publicly available so that the platform displaying the response card has access to the image.
buttons (list) --
A list of buttons that should be displayed on the response card. The arrangement of the buttons is determined by the platform that displays the button.
(dict) --
A button that appears on a response card show to the user.
text (string) --
The text that is displayed on the button.
value (string) --
The value returned to Amazon Lex when a user chooses the button.
sessionState (dict) --
Represents the current state of the dialog between the user and the bot.
Use this to determine the progress of the conversation and what the next action may be.
dialogAction (dict) --
The next step that Amazon Lex should take in the conversation with a user.
type (string) --
The next action that the bot should take in its interaction with the user. The possible values are:
Close - Indicates that there will not be a response from the user. For example, the statement "Your order has been placed" does not require a response.
ConfirmIntent - The next action is asking the user if the intent is complete and ready to be fulfilled. This is a yes/no question such as "Place the order?"
Delegate - The next action is determined by Amazon Lex.
ElicitSlot - The next action is to elicit a slot value from the user.
slotToElicit (string) --
The name of the slot that should be elicited from the user.
intent (dict) --
The active intent that Amazon Lex is processing.
name (string) --
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) --
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
activeContexts (list) --
One or more contexts that indicate to Amazon Lex the context of a request. When a context is active, Amazon Lex considers intents with the matching context as a trigger as the next intent in a session.
(dict) --
Contains information about the contexts that a user is using in a session. You can configure Amazon Lex to set a context when an intent is fulfilled, or you can set a context using the , , or operations.
Use a context to indicate to Amazon Lex intents that should be used as follow-up intents. For example, if the active context is order-fulfilled, only intents that have order-fulfilled configured as a trigger are considered for follow up.
name (string) --
The name of the context.
timeToLive (dict) --
Indicates the number of turns or seconds that the context is active. Once the time to live expires, the context is no longer returned in a response.
timeToLiveInSeconds (integer) --
The number of seconds that the context is active. You can specify between 5 and 86400 seconds (24 hours).
turnsToLive (integer) --
The number of turns that the context is active. You can specify up to 20 turns. Each request and response from the bot is a turn.
contextAttributes (dict) --
A lis tof 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.
(string) --
(string) --
sessionAttributes (dict) --
Map of key/value pairs representing session-specific context information. It contains application information passed between Amazon Lex and a client application.
(string) --
(string) --
originatingRequestId (string) --
interpretations (list) --
A list of intents that Amazon Lex determined might satisfy the user's utterance.
Each interpretation includes the intent, a score that indicates now confident Amazon Lex is that the interpretation is the correct one, and an optional sentiment response that indicates the sentiment expressed in the utterance.
(dict) --
An intent that Amazon Lex determined might satisfy the user's utterance. The intents are ordered by the confidence score.
nluConfidence (dict) --
Determines the threshold where Amazon Lex will insert the AMAZON.FallbackIntent, AMAZON.KendraSearchIntent, or both when returning alternative intents in a response. AMAZON.FallbackIntent and AMAZON.KendraSearchIntent are only inserted if they are configured for the bot.
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.
sentimentResponse (dict) --
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.
sentiment (string) --
The overall sentiment expressed in the user's response. This is the sentiment most likely expressed by the user based on the analysis by Amazon Comprehend.
sentimentScore (dict) --
The individual sentiment responses for the utterance.
positive (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.
negative (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.
neutral (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.
mixed (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.
intent (dict) --
A list of intents that might satisfy the user's utterance. The intents are ordered by the confidence score.
name (string) --
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) --
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
requestAttributes (dict) --
The attributes sent in the request.
(string) --
(string) --
sessionId (string) --
The identifier of the session in use.
Sends user input to Amazon Lex. You can send text or speech. 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 built for the bot.
See also: AWS API Documentation
Request Syntax
client.recognize_utterance(
botId='string',
botAliasId='string',
localeId='string',
sessionId='string',
sessionState='string',
requestAttributes='string',
requestContentType='string',
responseContentType='string',
inputStream=b'bytes'|file
)
string
[REQUIRED]
The identifier of the bot that should receive the request.
string
[REQUIRED]
The alias identifier in use for the bot that should receive the request.
string
[REQUIRED]
The locale where the session is in use.
string
[REQUIRED]
The identifier of the session in use.
string
Sets the state of the session with the user. You can use this to set the current intent, attributes, context, and dialog action. Use the dialog action to determine the next step that Amazon Lex should use in the conversation with the user.
string
Request-specific information passed between the client application and Amazon Lex
The namespace x-amz-lex: is reserved for special attributes. Don't create any request attributes for prefix x-amz-lex:.
string
[REQUIRED]
Indicates the format for audio input or that the content is text. The header must start with one of the following prefixes:
PCM format, audio data must be in little-endian byte order.
audio/l16; rate=16000; channels=1
audio/x-l16; sample-rate=16000; channel-count=1
audio/lpcm; sample-rate=8000; sample-size-bits=16; channel-count=1; is-big-endian=false
Opus format
audio/x-cbr-opus-with-preamble;preamble-size=0;bit-rate=256000;frame-size-milliseconds=4
Text format
text/plain; charset=utf-8
string
The message that Amazon Lex returns in the response can be either text or speech based on the responseContentType value.
If the value is text/plain;charset=utf-8, Amazon Lex returns text in the response.
If the value begins with audio/, Amazon Lex returns speech in the response. Amazon Lex uses Amazon Polly to generate the speech using the configuration that you specified in the requestContentType parameter. For example, if you specify audio/mpeg as the value, Amazon Lex returns speech in the MPEG format.
If the value is audio/pcm, the speech returned is audio/pcm at 16 KHz in 16-bit, little-endian format.
The following are the accepted values:
audio/mpeg
audio/ogg
audio/pcm (16 KHz)
audio/* (defaults to mpeg)
text/plain; charset=utf-8
bytes or seekable file-like object
User input in PCM or Opus audio format or text format as described in the requestContentType parameter.
dict
Response Syntax
{
'inputMode': 'string',
'contentType': 'string',
'messages': 'string',
'interpretations': 'string',
'sessionState': 'string',
'requestAttributes': 'string',
'sessionId': 'string',
'inputTranscript': 'string',
'audioStream': b'bytes'|file
}
Response Structure
(dict) --
inputMode (string) --
Indicates whether the input mode to the operation was text or speech.
contentType (string) --
Content type as specified in the responseContentType in the request.
messages (string) --
A list of messages that were last sent to the user. The messages are ordered based on the order that you returned the messages from your Lambda function or the order that the messages are defined in the bot.
interpretations (string) --
A list of intents that Amazon Lex determined might satisfy the user's utterance.
Each interpretation includes the intent, a score that indicates how confident Amazon Lex is that the interpretation is the correct one, and an optional sentiment response that indicates the sentiment expressed in the utterance.
sessionState (string) --
Represents the current state of the dialog between the user and the bot.
Use this to determine the progress of the conversation and what the next action might be.
requestAttributes (string) --
The attributes sent in the request.
sessionId (string) --
The identifier of the session in use.
inputTranscript (string) --
The text used to process the request.
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.
audioStream (bytes or seekable file-like object) --
The prompt or statement to send 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.
Removes session information for a specified bot, alias, and user ID.
You can use this operation to restart a conversation with a bot. When you remove a session, the entire history of the session is removed so that you can start again.
You don't need to delete a session. Sessions have a time limit and will expire. Set the session time limit when you create the bot. The default is 5 minutes, but you can specify anything between 1 minute and 24 hours.
If you specify a bot or alias ID that doesn't exist, you receive a BadRequestException.
If the locale doesn't exist in the bot, or if the locale hasn't been enables for the alias, you receive a BadRequestException.
See also: AWS API Documentation
Request Syntax
client.delete_session(
botId='string',
botAliasId='string',
localeId='string',
sessionId='string'
)
string
[REQUIRED]
The identifier of the bot that contains the session data.
string
[REQUIRED]
The alias identifier in use for the bot that contains the session data.
string
[REQUIRED]
The locale where the session is in use.
string
[REQUIRED]
The identifier of the session to delete.
dict
Response Syntax
{
'botId': 'string',
'botAliasId': 'string',
'localeId': 'string',
'sessionId': 'string'
}
Response Structure
(dict) --
botId (string) --
The identifier of the bot that contained the session data.
botAliasId (string) --
The alias identifier in use for the bot that contained the session data.
localeId (string) --
The locale where the session was used.
sessionId (string) --
The identifier of the deleted session.
Returns session information for a specified bot, alias, and user.
For example, you can use this operation to retrieve session information for a user that has left a long-running session in use.
If the bot, alias, or session identifier doesn't exist, Amazon Lex returns a BadRequestException. If the locale doesn't exist or is not enabled for the alias, you receive a BadRequestException.
See also: AWS API Documentation
Request Syntax
client.get_session(
botId='string',
botAliasId='string',
localeId='string',
sessionId='string'
)
string
[REQUIRED]
The identifier of the bot that contains the session data.
string
[REQUIRED]
The alias identifier in use for the bot that contains the session data.
string
[REQUIRED]
The locale where the session is in use.
string
[REQUIRED]
The identifier of the session to return.
dict
Response Syntax
{
'sessionId': 'string',
'messages': [
{
'content': 'string',
'contentType': 'CustomPayload'|'ImageResponseCard'|'PlainText'|'SSML',
'imageResponseCard': {
'title': 'string',
'subtitle': 'string',
'imageUrl': 'string',
'buttons': [
{
'text': 'string',
'value': 'string'
},
]
}
},
],
'interpretations': [
{
'nluConfidence': {
'score': 123.0
},
'sentimentResponse': {
'sentiment': 'MIXED'|'NEGATIVE'|'NEUTRAL'|'POSITIVE',
'sentimentScore': {
'positive': 123.0,
'negative': 123.0,
'neutral': 123.0,
'mixed': 123.0
}
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
}
},
],
'sessionState': {
'dialogAction': {
'type': 'Close'|'ConfirmIntent'|'Delegate'|'ElicitIntent'|'ElicitSlot',
'slotToElicit': 'string'
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
},
'activeContexts': [
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'contextAttributes': {
'string': 'string'
}
},
],
'sessionAttributes': {
'string': 'string'
},
'originatingRequestId': 'string'
}
}
Response Structure
(dict) --
sessionId (string) --
The identifier of the returned session.
messages (list) --
A list of messages that were last sent to the user. The messages are ordered based on the order that your returned the messages from your Lambda function or the order that messages are defined in the bot.
(dict) --
Container for text that is returned to the customer..
content (string) --
The text of the message.
contentType (string) --
Indicates the type of response.
imageResponseCard (dict) --
A card that is shown to the user by a messaging platform. You define the contents of the card, the card is displayed by the platform.
When you use a response card, the response from the user is constrained to the text associated with a button on the card.
title (string) --
The title to display on the response card. The format of the title is determined by the platform displaying the response card.
subtitle (string) --
The subtitle to display on the response card. The format of the subtitle is determined by the platform displaying the response card.
imageUrl (string) --
The URL of an image to display on the response card. The image URL must be publicly available so that the platform displaying the response card has access to the image.
buttons (list) --
A list of buttons that should be displayed on the response card. The arrangement of the buttons is determined by the platform that displays the button.
(dict) --
A button that appears on a response card show to the user.
text (string) --
The text that is displayed on the button.
value (string) --
The value returned to Amazon Lex when a user chooses the button.
interpretations (list) --
A list of intents that Amazon Lex determined might satisfy the user's utterance.
Each interpretation includes the intent, a score that indicates how confident Amazon Lex is that the interpretation is the correct one, and an optional sentiment response that indicates the sentiment expressed in the utterance.
(dict) --
An intent that Amazon Lex determined might satisfy the user's utterance. The intents are ordered by the confidence score.
nluConfidence (dict) --
Determines the threshold where Amazon Lex will insert the AMAZON.FallbackIntent, AMAZON.KendraSearchIntent, or both when returning alternative intents in a response. AMAZON.FallbackIntent and AMAZON.KendraSearchIntent are only inserted if they are configured for the bot.
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.
sentimentResponse (dict) --
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.
sentiment (string) --
The overall sentiment expressed in the user's response. This is the sentiment most likely expressed by the user based on the analysis by Amazon Comprehend.
sentimentScore (dict) --
The individual sentiment responses for the utterance.
positive (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.
negative (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.
neutral (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.
mixed (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.
intent (dict) --
A list of intents that might satisfy the user's utterance. The intents are ordered by the confidence score.
name (string) --
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) --
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
sessionState (dict) --
Represents the current state of the dialog between the user and the bot.
You can use this to determine the progress of the conversation and what the next action might be.
dialogAction (dict) --
The next step that Amazon Lex should take in the conversation with a user.
type (string) --
The next action that the bot should take in its interaction with the user. The possible values are:
Close - Indicates that there will not be a response from the user. For example, the statement "Your order has been placed" does not require a response.
ConfirmIntent - The next action is asking the user if the intent is complete and ready to be fulfilled. This is a yes/no question such as "Place the order?"
Delegate - The next action is determined by Amazon Lex.
ElicitSlot - The next action is to elicit a slot value from the user.
slotToElicit (string) --
The name of the slot that should be elicited from the user.
intent (dict) --
The active intent that Amazon Lex is processing.
name (string) --
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) --
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
activeContexts (list) --
One or more contexts that indicate to Amazon Lex the context of a request. When a context is active, Amazon Lex considers intents with the matching context as a trigger as the next intent in a session.
(dict) --
Contains information about the contexts that a user is using in a session. You can configure Amazon Lex to set a context when an intent is fulfilled, or you can set a context using the , , or operations.
Use a context to indicate to Amazon Lex intents that should be used as follow-up intents. For example, if the active context is order-fulfilled, only intents that have order-fulfilled configured as a trigger are considered for follow up.
name (string) --
The name of the context.
timeToLive (dict) --
Indicates the number of turns or seconds that the context is active. Once the time to live expires, the context is no longer returned in a response.
timeToLiveInSeconds (integer) --
The number of seconds that the context is active. You can specify between 5 and 86400 seconds (24 hours).
turnsToLive (integer) --
The number of turns that the context is active. You can specify up to 20 turns. Each request and response from the bot is a turn.
contextAttributes (dict) --
A lis tof 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.
(string) --
(string) --
sessionAttributes (dict) --
Map of key/value pairs representing session-specific context information. It contains application information passed between Amazon Lex and a client application.
(string) --
(string) --
originatingRequestId (string) --
Starts an HTTP/2 bidirectional event stream that enables you to send audio, text, or DTMF input in real time. After your application starts a conversation, users send input to Amazon Lex as a stream of events. Amazon Lex processes the incoming events and responds with streaming text or audio events.
See also: AWS API Documentation
Request Syntax
client.start_conversation(
botId='string',
botAliasId='string',
localeId='string',
sessionId='string',
conversationMode='AUDIO'|'TEXT',
requestEventStream={...}
)
string
[REQUIRED]
The identifier of the bot to process the request.
string
[REQUIRED]
The alias identifier in use for the bot that processes the request.
string
[REQUIRED]
The locale where the session is in use.
string
[REQUIRED]
The identifier of the user session that is having the conversation.
string
The conversation type that you are using the Amazon Lex. If the conversation mode is AUDIO you can send both audio and DTMF information. If the mode is TEXT you can only send text.
dict
[REQUIRED]
Represents the stream of events to Amazon Lex from your application. The events are encoded as HTTP/2 data frames.
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{
'responseEventStream': EventStream({
'PlaybackInterruptionEvent': {
'eventReason': 'DTMF_START_DETECTED'|'TEXT_DETECTED'|'VOICE_START_DETECTED',
'causedByEventId': 'string',
'eventId': 'string'
},
'TranscriptEvent': {
'transcript': 'string',
'eventId': 'string'
},
'IntentResultEvent': {
'inputMode': 'Text'|'Speech'|'DTMF',
'interpretations': [
{
'nluConfidence': {
'score': 123.0
},
'sentimentResponse': {
'sentiment': 'MIXED'|'NEGATIVE'|'NEUTRAL'|'POSITIVE',
'sentimentScore': {
'positive': 123.0,
'negative': 123.0,
'neutral': 123.0,
'mixed': 123.0
}
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
}
},
],
'sessionState': {
'dialogAction': {
'type': 'Close'|'ConfirmIntent'|'Delegate'|'ElicitIntent'|'ElicitSlot',
'slotToElicit': 'string'
},
'intent': {
'name': 'string',
'slots': {
'string': {
'value': {
'originalValue': 'string',
'interpretedValue': 'string',
'resolvedValues': [
'string',
]
}
}
},
'state': 'Failed'|'Fulfilled'|'InProgress'|'ReadyForFulfillment'|'Waiting',
'confirmationState': 'Confirmed'|'Denied'|'None'
},
'activeContexts': [
{
'name': 'string',
'timeToLive': {
'timeToLiveInSeconds': 123,
'turnsToLive': 123
},
'contextAttributes': {
'string': 'string'
}
},
],
'sessionAttributes': {
'string': 'string'
},
'originatingRequestId': 'string'
},
'requestAttributes': {
'string': 'string'
},
'sessionId': 'string',
'eventId': 'string'
},
'TextResponseEvent': {
'messages': [
{
'content': 'string',
'contentType': 'CustomPayload'|'ImageResponseCard'|'PlainText'|'SSML',
'imageResponseCard': {
'title': 'string',
'subtitle': 'string',
'imageUrl': 'string',
'buttons': [
{
'text': 'string',
'value': 'string'
},
]
}
},
],
'eventId': 'string'
},
'AudioResponseEvent': {
'audioChunk': b'bytes',
'contentType': 'string',
'eventId': 'string'
},
'HeartbeatEvent': {
'eventId': 'string'
},
'AccessDeniedException': {
'message': 'string'
},
'ResourceNotFoundException': {
'message': 'string'
},
'ValidationException': {
'message': 'string'
},
'ThrottlingException': {
'message': 'string'
},
'InternalServerException': {
'message': 'string'
},
'ConflictException': {
'message': 'string'
},
'DependencyFailedException': {
'message': 'string'
},
'BadGatewayException': {
'message': 'string'
}
})
}
Response Structure
(dict) --
responseEventStream (:class:`.EventStream`) --
Represents the stream of events from Amazon Lex to your application. The events are encoded as HTTP/2 data frames.
PlaybackInterruptionEvent (dict) --
Event sent from Amazon Lex to indicate to the client application should stop playback of audio. For example, if the client is playing a prompt that asks for the user's telephone number, the user might start to say the phone number before the prompt is complete. Amazon Lex sends this event to the client application to indicate that the user is responding and that Amazon Lex is processing their input.
eventReason (string) --
Indicates the type of user input that Amazon Lex detected.
causedByEventId (string) --
The identifier of the event that contained the audio, DTMF, or text that caused the interruption.
eventId (string) --
A unique identifier of the event sent by Amazon Lex. The identifier is in the form RESPONSE-N, where N is a number starting with one and incremented for each event sent by Amazon Lex in the current session.
TranscriptEvent (dict) --
Event sent from Amazon Lex to your client application that contains a transcript of voice audio.
transcript (string) --
The transcript of the voice audio from the user.
eventId (string) --
A unique identifier of the event sent by Amazon Lex. The identifier is in the form RESPONSE-N, where N is a number starting with one and incremented for each event sent by Amazon Lex in the current session.
IntentResultEvent (dict) --
Event sent from Amazon Lex to the client application containing the current state of the conversation between the user and Amazon Lex.
inputMode (string) --
Indicates whether the input to the operation was text or speech.
interpretations (list) --
A list of intents that Amazon Lex determined might satisfy the user's utterance.
Each interpretation includes the intent, a score that indicates how confident Amazon Lex is that the interpretation is the correct one, and an optional sentiment response that indicates the sentiment expressed in the utterance.
(dict) --
An intent that Amazon Lex determined might satisfy the user's utterance. The intents are ordered by the confidence score.
nluConfidence (dict) --
Determines the threshold where Amazon Lex will insert the AMAZON.FallbackIntent, AMAZON.KendraSearchIntent, or both when returning alternative intents in a response. AMAZON.FallbackIntent and AMAZON.KendraSearchIntent are only inserted if they are configured for the bot.
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.
sentimentResponse (dict) --
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.
sentiment (string) --
The overall sentiment expressed in the user's response. This is the sentiment most likely expressed by the user based on the analysis by Amazon Comprehend.
sentimentScore (dict) --
The individual sentiment responses for the utterance.
positive (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the POSITIVE sentiment.
negative (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEGATIVE sentiment.
neutral (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the NEUTRAL sentiment.
mixed (float) --
The level of confidence that Amazon Comprehend has in the accuracy of its detection of the MIXED sentiment.
intent (dict) --
A list of intents that might satisfy the user's utterance. The intents are ordered by the confidence score.
name (string) --
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) --
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
sessionState (dict) --
The state of the user's session with Amazon Lex.
dialogAction (dict) --
The next step that Amazon Lex should take in the conversation with a user.
type (string) --
The next action that the bot should take in its interaction with the user. The possible values are:
Close - Indicates that there will not be a response from the user. For example, the statement "Your order has been placed" does not require a response.
ConfirmIntent - The next action is asking the user if the intent is complete and ready to be fulfilled. This is a yes/no question such as "Place the order?"
Delegate - The next action is determined by Amazon Lex.
ElicitSlot - The next action is to elicit a slot value from the user.
slotToElicit (string) --
The name of the slot that should be elicited from the user.
intent (dict) --
The active intent that Amazon Lex is processing.
name (string) --
The name of the intent.
slots (dict) --
A map of all of the slots for the intent. The name of the slot maps to the value of the slot. If a slot has not been filled, the value is null.
(string) --
(dict) --
A value that Amazon Lex uses to fulfill an intent.
value (dict) --
The current value of the slot.
originalValue (string) --
The text of the utterance from the user that was entered for the slot.
interpretedValue (string) --
The value that Amazon Lex determines for the slot. The actual value depends on the setting of the value selection strategy for the bot. You can choose to use the value entered by the user, or you can have Amazon Lex choose the first value in the resolvedValues list.
resolvedValues (list) --
A list of additional values that have been recognized for the slot.
(string) --
state (string) --
Contains fulfillment information for the intent.
confirmationState (string) --
Contains information about whether fulfillment of the intent has been confirmed.
activeContexts (list) --
One or more contexts that indicate to Amazon Lex the context of a request. When a context is active, Amazon Lex considers intents with the matching context as a trigger as the next intent in a session.
(dict) --
Contains information about the contexts that a user is using in a session. You can configure Amazon Lex to set a context when an intent is fulfilled, or you can set a context using the , , or operations.
Use a context to indicate to Amazon Lex intents that should be used as follow-up intents. For example, if the active context is order-fulfilled, only intents that have order-fulfilled configured as a trigger are considered for follow up.
name (string) --
The name of the context.
timeToLive (dict) --
Indicates the number of turns or seconds that the context is active. Once the time to live expires, the context is no longer returned in a response.
timeToLiveInSeconds (integer) --
The number of seconds that the context is active. You can specify between 5 and 86400 seconds (24 hours).
turnsToLive (integer) --
The number of turns that the context is active. You can specify up to 20 turns. Each request and response from the bot is a turn.
contextAttributes (dict) --
A lis tof 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.
(string) --
(string) --
sessionAttributes (dict) --
Map of key/value pairs representing session-specific context information. It contains application information passed between Amazon Lex and a client application.
(string) --
(string) --
originatingRequestId (string) --
requestAttributes (dict) --
The attributes sent in the request.
(string) --
(string) --
sessionId (string) --
The identifier of the session in use.
eventId (string) --
A unique identifier of the event sent by Amazon Lex. The identifier is in the form RESPONSE-N, where N is a number starting with one and incremented for each event sent by Amazon Lex in the current session.
TextResponseEvent (dict) --
The event sent from Amazon Lex to your application with text to present to the user.
messages (list) --
A list of messages to send to the user. Messages are ordered based on the order that you returned the messages from your Lambda function or the order that the messages are defined in the bot.
(dict) --
Container for text that is returned to the customer..
content (string) --
The text of the message.
contentType (string) --
Indicates the type of response.
imageResponseCard (dict) --
A card that is shown to the user by a messaging platform. You define the contents of the card, the card is displayed by the platform.
When you use a response card, the response from the user is constrained to the text associated with a button on the card.
title (string) --
The title to display on the response card. The format of the title is determined by the platform displaying the response card.
subtitle (string) --
The subtitle to display on the response card. The format of the subtitle is determined by the platform displaying the response card.
imageUrl (string) --
The URL of an image to display on the response card. The image URL must be publicly available so that the platform displaying the response card has access to the image.
buttons (list) --
A list of buttons that should be displayed on the response card. The arrangement of the buttons is determined by the platform that displays the button.
(dict) --
A button that appears on a response card show to the user.
text (string) --
The text that is displayed on the button.
value (string) --
The value returned to Amazon Lex when a user chooses the button.
eventId (string) --
A unique identifier of the event sent by Amazon Lex. The identifier is in the form RESPONSE-N, where N is a number starting with one and incremented for each event sent by Amazon Lex in the current session.
AudioResponseEvent (dict) --
An event sent from Amazon Lex to your client application containing audio to play to the user.
audioChunk (bytes) --
A chunk of the audio to play.
contentType (string) --
The encoding of the audio chunk. This is the same as the encoding configure in the contentType field of the ConfigurationEvent.
eventId (string) --
A unique identifier of the event sent by Amazon Lex. The identifier is in the form RESPONSE-N, where N is a number starting with one and incremented for each event sent by Amazon Lex in the current session.
HeartbeatEvent (dict) --
Event that Amazon Lex sends to indicate that the stream is still open between the client application and Amazon Lex
eventId (string) --
A unique identifier of the event sent by Amazon Lex. The identifier is in the form RESPONSE-N, where N is a number starting with one and incremented for each event sent by Amazon Lex in the current session.
AccessDeniedException (dict) --
Exception thrown when the credentials passed with the request are invalid or expired. Also thrown when the credentials in the request do not have permission to access the StartConversation operation.
message (string) --
ResourceNotFoundException (dict) --
Exception thrown if one of the input parameters points to a resource that does not exist. For example, if the bot ID specified does not exist.
message (string) --
ValidationException (dict) --
Exception thrown when one or more parameters could not be validated. The message contains the name of the field that isn't valid.
message (string) --
ThrottlingException (dict) --
Exception thrown when your application exceeds the maximum number of concurrent requests.
message (string) --
InternalServerException (dict) --
An error occurred with Amazon Lex.
message (string) --
ConflictException (dict) --
Exception thrown when two clients are using the same AWS account, Amazon Lex bot, and session ID.
message (string) --
DependencyFailedException (dict) --
message (string) --
BadGatewayException (dict) --
message (string) --