Samyang Rasa Baru
Head Office Planetmoto
The Belleza Office Tower Lt. 7 Unit 1
Jln. Letjen Soepono No. 34, Arteri Permata Hijau
Grogol Utara, Kebayoran Lama, Jakarta Selatan
In Rasa, your domain defines the universe in which your assistant operates. Specifically, it lists:
If you are building an NLU-based assistant, refer to the Domain documentation to see how intents, entities, slot mappings, and slot featurization can be configured in your domain.
Select which actions should receive domain#
You can control if an action should receive a domain or not.
To do this you must first enable selective domain in you endpoint configuration for action_endpoint in endpoints.yml.
url: "http://localhost:5055/webhook" # URL to your action server
enable_selective_domain: true
After selective domain for custom actions is enabled, domain will be sent only to those custom actions which have specifically stated that they need it. Custom actions inheriting from rasa-sdk FormValidationAction parent class are an exception to this rule as they will always have the domain sent to them. To specify if an action needs the domain add {send_domain: true} to custom action in the list of actions in domain.yml:
- action_hello_world: {send_domain: True} # will receive domain
- action_calculate_mass_of_sun # will not receive domain
- validate_my_form # will receive domain
Responses go under the responses key in your domain file or in a separate "responses.yml" file. Each response name should start with utter_. For example, you could add responses for greeting and saying goodbye under the response names utter_greet and utter_bye:
If you are using retrieval intents in your assistant, you also need to add responses for your assistant's replies to these intents:
utter_chitchat/ask_name:
- text: Oh yeah, I am called the retrieval bot.
utter_chitchat/ask_weather:
- text: Oh, it does look sunny right now in Berlin.
Notice the special format of response names for retrieval intents. Each name starts with utter_, followed by the retrieval intent's name (here chitchat) and finally a suffix specifying the different response keys (here ask_name and ask_weather). See the documentation for NLU training examples to learn more.
The requested_slot slot#
The slot requested_slot is automatically added to the domain as a slot of type text. The value of the requested_slot will be ignored during conversations. If you want to change this behavior, you need to add the requested_slot to your domain file as a categorical slot with influence_conversation set to true. You might want to do this if you want to handle your unhappy paths differently, depending on what slot is currently being asked from the user. For example, if your users respond to one of the bot's questions with another question, like why do you need to know that? The response to this explain intent depends on where we are in the story. In the restaurant case, your stories would look something like this:
- story: explain cuisine slot
- intent: request_restaurant
- action: restaurant_form
- active_loop: restaurant
- requested_slot: cuisine
- action: utter_explain_cuisine
- action: restaurant_form
- story: explain num_people slot
- intent: request_restaurant
- action: restaurant_form
- active_loop: restaurant
- requested_slot: cuisine
- requested_slot: num_people
- action: utter_explain_num_people
- action: restaurant_form
Again, it is strongly recommended that you use interactive learning to build these stories.
Custom Slot Mappings#
If none of the predefined Slot Mappings fit your use
case, you can use the
Custom Action validate_
If you're using the Rasa SDK we recommend you to extend the provided FormValidationAction. When using the FormValidationAction, three steps are required to extract customs slots:
The following example shows the implementation of a form which extracts a slot outdoor_seating in a custom way, in addition to the slots which use predefined mappings. The method extract_outdoor_seating sets the slot outdoor_seating based on whether the keyword outdoor was present in the last user message.
from typing import Dict, Text, List, Optional, Any
from rasa_sdk import Tracker
from rasa_sdk.executor import CollectingDispatcher
from rasa_sdk.forms import FormValidationAction
class ValidateRestaurantForm(FormValidationAction):
def name(self) -> Text:
return "validate_restaurant_form"
async def required_slots(
slots_mapped_in_domain: List[Text],
dispatcher: "CollectingDispatcher",
domain: "DomainDict",
) -> Optional[List[Text]]:
required_slots = slots_mapped_in_domain + ["outdoor_seating"]
return required_slots
async def extract_outdoor_seating(
self, dispatcher: CollectingDispatcher, tracker: Tracker, domain: Dict
) -> Dict[Text, Any]:
text_of_last_user_message = tracker.latest_message.get("text")
sit_outside = "outdoor" in text_of_last_user_message
return {"outdoor_seating": sit_outside}
By default the FormValidationAction will automatically set the requested_slot to the first slot specified in required_slots which is not filled.
Session configuration#
A conversation session represents the dialogue between the assistant and the user. Conversation sessions can begin in three ways:
the user begins the conversation with the assistant,
the user sends their first message after a configurable period of inactivity, or
a manual session start is triggered with the /session_start intent message.
You can define the period of inactivity after which a new conversation session is triggered in the domain under the session_config key.
Available parameters are:
The default session configuration looks as follows:
session_expiration_time: 60 # value in minutes, 0 means infinitely long
carry_over_slots_to_new_session: true # set to false to forget slots between sessions
This means that if a user sends their first message after 60 minutes of inactivity, a new conversation session is triggered, and that any existing slots are carried over into the new session. Setting the value of session_expiration_time to 0 means that sessions will not end (note that the action_session_start action will still be triggered at the very beginning of conversations).
A session start triggers the default action action_session_start. Its default implementation moves all existing slots into the new session. Note that all conversations begin with an action_session_start. Overriding this action could for instance be used to initialize the tracker with slots from an external API call, or to start the conversation with a bot message. The docs on Customizing the session start action shows you how to do that.
The config key in the domain file maintains the store_entities_as_slots parameter. This parameter is used only in the context of reading stories and turning them into trackers. If the parameter is set to True, this will result in slots being implicitly set from entities if applicable entities are present in the story. When an entity matches the from_entity slot mapping, store_entities_as_slots defines whether the entity value should be placed in that slot. Therefore, this parameter skips adding an explicit slot_was_set step manually in the story. By default, this behaviour is switched on.
You can turn off this functionality by setting the store_entities_as_slots parameter to false:
store_entities_as_slots: false
If you're looking for information on the config.yml file, check out the docs on Model Configuration.
A story is a representation of a conversation between a user and an AI assistant, converted into a specific format where user inputs are expressed as intents (and entities when necessary), while the assistant's responses and actions are expressed as action names.
Here's an example of a dialogue in the Rasa story format:
- story: collect restaurant booking info # name of the story - just for debugging
- intent: greet # user message with no entities
- action: utter_ask_howcanhelp
- intent: inform # user message with entities
- action: utter_on_it # action that the bot should execute
- action: utter_ask_cuisine
- action: utter_ask_num_people
While writing stories, you do not have to deal with the specific contents of the messages that the users send. Instead, you can take advantage of the output from the NLU pipeline, which lets you use just the combination of an intent and entities to refer to all the possible messages the users can send to mean the same thing.
It is important to include the entities here as well because the policies learn to predict the next action based on a combination of both the intent and entities (you can, however, change this behavior using the use_entities attribute).
All actions executed by the bot, including responses are listed in stories under the action key.
You can use a response from your domain as an action by listing it as one in a story. Similarly, you can indicate that a story should call a custom action by including the name of the custom action from the actions list in your domain.
During training, Rasa does not call the action server. This means that your assistant's dialogue management model doesn't know which events a custom action will return.
Because of this, events such as setting a slot or activating/deactivating a form have to be explicitly written out as part of the stories. For more info, see the documentation on Events.
Slot events are written under slot_was_set in a story. If this slot is set inside a custom action, add the slot_was_set event immediately following the custom action call. If your custom action resets a slot value to None, the corresponding event for that would look like this:
- story: set slot to none
# ... other story steps
- action: my_custom_action
There are three kinds of events that need to be kept in mind while dealing with forms in stories.
A form action event (e.g. - action: restaurant_form) is used in the beginning when first starting a form, and also while resuming the form action when the form is already active.
A form activation event (e.g. - active_loop: restaurant_form) is used right after the first form action event.
A form deactivation event (e.g. - active_loop: null), which is used to deactivate the form.
In order to get around the pitfall of forgetting to add events, the recommended way to write these stories is to use interactive learning.
Slots and Conversation Behavior#
You can specify whether or not a slot influences the conversation with the influence_conversation property.
If you want to store information in a slot without it influencing the conversation, set influence_conversation: false when defining your slot.
The following example defines a slot age which will store information about the user's age, but which will not influence the flow of the conversation. This means that the assistant will ignore the value of the slot each time it predicts the next action.
influence_conversation: false
When defining a slot, if you leave out influence_conversation or set it to true, that slot will influence the next action prediction, unless it has slot type any. The way the slot influences the conversation will depend on its slot type.
The following example defines a slot home_city that influences the conversation. A text slot will influence the assistant's behavior depending on whether the slot has a value. The specific value of a text slot (e.g. Bangalore or New York or Hong Kong) doesn't make any difference.
influence_conversation: true
As an example, consider the two inputs "What is the weather like?" and "What is the weather like in Bangalore?" The conversation should diverge based on whether the home_city slot was set automatically by the NLU. If the slot is already set, the bot can predict the action_forecast action. If the slot is not set, it needs to get the home_city information before it is able to predict the weather.
Storing true or false values.
If influence_conversation is set to true, the assistant's behavior will change depending on whether the slot is empty, set to true or set to false. Note that an empty bool slot influences the conversation differently than if the slot was set to false.
Storing slots which can take one of N values.
If influence_conversation is set to true, the assistant's behavior will change depending on the concrete value of the slot. This means the assistant's behavior is different depending on whether the slot in the above example has the value low, medium, or high.
A default value __other__ is automatically added to the user-defined values. All values encountered which are not explicitly defined in the slot's values are mapped to __other__. __other__ should not be used as a user-defined value; if it is, it will still behave as the default to which all unseen values are mapped.
Storing real numbers.
max_value=1.0, min_value=0.0
If influence_conversation is set to true, the assistant's behavior will change depending on the value of the slot. If the value is between min_value and max_value, the specific value of the number is used. All values below min_value will be treated as min_value, and all values above max_value will be treated as max_value. Hence, if max_value is set to 1, there is no difference between the slot values 2 and 3.5.
Storing arbitrary values (they can be of any type, such as dictionaries or lists).
Slots of type any are always ignored during conversations. The property influence_conversation cannot be set to true for this slot type. If you want to store a custom data structure which should influence the conversation, use a custom slot type.
Maybe your restaurant booking system can only handle bookings for up to 6 people. In this case you want the value of the slot to influence the next selected action (and not just whether it's been specified). You can do this by defining a custom slot class.
The code below defines a custom slot class called NumberOfPeopleSlot. The featurization defines how the value of this slot gets converted to a vector so Rasa machine learning model can deal with it. The NumberOfPeopleSlot has three possible “values”, which can be represented with a vector of length 2.
from rasa.shared.core.slots import Slot
class NumberOfPeopleSlot(Slot):
def feature_dimensionality(self):
def as_feature(self):
r = [0.0] * self.feature_dimensionality()
You can implement a custom slot class as an independent python module, separate from custom action code. Save the code for your custom slot in a directory alongside an empty file called "__init__.py" so that it will be recognized as a python module. You can then refer to the custom slot class by it's module path.
For example, say you have saved the code above in "addons/my_custom_slots.py", a directory relative to your bot project:
│ └── my_custom_slots.py
Your custom slot type's module path is then addons.my_custom_slots.NumberOfPeopleSlot. Use the module path to refer to the custom slot type in your domain file:
type: addons.my_custom_slots.NumberOfPeopleSlot
influence_conversation: true
Now that your custom slot class can be used by Rasa, add training stories that diverge based on the value of the people slot. You could write one story for the case where people has a value between 1 and 6, and one for a value greater than six. You can choose any value within these ranges to put in your stories, since they are all featurized the same way (see the featurization table above).
- story: collecting table info
# ... other story steps
- action: action_book_table
- story: too many people at the table
# ... other story steps
- action: action_explain_table_limit
As of 3.0, slot mappings are defined in the slots section of the domain. This change removes the implicit mechanism of setting slots via auto-fill and replaces it with a new explicit mechanism of setting slots after every user message. You will need to explicitly define slot mappings for each slot in the slots section of domain.yml. If you are migrating from an earlier version, please read through the migration guide to update your assistant.
Rasa comes with four predefined mappings to fill slots based on the latest user message.
In addition to the predefined mappings, you can define custom slot mappings. All custom slot mappings should contain a mapping of type custom.
Slot mappings are specified as a YAML list of dictionaries under the key mappings in the domain file. Slot mappings are prioritized in the order they are listed in the domain. The first slot mapping found to apply will be used to fill the slot.
The default behavior is for slot mappings to apply after every user message, regardless of the dialogue context. To make a slot mapping apply only within the context of a form see Mapping Conditions. There is one additional default limitation on applying from_entity slot mappings in the context of a form; see unique from_entity mapping matching for details.
Note that you can also define lists of intents for the optional parameters intent and not_intent.
The from_entity slot mapping fills slots based on extracted entities. The following parameters are required:
The following parameters are optional and can be used to further specify when the mapping applies:
not_intent: excluded_intent
There is an intentional limitation on applying from_entity slot mappings in the context of a form. When a form is active, a from_entity slot mapping will be applied only if one or more of the following conditions are met:
This limitation exists to prevent a form from filling multiple required slots with the same extracted entity value.
For example, in the example below, an entity date uniquely sets the slot arrival_date, an entity city with a role from uniquely sets the slot departure_city and an entity city with a role to uniquely sets the slot arrival_city, therefore they can be used to fit corresponding slots even if these slots were not requested. However, entity city without a role can fill both departure_city and arrival_city slots, depending which one is requested, so if an entity city is extracted when slot arrival_date is requested, it'll be ignored by the form.
Note that the unique from_entity mapping constraint will not prevent filling slots which are not in the active form's required_slots; those mappings will apply as usual, regardless of the uniqueness of the mapping. To limit applicability of a slot mapping to a specific form, see Mapping Conditions.
The from_text mapping will use the text of the last user utterance to fill the slot slot_name. If intent_name is None, the slot will be filled regardless of intent name. Otherwise, the slot will only be filled if the user's intent is intent_name.
The slot mapping will not apply if the intent of the message is excluded_intent.
not_intent: excluded_intent
To maintain the 2.x form behavior when using from_text slot mappings, you must use mapping conditions, where both active_loop and requested_slot keys are defined.
The from_intent mapping will fill slot slot_name with value my_value if user intent is intent_name. If you choose not to specify the parameter intent, the slot mapping will apply regardless of the intent of the message as long as the intent is not listed under not_intent parameter.
The following parameter is required:
The following parameters are optional and can be used to further specify when the mapping applies:
Note that if you choose not to define the parameter intent, the slot mapping will apply regardless of the intent of the message as long as the intent is not listed under the not_intent parameter.
not_intent: excluded_intent
The from_trigger_intent mapping will fill slot slot_name with value my_value if a form is activated by a user message with intent intent_name. The slot mapping will not apply if the intent of the message is excluded_intent.
- type: from_trigger_intent
not_intent: excluded_intent
To apply a slot mapping only within the context of a form, specify the name of the form in the conditions key of a slot mapping. Conditions list the form name(s) for which the mapping is applicable in the active_loop key.
Slot mappings can now specify null as the value of active_loop to indicate that the slot should only be filled when no form is active. Note that requested_slot cannot be used in conjunction with active_loop: null.
Conditions can also include the name of the requested_slot. If requested_slot is not mentioned, then the slot will be set if relevant information is extracted, regardless of which slot is being requested by the form.
- active_loop: your_form
requested_slot: slot_name
- active_loop: another_form
If conditions are not included in a slot mapping, the slot mapping will be applicable regardless of whether any form is active. As long as a slot is listed in a form's required_slots, the form will prompt for the slot if it is empty when the form is activated.
Using a Custom Action to Ask For the Next Slot#
As soon as the form determines which slot has to be filled next by the user, it will
execute the action utter_ask_
from typing import Dict, Text, List
from rasa_sdk import Tracker
from rasa_sdk.events import EventType
from rasa_sdk.executor import CollectingDispatcher
from rasa_sdk import Action
class AskForSlotAction(Action):
def name(self) -> Text:
return "action_ask_cuisine"
self, dispatcher: CollectingDispatcher, tracker: Tracker, domain: Dict
) -> List[EventType]:
dispatcher.utter_message(text="What cuisine?")
Here is a full example of a domain, taken from the concertbot example:
influence_conversation: false
influence_conversation: false
influence_conversation: true
- text: "Sorry, I didn't get that, can you rephrase?"
- text: "You're very welcome."
- text: "I am a bot, powered by Rasa."
- text: "I can help you find concerts and venues. Do you like music?"
- text: "Awesome! You can ask me things like \"Find me some concerts\" or \"What's a good venue\""
- action_search_concerts
- action_search_venues
- action_show_concert_reviews
- action_show_venue_reviews
- action_set_music_preference
session_expiration_time: 60 # value in minutes
carry_over_slots_to_new_session: true
Checkpoints and OR statements#
Checkpoints and OR statements should be used with caution, if at all. There is usually a better way to achieve what you want by using Rules or the ResponseSelector.
You can use checkpoints to modularize and simplify your training data. Checkpoints can be useful, but do not overuse them. Using lots of checkpoints can quickly make your example stories hard to understand, and will slow down training.
Here is an example of stories that contain checkpoints:
- story: beginning of flow
- action: action_ask_user_question
- checkpoint: check_asked_question
- story: handle user affirm
- checkpoint: check_asked_question
- action: action_handle_affirmation
- checkpoint: check_flow_finished
- story: handle user deny
- checkpoint: check_asked_question
- action: action_handle_denial
- checkpoint: check_flow_finished
- checkpoint: check_flow_finished
- action: utter_goodbye
Unlike regular stories, checkpoints are not restricted to starting with user input. As long as the checkpoint is inserted at the right points in the main stories, the first event can be a custom action or a response as well.
Another way to write shorter stories, or to handle multiple intents or slot events the same way, is to use an or statement. For example, if you ask the user to confirm something, and you want to treat the affirm and thankyou intents in the same way. The story below will be converted into two stories at training time:
- action: utter_ask_confirm
- action: action_handle_affirmation
You can also use or statements with slot events. The following means the story requires that the current value for the name slot is set and is either joe or bob:
- action: utter_greet
or statements can be useful, but if you are using a lot of them, it is probably better to restructure your domain and/or intents. Overusing OR statements will slow down training.
Dynamic Form Behavior#
By default Rasa Open Source will ask for the next empty slot from the slots listed for your form in the domain file. If you use custom slot mappings and the FormValidationAction, it will ask for the first empty slot returned by the required_slots method. If all slots in required_slots are filled the form will be be deactivated.
If needed, you can update the required slots of your form dynamically. This is, for example, useful when you need further details based on how a previous slot was filled or you want to change the order in which slots are requested.
If you are using the Rasa SDK, we recommend you to use the FormValidationAction and
override required_slots to fit your dynamic behavior. You should implement
a method extract_
from typing import Text, List, Optional
from rasa_sdk.forms import FormValidationAction
class ValidateRestaurantForm(FormValidationAction):
def name(self) -> Text:
return "validate_restaurant_form"
async def required_slots(
slots_mapped_in_domain: List[Text],
dispatcher: "CollectingDispatcher",
domain: "DomainDict",
) -> Optional[List[Text]]:
additional_slots = ["outdoor_seating"]
if tracker.slots.get("outdoor_seating") is True:
additional_slots.append("shade_or_sun")
return additional_slots + slots_mapped_in_domain
Conditional Response Variations#
Specific response variations can also be selected based on one or more slot values using a conditional response variation. A conditional response variation is defined in the domain or responses YAML files similarly to a standard response variation but with an additional condition key. This key specifies a list of slot name and value constraints.
When a response is triggered during a dialogue, the constraints of each conditional response variation are checked against the current dialogue state. If all constraint slot values are equal to the corresponding slot values of the current dialogue state, the response variation is eligible to be used by your conversational assistant.
The comparison of dialogue state slot values and constraint slot values is performed by the equality "==" operator which requires the type of slot values to match too. For example, if the constraint is specified as value: true, then the slot needs to be filled with a boolean true, not the string "true".
In the following example, we will define one conditional response variation with one constraint, that the logged_in slot is set to true:
influence_conversation: False
influence_conversation: False
text: "Hey, {name}. Nice to see you again! How are you?"
- text: "Welcome. How is your day going?"
- action: action_log_in
- action: utter_greet
In the example above, the first response variation ("Hey, {name}. Nice to see you again! How are you?") will be used whenever the utter_greet action is executed and the logged_in slot is set to true. The second variation, which has no condition, will be treated as the default and used whenever logged_in is not equal to true.
It is highly recommended to always provide a default response variation without a condition to guard against those cases when no conditional response matches filled slots.
During a dialogue, Rasa will choose from all conditional response variations whose constraints are satisfied. If there are multiple eligible conditional response variations, Rasa will pick one at random. For example, consider the following response:
text: "Hey, {name}. Nice to see you again! How are you?"
name: eligible_for_upgrade
text: "Welcome, {name}. Did you know you are eligible for a free upgrade?"
- text: "Welcome. How is your day going?"
If logged_in and eligible_for_upgrade are both set to true then both the first and second response variations are eligible to be used, and will be chosen by the conversational assistant with equal probability.
You can continue using channel-specific response variations alongside conditional response variations as shown in the example below.
influence_conversation: False
influence_conversation: False
text: "Hey, {name}. Nice to see you again on Slack! How are you?"
- text: "Welcome. How is your day going?"
Rasa will prioritize the selection of responses in the following order:
You can make responses rich by adding visual and interactive elements. There are several types of elements that are supported across many channels:
Here is an example of a response that uses buttons:
- text: "Hey! How are you?"
payload: "/mood_great"
Each button in the list of buttons should have two keys:
If you would like the buttons to also pass entities to the assistant:
- text: "Hey! Would you like to purchase motor or home insurance?"
- title: "Motor insurance"
payload: '/inform{{"insurance":"motor"}}'
- title: "Home insurance"
payload: '/inform{{"insurance":"home"}}'
Passing multiple entities is also possible with:
'/intent_name{{"entity_type_1":"entity_value_1", "entity_type_2": "entity_value_2"}}'
You can use buttons to overwrite the NLU prediction and trigger a specific intent and entities.
Messages starting with / are sent handled by the RegexInterpreter, which expects NLU input in a shortened /intent{entities} format. In the example above, if the user clicks a button, the user input will be classified as either the mood_great or mood_sad intent.
You can include entities with the intent to be passed to the RegexInterpreter using the following format:
/inform{"ORG":"Rasa", "GPE":"Germany"}
The RegexInterpreter will classify the message above with the intent inform and extract the entities Rasa and Germany which are of type ORG and GPE respectively.
You need to write the /intent{entities} shorthand response with double curly braces in domain.yml so that the assistant does not treat it as a variable in a response and interpolate the content within the curly braces.
Keep in mind that it is up to the implementation of the output channel how to display the defined buttons. For example, some channels have a limit on the number of buttons you can provide. Check your channel's documentation under Concepts > Channel Connectors for any channel-specific restrictions.
You can add images to a response by providing a URL to the image under the image key:
- text: "Here is something to cheer you up:"
image: "https://i.imgur.com/nGF1K8f.jpg"
