Slot Example Rasa

Contents

Slot Filling

If you do not define slot mappings in the actions file, slots will be only filled by the entities with the same name as the slot that is picked up from the user input. Slots can be picked with the single entity but FormAction supports inputs like yes/no questions and free-text input. The way the slot influences the conversation will depend on its slot type. The following example defines a slot homecity 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. The slot is getting set but when i try with tracker.slots'sample' = value the slot value not persisting between the actions, I am writing a function with parameter as tracker so I need a way to set slot using tracker object or any solution to set slot from one helper function, So is there any way to persiste tracker.slotskey = value in.

One of the most common conversation patterns is to collect a few pieces ofinformation from a user in order to do something (book a restaurant, call anAPI, search a database, etc.). This is also called slot filling.

If you need to collect multiple pieces of information in a row, we recommendedthat you create a FormAction. This is a single action which contains thelogic to loop over the required slots and ask the user for this information.There is a full example using forms in the examples/formbot directory ofRasa Core.

You can take a look at the FormAction base class by clicking this link:

class rasa_core_sdk.forms.FormAction[source]¶

To add your forms to the domain file, reference their nameunder forms: section:

Using a FormAction, you can describe all of the happy paths with a singlestory. By “happy path”, we mean that whenever you ask a user for some information,they respond with what you asked for.

If we take the example of the restaurant bot, this single story describes all of thehappy paths.

In this story the user intent is request_restaurant, which is followed bythe form action restaurant_form. With form{'name':'restaurant_form'} theform is activated and with form{'name':null} the form is deactivated again.As shown in the section Handling unhappy paths the the bot can execute any kind ofactions outside the form while the form is still active. On the “happy path”,where the user is cooperating well and the system understands the user input correctly,the form is filling all requested slots without interruption.

The FormAction will only requests slots which haven’t already been set.If a user says“I’d like a vegetarian Chinese restaurant for 8 people”, they won’t beasked about the cuisine and num_people slots.

Note that for this story to work, your slots should be unfeaturized.If they’re not, you should add all the slots that have been set by the form.

The restaurant_form in the story above is the name of our form action.Here is an example of what it looks like.You need to define three methods:

name: the name of this action
required_slots: a list of slots that need to be filled for the submit method to work.
submit: what to do at the end of the form, when all the slots have been filled.

Once the form action gets called for the first time,the form gets activated and the FormPolicy jumps in.The FormPolicy is extremely simple and just always predicts the form action.See Handling unhappy paths for how to work with unexpected user input.

Every time the form action gets called, it will ask the user for the next slot inrequired_slots which is not already set.It does this by looking for a template called utter_ask_{slot_name},so you need to define these in your domain file for each required slot.

Once all the slots are filled, the submit() method is called, where you canuse the information you’ve collected to do something for the user, for examplequerying a restaurant API.If you don’t want your form to do anything at the end, just use return[]as your submit method.After the submit method is called, the form is deactivated,and other policies in your Core model will be used to predict the next action.

Some slots (like cuisine) can be picked up using a single entity, but aFormAction can also support yes/no questions and free-text input.The slot_mappings method defines how to extract slot values from user responses.

Here’s an example for the restaurant bot:

The predefined functions work as follows:

self.from_entity(entity=entity_name,intent=intent_name)will look for an entity called entity_name to fill a slotslot_name regardless of user intent if intent_name is Noneelse only if the users intent is intent_name.
self.from_intent(intent=intent_name,value=value)will fill slot slot_name with value if user intent is intent_name.To make a boolean slot, take a look at the definition of outdoor_seatingabove. Note: Slot will not be filled with user intent of message triggeringthe form action. Use self.from_trigger_intent below.
self.from_trigger_intent(intent=intent_name,value=value)will fill slot slot_name with value if form was triggered with userintent intent_name.
self.from_text(intent=intent_name) will use the nextuser utterance to fill the text slot slot_name regardless of user intentif intent_name is None else only if user intent is intent_name.
If you want to allow a combination of these, provide them as a list as in theexample above

After extracting a slot value from user input, the form will try to validate thevalue of the slot. By default, this only checks if the requested slot was extracted.If you want to add custom validation, for example to check a value against a database,you can do this by writing validate_{slot}() method.Here is an example which checks if the extracted cuisine slot belongs to alist of supported cuisines.

You can also deactivate the form directly during this validation step (in case theslot is filled with something that you are certain can’t be handled) by returningself.deactivate()

If nothing is extracted from the user’s utterance for any of the required slots, anActionExecutionRejection error will be raised, meaning the action executionwas rejected and therefore Core will fall back onto a different policy topredict another action.

Of course your users will not always respond with the information you ask of them.Typically, users will ask questions, make chitchat, change their mind, or otherwisestray from the happy path. The way this works with forms is that a form will raisean ActionExecutionRejection if the user didn’t provide the requested information.You need to handle events that might cause ActionExecutionRejection errorsin your stories. For example, if you expect your users to chitchat with your bot,you could add a story like this:

In some situations, users may change their mind in the middle of form actionand decide not to go forward with their initial request. In cases like this, theassistant should stop asking for the requested slots. You can handle such situationsgracefully using a default action action_deactivate_form which will deactivatethe form and reset the requested slot. An example story of such conversation couldlook as follows:

It is strongly recommended that you build these stories using interactive learning.If you write these stories by hand you will likely miss important things.Please read Interactive Learning with Formson how to use interactive learning with forms.

The slot requested_slot is automatically added to the domain as anunfeaturized slot. If you want to make it featurized, you need to add itto your domain file as a categorical slot. You might want to do this if youwant to handle your unhappy paths differently depending on what slot iscurrently being asked from the user. For example, say your users respondto 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:

Again, is is strongly recommended that you use interactivelearning to build these stories.Please read Interactive Learning with Formson how to use interactive learning with forms.

Many forms require more logic than just requesting a list of fields.For example, if someone requests greek as their cuisine, you may want toask if they are looking for somewhere with outside seating.

You can achieve this by writing some logic into the required_slots() method,for example:

This mechanism is quite general and you can use it to build many differentkinds of logic into your forms.

To use forms, make sure to include the FormPolicy in your policyconfiguration file. For example:

The first thing to try is to run your bot with the debug flag, see Debugging for details.If you are just getting started, you probably only have a few hand-written stories.This is a great starting point, butyou should give your bot to people to test as soon as possible. One of the guiding principlesbehind Rasa Core is:

Learning from real conversations is more important than designing hypothetical ones

So don’t try to cover every possibility in your hand-written stories before giving it to testers.Real user behavior will always surprise you!

We have a very active support community on Rasa Community Forumthat is happy to help you with your questions. If you have any feedback for us or a specificsuggestion for improving the docs, feel free to share it by creating an issue on Rasa CoreGitHub repository.

Here is the full list of slot types defined by Rasa Core.

Slots are your bot’s memory. They act as a key-value storewhich can be used to store information the user provided (e.g their home city)as well as information gathered about the outside world (e.g. the result of adatabase query).

Most of the time, you want slots to influence how the dialogue progresses.There are different slot types for different behaviors.

For example, if your user has provided their home city, you mighthave a text slot called home_city. If the user asks for theweather, and you don’t know their home city, you will have to askthem for it. A text slot only tells Rasa Core whether the slothas a value. The specific value of a text slot (e.g. Bangaloreor New York or Hong Kong) doesn’t make any difference.

If the value itself is important, use a categorical or a bool slot.There are also float, and list slots.If you just want to store some data, but don’t want it to affect the flowof the conversation, use an unfeaturized slot.

How Rasa Uses Slots¶

The rasa_core.policies.Policy doesn’t have access to thevalue of your slots. It receives a featurized representation.As mentioned above, for a text slot the value is irrelevant.The policy just sees a 1 or 0 depending on whether it is set.

You should choose your slot types carefully!

How Slots Get Set¶

You can provide an initial value for a slot in your domain file:

There are multiple ways that slots are set during a conversation:

Slots Set from NLU¶

If your NLU model picks up an entity, and your domain contains aslot with the same name, the slot will be set automatically. For example:

In this case, you don’t have to include the -slot{} part in thestory, because it is automatically picked up.

Slots Set By Clicking Buttons¶

You can use buttons as a shortcut.Rasa Core will send messages starting with a / to theRegexInterpreter, which expects NLU input in the same formatas in story files, e.g. /intent{entities}. For example, if you letusers choose a color by clicking a button, the button payloads mightbe /choose{'color':'blue'} and /choose{'color':'red'}.

You can specify this in your domain file like this:(see details in Domain Format)

Slots Set by Actions¶

The second option is to set slots by returning events in Actions.In this case, your stories need to include the slots.For example, you have a custom action to fetch a user’s profile, andyou have a categorical slot called account_type.When the fetch_profile action is run, it returns arasa_core.events.SlotSet event:

In this case you do have to include the -slot{} part in your stories.Rasa Core will learn to use this information to decide on the correct action totake (in this case, utter_welcome_premuim or utter_welcome_basic).

Note

It is very easy to forget about slots if you are writingstories by hand. We strongly recommend that you build up thesestories using Interactive Learning rather than writing them.