I am using dialog flow to make a chat bot, but gets stuck.
I have an if-else condition which consists of 14-15 question.
How to handle condition type of question in dialog flow. until now, maybe fulfillment works, but how?
Please provide more details. Give an example of such question.
You don't need to use filfillments, you can solve it with input/output contexts.
// some example intents
study.start (output-context: study.yes & study.no)
study.no (input-context: study.no)
study.yes (input-context: study.yes, output-context: study.howlong.good &
study.howlong.bad)
> Did you study for the test? No -> You need to study!
> Did you study for the test? Yes -> For how long?
> For how long? 1 hour -> Study more!
> For how long? 5 hours -> Good!
You simply write example phrases which will match given the active contexts. Remember to only set a lifespan of 1 for your output contexts.
Related
Using serenity-js, with cucumber and screenplay, i can't get to pass data from one step to another. E.g. : a "When" step defined by a pretty user.attempsTo() that simply calls a webservice, and a "Then" step that should simply checks the response of the webservice. "TakeNote" forgets the data of the previous step ( as i could see, even surprising) and "LastResponse" context might be lost also...
I guess there is a simple way to store an object (as a Question maybe) in one Activity of the "When" step, and get back this object in an Activity of the "Then" step.
Without Serenity, i would use a World object that is clearly a simple way to do the job, but i'm sure there a Serenity pretty way to do the trick.
Thank you.
Bruno
I tried to pass the object with LastResponse, with TakeNotes. But the object seems to be lost.
I found what was wrong (answering to myself).
user.attempsTo() is actually processed prior to the next step only if a resolution of the promise is asked, so if preceded by return, or await, or if it is declared as an implicit return using arrow function like this ( user :Actor) => attempsTo(...) ).
Without the promise resolution, interactions are not executed in the described sequence, and this is really no good.
The symptom for a bad code is that the interactions are not logged in their steps, but in step further. Hope this helps.
Background
I have an Intent that fetches some Data from an API. This data contains an array and I am iterating over the first 10 entries of said array and read the results back to the user. However the Array is almost always bigger than 10 entries. I am using Lambda for my backend and NodeJS as my language.
Note that I am just starting out on Alexa and this is my first skill.
What I want to archive is the following
When the user triggers the intent and the first 10 entries have been read to the user Alexa should ask "Do you want to hear the next 10 entries?" or something similar. The user should be able to reply with either yes or no. Then it should read the next entries aka. access the array again.
I am struggling with the Alexa implementation of this dialog.
What I have tried so far: I've stumbled across this post here, however I couldn't get it to work and I didn't find any other examples.
Any help or further pointers are appreciated.
That tutorial gets the concept right, but glosses over a few things.
1: Add the yes and no intents to your model. They're "built in" intents, but you have to add them to the model (and rebuild it).
2: Add your new intent handlers to the list in the .addRequestHandlers(...) function call near the bottom of the base skill template. This is often forgotten and is not mentioned in the tutorial.
3: Use const sessionAttributes = handlerInput.attributesManager.getSessionAttributes(); to get your stored session attributes object and assign it to a variable. Make changes to that object's properties, then save it with handlerInput.attributesManager.setSessionAttributes(sessionAttributes);
You can add any valid property name and the values can be a string, number, boolean, or object literal.
So assume your launch handler greets the customer and immediately reads the first 10 items, then asks if they'd like to hear 10 more. You might store sessionAttributes.num_heard = 10.
Both the YesIntent and LaunchIntent handlers should simply pass a num_heard value to a function that retrieves the next 10 items and feeds it back as a string for Alexa to speak.
You just increment sessionAttributes.num_heard by 10 each time that yes intent runs and then save it with handlerInput.attributesManager.setSessionAttributes(sessionAttributes).
What you need to do is something called "Paging".
Let's imagine that you have a stock of data. each page contains 10 entries.
page 1: 1-10, page 2: 11-20, page 3: 21-30 and so on.
When you fetching your data from DB you can set your limitations, In SQL it's implemented with LIMIT ,. But how you get those values based on the page index?
Well, a simple calculation can help you:
let page = 1 //Your identifier or page index. Managed by your client frontend.
let chunk = 10
let _start = page * chunk - (chunk - 1)
let _end = start + (chunk - 1)
Hope this helped you :)
Is there a way to specify that a session should be ended, or to clear out the memory of previous actions? In my testing (simulator only) I'm seeing a couple cases where Bixby is remembering a previous entry that isn't relevant anymore.
Example utterances
remove wet diaper
wet diaper
In this case there's 2 possible enums that can be said. "actionType" that is optional, in this case "remove" and "statType", in this case "wet diaper".
What is happening is on the second phrase it's caching the actionType. So, the second phrase my JavaScript still receives the "remove" even though it's not included.
I haven't tried this on an actual device (only the simulator) so it's possible this is just a simulation quirk.
This is kind of related to this question. There was a follow-up comment that the OP asked related to session management.
How does Bixby retain data from a previous NL input?
So, if you read that link. Is there a way I can signal to bixby that the conversation is over, or at least to not remember previous entries for the action?
One way would be to use the transient feature. Here is more information
For example, alter your input type so it doesn't carry over across executions.
name (ActionType) {
features {
transient
}
}
make sure all input types are NL friendly. name/enum concepts are meant for NL and you can attach vocabulary to them.
I used to have a similar issue like yours, in my case, my problem was related to the type of the 'requires' property inside the input-group declared in my action.model.bxb.
You need to handle by separate this two input cases in diferent action.model.bxb files:
In one of them you might have something like (model 1):
input-group(removeWeaper){
requires (OneOrMoreOf)
collect{
input (ActionType) {
type (Type)
min (Optional)
}
input (StatType) {
type (Type)
min (Optional)
}
}
Here, Bixby Will know that at least one of these properties will be apear in your input and will be waiting for an input with that structure.
In the other file you might have (model 2):
input-group(Weaper){
requires (OneOf)
collect{
input (StatType) {
type (Type)
min (Optional)
}
}
Here, Bixby will be waiting to catch an input that contains only one of the indicated values in you input.
(model 1) This could be ok only if you run 'wet diaper' by first time, also when you try again and run 'remove wet diaper' it might work, the problem is when you run again 'wet diaper' because Bixby Stores you previous approach including "remove". i'm not sure if there is something to clear the stored values, but, here is when (model 2) will help you to catch only the input 'wet diaper' as a different statement.
I share you this work around as my own experience, and i hope this could help you solving or getting another perspective of how you could handle or solve your problem.
I'm trying to write a step that will match the following steps that are similar and capture parameters:
Step1: And I delete the filter(s) using the "UI"
Step2: Then I delete the filter(s) using the "API" for "doc-browser" context
Step3: I delete the filter(s) using the "API" for "doc-browser" context with user "file_user2"
I don't want to create 3 separate steps, they all start with I delete the filter using the #{arg} and the last 2 just extend on that.
I thought this was going to accomplish it:
And(/^I delete the filter\(s\) using the "([^"]*)"(?: for "([^"]*)" context| with user "([^"]*)")?/) do |delete_method, context, user|
case delete_method
when 'API'
if user.nil?
SearchFilters.new.delete_global_local_filters(delete_method, api_context_val: context)
else
SearchFilters.new.delete_global_local_filters(delete_method, { api_context_val: context, username: user })
end
when 'UI'
SearchFilters.new.delete_global_local_filters(delete_method, filter_name: #filter_name)
end
end
However, I'm not capturing my username.
Is it possible to accomplish having one step definition that captures all 3 variations and still captures my arguments?
Just duplicating my mailing list answer in case anyone else is interested in this question.
I understand you don't want to use three different steps, but in this case you really should because
The implementation of each step is a clear one liner, so you are removing a case statement.
The regex for this step is horrible and you will be removing that
Each individual step provides the opportunity to simplify the parameters being passed, you have 2 API and one UI paramter which can just be removed entirely (if I understand the code correctly you can remove all the params and regexs)
This is a clear case where a little bit of repetition is a price well worth paying for a simpler implementation.
Reducing the number of step definitions by using regex's and params is often an anti-pattern.
All best
Andrew
It's a mess in my head right now. I've seen this video tutorial to understand Wit.ai logic : https://www.youtube.com/watch?v=yLAHVPaHWFA
It's a really good video for basic training. But I can't still understand the logic.
I want to create a story like that Human(H) / Robot(R):
(H) Hello
(R) Hello human, you can choose A action or B action
(H) A action
(R) Ok human, this is A action
It's really simple but I don't know what to declare in "understanding" section.
1 - Do I have to create a "Say Hello" intent
2 - If yes, Do I have to create an "hello" entity and feed it with other salutations like "Hi", "yo", "What's up?", ...
3 - Do I have to create a "choose action" intent or it's just one intent for one story ? This is exactly what I don't understand.
4 - If yes, A&B action are free-text like ("An hotel", "a restaurant"). How can I teach the bot to recognized them ?
I just need some enlightening about those points ! It's really hard for me to translate and understand correctly. Thank you for you help !
You may declare a "greeting" intent(Intents are just user-created entities). After that, you can validate(feed) it with many other words like "Hey buddy, Sup bud, Hellloooo, Hi bot, etc". Also, you can give values to that intent such as Negative or Positive values.
For instance:
" Hey dumb f* " >> "greeting" Intent + Negative value ❌
" Hi brother! " >> "greeting" Intent + Positive value ✅
So that you can decide between:
"Language, please... Anyway. Hey {user_name}"
or
"Hey {user_name} ! :) Really nice to see you here ! "
to respond to the user's simple hi text.
Other than that:
(R) Hello human, you can choose A action or B action
(H) A action
(R) Ok human, this is A action
This type of interaction needs the usage of /converse API
https://wit.ai/docs/recipes#converse-link
In this above link go down to the "Handle yes/no answers" section.
Also, you can use Quick Replies for letting the user choose between the A Action or B Action. Quick Replies are really useful for this type of interactions.
https://developers.facebook.com/docs/messenger-platform/send-api-reference/quick-replies