I have a question about the Carousel and list selector. How to use actions.intent.OPTION in Dialogflow for Actions on Google? I have tried adding actions_intent_OPTION in event section of every intent that the user will be selecting. But every time the response came from a single intent.
An API.AI/Dialogflow event tends to override anything that may have been "said" by the user, so Dialogflow's processing stops when it gets the first event that matches and handles that as the Intent. Option processing tends to be done in fulfillment. Rather than trying to match the option key or title against any phrases, anything said that matches the title or key will return the key as the matched "phrase".
Related
I have an intent with an Assistant List containing two options, Apples and Cheese. I want to provide a different response to each option chosen.
My first attempt was to use follow-up intents for each item, but when I do this I get a “not understood” message when tapping/choosing the item. On reading more, I understand this is because the actions_intent_OPTION event has been fired and there is no intent to handle it.
My second attempt was to add the actions_intent_OPTION event handler to each of my follow-up intents. When I did this, only the Cheese intent was invoked each time. I understand this is because actions_intent_OPTION can only be handled by a single intent.
So my conclusion is that the only way I can provide different responses for different items in an Assistant List is to handle this event with a webhook, and that it’s not possible using Dialogflow alone. Can anyone confirm or point me in the right direction if not?
The answer is, as suspected, that you can’t use an Assistant List purely in Dialogflow, you have to add a handler function in the fulfilment, that fires on the event actions_intent_OPTION. For example:
const option = conv.arguments.get('OPTION');
if (!option) {
conv.ask('No choice made');
} else if (option === 'optionA') {
// Do something
} else if (option === 'optionB') {
// Do something else
}
Follow this ideal approach:
remove follow-up intents
add a new intent with event set as actions_intent_OPTION
enable webhook for the new intent
in the webhook extract the selected option
based on the selected option, pass the required response
If you want to use only Dialogflow, then it won't work! This is because, when you select an option, the output context and the generated event both will be the same as the 2 intents - cheese and apple. There will be no way for the AI engine to decide which Intent should be triggered. Whichever intent is first, it will be called every time.
I tried to recreate what you did all be Dialogflow and even put cheese and apple as training phrases for the 2 intents just to provide some differentiation to the AI engine, but it still selected only one intent.
I'm trying to create a mock interview Action that asks a specific set of questions in a specific order, regardless of what the user says in response to each question. How can I set up the intent in Dialogflow to accept any phrase from a user to trigger the next question as the response?
Ex of the dialog path:
User: "I want to practice for an interview"
Google: "Question 1: tell me about yourself"
User: [says literally anything]
Google: "Great job. Question 2..."
User: [says literally anything]
Google: "Okay! Question 3..."
Using Dialogflow, you can create an intent that accepts any input by taking the user utterances and marking them as #sys.any.
Then you can do one of the following:
Use Dialogflow contexts to make the next step dependent on the first (this is good if you want to do everything in Dialogflow)
Keep track of the conversational state in your webhook using the app.data object.
There are a few good ways to handle what you want, the best solution will depend on your other needs.
If you're using a fulfillment webhook, you can handle this as part of the Fallback Intent. Make sure the checkbox to use fulfillment is on for the Fallback Intent, and you'll be sent everything that the user says that doesn't meet other structures. You'll need to keep count of how many times you've been called and you can store this as a parameter in a context, as part of the app.data session storage object, or as part of the app.userStore cross-session storage object. Your webhook will return the next question as a response.
If you want to avoid fulfillments and handle it through Dialogflow, you can use the same general idea, but you will need to keep track of which question you're on for each time. You can do this by creating multiple Fallback Intents with each one having as an Incoming Context a context named after which question you're expecting the user to answer (say "question_1") and the Outgoing Context named after the question that is in the reply (for example, "question_2").
I'm writing a simple action on google without any webhooks. Every response is generated by dialogflow.
I have an intent that works flawless if I call it by speech or type but if I call it by selecting it from a list it doesn't work and the Default Fallback is called.
In the simulator it show the right "text" when I click on the list.
Have I done something wrong or did I need to specify something in the list?
This is how the list is generated
This is my intent
This is what happens in the simulator if I click on the "easyTravel" item in the list (it trigger the default fallback intent)
This is what happens in the simulator if I type "easyTravel" (the right intent is executed)
To catch a click on a list I need an intent configured to be triggered by the event actions_intent_OPTION
Only once I read this question - and your anwser - I could fix my own problem. Just to share: if you are using a webhook and are waiting for a webhook actions in your script, you can create a new intent, which has the event as #Edo states: actions_intent_OPTION. If you define an action in that intent, this is what will be trigger by your webhook. You can then get the parameter by (node.js):
const param = app.getSelectedOption();
Without the 'empty' intent, with the event and action, I was not receiving any input.
In the DialogFlow console, you can set an input and output context for an intent.
I would like to have the same functionality using the Actions SDK.
Since I can set the context in my fullfilment webhook in the code, the output SDK is covered.
However, how do I set the input context for an intent to only trigger if that context was fetched?
I could not find this in the documentation examples.
I don't believe you can in the same way, which is part of why they added Dialogflow.
Although as part of your response you can indicate the ExpectedInput for the next Intent, the documentation for the ExpectedIntent makes it clear that your Intents are only used for speech biasing - you'll always get the built-in TEXT Intent.
In fact, this documentation says that you'll only get custom Intents for the initial call - later Intents are always triggered with a built-in one.
Update: One thing you can do is to include information in the response that will be sent back to you in the next request.
If you're using the JavaScript SDK, this is done with the second parameter to ask() and is available via the getDialogState() function.
If you're sending back JSON, this is done using the conversationToken attribute and is available in conversation.conversationToken in the request object you're sent the next round.
TLDR; # bottom
I asked the following question in the Facebook bugs section
NOTE: This is more of a platform design suggestion than a bug, as I failed to find a Chat API feedback portal
Currently I'm building a Chat bot that allows the user to track a goal. It will say something like "Did you go for a walk on July 12, 2016 ?" and have Yes/NO buttons below.
Currently in order to pass the intent, the day and the achievement boolean I need to template a string like this "==GOAL== achieved? <<<{goal_achieved}>>>, date tracked [[[{date_tracked}]]]" and use regex to capture the delimited variables. This is prone to parsing error in other cases where the templated strings in the payload are user-input variables i.e. if the '{goal_achieved}' were replaced with the goal variable '>>meditated" then the regex that captures the templated variable could fail.
One could use the postback payload to store a JSON-encoded string but the problem with this is that the payload string gets logged into the user output and JSON strings are a bit ugly and confusing. The challenges I face could be easily remedied if the payload was not logged to the user Instead log the text for the button to help the user confirm the button was clicked.
If that is not possible, is there any other advice for encoding data into button payload ?
The following answer was offered (Mark Wiltse)
Hi Justin,
Unfortunately at this time our payload structure does not support the functionality that you are trying to implement. From my understanding you want to use the Payload to inform your backend if the user accomplished their 'goal' on that specific date. I would suggest that you create your payload response for the button on your end before passing it to us, which is basically the JSON idea that you had initially.
I know this is a bit cumbersome to handle but the payload response passed back is independent of the text that was provided with the messenger thread.
I would suggest that you also attempt to sanitize your strings if you are worried a user has previously provided you would cause an issue with your regex. You should be able to implement this functionality if the prior user data is sanitized to avoid any issues with regex/json parsing.
Since this is an implementation question I will have to close this report as Invalid. If you are still looking for additional insights and concrete tips for implementing this flow please post to our stack overflow where we have Facebook Engineers and a wide range of community members who also contribute.
http://facebook.stackoverflow.com/
Take care and best wishes with your messenger bot.
Mark
This sentence was particularly unclear:
I know this is a bit cumbersome to handle but the payload response
passed back is independent of the text that was provided with the
messenger thread.
TLDR;
Can anyone inform me of how to prevent the button from logging the payload string so that I can use it to pass JSON to my app without the user seeing it ?
Make sure to comment out sendTextMessage() in your receivedPostback() call :
function receivedPostback(event){
sendTextMessage(senderID, event.postback.payload);
}
From my understanding you're saying that when you press a button the PAYLOAD instead of the button's text is showing up.
Are you defining your buttons like this?
{
type: "postback",
title: "View Details",
payload: "details:12345"
}
I'd recommend removing any special characters that would mess with the parsing of your payload. As long as the special characters are not crucial to the user experience this is probably a fine solution.
If this doesn't solve your issue:
Can you add a screenshot showing the button you are pressing, and the log message you are talking about? From my understanding you're saying that when you press a button the PAYLOAD instead of the button's text is showing up. That's not the case for me, my buttons text shows up when I press a button.