I am trying to add in the custom payload wihin Dialogflow a text response along with an output context. How can this be done?
Custom payload does not contain output context.
If you want to add output context you need to add it in output contexts like in the image below :
Hope it helps.
Related
Hi I’m look in for simple solutions for passing values between intents and contexts.
I’ve tried to set output context (c1) for intent A, and use c1 as input context for intent B. However, I’m not able to access the parameters value within intent B. Do I have to use fullfillment to implement this ?
Besides, I also want to use the previous parameters’ value of intent A when intent A is triggered next time. Again, can we do this without using fullfillment?
If fullfillment is essential, can you give some guidance please?
Accessing parameter values from one intent to another where contexts are used can be done from the Console itself. Fulfillment Webhook response can also be used but for your use case this can be done from the Console itself.
You can refer to the below replication steps:
In the text response of Default Welcome Intent add Hi what is your name? and add an output context awaiting_name.
Create another Intent Get Name and in that pass “awaiting_name” as input context . Pass some training phrases like "john,sandeep,jacob" and map it with them to the #sys.given.name entity.
In the Get Name Intent the text response is Ok $name, what is your email address?. Add awaiting_email in the output context field of this intent.
Create another intent “Get Email” and add awaiting_email in the Input context. Add training phrases like "sandeep#abc.com","john#xyz.com" and map them with #sys.email entity.
When you want to fetch the parameter value from another intent to the present intent where context is used you need to call it by #context-name.parameter-name as per this doc.
My final output response is Thanks #awaiting_name.name we will contact you soon on $email
I'm using for the first time DialogFlow and I'm trying to use Class Tokens. How can I use them? In the Inline Editor of the Fulfillment? Thank you in advance.
In order to use class tokens you must add your token in phrases array under the speechContexts parameter in the recognitionConfig which is passed as input to the detectIntent or detectStreamingIntent Function in your webhook code.
Checkout these links for reference.
https://cloud.google.com/speech-to-text/docs/speech-adaptation#class_tokens
https://cloud.google.com/dialogflow/es/docs/speech-adaptation
https://cloud.google.com/dialogflow/es/docs/how/detect-intent-stream
I'm having an issue when attempting to enter specific intents based on the value of a property.
I currently have a question that gets asked, which then fires off to the Microsoft Translator via a HTTP Request and from that, it fires off to the LUIS API with that text.
After that, I would like to enter an intent based on the top intent that the LUIS API Call brought back.
I have the Translator and The LUIS API bringing back values and I can output these using Send Responses:
However, when I attempt to call an intent based on the value of the property, I just get an Object Reference error:
Is what I'm trying to do possible and if so am I going about this entirely the wrong way causing more issues for myself?
Thanks In Advance
I'm trying to understand exactly what you are trying to achieve. Do I summarize it correctly as following?
You start a main dialog. In that dialog you take some user input.
You translate the input, and manually send the the translated text off to LUIS for intent recognition.
Based on the recognized intent, you want to start a specific sub dialog.
I don't believe you can just 'call an intent'. An intent is the result of a LUIS or Regex recognizer, which is processed automatically by Bot Framework. The recognizer is processed at every user input. There is no need to call LUIS yourself as a HTTP request. The recognizer (LUIS or RegEx) is configured on the main dialog properties in Bot Framework Composer:
Although in this case it looks like you are manually doing the LUIS intent recognition, because you want to do translation upfront. To achieve that scenario with the built-in recognizer, you would need a translation middleware. There is a short discussion going on here on Github about translation middleware for Bot Framework Composer, although the sample code is not ready yet.
While there is no code samples for the translation middleware yet, I believe what could already help you today is to start a subdialog based on the recognized intent, similar to what you already show in your screenshots.
Basically instead of "Send a response" at the end of your dialog, you would have something following like:
My sample here uses user input instead of the recognized intent. You would replace the user input with your intent variable instead. Based on the recognized intent, you would be able to spin up a specific dialog to handle that recognized intent.
The result would look something like:
About triggers, what you currently configured in your screenshot shows "no editor for null". I believe this might cause the "object reference" issue. Normally it should display a trigger phrase. For example, the below means:
If user inputs the text "triggerphrase"
And the dialog variable 'topintent' was previously set to 'test', then run this trigger.
I'm working on a Dialogflow chatbot, and I'm currently giving the response hard coded in fulfillment using agent.add(). However, the product owner wants to be able to modify the wordings without having to change and redeploy code. What are the options for this, other than storing responses in a file or in a database? Is there a way to have variables in the response when you add it in the response section in the Dialogflow console, where that variable is set in fulfillment, but otherwise the response is given as per the response in the console? Is there a way to select which response is given out of the ones set in the Dialogflow console from fulfillment? I'm using the nodejs fulfillment library without actions on google.
I think you have two options:
Use one intent only with various parameters
You can have multiple variants of responses in one intent. These will be prioritized by the maximum parameters they can fill. For example, if you are sending parameter "a" to a single intent using detectIntent API, the second response here will be triggered and shown to the user.
This is a response1 without parameters
This is a response1 with parameter $a <-- This will be triggered
This is a response1 with parameter $a and $b
As a little hack, you can also send an empty unicode space character here, if you prefer not to generate any parameters on the backend. Not too clean, but would work.
Use events triggered from your backend
In this case, your webhook/backend would choose a proper event to call. Hence, you would have mutliple intents, each with a unique response. You can also combine this approach with the first point above. You can read more about events here.
While creating Intents in Api.ai, I can parse sys or user parameters as listed here:
https://docs.api.ai/docs/concept-entities#section-user-entities
However if I have to parse a string response, there isn't a way to add that as a parameter. Any workaround to parse a string response from user to fetch an entity?
Like for e.g.,
Customer's name is John.
I want to retrieve John in my action.
I think you can utilize api.ai Contexts to Achieve that..
check Context documentation
Yes , It is possible.
1)First you should set the output context in intent from which you want to fetch customer's name
e.g. setting output context
2) Then define the input context with same name in intent where you want to get your customer's name e.g. setting input context
3) then you can access name by defining the parameter with #<context_name>.<parameter_name> e.g. #send.name
Hope this might help!!