How I can specify multiple answers for a specific dialog node? For example, when user asks “What is your name”, my VA should reply “My name is Alexander”, or “You can call me Alexander”, or “Friends call me Alex”.
Maybe Conversation service must return a code and application checks the code and choose a random answer from answer's db.
For the application node that gives the response, select advanced mode and change to this:
{
"output": {
"text": {
"values": [
"My name is Alexander.",
"You can call me Alexander",
"Friends call me Alex"
],
"selection_policy": "random",
"append": false
}
}
}
Related
I'm struggling to build my Alexa Interaction model. My application is used for requesting live data from a smart home device. All i do is basically calling my Server API with a Username & Password and i get a value in return. My interaction model works perfectly for requesting the parameters, for example i can say "Temperature" and it works perfectly fine across all testing devices. For that intent i got a custom RequestType.
However for setting up Username & Password i need to use an built-it slot type: AMAZON.NUMBER. As i only need numbers for my credentials this should work perfectly fine in theory.
I got a interaction model setup which works perfectly fine when i press "Evaluate Model" in Alexa developer console. However once i go to Test on the simulator or to my real Alexa device it's absolutely impossible to call the intent. It always calls one of more other intents? (I see this in the request JSON).
Here's how the intent looks:
{
"name": "SetupUsername",
"slots": [
{
"name": "username",
"type": "AMAZON.NUMBER"
}
],
"samples": [
"my user id is {username}",
"username to {username}",
"set my username to {username}",
"set username to {username}",
"user {username}",
"my username is {username}",
"username equals {username}"
]
}
Whatever i say or type in the Simulator, i cannot call this intent. I have no overlaps from other intents. Does anyone see an issue here?
Thank you in advance
EDIT: I just realized that if you want to do account linking on Alexa you need to implement OAuth2 - maybe my intents are never called because they want to bypass me implementing my own authentication?
UPDATE:
This is the intent that is usually called instead - it's my init intent. So for example is i say "my username is 12345" the following intent is gonna be called:
UPDATE 2:
Here is my full interaction model.
(HelpIntent and SetPassword are only for testing purposes, they don't make sense right now)
It's impossible calling SetupUsername with any of the samples in my model.
You need to build the interaction model. Saving is not enough
When you develop your Interaction Model, you have to save it AND build it. Otherwise only the evaluation model will work (documentation about it).
Then when you test in the test console, you should see in the JSON Input, at the bottom, which intent was called:
"request": {
"type": "IntentRequest",
"requestId": "xxxx",
"locale": "en-US",
"timestamp": "2021-10-20T14:38:59Z",
"intent": {
"name": "HelloWorldIntent", <----------- HERE
"confirmationStatus": "NONE"
}
}
My application was designed to add a user to my Azure AD B2C using Azure AD Graph API. I also handled the case where I'd be calling the add user graph API with an email ID that already exists in AD. I was looking for the error message in the response body to handle this. Has there been any change w.r.t the response message?
POST
https://graph.windows.net/{tenant}/users?api-version=1.6
Request Body :
{
"accountEnabled": true,
"signInNames": [
{
"type": "EmailAddress",
"value": "TestGraphApiCreatedUser#TestGraphApiCreatedUser.com"
}],
"displayName": "TestGraphApiCreatedUser",
"mailNickname": "TestGraphApiCreatedUser",
"passwordProfile" : {
"forceChangePasswordNextLogin": false,
"password": "vhkjds#fceu456VCHU"
},
"creationType": "LocalAccount",
"passwordPolicies": "DisablePasswordExpiration"
}
If a user already exists with the given email address, the error I was getting earlier was
{
"odata.error": {
"code": "Request_BadRequest",
"message": {
"lang": "en",
"value": "Another object with the same value for property signInName already exists."
}
}
}
Now, for the same flow, I'm getting below error :
{
"odata.error": {
"code": "Request_BadRequest",
"message": {
"lang": "en",
"value": "Another object with the same value for property userPrincipalName already exists."
}
}
}
Is there any difference between the two error messages. Since there isn't any error code, I had hard coded the whole error message. Now that there is a slight change in the message, I've to update my code. How can I handle this in a better way?
I didn't check to confirm if they changed the error message, but it wouldn't surprise me at all if they did. The userPrincipalName may be coming from the underlying AAD, maybe MS changed the B2C implementation and now it exposes an error message from there?
In your particular case, a better option may be to check if the email address exists in B2C just before calling the API to create the new user. It's an extra API call, but it shouldn't matter much unless you're creating many users at a time, e.g. in a batch. You'll still have to handle the user creation call failure, but if it happens you could just return a generic error message.
If the user logins to the website in morning, watson would say Good Morning!
If the user logins to the website in afternoon, watson would say Good afternoon!
If the user logins to the website in evening, watson would say Good Evening!
I've written like this
{
"conditions": "now().before('12:00:00')",
"output": {
"text": {
"values": [ "Good morning!" ]
}
}
}
But after closing the json editor the code is changing to like this:
{
"output": {
"text": {
"values": [
"Good morning!"
]
}
}
}
Can anyone please say what the solution is? Please provide the entire code for
["good morning,good afternoon,good evening"]
`
You can't define conditions in the JSON editor. So it deletes any field that is not part of the schema.
You can set the condition within the tooling UI at the IF statement section. Just paste in your condition part. As the functionality has recently changed, you will need to do the following.
On the Welcome node, click the "Customise" Cog. Select "Allow multiple responses".
Set your conditions now at each response part.
If you are using the workspace API, then I recommend to export your workspace to see how a node block is correctly structured. Alternatively you can check the API spec.
https://www.ibm.com/watson/developercloud/conversation/api/v1/#create_workspace
I am failing to understand the simple passing of parameters to and fro via webhook. i am trying to build a simple bot using dialog flow and fb messenger. i have requirement to show two buttons to the end user to pick a cake type. i am able to show the options using the below custom response:
{
"facebook": {
"attachment": {
"type": "template",
"payload": {
"template_type": "button",
"text": "What kind of cake would you like?",
"buttons": [
{
"type": "postback",
"payload": "witheggs",
"title": "Contain Eggs"
},
{
"type": "postback",
"payload": "noeggs",
"title": "Eggless"
}
]
}
}
}
}
once user tap one of the two buttons then how do i set it to some variable in dialog flow and then ask next set of question?
I guess you're missing few steps here. Before, I explain you what to do, be sure to know what a postback is! Postback, when tapped, the text is sent as a user query to dialogflow.com.
Step-1: I created an intent with custom payload as follows:
Step-2: Now, I created a new intent where I have entered user says as noeggs which is of type postback & payload as noeggs the in previous image.
Step-3: Save & test it in FB Messenger.
So basically, what has happened here is, when you click on Eggless button, postback as noeggs is sent as user query to dialogflow.com where there is an intent which matches user says with noeggs & sends response back.
I'm creating sample application using Watson conversation API in nodejs. I'm trying to get username and send them to Watson and then I want to say hello "$username", also I want to keep that throughout the conversation so that I can if the user ask if I remember the name, Watson can say "yes, "$username"".
Can someone help me with sample code, how to use intent in this use case.
// Start conversation with Hello message.
conversation.message({
input: { text: "Hello" },
}, processResponse);
// Process the conversation response.
function processResponse(err, response) {
if (err) {
console.error(err); // something went wrong
return;
}
// If an intent was detected, log it out to the console.
if (response.intents.length > 0) {
//console.log('Detected intent: #' + response.intents[0].intent);
console.log(response.context)
}
// Display the output from dialog, if any.
if (response.output.text.length != 0) {
console.log("Watson : "+response.output.text[0]);
}
// Prompt for the next round of input.
var newMessageFromUser = prompt('Me : ');
// Send back the context to maintain state.
conversation.message({
input: { text: newMessageFromUser },
context : response.context,
}, processResponse)
}
You can use context variables for that.
To extract the name, request the name in 1º node, and in the next node, add this JSON:
{
"context": {
"name": "<? input.text ?>"
},
"output": {
"text": {
"values": [
"Hello $name."
],
"selection_policy": "sequential"
}
}
}
The input.text capture all user has typed.
You can use $ for set and get the context variable with the name: $name will show what user has typed.
In other case, if user typed my name is XXXXX, you can use regex inside your context variable. Check this example for use REGEX inside context variables:
"name" : "<? input.text.extract('^[A-Z][-a-zA-Z]+$') ?>"
#MichelBida did one example with regex, but with another request for user, check this link.
EDIT:
Use:
context.myproperty = "Hello World";
And now have the System Entity #sys-person, this entity extracts names from the user's input. Names are not normalized by the system, so "Will" is not treated as "William", nor vice versa, see official documentation. This entity can be active within Entity -> System Entities -> #sys-person