I'm using watson assistant were i have created a skill and in that i have used "option response". so i am deploying it in node-RED.
The problem is that in UI when watson interact with user upto when its not came up with "option response" but when watson has to response with option functionality then it's not showing any option!
as you can see here watson asked for email address and then next watson reply has to be in "option response" but its not showing.....
in function 1 node code is :-
msg.payload = msg.payload.text;
return msg;
in function 2 node code is :-
msg.payload = msg.payload.output.text[0];
return msg;
in form node :-
I tried to explain my problem as clear as I can. please! please! help me out with that.
if I have used less nodes or whatever it is please let me know.
I want to show what output watson has to show :
when I tried typing this code in function node 2 :
msg.payload =payload
then in debug node at that point where watson has to option response is like that :
Forgive me if I misunderstand you, but I believe you are trying to output into your bot response the options that Watson Assistant responds with. If this is the case you need to look at the JSON payload that is returned from Watson, as displayed in the debug node. Your function 2 is only returning the text response from assistant. The option responses are within a different part of the json payload, i.e.
msg.payload = msg.payload.output.generic[0].options[0].label
timd’s answer is actually correct. If you send only the text to the bot node, it will only display the test.
You need to check what format the bot node you are using expects payload to be in, and whether it can cope with options, and how it expects options to look like.
In your function node you will need to transform the output from the Assistant node into the expected input for the bot node.
Without knowing what bot node you are using and the input format it expects it is very difficult to go into more specifics, other than you are sending the wrong data.
Related
I'm building a react-native app with spanish as default language, the problem is that I'm using a open source backend service to serve data and this data comes is in english by default. What I want is to transalate this data/messages that comes from server in my react-native app to show to the user the messages in spanish not in english.
This is the first time I am doing this process and it is not clear to me what are the steps or the flow that is generally followed for this kind of proces(translate messages that comes from server in my app).
You have many approaches to such a thing one comes to mind is
Catch the error/api response message which mostly server error messages comes in codes and messages.
set a condition statement if code equal 2 that means the server is down for example
Example:
You made a request to the server and there was an error with the server let say wrong username and password, now the server returns a message and a error code you have to get the code or the message and show your own message
.....made the request the server returned
{ code: 192, message: Wrong username/Password }
now in your code you will do the following
if(code == 192){
...do your message
}
P.S this is just on top my head since you didn't share any codes or responses from your server.
UPDATE :
If you want to translate all your strings/messages that comes from the server you would need to do another approche something like this
Create a file contain all the strings/codes from the server
compare messages/code comes from the server and the file will return the text you want
{ "102": "Hola", "103": "Bien", "104": "Nada", "105": "Si", }
now this file contain the error/message code all you have to do is when you receive the code grab the message from this file
let translation = {
"101": "Hola",
"102":"Si"
};
translation["102"]; // Result will be Si
Now this is the most accurate approach but you have to know all the messages/codes comes from the server, now if you want something to translate on the fly you might wanna use translation library and may not be accurate translation
I have been working on a way within my discord server to try to automate the flow of users who want to try out for a team using bots. Currently I have adopted YAGPDB and have a role menu created in a community level (category) #general_tryouts channel with reactions to specify which game they want to pursue. When they select a reaction they are assigned a temporary role (24 hours) which will grant them access to the game specific category #tryouts channel they've selected. I've been successful with getting all of the roles assigned using YAG's gui interface. However, I would also like for a message to be sent to the game specific #tryouts channel with an embed (similar to a welcome message) stating that they would like to tryout, to notify the 'team' that they are "in the queue". So the process would look something like this:
User A pops into (Some Community) #general-tryouts -> reads the menu asking them which team they want to tryout for and selects option 1 (':one:') -> User A is given the role for TempGame1 and can now see (Some Game) #tryouts AND simultaneously a message is sent to (Some Game) #tryouts on their behalf.
If they choose option 2 they will receive a TempGame2 role and a message should be sent to (Another Game) #tryouts.
If they choose option 3 they will receive a TempGame3 role and a message should be sent to (ThisOther Game) #tryouts.
YAGPDB has the option with it's custom commands to fire a command triggered by a reaction given in a certain channel by someone with a certain role. The issue is getting the result of which reaction they selected, and that dictating where the message is sent. I'm really not even concerned if it's just a generic message. I just want User A to be able to react at a 'community' level and a message to get passed in to (Some Game) #tryout, (Another Game) #tryouts, or (ThisOther Game) #tryouts based on their selection.
My apologies in advance. I am only proficient enough to code a simple I say "ping" you output "pong" sort of transaction, and got in a little over my head in short order. I have looked at the developer resources trying to piece something together to no avail, as well as pulling a similar snippet of code from here and attempting to modify it to suit my needs, also to no avail. Any help would be greatly appreciated.
Code Sample
if (reaction.message.id === '730000158745559122') {
let channel = reaction.message.guild.channels.cache.get(targetChannelId);
console.log(reaction.emoji)
if (channel) {
let embed = new Discord.MessageEmbed();
embed.setAuthor(
user.tag,
user.displayAvatarURL({
dynamic: true,
format: 'png',
}),
);
embed.setDescription(`${user} has react a: ${reaction.emoji}`);
channel.send(embed);
}
}
Visual Representation
New
in the code if (reaction.message.id === '730000158745559122') the 73000 portion represents that whole message as a focal point on what the bot is 'listening' for. Any reaction to it, be it 1, 2, or 3 will trigger this singular process. So by what you are saying by using the (id === 123 || id === 456 || id === 789) {} would likely be the way to go if I had more than one message is was 'collecting' on for a lack of better way to state it. I believe what I need to do is
`if (reaction(':one:').message.id === 123 {send message ('nifty embed')to channel.id 12345}
if (reaction(':two:').message.id === 123 {send message ('nifty embed') to channel.id 67890}
if (reaction(':three:').message.id === 123 {send message ('nifty embed') to channel.id 16273}`
I have created a skill with name "BuyDog" and its invocation name is "dog app"
So that should mean, I can use the intents defined inside only after the invocation name is heard. (is that correct?)
Then I have defined the Intents with slots as:
"what is {dog} price."
"Tell me the price of {dog}."
where the slot {dog} is of slot type "DogType". I have marked this slot as required to fulfill
Then I have added the endpoint to AWS lambda function where I have used the blueprint code of factskills project in node.js, and done few minor changes just to see the working.
const GET_DOG_PRICE_MESSAGE = "Here's your pricing: ";
const data = [
'You need to pay $2000.',
'You need to pay Rs2000.',
'You need to pay $5000.',
'You need to pay INR 3000.',
];
const handlers = {
//some handlers.......................
'DogIntent': function () {
const factArr = data;
const factIndex = Math.floor(Math.random() * factArr.length);
const randomFact = factArr[factIndex];
const speechOutput = GET_DOG_PRICE_MESSAGE + randomFact;
}
//some handlers.......................
};
As per the about code I was expecting when
I say: "Alexa open dog app"
It should just be ready to listen to the intent "what is {dog} price." and the other one. Instead it says a random string from the node.js code's data[] array. I was expecting this response after the Intent was spoken as the slot was required for intent to complete.
And when
I say: "open the dog app and Tell me the price of XXXX."
It asks for "which breed" (that is my defined question) But it just works fine and show the pricing
Alexa says: "Here's your pricing: You need to pay $5000."
(or other value from the data array) for any XXXX (i.e. dog or not dog type).
Why is alexa not confirming the word is in slot set or not?
And when
I say: "open the dog bark".
I expected alexa to not understand the question but it gave me a fact about barking. WHY? How did that happen?
Does alexa have a default set of skills? like search google/amazon etc...
I am so confused. Please help me understand what is going on?
Without having your full code to see exactly what is happening and provide code answers, I hope just an explanation for your problems/questions will point you in the right direction.
1. Launching Skill
I say: "Alexa open dog app"
It should just be ready to listen to the intent...
You are expecting Alexa to just listen, but actually, Alexa opens your skill and is expecting you to have a generic welcome response at this point. Alexa will send a Launch Request to your Lambda. This is different from an IntentRequest and so you can determine this by checking request.type. Usually found with:
this.event.request.type === 'LaunchRequest'
I suggest you add some logging to your Lambda, and use CloudWatch to see the incoming request from Alexa:
console.log("ALEXA REQUEST= " + event)
2. Slot Value Recognition
I say: "open the dog app and Tell me the price of XXXX."
Why is alexa not confirming the word is in slot set or not?
Alexa does not limit a slot to the slot values set in the slotType. The values you give the slotType are used as a guide, but other values are also accepted.
It is up to you, in your Lambda Function, to validate those slot values to make sure they are set to a value you accept. There are many ways to do this, so just start by detecting what the slot has been filled with. Usually found with:
this.event.request.intent.slots.{slotName}.value;
If you choose to set up synonyms in the slotType, then Alexa will also provide her recommended slot value resolutions. For example you could inlcude "Rotty" as a synonym for "Rottweiler", and Alexa will fill the slot with "Rotty" but also suggest you to resolve that to "Rottweiler".
var resolutionsArray = this.event.request.intent.slots.{slotName}.resolutions.resolutionsPerAuthority;
Again, use console.log and CloudWatch to view the slot values that Alexa accepts and fills.
3. Purposefully Fail to Launch Skill
I say: "open the dog bark".
I expected alexa to not understand the question but it gave me a fact about barking.
You must be doing this outside of your Skill, where Alexa will take any inputs and try to recognize an enabled skill, or handle with her best guess of default abilities.
Alexa does have default built-in abilities (not skills really) to answer general questions, and just be fun and friendly. You can see what she can do on her own here: Alexa - Things To Try
So my guess is, Alexa figured you were asking something about dog barks, and so provided an answer. You can try to ask her "What is a dog bark" and see if she responds with the exact same as "open the dog bark", just to confirm these suspicions.
To really understand developing an Alexa skill you should spend the time to get very familiar with this documentation:
Alexa Request and Response JSON Formats
You didn't post a lot of your code so it's hard to tell exactly what you meant but usually to handle incomplete events you can have an incomplete even handler like this:
const IncompleteDogsIntentHandler = {
// Occurs when the required slots are not filled
canHandle(handlerInput) {
return handlerInput.requestEnvelope.request.type === 'IntentRequest'
&& handlerInput.requestEnvelope.request.intent.name === 'DogIntent'
&& handlerInput.requestEnvelope.request.dialogState !== 'COMPLETED'
},
async handle(handlerInput) {
return handlerInput.responseBuilder
.addDelegateDirective(handlerInput.requestEnvelope.request.intent)
.getResponse();
}
you add this handler right above your actual handler usually in the index.js file of your lambda
This might not fix all your issues, but it will help you handle the event when a user doesn't mention a dog.
In Details:
Example:
user:- asks About Cricket News.
Alexa:- Reads about the new.
If users says come again or replay
user: Come again.
Alexa: Must read it again what it spoke earlier.
How to handle this situation using webhooks.
Thanks in advance.
You can make use of sessionAttributes to keep track of the last response that Alexa spoke. Whenever you return a response just store the speech and re-prompt in sessionAttributes and whenever a ComeAgainIntent is triggered, take the value from the sessionAttributes and respond accordingly.
Ex:
...
"sessionAttributes": {
"lastResponse": {
"speech": "This was my last speech",
"reprompt": "This was my lst reprompt"
}
}
...
Every time before building the response store the response as lastSpeech in session attributes and write a comeAgainIntent or use amazon.REPEAT intent to repeat the response by getting lastSpeech from session attributes.
I would like to know how to display a file when a user types something.
Ex: Show me the course details
Output: The file(pdf format) which is on my PC gets displayed.
Basically, you need to know how to work conversation: is one API for creating Intents, Entities and your Dialog flow.
Your application will access all nodes with the return from the API, and you will create conditions to get something for know if the user asked something about "Show me the course details".
I recommend to you create one intent like #aboutCourse and show examples to Watson know if the user will ask something with this purpose.
Something like:
Watson says: Hi! How can I help you?
User: Please show me the course details
Watson will recognize your intent and response what you paste within the node with the Intent condition #aboutCourse.
Make sure if the user really want this with:
Watson says: You really want to know details about the course?
User: yes / ok // or something to confirm
Or you can add some Intent confidence level for this node condition like: intents[0].confidence >= 0.75
And your code will check if the Intent is #aboutCourse and the entity is #yes, and do something in your application.
Or, you can create one context variable too, because, depends on your node flow, the intents will modify within your flow because every time Watson try to recognize what the user wants.
With your dialog flow, you will create one context variable and check if user says yes, like:
{
"context": {
"courseConfirm": "<? #yes ?>" //create one intent with confirm examples and value equal yes
},
"output": {
"text": {
"values": [
"Ok, you say #yes. I'll check, one moment."
],
"selection_policy": "sequential"
}
}
}
And within your application:
function updateMessage(input, response) {
if (response.context.courseConfirm == 'yes') {
//do something with code with code
}
}
Or you can create one function inside my example, like this answer.
Obs.: This code example is with conversation-simple project, from IBM Developers, but you will do something like my example with the same logic:get the return from API and do something within your application.