I am having a problem similar to Botframework findEntity() issue.
I have created a node.js botframework app using the azure interface. I am using the azure ide for development (to keep things simple).
The relevant code is:
// Main dialog with LUIS
var recognizer = new builder.LuisRecognizer(LuisModelUrl);
var intents = new builder.IntentDialog({ recognizers: [recognizer] })
/*
.matches('<yourIntent>')... See details at http://docs.botframework.com/builder/node/guides/understanding-natural-language/
*/
.matches('Help',(session, args) => {
var entities = args.entities;
var itype = builder.EntityRecognizer.findEntity(args.entities, 'ItemTypes');
session.send(args.entities[0]["entity"]);
session.send(args.entities[0]["type"]);
session.send('How may I assist you? ' + JSON.stringify(args));
session.send('Value of entity (didnt match) you said: \'%s\'.', itype);
})
the findEntity function returns null in itype (at least that is what I see in the session.send results.
I tried using both args.entities and args.intents.entities, no change.
When I look at the results of the args.entities[0]["entity"] and [type] I do get values. The results of the JSON.stringify are below (also showing it is finding the entity).
How may I assist you?
{"score":0.970185757,"intent":"Help","intents":[{"intent":"Help","score":0.970185757},{"intent":"Joke","score":0.0711096451},{"intent":"Greeting","score":0.0438234434},{"intent":"None","score":0.0408537947},{"intent":"Goodbye","score":0.04074517}],"entities":[{"entity":"stapler","type":"ItemTypes","
I'm assuming there is more but that it was cut off by the chat window.
I'm new to every technology involved and will take any help I can get.
Related
I am trying to save the new questions asked by the user to my QnA maker bot into an Azure database so that I can add the answers to those questions to my knowledge base.
Currently, I am asking the users to write their question in a feedback form when they don't get a response from my bot. This is taking make time also the user is annoyed by writing. I want my bot to collect these questions and store it a database.
So, please guide how to achieve this, any links or suggestions appreciated.
I was able to achieve something similar using a SharePoint list.
https://stackoverflow.com/a/56612401/9611859
If you want to add a no answer to a SharePoint List, I managed to get it working using the csom-node package and Bot Framework v4 / NodeJS. Granted, it's not the most elegant solution, but it works.
Bot.JS
const csomapi = require('../node_modules/csom-node');
settings = require('../settings').settings;
// Set CSOM settings
csomapi.setLoaderOptions({url: settings.siteurl});
Bit further down the page...
// If no answers were returned from QnA Maker, reply with help.
} else {
await context.sendActivity("Er sorry, I don't seem to have an answer.");
console.log(context.activity.text);
var response = context.activity.text;
var authCtx = new AuthenticationContext(settings.siteurl);
authCtx.acquireTokenForApp(settings.clientId, settings.clientSecret, function (err, data) {
var ctx = new SP.ClientContext("/sites/yoursite"); //set root web
authCtx.setAuthenticationCookie(ctx); //authenticate
var web = ctx.get_web();
var list = web.get_lists().getByTitle('YourList');
var creationInfo = new SP.ListItemCreationInformation();
var listItem = list.addItem(creationInfo);
listItem.set_item('Title', response);
listItem.update();
ctx.load(listItem);
ctx.executeQueryAsync();
});
}
I'm currently developing a webOS TV application which includes a background running service. I'm having trouble getting logs to print in the NodeJS console.
I have no prior experience working with Node so I'm unsure whether any additional modules are required to get this done(but I highly doubt it, and the docs don't seem to suggest so.)
As of now my service side code is as follows;
var Service = require('webos-service');
var service = new Service("com.nuwan.helloworld.service");
// code to keep the service from being terminated
var keepAlive;
service.activityManager.create("keepAlive", function(activity) {
keepAlive = activity;
});
service.activityManager.complete(keepAlive, function(activity) {
console.log("completed activity");
});
// hello command implementation
service.register("hello", function(message) {
var response = message.respond({
data: "Hello, " + message.payload.name + "!"
});
});
It would be great if someone could give me some pointers.
As it is right now, I'm not getting any output whatsoever on the Node Profiler console.
The way i did it ( i don't know if that's the only way) to debug the code is through the chromium debugger eg.
This is a generic image to see from where you are going to check the code.
I am currently working on a project where visitors are normally using both English and Chinese to talk to each other.
Since LUIS did not support multi-language very well (Yes I know it can support in certain ways but I want a better service), I would like to build my own Neural Network as a REST API so that, when someone submits their text, we can simply predict the "Intent", while we are still using MS BotFramework (NodeJS).
By doing this we can bypass MS LUIS and using our own Language understanding service.
Here are my two questions:
Has anyone done that before? Any GitHub link I can reference to?
If I did that, what is the BotFramework API I should use? There is a recognizer called "Custom Recognizer" and I wonder if it really works.
Thank you very much in advance for all your help.
Another option apart from Alexandru's suggestions is to add a middleware which will call the NLP service of your choosing everytime the bot receive a chat/request.
Botbuilder allows middleware functions to be applied before handling any dialogs, I created a sample code for a better understanding below.
const bot = new builder.UniversalBot(connector, function(session) {
//pass to root
session.replaceDialog('root_dialog');
})
//custom middleware
bot.use({
botbuilder: specialCommandHandler
});
//dummy call NLP service
let callNLP = (text) => {
return new Promise((resolve, reject) => {
// do your NLP service API call here and resolve the result
resolve({});
});
}
let specialCommandHandler = (session, next) => {
//user message here
let userMessage = session.message.text;
callNLP.then(NLPresult => {
// you can save your NLP result to a session
session.conversationData.nlpResult = NLPResult;
// this will continue to the bot dialog, in this case it will continue to root
// dialog
next();
}).catch(err => {
//handle errors
})
}
//root dialog
bot.dialog('root_dialog', [(session, args, next) => {
// your NLP call result
let nlpResult = session.conversationData.nlpResult;
// do any operations with the result here, either redirecting to a new dialog
// for specific intent/entity, etc.
}]);
For Nodejs botframework implementation you have at least two ways:
With LuisRecognizer as a starting point to create your own Recognizer. This approach works with single intent NLU's and entities arrays (just like LUIS);
Create a SimpleDialog with a single handler function that calls the desired NLU API;
Im working with Microsoft Dynamics CRM. The client is requesting to be able to add notes from a webresources.
I thought that something like this will do the trick:
Xrm.Utility.openEntityForm("annotation", null, parameters);
or even the classic
/main.aspx?etn=annotation&pagetype=entityrecord#
But I receive a "Query Builder Error: The specified record type does not exist in Microsoft Dynamics CRM"
It seems like notes is not something we can open in that way but I cannot found the right way (if even exists!)
Any help?
Maybe this can help someone in the future: This will open a dialog with the Regarding field filled, the textboxs for title and description and the attachments field.
function createNote() {
var EntityID = Xrm.Page.data.entity.getId(); // to get entity id
var ServicerURL = Xrm.Page.context.getClientUrl(); // to get server url
var etc =Xrm.Page.context.getQueryStringParameters().etc; // to get entity type code, make sure not to hard code it, because it could changed in another deployment
var NotesURL = ServicerURL + "/notes/edit.aspx?pId=" + EntityID + "&pType=" + etc;
var features = "copyhistory=no,top=110,left=280,width=600,height=400";
window.open(NotesURL, "", features);
}
I've been reading so much a bout node js lately, and the chat capabilities seem very nice. However, the only chat examples I've seen basically broadcast a chat server to a fixed URL (like a meeting room). Is it possible to use node js in part to create a chat client more like gchat? - where a chat window is popped up on the current page and then persists through multiple pages. Has anyone seen an example of this yet?
If not, suggestions for other technologies to use for this purpose (I know that's been answered in other questions)?
Thanks.
I'll give you a pseudo implementation relying on jquery and now to abstract away tedious IO and tedious DOM manipulation from the solution.
// Server
var nowjs = require('now');
var everyone = nowjs.initialize(httpServer);
everyone.now.joinRoom = function(room) {
nowjs.getGroup(room).addUser(this.user.clientId);
}
everyone.now.leaveRoom = function(room) {
nowjs.getGroup(room).removeUser(this.user.clientId);
}
everyone.now.messageRoom = function(room, message) {
nowjs.getGroup(room).now.message(message);
}
// Client
var currRoom = "";
$(".join").click(function() {
currRoom = ...
now.joinRoom(currRoom);
});
$(".send").click(function() {
var input = ...
now.messageRoom(currRoom, input.text());
});
now.messageRoom = function(message) {
$("messages").append($("<div></div>").text(message));
};
I only just noticed myself that the new version of nowjs (0.5) has the group system in build. This basically does what you want for you. No hassle.
If you want you can remove the nowjs dependency and replace it with 100/200 lines of code. I'll leave that as an exercise for the user.
Take a look at AjaxIM: https://github.com/freq32/AjaxIM
This is a facebook-style chat application (think friends list, small persistent chat bar at the bottom of the screen, popup chats) based on nodejs.