Chat Bot Using Microsoft Bot Framework With LUIS - Part Two

Akshay Deshmukh

26 Comments

Join the conversation! Your thoughts help the community grow.

Savvy Sequeira7y ago
Hi Akshay, I am working on a Luis Chatbot. While testing it locally on Bot Emulator, I am not being able to connect to the bot. It shows" Taking longer than usual to connect". I have selected the ngrok in the settings as well but still no luck. Could you please help me with it.
- Rohan Rao6y ago
  In Savvy, in this case you compiler your application using Ctrl + Shift+ B in Visual Studio. Open your Bot Framework and then in the welcome page > click on Open Bot > Enter your URL and Click COnnect. I am sure your issue will be solved.
Raja Barad8y ago
Hello,how to connect to sql database when one of luis intent is being hit, build a form and store the information back into database (visual studio). please help.. i will be grateful
- Akshay Deshmukh8y ago
  You can call FormFlow in function called while intent found. On Form completion, you can save data to SQL. Try using EntityFramework.
- Akshay Deshmukh8y ago
  Yes, I was talking about same
- Raja Barad8y ago
  [LuisIntent("export")] public async Task export(IDialogContext context, IAwaitable<IMessageActivity> activity, LuisResult result) { string message = "please answer these.."; await context.PostAsync(message); var exportFormFlow = new FormDialog<exportFormFlow>(hotelsQuery, this.exportFormFlow); context.Call(exportFormFlow, this.exportFormFlow); } public class exportFormFlow { public enum Expo_Def { Bangalore, Chennai, Madurai, Trichy, Coimbatore, Tanjore, Pudukkottai } public enum Activity_period { Bangalore, Chennai, Madurai, Trichy, Coimbatore, Tanjore, Pudukkottai } public enum Shedule_export { AC, NonAC, Slepper, Siting } public Expo_Def? FromAddress; public Activity_period? ToAddress; public DateTime? StartDate; public Shedule_export? BusTypes; public string Name; public int Age; public static IForm<exportFormFlow> BuildForm() { return new FormBuilder<exportFormFlow>() .Message("Welcome to the BotChat Bus Booking !") .OnCompletion(async (context, profileForm) => { string message = "Your Bus booking Successfully Completed .You will get confirmation email and SMS .Thanks for using Chat Bot Bus Booking , Welcome Again !!! :"; await context.PostAsync(message); }) .Build(); } }
rashik rash8y ago
I connected to my LUIS app using the published url. But it gives error code:500 while calling using httpclient. What might be the possible error? Thanks in advance.
- rashik rash8y ago
  I resolved the error. The proxy default (defaultusercredential)was not present in config file. Thank you for the quick response.
- Akshay Deshmukh8y ago
  Please check subscription_key and app_id parameters you sent for request.
Mansour Rakia8y ago
Hello what is the error please "Exception: The response status code does not indicate success: 404 (Resource Not Found).[File type 'text / plain']"
- nazim shaik8y ago
  Even I am facing this issue, could you please reply back
lalitha kantipudi8y ago
Hello, I am working on chatbot using Luis. It should identify the emotion in the text and should reply with an image or a video. How can I add them?
- Akshay Deshmukh8y ago
  You can use Azure's text analytics API. Take a look at https://azure.microsoft.com/en-in/services/cognitive-services/text-analytics/
prasanna raj9y ago
Hi Akshay, sorry for asking lot of questions, is there any way to achieve auto complete , finally we want to use in Skype Bot.
- Akshay Deshmukh9y ago
  As per my observation, skype does not support @autocomplete
prasanna raj9y ago
Hi Akshay, thanks for replay , is there any option using @symbol to populate data's from database or Json, please refer this link "https://docs.microsoft.com/en-us/microsoftteams/platform/concepts/bots/bots-cards". am trying for auto complete past three days , please check the link and let me know if possible or not.
- Akshay Deshmukh9y ago
  Link is regarding inline images in cards. Its not for autocomplete. For autocomplete you need to capture "typing event of user and show options in chat box". Some chat interfaces and connectors like Facebook; supports it but I don't think its possible in emulator
prasanna raj9y ago
Hi Akshay, help me is there any way to do autocomplete (from database or Json) in Bot framework emulator ?
- Akshay Deshmukh9y ago
  You can not have autocomplete functionality in emulator. You can get data from DB and show it as options in bot using FormFlow feature. Check my article on FormFlow "http://www.c-sharpcorner.com/article/guided-conversation-in-chatbot-using-formflow/"
prasanna raj9y ago
Hi Akshay Deshmukh, Nice job man, its usefull to me , i want to do autocomplete with same , i checked Knowledge Exploration Service API , i dont know how to use in .net framework , please give me suggestion .
- Akshay Deshmukh9y ago
  Thank you Prasanna :) Feeling good that my contribution is helping a community
Ananth Babu9y ago
Hi Akshay, correct me if I am wrong, I have seen the BotAuthentication attribute in controller class not from dialog, even I removed from there also I am getting the same error.
- Akshay Deshmukh9y ago
  Yes it was in controller (I updated my comment). If you are trying from emulator, do not put Microsoft app id and Microsoft app password. If possible can you share code snippet.
Ananth Babu9y ago
Hi Akshay, I am getting 401 un-authorized error message while running the bot emulator even the key has been given.
- Akshay Deshmukh9y ago
  Hello Ananth, remove BotAuthentication attribute of controller class and try.

In previous articles, I have explained how to create and configure a LUIS app. In this article, we will discuss how to integrate this app in Bot application created using Microsoft Bot Framework.

We are going to build a bot which will reply as per the intents which we have added in the previous article.

Highlights of the article

Publish app
Consume LUIS app to extract intents and entities. You can pull code from here.

Prerequisite

Create LUIS app - refer previous article.
Be ready with bot framework dev environment - refer this article.

Publish LUIS app

Click on ‘Publish App’ option in left side bar menu. It will show the following page.

Here, you can choose Endpoint Key. Select purchased key. If you have not purchased any key, then select Bootstrap key, which is for experimental purpose.

In ‘Publish Settings’, you can select Endpoint slots as Staging or Production. If you select it as Staging, it will be available over http but you can’t access it though chat bot app. For our development, select it as Production.

We can enable verbose flag and Bing spell check if required. You can select time zone as per requirement.

Under ‘Add Key Association’, we can add key required for BingSpellChecker, if enabled above.

Click on Train >> Publish.

It will show success message and Endpoint url to access service over HTTP.

https://westus.api.cognitive.microsoft.com/luis/v2.0/apps/{{app_id}}?subscription-key={{subscription_key}}&timezoneOffset=0&verbose=true&spellCheck=false&q=

To test output of service, I hit the above url with different values for parameter ‘q’.

q=Hi, Output - top scoring intent – Greet.Welcome

{
"query": "hi",
"topScoringIntent": {
"intent": "Greet.Welcome",
"score": 0.792347133
},
}

q=Bye, Output: top scoring intent – Greet.Farewell

{
"query": "bye",
"topScoringIntent": {
"intent": "Greet.Farewell",
"score": 0.455509841
},
}

q=Search Amit, Output: top scoring intent – Search.People, entity – Amit, type – Person.Name

{
"query": "Search Amit",
"topScoringIntent": {
"intent": "Search.People",
"score": 0.500412941
},
}

Perfect! Our app is able to extract right intent and entity. Now, we will setup bot application.

If you are ready with prerequisites for development with bot framework, then let’s create new dialog in Dialog folder as IntelligentDialog and new Controller as IntelligentController.

IntelligentController.cs

I have updated Post( ) method to invoke IntelligentDialog with parameter activity.

public async Task < HttpResponseMessage > Post([FromBody] Activity activity) {
if (activity.Type == ActivityTypes.Message) {
await Conversation.SendAsync(activity, () => new Dialogs.IntelligentDialog(activity));
} else {
HandleSystemMessage(activity);
}
var response = Request.CreateResponse(HttpStatusCode.OK);
return response;
}

IntelligentDialog.cs

[Serializable]
[LuisModel(Constants.LUIS_EMPLOYEE_HELPER_APP_ID, Constants.LUIS_SUBSCRIPTION_KEY)]
public class IntelligentDialog: LuisDialog < object > {
private string userName;
private DateTime msgReceivedDate;
public IntelligentDialog(Activity activity) {
userName = activity.From.Name;
msgReceivedDate = activity.Timestamp ? ? DateTime.Now;
}
[LuisIntent("")]
[LuisIntent("none")]
[LuisIntent("None")]
public async Task None(IDialogContext context, LuisResult luisResult) { ...
}
[LuisIntent("Greet.Welcome")]
public async Task GreetWelcome(IDialogContext context, LuisResult luisResult) { ...
}
[LuisIntent("Greet.Farewell")]
public async Task GreetFarewell(IDialogContext context, LuisResult luisResult) { ...
}
[LuisIntent("Search.People")]
public async Task SearchPeople(IDialogContext context, LuisResult luisResult) { ...
}
}

We need to inherit IntelligentDialog from LuisDialog<object> to use LUIS intelligence. After inheritance, to integrate LUIS app we need to specify attribute LuisModel with LUIS app ID and your subscription key, for IntelligentDialog class. You can get these values from HTTP endpoint url.

I have added two private properties username and msgReceivedDate to IntelligentDialog class. Initialize those properties in its constructor (shown below). We are going to use these properties while communicating with user.

I have added methods for each Intent specified in LUIS app. To invoke those methods when intent matches, we need to specify LuisIntent attribute for each method with intent name as parameter.

For chat text from user ‘Hello Employee Helper’, intent will be matched with ‘Greet.Welcome’ and ‘GreetWelcome( )’ method will be invoked.

[LuisIntent("Greet.Welcome")]
public async Task GreetWelcome(IDialogContext context, LuisResult luisResult) {
string response = string.Empty;
if (this.msgReceivedDate.ToString("tt") == "AM") {
response = $ "Good morning, {userName}. :)";
} else {
response = $ "Hey {userName}. :)";
}
await context.PostAsync(response);
context.Wait(this.MessageReceived);
}

For chat text from user ‘Thanks dude, talk to you later’, intent will be matched with ‘Greet.Farewell’ and ‘GreetFarewell( )’ method will be invoked. In this method, we are sending response on the basis of ‘AM’ or ‘PM’ of msgReceivedDate.

[LuisIntent("Greet.Farewell")]
public async Task GreetFarewell(IDialogContext context, LuisResult luisResult) {
string response = string.Empty;
if (this.msgReceivedDate.ToString("tt") == "AM") {
response = $ "Good bye, {userName}.. Have a nice day. :)";
} else {
response = $ "b'bye {userName}, Take care.";
}
await context.PostAsync(response);
context.Wait(this.MessageReceived);
}

For chat text ‘Could you please find Akshay’ from user, intent will be matched with ‘Search.People’ and ‘SearchPeople( )’ method will be invoked. In this method, we check whether Entity ‘Person.Name’ is present in LuisResult. With TryFindEntity employee name is extracted from result.

[LuisIntent("Search.People")]
public async Task SearchPeople(IDialogContext context, LuisResult luisResult) {
EntityRecommendation employeeName;
string name = string.Empty;
if (luisResult.TryFindEntity("Person.Name", out employeeName)) {
name = employeeName.Entity;
}
await context.PostAsync($ "You have searched for {name}");
context.Wait(this.MessageReceived);
}

Hit F5 to test a bot application. It will host an application with IIS Express and open browser. To understand the control flow, insert breakpoints in Post( ) method of IntelligentController and each method of IntelligentDialog.

Now launch bot emulator app. Put URL as 'http://localhost:{{port no. from browser url}}/api/intelligent' to connect emulator with bot application. Keep App ID and App Password blank, click on connect.

Keep teaching (more intents to your LUIS app) and keep chatting!