luis

We have a bot deployed on Azure but we want to give it to a client so he can deploy it run it using his own resources. We need to give them a Powershell script that magically create and deploy all the resources needed for the bot to work. My bot architecture consists on the following parts: Bot's Logic (ASP.NET Web API Project deployed over an Azure App Service ) LUIS Model (published over a Cognitive Services Account ) QnA Service Knowledge Base done with QnA Maker ( published directly from the QnaMaker Portal (have no idea where it's deployed ) Azure Table Storage My Questions are: 1) How to

I have a travel bot with following intents:- BookAFlight (trained with 20 utterances) GetTicketCopy (trained with 20 utterances) CancelTicket (trained with 20 utterances) None (default) (currently not trained) MS documentation suggests that I train None for atleast 1-2 utterances for every 10 utterances added to other intents. Which means I would need say 6-12 utterances to train None. My query is what kind of utterances should be used to train None? Everything under the sun apart from what is relevant to my bot ( for e.g. I want to order a pizza, How is the weather today, Who is the president

I'm developing a chatbot using Microsoft Bot Framework with Node.js SDK. I've integrated LUIS and QnA maker but I want to create this scenario if it's possible. Taking in example the following link and in particular this section: There are a few ways that a bot may implement a hybrid of LUIS and QnA Maker: Call LUIS first, and if no intent meets a specific threshold score, i.e., "None" intent is triggered, then call QnA Maker. Alternatively, create a LUIS intent for QnA Maker, feeding your LUIS model with example QnA questions that map to "QnAIntent." Just an example: I have my QnA KB in which

I am developing a Bot Framework application that integrates with Slack using Microsoft Bot technology. In the bot project, I was trying to get the user location when the user sends a message. What I am trying to achieve is that, when a user types the message "Show me nearby hospitals", I want to get the users Geo coordinates and pass them to an API that will return a list of hospitals near that location. So any idea on how to get the user's current location in the Microsoft Bot project? I tried using the Geo location class, however I am not able to add the class reference directly and when I

I have created a bot, having a FormFlow in it. Now if you type I want to launch a product, LUIS will tell which dialog it has to go to : internal static IDialog<AssesmentHelper> CreateProduct() { return Chain.From(() => FormDialog.FromForm(AssesmentHelper.BuildForm)) .Do(async (context, profileForm) => { try { var completed = await profileForm; } catch (FormCanceledException<AssesmentHelper> e) { string reply; if (e.InnerException == null) { reply = $"You quit on {e.Last}--maybe you can finish next time!"; } else { reply = Responses.ShortCircuit; } await context.PostAsync(reply); } }); }

Is it possible to have a conversational bot using the bot framework of Microsoft? I'm currently using Luis and Qna maker combined, but it is still pretty much a single question and answer bot, what can I do to make it more of a conversational bot? where the user can ask the bot to justify its previous answer more like a human? I've seen a a bot that is very intelligent, Mitsuku how can i make my bot similar or close to this? It appears that it can review all the previous conversation we had and it can also justify its answers pretty much well, i can pick any word from his response and it can

I have a bot that uses .NET, MS Bot Framework and LUIS.ai for its smarts. All's fine, except that I need to provide a way for non-technical users to train the bot and teach it new things , i.e. new intents in LUIS.ai. In other words, suppose that right now the bot can answer messages like "hey bot where can i get coffee" and "where can I buy some clothes" with simple phrases containing directions. Non-technical users need to be able to train it to answer "where can I get some food" too. Here's what I have considered: Continuing to use LUIS.ai. Doesn't work because LUIS.ai doesn't have an API.