LUIS Overview & Demo
Utterances, Intents & Entities
Training, Testing, and Publishing a Model
The course is part of this learning path
This course focuses on how to use the LUIS (Language Understanding Intelligent Service) portal to create new LUIS models, how to enrich them with intents, entities, and utterances, and how to train and apply apps.
Not only will you get theoretical knowledge of LUIS and its components, but you'll also follow along with demonstrations from the LUIS portal to get a practical understanding of how to use the service.
- Obtain a general understanding of what LUIS is and how to interact with it
- Create LUIS resources
- Learn about utterances, intents, and entities and how they are used in language understanding at a practical level
- Learn how to test, train, and publish your LUIS models
This course is made for developers or architects who would like to know more about how to use the Language Understanding Intelligent Service, LUIS, to improve their chatbot development and experience.
To get the most out of this course, you should have some Azure experience, particularly surrounding subscription and resource groups as well as chatbots and language services. Some developer experience, including familiarity with terms such as REST API and SDKs, would also be beneficial.
So we're here in the Azure portal, and I want to first create our LUIS resource. To do that, I'll click here on the menu on the top and select Create a Resource. Then I'll type LUIS in the search box, and Language Understanding just appears for me, so click on it. Then I'll click on the Create button. Here you can see that my first option is to decide whether this LUIS resource we have Authoring, Prediction, or both of them. I'll leave it on Both.
My Azure subscription is already selected, so just click to create a new Resource Group and name that CloudAcademy. Then I'll click OK. Under name, let's name that AI-102LUIS. Under Authoring Location, notice that I only have a few datacenters available for that. That's not much of a problem, as LUIS is a pretty lightweight resource and most major geographic locations, Americas, EMEA and APAC are covered. I'll set that to Australia East, and set the pricing tier to F0 which is free.
For the Prediction resource, however, I have a comprehensive list of Azure Datacenters available to me. This ensures that LUIS will be closer to both my clients and chatbots which is essential to give a better user experience. I'll select also Australia East, then again, the free tier. Click Review and Create and then click on the Create button. That should take a few seconds. So in the meantime, let's switch to the LUIS portal.
I'll open a new tab and type www.luis.ai. Then I'll click on the Sign In button, and now I can see this screen where I'm asked to select my Authoring Resource or to create a new one. I'll select my Azure subscription and click on this big button over here. On the next page, I'll select the new Resource that I have created, AI-102LUIS. Notice that it has the dash Authoring suffix, to indicate that this is the authoring endpoint. Then I'll click on Done to finish.
On the next screen, let's click on the down arrow close to the New App button, and notice that I can also create new apps from JSON or .lu files. .lu is an extension of specific LUIS. But as I don't yet have any, let's just click here on the New App button. On the new dialog box that opens, I'll name this EmiliosPizzaChatBot, named after my fictitious wanna be Italian restaurant. The culture will be English, but if I click here on the list, you see that we have several different languages and a lot of them in preview. This is a very good sign as it indicates Microsoft's investment in LUIS for international audiences.
For description, I'll type Emilio's Pizza LUIS App, select the Prediction resource that I have created and click on Done. After a few seconds, I get this dialog box that tries to give me a few tips and tricks on how to configure the LUIS app, but I'll just click on close for now.
On this next screen, we have far more options to work with. We have tabs to Monitor, Build, the app that we're currently on and Manage our App. We have buttons to Train, Test, and Publish our model. And most importantly, here on the left, we have options to create our intents and entities and to add prebuilt domains to the model. This should be the next logical step when creating a LUIS app. So we'll see that next.
Emilio Melo has been involved in IT projects in over 15 countries, with roles ranging across support, consultancy, teaching, project and department management, and sales—mostly focused on Microsoft software. After 15 years of on-premises experience in infrastructure, data, and collaboration, he became fascinated by Cloud technologies and the incredible transformation potential it brings. His passion outside work is to travel and discover the wonderful things this world has to offer.