Artificial Intelligence is not a future or distant concept; it is here and now, and being used by many companies of various sizes and industries. The foundational theory for AI was actually developed several decades ago, but recent advancements in big data, computing power, cloud, and algorithms have made it affordable and widespread today. With AI and Machine Learning, computers are now able to start reasoning, understanding, and interacting in ways that were never possible before.
Microsoft has created a predefined set of AI models available for companies of all sizes to start with called Cognitive Services, and best of all, they require little to no knowledge of data science. In this course, you will learn how to infuse your apps—on an architectural level—with the intelligence that Cognitive Services provide. We will cover what Cognitive Services are and how to use the various solutions they provide, including Vision, Speech, Language, Decision, and Web Search.
Learning Objectives
- Understand the functionality provided by Azure Cognitive Services
- Learn how to incorporate these services into your apps
Intended Audience
- People who want to learn more about Azure Cognitive Services
Prerequisites
- Knowledge of Azure
- Knowledge of at least one programming language
- Experience using REST APIs
Okay, so for this demo, I will also use PowerShell to give you an idea of how simple it is to call these APIs through code. Here I have a PowerShell script that calls the Translator Text API. The first three lines build a header for the HTTP POST method. First, I'm adding the subscription key, which you can get from the Portal, and then the content type for the text to be sent, which is application/json.
Line 5 has the URI for the call. As you already know, you can get all these values in the API documentation for each Cognitive Service. As you can see here, I am trying to translate from English to Spanish.
Finally, line 6 has the API call with the text "This is a test of the Translator Text API." If I run this, I get my results here below in Spanish. Let's now switch to German, which is DE, and try again. Pretty simple, huh?
Now let's switch to LUIS. Here, I'm on the home page of luis.ai. I will create a new app, call it Restaurant Booking, and then click Done. Then I have some instructions here to help me create a better model, but I'll just close this. Let me now switch to the Build tab.
Here on the Build tab, I have my entities and intents, as shown here on the top. As you can see, I have no intents or entities right now. But I also have this Prebuilt Domains button on the bottom. It's still in preview but it's perfect for this demo. Let's click on it, navigate down to Restaurant Reservation, and click on the Add Domain.
Now if I go back to my Intents, look at how many intents are populated! And if I click here in Change Reservation, here are all the utterances that Microsoft configured for me on this Prebuilt Domain. You can, of course, create your own from scratch, but if there is an existing domain that you can start from, even better! Then I just need to click here on Train, and my model will be ready to be published!
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.