At the time of writing this blog post, the BOT framework is still in preview so things are subject to change! However, if you already played with it and tried to enable the Teams Channel for one of your BOTs, you’ll see that it behaves differently than for the WebChat Channel.
I had the opportunity to work with LUIS (Language Understanding Intelligent Service) recently in order to make an “intelligent” BOT. NLP (Natural Language Processing) and artificial intelligence in general are not new as Alan Turing was already busy with that decades ago but today, we have more power and more data than ever…
In general, if you want to have a reliable NLP engine, it’s always a good idea to restrict the scope of the application domain and that’s exactly what LUIS allows you to do in an easy way.
In this post, I will explain how you can transparently authenticate end users to a BOT whose the backend is hosted in Azure.
I’m only covering the webchat channel and more particularly the webchat control that is available out of the box when enabling the web chat channel in the BOT configuration page. As this sample leverages various building blocs, I assume that you already know ADAL and the Microsoft BOT framework.
At the time of writing this blog post, the framework is still in preview so things are subject to change in the future.
I’ve recently worked on creating a BOT with the Microsoft Bot framework that handles queries from end users expressed in natural language. The BOT leverages #LUIS, Microsoft’s NLP engine, in order to extract entities and semantics our of the queries. At the time of writing, both LUIS and the Microsoft Bot framework are still in preview but they let us envision great possibiliities.
Microsoft recently made Azure Cognitive Services available (in preview at the time of writing). This new set of APIs is built on top of Azure’s API Management building block and points to well known APIs (Machine Learning, Bing…) that Microsoft was offering for a while but in different flavors. Thanks to Azure Cognitive Services, we now have a single way of consuming these APIs which makes our life better!
If you keep receiving this exception: Internal error while executing BES operation from the Topic Detection operation of the Text Analytics API, you might want to double-check the following things: