So, I am pretty new when it comer to the development os AI's, principally with Microsoft Azure's tools. I was using Azure's QnA Maker Preview to develop a FAQ bot. But just today, Microsoft released a huuuuge update, making this servisse much more powerful, adding, together with other new features, the concept of metadata. I understood that it is supposed to make your system more powerful, fast and intelligent, but I didn't understand how it should be used and what exactly it does. Can anyone help me to understand this new tool? Thanks!
QnA Maker lets you add metadata, in the form of key and value pairs, to your pairs of questions and answers. You can then use this information to filter results to user queries, and to store additional information that can be used in follow-up conversations.
QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information.
Azure QnA Maker API is a free, easy-to-use, REST API and web-based service that trains AI to respond to user's questions in a more natural, conversational way.
You can use metadata as a key value pair collection to differentiate questions. For example ‘categories’. You can then use these when you query generateAnswer endpoint to filter your matches. Check out the v3 generateAnswer api documentation for an example post payload.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With