This one is a fully-managed document search service that is powered by machine learning and it allows you to extract answers from within a document.
That document could be text, PDF, HTML, PowerPoints, Microsoft Word, FAQs, etc.
So you have a lot of data sources where these documents may be like Google Drive, and they're going to be indexed by Amazon Kendra which is going to build internally a knowledge index powered by machine learning.
And how does it help from an end-user perspective?
Well, we get natural language search capabilities just like you go on Google.
So for example, if a user says, where is the IT support desk into Amazon Kendra?
Kendra can reply, 1st floor.
And this could be due to the fact that Kendra knows from all the resources that it took that the IT support desk was on the 1st floor, which is quite awesome.
And also, you can just do a normal search it will learn from the user interaction and feedback to promote preferred search results which is called incremental learning.
Finally, you can fine tune the search results, for example, based on the importance of data, the freshness, or whatever custom filters you have, okay?
Okay.
Top comments (0)