Reducing amount of download files and memory strain for OBQA by using wikipedia api instead of local downloads.

[Aryagm]

Want to contribute to DeepPavlov? Please read the contributing guideline first.

What problem are we trying to solve?:

The OBQA model needs very large download files and lots of RAM.

How can we solve it?:

Maybe we can use the[ wikipedia api](https://pypi.org/project/Wikipedia-API/) to get the text in the article instead of  storing the articles locally.

Are there other issues that block this solution?:

Not sure.