Thanks Samreen, for your feedback :)

Yep, I didn't want to go into depth in this article, I wanted to give the idea of Vector DB.

I have written about different retriever algorithms in my second article of the series: https://medium.com/@kaushikshakkari/open-domain-question-answering-series-part-2-machine-reading-comprehension-at-scale-7ca0b75dbd3a

But sure, I will try to write future articles on how to preprocess data and create the inverted index, etc.