To recall, Integrating our private documents with LLM is called RAG.

Lets assume that, we have some pdfs containing our data. That data in the pdf will be broken down into chunks based on some criteria. That chunk will be fed as input to the model. More specifically embedding model. This model will generate a point. How the point is generated ?

Lets take a simple example:

Today is Wednesday

Tomorrow is Thursday

I am travelling today

Wednesday is a nice series

Lets construct a sentence now containing only unique words from the above set of sentences:

Today, is, Wednesday, Tomorrow, Thursday, I, am, travelling, a, nice, series

We are now going to construct each sentence into a number format.…