RAG

Question 1

what is TF and IDF?

Answer 1

TF is term frequency it is the number of times a term occurs in a given document divided by total number of words in the document
IDF is inverse document frequency, think document frequency first so that’s the number of documents in which a term occurs divided by total number of documents
TF-IDF is the product of TF and inverse of IDF.

Question 2

what is BM25

Answer 2

Best Match 25 is a modification to TF IDF which let’s it work much better