Can anyone explain how exactly the reranker is calculating the score?

Could someone explain how the reranker calculates its scores? I'm observing scores such as 15.67 and 12.33, which are unexpected because I anticipated scores like 97 or 96. I use LangChain's `get_relevant_docs `to retrieve documents with relevance scores such as 98 and 96, and then send these snippets to the ColBERT reranker for reranking. The reranker then returns scores like 15.67 and 12.33. Should I consider a higher reranker score as indicative of a better snippet? Additionally, I would like to understand the technique used by the reranker to compute these scores.

Start by reading the ColBERT reranker's scoring entry point and comparing its output with LangChain's get_relevant_docs results. Document how the reranker computes and orders scores, whether higher scores are better, and why its scale differs from LangChain's relevance scores.

Written by the indexing model from the issue text.