Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Patterns for Building LLM-Based Systems and Products. Parent comment
Basically, get the BM25 results and normalize them to be between 0 and 1, then take the (potentially weighted) average of them and the cosine similarity results (already between 0 and 1) to get the final ranking.
There are no comments on this comment yet.
Basically, get the BM25 results and normalize them to be between 0 and 1, then take the (potentially weighted) average of them and the cosine similarity results (already between 0 and 1) to get the final ranking.