Quantcast
Channel: Weaviate Community Forum - Latest posts
Viewing all articles
Browse latest Browse all 3590

Possible bug with relativeScoreFusion

$
0
0

IMHO the documents retrieved only via vector search must be assigned a value of 0 for the bm25 part before applying the fusion, by doing that the last bm25 result will rank up as the normalized score won’t be zero.

relativeScoreFusion just normalizes linearly from [worst_score, best_score] to [0, 1]. The problem is that if a document does not have a BM25 score, we simply cannot scale it.

Is that a bug or is it by design?

It is more a limitation of the current design. In principle, you could compute the missing vector/Bm25 scores before fusion, but it is not trivial


Viewing all articles
Browse latest Browse all 3590

Trending Articles