Skip to content

fix: default BM25 tokenizer splits CJK characters for bare-term retrieval - #12837

Merged
sjrl merged 2 commits into
deepset-ai:mainfrom
Rainmemery:fix/bm25-cjk-tokenization
Sep 28, 2026
Merged

sjrl merged 2 commits into
deepset-ai:mainfrom
Rainmemery:fix/bm25-cjk-tokenization

Commits

Commits on Sep 23, 2026

Commits on Sep 26, 2026