Summary

Weaviate is not supports Chinese bm25 in last version。
I looked up Weaviate's official website and found that Weaviate added support for jieba word segmentation after 1.24. The previous version segmented words based on spaces, which does not work for Chinese. The following is my modification method. If there is no problem, I will submit it，Of course it is configurable in docker-compose.yaml.
1、Upgraded Weaviate version
2、Modify the default word segmenter

Resolves #12223

Reference Links：
https://weaviate.io/developers/weaviate/config-refs/schema#gse-and-trigram-tokenization-methods
https://pkg.go.dev/github.com/go-ego/gse#section-readme

Screenshots

Before	After
...

|

Checklist

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods