docling-project / docling-project/docling-core
Support newer semchunk
Open
- Dominant language
- HTML
- Stars
- 282
- Forks
- 214
- Avg merge
- 2d 15h
- Merged PRs (30d)
- 21
Description
Semchunk is now on version 3.2.1, as far as I can tell, to support it we'd merely need to change
https://github.com/docling-project/docling-core/blob/main/docling_core/transforms/chunker/hybrid_chunker.py#L227
```diff
- segments = sem_chunker.chunk(text)
+ segments = sem_chunker(text)
```
and reflect the version bump in pyproject.toml
I've experimentally done this for myself and it appears to work.
Happy to PR if this upgrade is desirable.
Contributor guide
Assessment
This issue has not been assessed yet.