docling-project / docling-project/docling
Hierarchical Chunker split chunks in the middle of a sentence.
Open
question
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
I noticed that Hierarchical Chunker often split chunks in the middle of a sentence like this:
Chunk # 17:
> ...This behavior demonstrates that the two end members formed a complete solid solution in the given range of
Chunk # 18:
> the x values. The shoulder peak at...
Did anyone run into the same issue before? If yes, how did you solve it?
Many thanks!!!
Contributor guide
Assessment
This issue has not been assessed yet.