docling-project / docling-project/docling
Hybrid Chunker should enable bypassing semantic chunking for certain doc_item types
Open
enhancement
- Dominant language
- Python
- Stars
- 66.4k
- Forks
- 4.8k
- Avg merge
- 2d 21h
- Merged PRs (30d)
- 84
Description
### Requested feature
The Docling Hybrid Chunker should support NOT splitting certain doc_item types.
I would prefer not to split a table or a code block using the semantic splitter.
Contributor guide
Assessment
This issue has not been assessed yet.