docling-project / docling-project/docling-sdg
Improve the generation of QA pairs on tables
Open
enhancement
- Dominant language
- Python
- Stars
- 51
- Forks
- 21
- PR merge metrics
- No merged PRs in 30d
Description
The current version supports Q&A generation on tabular data.
With the [ChunkingDocSerializer](https://github.com/docling-project/docling-core/blob/main/docling_core/transforms/chunker/hierarchical_chunker.py#L175 we can leverage tables from chunks in markdown format and fine tuned the LLM prompts.
Contributor guide
Assessment
This issue has not been assessed yet.