docling-project / docling-project/docling-eval
[feature-request]: Add ParseBench support
Open
- Dominant language
- Python
- Stars
- 77
- Forks
- 14
- PR merge metrics
- No merged PRs in 30d
Description
It'd be nice to add support for [ParseBench](https://huggingface.co/datasets/llamaindex/ParseBench) to evaluate docling alongside all the existing datasets here. Happy to help contribute if this sounds interesting
Contributor guide
Research direction
Inspect the existing dataset integrations and evaluation entry points in docling-eval to see how datasets are registered and run. Use the linked Hugging Face ParseBench dataset as the input, and consider the work complete when ParseBench can be selected and evaluated alongside the existing datasets.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- machine-learning, testing
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 55/100