Christoph Auer
Christoph Auer
Many thanks!
@mmb78 Could you provide an affected PDF for us to check with? Thanks.
@MahmoudAtef999 thanks, I can reproduce this issue and will investigate further. The expectation should be that row spans are detected correctly here. On a sidenote, the _source of truth_ is...
@MahmoudAtef999 We are in the process of re-training the table model, and your sample will act as a test case. There will be a future release that improves on the...
@Manamama thanks for your report. Setting the OCR language is currently supported in the python interface, but not on the CLI or through environment variables. Example: ```python input_doc_path = Path("./tests/data/2206.01062.pdf")...
It appears that this issue is addressed in multiple places and can be closed. 1. Using `pipeline_options.ocr_options.force_full_page_ocr = True` (or `--force-ocr` on the CLI) in case you have a PDF...
@InbarShapira can you please deliver some detail which overlapping clusters and duplicated cells you are seeing with the example, that would help. You can also use the docling CLI with...
@ninedesu Since docling provides full control over GPU accelerators now, this should no longer be of concern. Please re-open this issue if you still find issues. Thanks.
@jiraiya1729 Thanks for the report. Mathematical expressions in digital PDFs are often encoded in various obfuscated and incomplete ways, such as seen in your case. We are actively working on...
@harinisri2001 I hope your issue is addressed with the pointers from @dolfim-ibm. I will close this until further feedback.