Michele Dolfi
Michele Dolfi
In general, I see two options which could be useful for you 1. Depending on the downstream application you have in mind, there could be other techniques/formats instead of markdown...
@aditya0yadav sure please ahead. do you have already a PR?
@mkrssg your PR got into some issue with a test which got fixed in `main`. If you update your PR with the latest version we should be able to have...
@nanzai1 there have been some important fixes for docx in the recent releases. Can you please confirm your issues with the latest Docling version? cc: @maxmnemonic
@Swaymaw we will check if adding the packages as extras work for us. Meanwhile, can you please make sure to add those manual dependencies in the CI tests?
> Hope this merge successfully ! @ezscode I think this PR will be superseded by #415
> @dolfim-ibm Should I close this pull request to avoid any confusion? @Swaymaw yes, I'm closing as discussed in #415 .
Interesting, I would anyway suggest bringing it up as a feature for Dify itself.
I think we should switch all function typing to Pydantic BaseModel.
> 1. If we input a `.xml` file which do not match the JATS schema, docling raises an error: > > > ``` > docling.exceptions.ConversionError: File format not allowed: /home/lum/Documents/public/docling/tests/data/pubmed/test.xml...