Michele Dolfi comments

Results 54 comments of


                                            Michele Dolfi

trafficstars

Result viewer application

Short update in the thread. We are finalizing an actual typescript/javascript SDK which will allow to operate directly with all the features of the DoclingDocument format.

docs: fix parameter in usage.md

@capsenz thanks for your first contribution. Before we can approve and merge this, we require you to rebase your commit with a sign-off. See the the [CONTRIBUTING.md](https://github.com/DS4SD/docling/blob/main/CONTRIBUTING.md) guidelines. In practice,...

When the file name has Chinese, an error occurred when converting pdf

We cannot reproduce the issue. Could it be something specific to the Windows OS? Can you please share the stackstrace produced?

[FEAT] Make installation of non-essential dependencies optional

When this Python extension is implemented, we could switch to it https://peps.python.org/pep-0771/

Can't find a way to use `ImageRefMode.EMBEDDED` in `generate_multimodal_pages`

Thanks for the report, we will have a look and first update the examples.

Can't find a way to use `ImageRefMode.EMBEDDED` in `generate_multimodal_pages`

I'm closing this issue in favour of a broader story in #835. New examples for multimodal exports and datasets creation are coming.

[Feature] Create vector embeddings

Done in https://github.com/IBM/data-prep-kit/pull/461

[Feature] Capability to chunk text for RAG systems

Done in https://github.com/IBM/data-prep-kit/pull/461

[Bug] text_encoder tests are not verifying the resulting embeddings to avoid floating point rounding errors

No, I don't think anything was done here.

[Feature] Create a demo notebook for RAG

A first draft of the notebook is here https://github.com/IBM/data-prep-kit/pull/461. At the moment it still depends on some internal transforms which are being pushed soon.