Veganism Social

Thomas Vitale ☀️Arconia is a framework I've been building on top of Java and Spring Boot, focusing on developer experience and cloud native. In the latest release, I shipped a new module to integrate with Docling, an open-source, AI-powered, advanced document processor. JBang makes it really convenient to run!Code: <a href="https://gist.github.com/ThomasVitale/06932a1e872935de7d4587a4519eb76f" rel="nofollow noopener" translate="no" target="_blank">https://gist.github.com/ThomasVitale/06932a1e872935de7d4587a4519eb76f</a>Docs: <a href="https://arconia.io/docs/arconia/latest/integrations/docling/" rel="nofollow noopener" translate="no" target="_blank">https://arconia.io/docs/arconia/latest/integrations/docling/</a>Docling: <a href="https://docling-project.github.io/docling/" rel="nofollow noopener" translate="no" target="_blank">https://docling-project.github.io/docling/</a><a href="https://mastodon.online/tags/Java" class="mention hashtag" rel="nofollow noopener" target="_blank">#Java</a> <a href="https://mastodon.online/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://mastodon.online/tags/Docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#Docling</a>

scy<a href="https://chaos.social/tags/Docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#Docling</a> sounds pretty interesting on their website (<a href="https://docling-project.github.io/docling/" rel="nofollow noopener" translate="no" target="_blank">https://docling-project.github.io/docling/</a>), but after having played around with it for a bit, I found the JSON/Markdown/HTML results pretty disappointing.OCR was mediocre to bad, table/heading/list recognition too. It didn't even add line breaks between the lines in the address part of a letter.But I'm using the defaults. Any suggestions on, like, different models or engines and stuff?

scyYeah, colors and formatting in CLI tools is usually a good thing, but if your --help looks like this, you probably need to take a step back.<a href="https://chaos.social/tags/docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#docling</a> <a href="https://chaos.social/tags/CLI" class="mention hashtag" rel="nofollow noopener" target="_blank">#CLI</a> <a href="https://chaos.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#Python</a>

Xavier «X» Santolaria :verified_paw: :donor:LOVE it 💙 <a href="https://www.ibm.com/new/announcements/ibm-adds-open-source-projects-docling-beeaI-and-data-prep-kit-added-to-the-linux-foundation" rel="nofollow noopener" translate="no" target="_blank">https://www.ibm.com/new/announcements/ibm-adds-open-source-projects-docling-beeaI-and-data-prep-kit-added-to-the-linux-foundation</a><a href="https://infosec.exchange/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://infosec.exchange/tags/tech" class="mention hashtag" rel="nofollow noopener" target="_blank">#tech</a> <a href="https://infosec.exchange/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#opensource</a> <a href="https://infosec.exchange/tags/ibm" class="mention hashtag" rel="nofollow noopener" target="_blank">#ibm</a> <a href="https://infosec.exchange/tags/beeai" class="mention hashtag" rel="nofollow noopener" target="_blank">#beeai</a> <a href="https://infosec.exchange/tags/docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#docling</a> <a href="https://infosec.exchange/tags/dataprepkit" class="mention hashtag" rel="nofollow noopener" target="_blank">#dataprepkit</a> <a href="https://infosec.exchange/tags/linuxfoundation" class="mention hashtag" rel="nofollow noopener" target="_blank">#linuxfoundation</a>

Recent searches

Search options

Administered by:

Server stats:

#docling