toad.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Mastodon server operated by David Troy, a tech pioneer and investigative journalist addressing threats to democracy. Thoughtful participation and discussion welcome.

Administered by:

Server stats:

230
active users

#docling

0 posts0 participants0 posts today
scy 🔜 WHY<p><a href="https://chaos.social/tags/Docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Docling</span></a> sounds pretty interesting on their website (<a href="https://docling-project.github.io/docling/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">docling-project.github.io/docl</span><span class="invisible">ing/</span></a>), but after having played around with it for a bit, I found the JSON/Markdown/HTML results pretty disappointing.</p><p>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.</p><p>But I'm using the defaults. Any suggestions on, like, different models or engines and stuff?</p>
scy 🔜 WHY<p>Yeah, 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.</p><p><a href="https://chaos.social/tags/docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>docling</span></a> <a href="https://chaos.social/tags/CLI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CLI</span></a> <a href="https://chaos.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a></p>
InstructLab<p>Check out the sessions in the AI track on <a href="https://mastodon.social/tags/RHSummit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RHSummit</span></a> Community Day!</p><p><a href="https://events.experiences.redhat.com/widget/redhat/sum25/SessionCatalog2025?tab.day=20250519&amp;search.communityday=option_1737580301897" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">events.experiences.redhat.com/</span><span class="invisible">widget/redhat/sum25/SessionCatalog2025?tab.day=20250519&amp;search.communityday=option_1737580301897</span></a></p><p>We have topics ranging from <a href="https://mastodon.social/tags/Docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Docling</span></a> to <a href="https://mastodon.social/tags/TrustyAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TrustyAI</span></a>, inferencing to features stores, topped with your favourite <a href="https://mastodon.social/tags/InstructLab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>InstructLab</span></a> tools and <a href="https://mastodon.social/tags/Granite" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Granite</span></a> models. Register and add the sessions to your schedule!</p>
Xavier «X» Santolaria :verified_paw: :donor:<p>LOVE it 💙 </p><p><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"><span class="invisible">https://www.</span><span class="ellipsis">ibm.com/new/announcements/ibm-</span><span class="invisible">adds-open-source-projects-docling-beeaI-and-data-prep-kit-added-to-the-linux-foundation</span></a></p><p><a href="https://infosec.exchange/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <a href="https://infosec.exchange/tags/tech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tech</span></a> <a href="https://infosec.exchange/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> <a href="https://infosec.exchange/tags/ibm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ibm</span></a> <a href="https://infosec.exchange/tags/beeai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>beeai</span></a> <a href="https://infosec.exchange/tags/docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>docling</span></a> <a href="https://infosec.exchange/tags/dataprepkit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dataprepkit</span></a> <a href="https://infosec.exchange/tags/linuxfoundation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linuxfoundation</span></a></p>
Markus Eisele<p>Docling, IBM’s new open-source toolkit, is designed to more easily unearth that information for generative AI applications. The toolkit streamlines the process of turning unstructured documents into JSON and Markdown files that are easy for large language models (LLMs) and other foundation models to digest.</p><p><a href="https://github.com/DS4SD/docling" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/DS4SD/docling</span><span class="invisible"></span></a><br><a href="https://mastodon.online/tags/docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>docling</span></a> <a href="https://mastodon.online/tags/aiml" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>aiml</span></a> <a href="https://mastodon.online/tags/ml" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ml</span></a> <a href="https://mastodon.online/tags/genai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>genai</span></a></p>
Carol Chen<p>Great to see <a href="https://mastodon.org.uk/tags/Docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Docling</span></a> generating much well-deserved buzz and trending on GitHub! This <a href="https://mastodon.org.uk/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> document ingestion tool by <a href="https://mastodon.org.uk/tags/IBMResearch" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IBMResearch</span></a> is already in use by <a href="https://mastodon.org.uk/tags/InstructLab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>InstructLab</span></a> (and soon <a href="https://mastodon.org.uk/tags/RHELAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RHELAI</span></a>). Exciting stuff! </p><p><a href="https://www.redhat.com/en/blog/docling-missing-document-processing-companion-generative-ai" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">redhat.com/en/blog/docling-mis</span><span class="invisible">sing-document-processing-companion-generative-ai</span></a></p>