dadokkio.bsky.social
👤 Joined on 20 November 2024
Followers
Following
Total Posts
@dadokkio.bsky.socialThe first version of my spaCy + Docling integration is here: 📚 process PDFs, Word documents & more 📝 structured text-based output via spaCy's Doc object 🏷 layout spans for sections, headings etc. 🔮 apply NLP pipelines to PDF contents ✂️ chunk your data for RAG github.com/explosion/sp...
Show Post