Introducing Hybrid Chunker for leveraging both document structure and tokenization awareness #548
vagenas
announced in
Announcements
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
🎉 We are happy to announce that, as of docling 2.9.0 (or docling-core 2.8.0), Docling now provides Hybrid Chunker, an additional chunker implementation that uses a hybrid approach, applying tokenization-aware refinements on top of document-based hierarchical chunking.
👉 For more details, check out the docs.
🧪 Get started with a sample notebook.
Beta Was this translation helpful? Give feedback.
All reactions