Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Upgrade Docling to v2.21 #1031

Merged
merged 3 commits into from
Feb 10, 2025
Merged

Upgrade Docling to v2.21 #1031

merged 3 commits into from
Feb 10, 2025

Conversation

dolfim-ibm
Copy link
Member

@dolfim-ibm dolfim-ibm commented Feb 10, 2025

Why are these changes needed?

Upgrade of Docling to the latest version (2.21.0). This will introduce, among others

  • Multiple fixes in document parsing. Both quality and speed.
  • Improved support for accelerators
  • Support for right-to-left
  • Fixes and improvement for parsing markdown inputs
  • Fixes in docx and pptx input formats
  • Support for XML inputs such as USPTO patents and PubMed articles
  • More OCR engines (e.g. native macos OCR). (not yet enabled in DPK)
  • Support for Python 3.13
  • Support for picture classification, code and formula enrichment, figure captioning via vlm (not yet enabled in DPK)
  • ..and much more

Related issue number (if any).

Resolves #1011.

@dolfim-ibm dolfim-ibm requested review from daw3rd and touma-I February 10, 2025 16:08
Copy link
Collaborator

@touma-I touma-I left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for the quick action !! Will merge it and build a new wheel by end of day today

@touma-I touma-I merged commit 2dca254 into dev Feb 10, 2025
14 checks passed
@touma-I touma-I deleted the docling-2.21 branch February 10, 2025 23:20
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Bug] pdf2parquet duplicating lines
2 participants