Skip to content

Conversation

@Paul-Cornell
Copy link
Collaborator

@Paul-Cornell Paul-Cornell commented Nov 19, 2025

Main updates include:

  • Use Gemini 2.0 Flash for VLM during partitioning (tried all available VLMs and this one gave the most accurate output on the first pass for international character sets).
  • Steer toward using latest providers/models for enrichments, wherever possible.
  • Make all chunking steps optional except for Chunk By Character.
  • Make embedding step optional.

Copy link
Collaborator

@ron-unstructured ron-unstructured left a comment

Choose a reason for hiding this comment

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

LGTM

@Paul-Cornell Paul-Cornell merged commit cbf9b20 into main Nov 20, 2025
3 checks passed
@Paul-Cornell Paul-Cornell deleted the walkthrough-models-2025-11-19 branch November 20, 2025 17:41
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.

3 participants