Skip to content

Conversation

@ivichadriana
Copy link

The following PR has the changes to use the user's name instead of the previously defined "Figure X" names.

  • The prompts for (most) agents now include (the same) instruction to cite supplemental figures too. Currently it might now. be needed, since the name the user gives is used and there is no true difference in how main figures and supplemental figures are handled.. but it's there just in case this changes in the future.
  • The most important change is using the user-given name of the figures throughout the text essentially.
  • Considerations for future work: the names would ideally be "flexible" i.e., the text box should be able to be changed, and that should change the order and name that the figures are used in the text. This PR currently only includes using the first given name, not a flexible way.

added two supplemental figure descriptions/keys.
added parameter figure_type to the SingleFigureDescription funct to support either main or supplemental
added imports to figure/agent.py
the counts for figures need to be split into the "supplemental" and the "main separately.
now figure descriptions have 2 types: supplemental and main
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.

1 participant