feat: support multiple images per column in image context#257
Merged
nabinchha merged 4 commits intoJan 28, 2026
Merged
Conversation
johnnygreco
reviewed
Jan 28, 2026
Comment on lines
+56
to
+64
| { | ||
| "type": "image_url", | ||
| "image_url": {"url": "data:image/png;base64,image1base64", "format": "png"}, | ||
| }, | ||
| { | ||
| "type": "image_url", | ||
| "image_url": {"url": "data:image/png;base64,image2base64", "format": "png"}, | ||
| }, | ||
| { |
Contributor
There was a problem hiding this comment.
maybe a dumb question, but is there any case in which you'd like to identify a particular context out of the group of contexts? Here I guess you have index but then you need to know the order.
Contributor
Author
There was a problem hiding this comment.
Yes, you'd need to call out by the order... like "what are the difference between the scene in the 1st and the 3rd picture?"
johnnygreco
previously approved these changes
Jan 28, 2026
Contributor
Author
|
I'll merge this shortly once I verify a test workflow I have looks gtg. |
8501781
johnnygreco
approved these changes
Jan 28, 2026
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
📋 Summary
Adds support for handling multiple images per column in image context configurations. Previously, each image context column could only reference a single image. This change enables columns to contain multiple images as a list or JSON-serialized array.
🔄 Changes
✨ Added
ImageContext.get_contexts()(models.py)🔧 Changed
ModalityContext.get_context()→get_contexts()to return list instead of single dict (models.py) though this is mostly internal and not user facing.ImageContext.get_contexts()to parse and normalize various input formats to list of contexts (models.py)extend()instead ofappend()(llm_completion.py)998d880)🔍 Attention Areas
packages/data-designer-config/src/data_designer/config/models.py- Breaking API change:get_context()→get_contexts()with list return type🤖 Generated with AI