Deduplicate image description by moving it to img alt text#999
Open
Br1an67 wants to merge 1 commit intodatalab-to:masterfrom
Open
Deduplicate image description by moving it to img alt text#999Br1an67 wants to merge 1 commit intodatalab-to:masterfrom
Br1an67 wants to merge 1 commit intodatalab-to:masterfrom
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Fix image descriptions appearing twice in output when
use_llm=True— once as a separate text paragraph and once embedded with the image.When the LLM generates an image description,
Picture/Figure.assemble_html()creates a<p role='img'>paragraph with the description. When images are also being extracted, this description paragraph ends up in the output alongside the<img>tag, causing duplication.The fix extracts the description from the
<p role='img'>tag, moves it into the<img>tag'saltattribute, and removes the separate paragraph. This produces clean output like:Instead of the duplicated:
Closes #955
Changes
HTMLRenderer.extract_html()to extract description fromp[role='img']and use it as the<img>alt text