Fixing Docling missing formulae in edge case #1225
Merged
+38
−9
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
jamesbraza
requested review from
MicPie,
maykcaldas,
mskarlin,
nadolskit,
sidnarayanan and
whitead
dosubot
bot
added
the
size:M
|
Documentation Updates 1 document(s) were updated by changes in this PR: paper-qa How did I do? Any feedback? |
Copilot finished reviewing on behalf of
jamesbraza
December 2, 2025 22:18
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes an edge case where Docling was not properly handling FormulaItem elements in PDFs. The fix was exposed by adding logos to the media duplication test PDF.
Key Changes
- Added support for
FormulaItemin both text extraction and media parsing - Added fallback to
item.origwhen formula text sanitization fails - Updated test expectations to account for logo images being detected
Reviewed changes
Copilot reviewed 3 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| tests/duplicate_media_template.md | Added Wikimedia logos to each page and updated pandoc command instructions |
| packages/paper-qa-docling/tests/test_paperqa_docling.py | Updated expected image counts and deduplication thresholds to account for additional logo images |
| packages/paper-qa-docling/src/paperqa_docling/reader.py | Added FormulaItem handling for text extraction and media parsing, with defensive annotation access |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
whitead
approved these changes
Dec 3, 2025
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Outdated suggestions cannot be applied.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.
Adding a logo to the media duplication PDF somehow now exposes Docling not handling an edge case of
FormulaItemin text