Repository navigation
fix(import): keep short pdfs, stitch long tables and stop doubled or dropped charts - #131
Merged
vishwajeet-13 merged 1 commit intoOct 10, 2026
Conversation
…dropped charts - page plan: a doc with no page-worthy section keeps its first section as the page, and children of a leading section fold with it instead of raising KeyError - figures: image tags the vlm made up mark where crops go instead of turning into full-page images - tables: a table over three or more pages is joined at every page break, and its section keeps the pages the rows came from - tables: lettered sub-step rows are no longer merged into the numbered row above - contents: a numbered data table under its own header is not read as a contents page - figures: a chart followed by a table typed on the page is kept - boilerplate: the low repeat threshold applies only to the outermost edge line, so repeated section headings survive
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Follow-up to #124. These fixes were merged in #129, but into the
fix/nephrology-fidelitybranch after #124 had already landed, so they never reachedmain. This is the same commit applied to currentmain.KeyErrorScreenshots
Same PDFs imported on
main(before) and on this branch (after).Short PDF: the whole wiki was empty, now the memo shows
Image tag the model made up: the full PDF page was pasted in, now only the chart is cropped
Table over 3 pages: split in two with the header repeated, now one table
Two-column paper: the chart was dropped, now it sits above its caption