Fix year caching not updating for new PDFs#177
Open
TyHil wants to merge 1 commit into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
A bit ago I switched to caching budget parsing using just the year (ex. "2025") instead of a hash of the whole prompt. This was because it seemed the prompt was not always consistent, likely due to some inconsistencies in
pdftotext.Well I realized the one time we will want it to regenerate the parsing is when a new PDF is uploaded (new as in another PDF not a new version of a preexisting PDF). Like for example 2026 only has the planned budget PDF but later the "AFR" PDF will be uploaded and we'll want the parsing to regenerate then to include all that new data.
This fixes this by hashing based off the file names. So the AI won't rerun just because of small changes due to
pdftotextbut will rerun when the hash "2026-fy26utdallasoperatingbudget(pdf).json" changes to "2026-afrfy26exhibitsa-c(pdf)fy26utdallasoperatingbudget(pdf).json"I did not enjoy how some of the file names have non-ASCII space characters in them :/ Thanks UTD
Already uploaded new renamed cache files to the bucket