feat(knowledge): read a PDF's text layer before paying for OCR - #6850

Merged

waleedlatif1 merged 6 commits into

feat/pdf-ocr-triage

Aug 19, 2026

Commits on Aug 19, 2026

feat(knowledge): read a PDF's text layer before paying for OCR
waleedlatif1
committed
78bb3d6
fix(knowledge): route a truncated PDF extraction to OCR, and drop the threshold env var
waleedlatif1
committed
fbfe406
fix(knowledge): take the page count from the parse that produced the text
waleedlatif1
committed
47cd6e1
fix(knowledge): chunk a long PDF for Azure OCR instead of refusing it
waleedlatif1
committed
58aa669
fix(knowledge): keep an unsplittable PDF and an empty OCR response honest
waleedlatif1
committed
fc8af91
fix(knowledge): fail a PDF whose OCR only partly came back
waleedlatif1
committed
0dabda6