Enhanced PDF Parsing

You can parse complex PDFs with higher accuracy, including multi‑column layouts, nested tables, headers and footers, scanned documents via OCR, and embedded links or bookmarks. Your ingested content is cleaner and search relevance improves. Processing is also faster and supports larger files, so bulk imports complete more reliably during peak hours.

Available today on all plans.

Improvements

• Improve PDF parsing capabilities for better table extraction, multi‑column handling, OCR on scans, and faster processing; reprocess files to apply

Fixes

• Bug: Fix Google Drive connection error so you can connect and sync without intermittent authorization failures

• Bug: crawls and scheduled jobs no longer blocked by intermittent limit‑check failures