Home · Docs · Import + Export · Importing PDF

Importing PDF

PDF import goes through LlamaParse — layout-aware extraction that handles tables, multi-column layouts, and scanned (OCR) documents. Counts against your AI quota.

PDFs convert server-side via /api/ai/convert-pdf, which uses LlamaParse for layout-aware extraction. We chose LlamaParse over a local PDF.js extraction because real-world PDFs (multi-column papers, scanned forms, table-heavy reports) need actual layout reconstruction — and a local fallback would be worse, so we don’t bother.

My Documents
  • Converting…
  • kyoto-trip
  • Pricing notes
Converting research-paper.pdf…Page 4 of 12

What LlamaParse handles well

What’s harder

TypeResult
Forms with overlapping fieldsOK, but read-order may need cleanup
Heavy graphics / diagramsReplaced with placeholder image markers or dropped
Math equations (rendered as text)Captured as text approximation; full LaTeX is not recovered
Two-page spreads at full bleedRead column by column; layout reconstruction depends on the PDF’s text frames
Watermarks / page numbers / headers/footersBest-effort filtered out; some may remain
Right-to-left scriptsSupported; quality depends on the source font

Auth and quota

PDF import is not anonymous — you must be signed in. The endpoint enforces:

If you hit the quota mid-import, the error message tells you what plan resets are available:

Conversion quota reached for this month. Pro raises the cap.

How the import looks

PDFs aren’t instant — typical conversion takes a few seconds per page. The pipeline:

  1. You drop the PDF; sweetdocs uploads it to /api/ai/convert-pdf with your auth token
  2. The server queues a LlamaParse job
  3. Progress flows back as the response streams; the doc is created on success
  4. The Markdown body lands in the new document; the title is the filename minus .pdf

Warnings from the converter (e.g., “page 4 had no extractable text”) show as a toast and are recorded in the doc — usually as a placeholder where the page would have gone.

What you’ll see in the result

Cleanup tips after a PDF import

PDF source varies widely. After import, the AI Author panel is the quickest cleanup tool:

What’s not in v1

MissingNotes
Selecting specific page ranges to importWhole file converts
OCR language hintsLlamaParse auto-detects
Form-field extraction as structured dataForms come through as text
Watermark removalBest-effort only
Hyperlink preservation from PDF annotationsUsually retained, but quality varies