Docs/Ingest/PDF ingest

PDF ingest

Add a PDF and Minerva pulls its text in so you can read, search, and cite it alongside your notes. Most PDFs come in cleanly. Scanned documents — pages that are really just images of text — get one extra step.

Most PDFs

Whether you add a PDF from your computer or from a link, Minerva reads its text page by page and saves it as a source, along with any title, author, and date the PDF already carries. From there it behaves like any other source you've added: readable, searchable, and ready to cite.

Scanned PDFs

Some PDFs are scans, so their pages are pictures rather than text Minerva can read. When that happens, Minerva offers to recognize the text for you and asks before it starts. This runs entirely on your own machine.

If you run it
Minerva reads each page and fills in the text, so the PDF becomes fully readable and searchable like any other source.
If you skip it
The PDF is still saved with its details intact. Nothing is lost — you can open it later and run text recognition whenever you like.
🔍
Screenshot — Offer to recognize a scanned PDF
A short prompt appears after you add a scanned PDF, telling you how many pages it has and letting you start text recognition or skip it for now.
Good to know

A password-protected PDF can't be added until you remove its protection first. And if the same paper reaches you more than one way — say, a PDF now and a link later — see Citing & duplicates for how Minerva keeps them tidy.