AppsDrive

Search and OCR · Autessa Drive

Text extraction and OCR

Autessa Drive extracts the text of every upload in the background so it can be searched and cited. Text and code keep their real line numbers, PDFs and Office files are extracted page by page, and scanned PDFs and images are read with OCR (optical character recognition) in the language you choose; a status dot on each file shows when it is searchable.

Goes beyond a typical cloud drive
Start free
scanned-lease-1998.pdfOCR · engSAMPLE
LEASE AGREEMENT
The Tenant shall pay rent on the first day of each month…
Initialed: J.R. (handwritten)
Searchable
The text is ready for search.
Processing
Extraction or indexing still running.
Some pages aren’t searchable
A few scanned pages could not be read.
Not searchable
No extractable text, such as a ZIP.
Page 3 read with low confidence. Unclear pages are kept as read.

the-problem.md

Scanned documents are invisible to search

Contracts, leases and forms often exist only as scans. Without OCR they are pictures, so neither people nor agents can find or quote what they say.

README · what you get
  • Text, code, CSV, JSON and Markdown keep their real line numbers.
  • PDFs, Word documents, spreadsheets and presentations are extracted page by page, so results point at a page and a line on that page.
  • Scanned PDFs and images are read with OCR during extraction.
  • Set the OCR language in the drive’s Settings, such as eng, or several joined with +, such as eng+fra.
  • Pages read with low confidence, such as handwriting, keep the text OCR found and are flagged in the preview.
  • A status dot shows Processing, Searchable, Some pages aren’t searchable, or Not searchable.
  • Identical files are extracted only once, even if uploaded to several folders.
  • OCR’d pages count toward the drive’s monthly extracted-pages allowance and are not billed as AI tasks.

how-it-works

How does text extraction and OCR work in Autessa Drive?

  1. 1

    Upload

    Extraction starts on its own after each upload or save.

  2. 2

    Watch the dot

    Processing turns to Searchable when the text is ready.

  3. 3

    Check scanned pages

    The preview lists pages that couldn’t be read and flags low-confidence ones.

  4. 4

    Set the language

    Change the OCR language in Settings for documents in other languages.

every-option

Extraction statuses and options

OptionWhat it does
ProcessingExtraction or indexing still running; preview and download work.
SearchableText ready for search.
Some pages aren’t searchableSome scanned pages couldn’t be read; the preview lists them.
Not searchableNo extractable text (such as a ZIP), extraction failed, or too large to index fully; the first part of a very large file stays searchable.
OCR languageeng, or several joined with +.
DeduplicationIdentical files are extracted once.

permissions

Who can do what?

WhoCan
Drive owner and drive adminsSet the OCR language.
ViewerSee status and search extracted text.
Agent with a Drive toolCheck status with drive_stat and read extracted pages.

AI agents

How AI agents use it

Extraction is what lets an agent read page 4 line 12 of a scanned lease. For pages where the picture matters, such as a chart, stamp or signature, the agent can fetch the page with view on and look at it directly.

Agents only reach files the person they act for can open, and every agent write is a version you can undo.

About Drive tools for agents →

connected

How it connects to the rest of Autessa Drive

DRIVE FEATURE

Search

Searches extracted text.

DRIVE FEATURE

Cited answers

Page and line locators come from extraction.

DRIVE FEATURE

OCR language

Set per drive.

AUTESSA PRODUCT

Redact

Burn in redactions before sharing scans.

faq.md

Questions about text extraction and OCR

Does Autessa Drive OCR scanned PDFs?

Yes. Scanned PDFs and images are read with OCR during extraction, so their text becomes searchable by page and line.

Can OCR read other languages?

Yes. Set the OCR language in the drive’s Settings, as one code such as eng or several joined with +, such as eng+fra.

How do I know a file is searchable?

A small dot next to each file shows Processing, Searchable, Some pages aren’t searchable, or Not searchable.

Is OCR billed as AI?

No. OCR’d pages count toward the drive’s monthly extracted-pages allowance like any other extracted page and are not billed as AI tasks.

Autessa Drive

Try text extraction and OCR in Autessa Drive

Autessa Drive extracts the text of every upload page by page, reads scanned PDFs and images with OCR, and shows a status dot on each file so you know when it is searchable.

Start free

100% customizable, code and all

Make Autessa Drive fully your own.

Use it out of the box, then change anything. Ask Autobot, Autessa’s AI builder, for a new field, screen, report, workflow or agent and it builds it into your copy of the app. Or open the code and edit it yourself. Nothing is locked: the app, its data and its code are yours.

Start free and make it yours