MoongraphMoongraph

Extraction

Extract structured data from documents using schemas.

Extraction

Extraction lets you pull structured information from documents automatically. Define what you're looking for with a schema, run extraction on selected documents, and get organized results you can export.

Getting started

How it works

  1. Create a schema — Define field names and types (text, number, enum, etc.)
  2. Select documents — Choose individual documents or a folder (up to 50)
  3. Run extraction — Processing happens in the background
  4. View results — See structured data with provenance
  5. Export CSV — Download for analysis in Excel, Sheets, etc.

The Extract page

Navigate to Extract in the sidebar to see:

TabContents
RunsYour extraction jobs — status, results, export
SchemasAvailable templates — yours, team, admin templates

Schemas

A schema defines what to extract:

  • Field names — Column headers for your results
  • Field types — Text, Number, Boolean, Enum, Object, Array
  • Instructions — Natural language guidance for accuracy

Create your own or clone from templates.

Provenance

Every extracted value includes the source quote — the exact text passage it came from. Click to verify accuracy or check context.

Processing speed

Extraction processes roughly 10 pages per minute.

Documents × PagesEstimated time
10 × 20 = 200 pages~20 minutes
50 × 20 = 1,000 pages~100 minutes

Limits

LimitValue
Documents per run (folder)50
Fields per schema50
Items extracted per document5,000

Learn more

On this page