Skip to main content

Extract data from documents

Extraction pulls structured data from unstructured documents using AI.

Run an extraction job​

  1. Go to Extractions in the sidebar
  2. Click New Extraction
  3. Select an extraction model (or create one)
  4. Choose the documents to process
  5. Click Run

OCR to Excel​

For scanned documents or images, use OCR to Excel to convert them into structured spreadsheets that you can work with.

Best for:

  • Scanned bank statements
  • Image-based PDFs
  • Tables in scanned documents

Validate and export​

After extraction, review the results alongside the source document:

  1. Open the extraction results
  2. Click on any value to see grounding
  3. Correct any errors directly in the interface
  4. Export to Excel when satisfied

Batch extraction​

For processing many similar documents:

  1. Create or select an appropriate extraction model
  2. Select multiple documents
  3. Run extraction as a batch
  4. Review results in bulk
Processing limits

Extraction processes the first 200 pages of each document. For longer documents, split them before processing.