Extraction guide

Extract a packing slip PDF to JSON

Everything below is the response the live API returned for a packing slip, generated when this page was built. Not a description of what it would return — the output itself, including what it scored low on.

Who this is for

Third-party logistics and inventory software receiving goods against a purchase order.

The job, in the words people search for: “read packing slips into a warehouse system”.

What makes this shape awkward

Quantities are the only numeric column and they are small integers, so numeric contrast is weak evidence. Header detection has to fall back on the font the header row is set in.

The measured result

Pages read	1
Time	12 ms (12 ms/page)
Labelled fields found unprompted	5
Tables	1 (12 rows)
Input	packing-slip.pdf (31 KB — synthetic, generated from a spec in the repo; real documents of this type cannot be published)

Fields, with a schema

Ask for the fields you want by the label printed on the page. Each answer carries the text exactly as printed (raw), the value coerced to the type you asked for, a confidence, and a bounding box you can draw on the page to check it.

curl -X POST https://api.pdfcraft.dev/v1/extract \
  -H "Authorization: Bearer $PDFCRAFT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "file": "<base64 of your packing slip>",
    "schema": {
      "shipment_number": "string",
      "purchase_order": "string",
      "ship_date": "date"
    }
  }'

What came back

Field	raw	value	confidence
`shipment_number`	SHP-771204	`"SHP-771204"`	60%
`purchase_order`	PO-88213	`"PO-88213"`	60%
`ship_date`	2026-03-18	`"2026-03-18"`	70%

Every label it found without being asked

Send no schema and you get all of these, keyed by the label as printed. Useful for discovering what a new supplier’s layout actually contains before you write a schema against it.

Shipment Number, Purchase Order, Ship Date, Carrier, Tracking Number

Tables

SKU · Item · Ordered · Shipped · Backordered · 12 rows × 5 columns · page 1

Table confidence 90%. Header confidence 100% — the first row was promoted out of the data.

SKU	Item	Ordered	Shipped	Backordered
SKU-4100	Hex bolt M8	11	10	1
SKU-4107	Washer, nylon	7	7	0
SKU-4114	Spring clip	2	2	0

First 3 of 12 rows.

With options.rows_as_objects, the same row keyed by its header:

{
  "SKU": "SKU-4100",
  "Item": "Hex bolt M8",
  "Ordered": "11",
  "Shipped": "10",
  "Backordered": "1"
}

What this does not do

No OCR. This reads the PDF’s text layer. A scanned or photographed packing slip has no text layer and returns 422 extraction_failed with the page numbers that were blank — deliberately, and quickly, so you can route it somewhere that does OCR rather than waiting on a guess.
No model. Run the same file twice and you get the same bytes back. That is the trade: it cannot infer a field that is not printed, and it cannot hallucinate one either.
Ambiguity is reported, not resolved. A date like 03/04/2026 stays a string, and a bare $ returns a null currency, because guessing wrong on either is not something you can recover from downstream.

Try it on your own packing slip

The playground takes a file and shows the same JSON, with every bounding box drawn over the page. No key and no signup for the first few; a free key gives you 100 pages a month.