READ · Document Extraction
Start an extraction
Extract your own fields from one or many documents.
POSThttps://api.rowland.ai/v1/read/extractions
Body parameters
documentsstring[]RequiredThe documents to read.
schemaobjectRequiredThe fields you want, as a JSON Schema. Each property’s
descriptiontells Rowland what to look for.perstringOptionaldocument: one record per document.item: one record per item found, such as every tract or every well.itemstringOptionalWith
per: item, what one item is, such astract.instructionsstringOptionalAnything the schema cannot say, such as which royalty to use when a lease states two.
Returns
202Accepted: the work continues in the background. For failures, see Errors.
idstringThe extraction ID, starting
ext_.statusstringrunning, thencompletedorfailed.
curl -X POST "https://api.rowland.ai/v1/read/extractions" \
-H "x-api-key: $ROWLAND_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"documents": [
"doc_2Hq8kLm4Vt",
"doc_7Rw3nPz9Xc"
],
"schema": {
"type": "object",
"properties": {
"lessor": {
"type": "string",
"description": "Every lessor named"
},
"royalty": {
"type": "number",
"description": "Landowner royalty as a decimal, e.g. 0.1875"
},
"depth_limit": {
"type": "string",
"description": "Any depth limitation, as written"
}
}
},
"per": "document"
}'Response202
{
"object": "extraction",
"id": "ext_9Fd2sQw7Lp",
"status": "running",
"documents": 2,
"created_at": "2026-11-20T15:10:00Z"
}