result.result_type: "extract". not_found on a
field is an answer about the document. The job status is still succeeded.
{
"result_type": "extract",
"data": { "invoice_number": "INV-1042", "total": null },
"fields": [
{
"path": "/invoice_number",
"value": "INV-1042",
"status": "found",
"confidence": null,
"citations": [
{
"location": { "kind": "page_region", "page": 1, "polygons": [] },
"source_text": "Invoice INV-1042"
}
]
},
{
"path": "/total",
"value": null,
"status": "not_found",
"citations": []
}
],
"schema_id": null,
"schema_version": null,
"units": 1,
"warnings": []
}
Payload
| Field | Meaning |
|---|---|
data | Object shaped by your schema. Missing values are null, not omitted |
fields | One entry per schema field, including not_found. A missing value is never silently dropped |
schema_id / schema_version | Set when you used a catalog schema. Null for an inline schema |
units | Billable units for this extraction |
warnings | Non-fatal notes, such as instructions that no declared field can satisfy |
instructions on the request cannot add undeclared result fields.
Fields
| Field | Meaning |
|---|---|
path | JSON Pointer of this schema leaf (/invoice_number). Stable join key between data and fields |
value | Extracted scalar for this path, or null when the field was not found. Nested non-scalars are returned as JSON strings |
status | Whether this leaf was filled. found has a value. not_found means the document was examined and the field is absent — the job still succeeded. ambiguous means a value is present but could not be uniquely chosen |
confidence | Evidence-support score for a found top-level scalar when the runtime produced one. null for nested paths, arrays, not_found, and unverifiable fields |
citations | Where the value was read: a location plus optional source_text quote. Empty when citations are off or the field was not found. PDF/image citations include a polygon when Parse matched the quote to a layout block |