Extract | Developer tools Docs

nace extract https://example.com/invoice.pdf --schema invoice.schema.json -o result
nace extract job:<parse job id> --schema-id sch_... --schema-version 2

Flag	What it does
`-s, --schema SCHEMA`	The fields to extract, as a JSON Schema: a file path, `@FILE`, inline JSON, or `-`.
`--schema-id ID`	A saved schema (`sch_...`) instead, at its latest version.
`--schema-version N`	With `--schema-id`, use version `N`.
`--instructions TEXT`	Extra guidance for filling the fields.
`--no-citations`	Don't say where each field was read: sends `citations.enabled: false`, keeping the rest of `citations`.

Pass exactly one of -s and --schema-id, or name the schema as schema or schema_id in --options. A flag replaces any schema the options name. Neither, both flags, both schema and schema_id in the options, or --schema-version without --schema-id exits 2. Drex has no route that only checks a schema, so there is no --validate: a schema the document service refuses fails the create with 422, before any job.

invoice.schema.json

{
  "type": "object",
  "properties": {
    "invoice_number": { "type": "string" },
    "total": { "type": "number" }
  },
  "required": ["invoice_number", "total"]
}

Point it at a finished parse to avoid parsing, and paying for, the document twice:

nace parse https://example.com/invoice.pdf -o id
# 6f1a2b3c-...
nace extract job:6f1a2b3c-... --schema invoice.schema.json

See Extract.