Dokumente extrahieren
document
Turn one PDF into structured JSON: header fields, tables as rows and columns, key value pairs and per page full text, each field with its page, position and confidence.
POST https://doc.halowerk.com/documentEingaben
| Feld | Typ | Pflicht | Beschreibung |
|---|---|---|---|
| pdf_base64 | string | Nein | The PDF as base64. Use this or "url", not both. |
| url | string | Nein | Public http or https URL of the PDF. Use this or "pdf_base64", not both. |
| schema | object | Nein | Optional JSON Schema. Every property is looked up in the document and returned with value, confidence and source. A property that is not in the document stays empty. |
| pages | Siehe Schema | Nein | Optional page range, for example "1-5", "2,4,7" or [1,2,3]. At most 20 pages per call. |
| include_raw | boolean | Nein | With a schema, also return header data, tables and key value pairs alongside the mapped result. |
Vollständiges Eingabeschema anzeigen
{
"type": "object",
"properties": {
"pdf_base64": {
"type": "string",
"description": "The PDF as base64. Use this or \"url\", not both."
},
"url": {
"type": "string",
"format": "uri",
"description": "Public http or https URL of the PDF. Use this or \"pdf_base64\", not both."
},
"schema": {
"type": "object",
"description": "Optional JSON Schema. Every property is looked up in the document and returned with value, confidence and source. A property that is not in the document stays empty."
},
"pages": {
"description": "Optional page range, for example \"1-5\", \"2,4,7\" or [1,2,3]. At most 20 pages per call.",
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "integer",
"minimum": 1
}
}
]
},
"include_raw": {
"type": "boolean",
"default": false,
"description": "With a schema, also return header data, tables and key value pairs alongside the mapped result."
}
}
}Veröffentlichtes Eingabebeispiel
{
"include_raw": false,
"pdf_base64": "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"
}Ergebnis & Dokumentation
Maschinenlesbare Dokumentation dieses Hubs
Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.
Weitere Endpunkte dieses Hubs
- Dokumente extrahieren0,006 USDC
ocr
POSThttps://doc.halowerk.com/ocrRead a picture, a scan or a screenshot: full text in reading order, typed blocks with their box on the page, tables as a matrix plus markdown, and every QR code and barcode with its decoded content.