mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-31 14:34:40 +00:00
31 lines
1.1 KiB
JSON
31 lines
1.1 KiB
JSON
{
|
|
"title": "Docling Actor Input",
|
|
"description": "Options for running Docling CLI on the Apify platform.",
|
|
"type": "object",
|
|
"schemaVersion": 1,
|
|
"properties": {
|
|
"documentUrl": {
|
|
"title": "Document URL",
|
|
"type": "string",
|
|
"description": "URL of the document to process with Docling. Supported formats: images, 'pdf', 'docx', 'pptx', 'xlsx, 'html', 'md', 'xml_pubmed', 'asciidoc', 'xml_uspto'.",
|
|
"prefill": "https://arxiv.org/pdf/2408.09869.pdf",
|
|
"editor": "textfield"
|
|
},
|
|
"outputFormat": {
|
|
"title": "Output Format",
|
|
"type": "string",
|
|
"description": "Specifies the desired output format after processing the document. Supported formats: 'md', 'json', 'html', 'text', 'doctags'.",
|
|
"enum": ["md", "json", "html", "text", "doctags"],
|
|
"default": "md",
|
|
"editor": "select"
|
|
},
|
|
"ocr": {
|
|
"title": "Enable OCR",
|
|
"type": "boolean",
|
|
"description": "If true, OCR will be applied to scanned PDFs for text recognition.",
|
|
"default": true
|
|
}
|
|
},
|
|
"required": ["documentUrl"]
|
|
}
|