mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-30 14:04:27 +00:00
9f86971fad
This commit transitions the Actor from using the full Docling CLI package to the more lightweight docling-serve API. Key changes include: - Redesign Dockerfile to use docling-serve as base image - Update actor.sh to communicate with API instead of running CLI commands - Improve content type handling for various output formats - Update input schema to align with API parameters - Reduce Docker image size from ~6GB to ~600MB - Update documentation and changelog to reflect architectural changes The image size reduction will make the Actor more cost-effective for users while maintaining all existing functionality including OCR capabilities. Issue: No official docling-serve Docker image is currently available, which will be addressed in a future commit. Signed-off-by: Václav Vančura <commit@vancura.dev>
31 lines
986 B
JSON
31 lines
986 B
JSON
{
|
|
"title": "Docling Actor Input",
|
|
"description": "Options for processing documents with Docling via the docling-serve API.",
|
|
"type": "object",
|
|
"schemaVersion": 1,
|
|
"properties": {
|
|
"documentUrl": {
|
|
"title": "Document URL",
|
|
"type": "string",
|
|
"description": "URL of the document to process. Supported formats: PDF, DOCX, PPTX, XLSX, HTML, MD, XML, images, and more.",
|
|
"prefill": "https://arxiv.org/pdf/2408.09869.pdf",
|
|
"editor": "textfield"
|
|
},
|
|
"outputFormat": {
|
|
"title": "Output Format",
|
|
"type": "string",
|
|
"description": "Desired output format after processing the document.",
|
|
"enum": ["md", "json", "html", "text", "doctags"],
|
|
"default": "md",
|
|
"editor": "select"
|
|
},
|
|
"ocr": {
|
|
"title": "Enable OCR",
|
|
"type": "boolean",
|
|
"description": "If enabled, OCR will be applied to scanned documents for text recognition.",
|
|
"default": true
|
|
}
|
|
},
|
|
"required": ["documentUrl"]
|
|
}
|