26 lines
616 B
JSON
26 lines
616 B
JSON
{
|
|
"document": "../../../test_documents/images/jpn_vert.jpeg",
|
|
"file_type": "jpeg",
|
|
"file_size": 35012,
|
|
"expected_frameworks": [
|
|
"kreuzberg",
|
|
"docling",
|
|
"markitdown",
|
|
"pymupdf4llm",
|
|
"tika",
|
|
"unstructured"
|
|
],
|
|
"metadata": {
|
|
"description": "Vertical Japanese text image requiring OCR - 35KB JPEG",
|
|
"category": "image-text",
|
|
"size_class": "small",
|
|
"requires_ocr": true,
|
|
"languages": ["ja"],
|
|
"text_orientation": "vertical"
|
|
},
|
|
"ground_truth": {
|
|
"text_file": "../../../test_documents/ground_truth/jpeg/image_text.md",
|
|
"source": "mistral-pixtral"
|
|
}
|
|
}
|