Files
fil/tools/benchmark-harness/fixtures/image_text.json

26 lines
616 B
JSON
Raw Normal View History

2026-06-01 23:40:55 +02:00
{
"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"
}
}