23 lines
496 B
JSON
23 lines
496 B
JSON
|
{
|
||
|
|
"document": "../../../test_documents/images/ocr_image.jpg",
|
||
|
|
"file_type": "jpg",
|
||
|
|
"file_size": 73717,
|
||
|
|
"expected_frameworks": [
|
||
|
|
"kreuzberg",
|
||
|
|
"docling",
|
||
|
|
"markitdown",
|
||
|
|
"mineru",
|
||
|
|
"pymupdf4llm",
|
||
|
|
"tika",
|
||
|
|
"unstructured"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"description": "Image requiring OCR - Hello World test image",
|
||
|
|
"category": "ocr"
|
||
|
|
},
|
||
|
|
"ground_truth": {
|
||
|
|
"text_file": "../../../test_documents/ground_truth/jpg/image_ocr.md",
|
||
|
|
"source": "mistral-pixtral"
|
||
|
|
}
|
||
|
|
}
|