24 lines
554 B
JSON
24 lines
554 B
JSON
|
{
|
||
|
|
"document": "../../../test_documents/images/sample_text.bmp",
|
||
|
|
"file_type": "bmp",
|
||
|
|
"file_size": 60138,
|
||
|
|
"expected_frameworks": [
|
||
|
|
"kreuzberg",
|
||
|
|
"docling",
|
||
|
|
"markitdown",
|
||
|
|
"pymupdf4llm",
|
||
|
|
"tika",
|
||
|
|
"unstructured"
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"description": "BMP image with 'Hello World' text for OCR testing - 60KB 24-bit BMP",
|
||
|
|
"category": "image",
|
||
|
|
"size_class": "small",
|
||
|
|
"requires_ocr": true
|
||
|
|
},
|
||
|
|
"ground_truth": {
|
||
|
|
"text_file": "../../../test_documents/ground_truth/bmp/image_bmp.txt",
|
||
|
|
"source": "vision"
|
||
|
|
}
|
||
|
|
}
|