16 lines
497 B
JSON
16 lines
497 B
JSON
{
|
|
"document": "../../../test_documents/docx/word_image_anchors.docx",
|
|
"file_type": "docx",
|
|
"file_size": 18560,
|
|
"expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
|
|
"metadata": {
|
|
"description": "DOCX with embedded images and anchors - 18KB document",
|
|
"category": "docx-images",
|
|
"size_class": "small"
|
|
},
|
|
"ground_truth": {
|
|
"text_file": "../../../test_documents/ground_truth/docx/docx_images.txt",
|
|
"source": "vision"
|
|
}
|
|
}
|