31 lines
833 B
JSON
31 lines
833 B
JSON
{
|
|
"document": "../../../test_documents/pdf/google_doc_document.pdf",
|
|
"file_type": "pdf",
|
|
"file_size": 80100,
|
|
"expected_frameworks": [
|
|
"kreuzberg",
|
|
"docling",
|
|
"markitdown",
|
|
"mineru",
|
|
"pdfminer",
|
|
"pdfplumber",
|
|
"pdftotext",
|
|
"pymupdf4llm",
|
|
"pypdf",
|
|
"tika",
|
|
"unstructured"
|
|
],
|
|
"metadata": {
|
|
"description": "Google Docs exported PDF - 78KB document generated from Google Docs to test extraction of cloud-native document formats",
|
|
"category": "pdf-generated",
|
|
"size_class": "small",
|
|
"source": "google-docs",
|
|
"special_handling": "cloud_generated"
|
|
},
|
|
"ground_truth": {
|
|
"text_file": "../../../test_documents/ground_truth/pdf/pdf_google_docs.txt",
|
|
"source": "vision",
|
|
"markdown_file": "../../../test_documents/ground_truth/pdf/pdf_google_docs.md"
|
|
}
|
|
}
|