hjess/fil
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Nomad changes
All checks were successful
Deploy fil (kreuzberg) / deploy (push) Successful in 49s
Details

Browse Source
This commit is contained in:
Henrik Jess Nielsen
2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
tools/benchmark-harness/fixtures/txt/2203.01017v2.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/2203.01017v2.doctags.txt",
"file_type": "txt",
"file_size": 66446,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/2203.01017v2.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/2206.01062.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/2206.01062.doctags.txt",
"file_type": "txt",
"file_size": 55990,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/2206.01062.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/2305.03393v1-pg9.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/2305.03393v1-pg9.doctags.txt",
"file_type": "txt",
"file_size": 3210,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/2305.03393v1-pg9.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/2305.03393v1.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/2305.03393v1.doctags.txt",
"file_type": "txt",
"file_size": 39960,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/2305.03393v1.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/amt_handbook_sample.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/amt_handbook_sample.doctags.txt",
"file_type": "txt",
"file_size": 4597,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/amt_handbook_sample.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/code_and_formula.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/code_and_formula.doctags.txt",
"file_type": "txt",
"file_size": 6418,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/code_and_formula.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/multi_page.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/multi_page.doctags.txt",
"file_type": "txt",
"file_size": 12778,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/multi_page.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/picture_classification.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/picture_classification.doctags.txt",
"file_type": "txt",
"file_size": 4075,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/picture_classification.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/redp5110_sampled.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/redp5110_sampled.doctags.txt",
"file_type": "txt",
"file_size": 44745,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/redp5110_sampled.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/right_to_left_01.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/right_to_left_01.doctags.txt",
"file_type": "txt",
"file_size": 2658,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/right_to_left_01.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/right_to_left_02.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/right_to_left_02.doctags.txt",
"file_type": "txt",
"file_size": 2235,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/right_to_left_02.doctags.txt",
"source": "vision"
}
}

15
tools/benchmark-harness/fixtures/txt/right_to_left_03.doctags.json Normal file
View File

@@ -0,0 +1,15 @@
{
"document": "../../../../test_documents/vendored/docling/txt/right_to_left_03.doctags.txt",
"file_type": "txt",
"file_size": 3199,
"expected_frameworks": ["kreuzberg", "pandoc", "pymupdf4llm", "tika", "unstructured"],
"metadata": {
"description": "Document from docling test suite",
"source": "docling",
"size_category": "small"
},
"ground_truth": {
"text_file": "../../../../test_documents/ground_truth/txt/right_to_left_03.doctags.txt",
"source": "vision"
}
}