Nomad changes

2026-06-01 23:40:55 +02:00
parent 72b1a0a6ed
commit b4c07d3693
5723 changed files with 1130655 additions and 0 deletions
--- a/tools/benchmark-harness/fixtures/docx_large_formatted.json
+++ b/tools/benchmark-harness/fixtures/docx_large_formatted.json
@@ -0,0 +1,15 @@
+{
+  "document": "../../../test_documents/docx/test_emf_docx.docx",
+  "file_type": "docx",
+  "file_size": 426097,
+  "expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
+  "metadata": {
+    "description": "Large formatted DOCX - 416KB document with EMF graphics",
+    "category": "docx-complex",
+    "size_class": "medium"
+  },
+  "ground_truth": {
+    "text_file": "../../../test_documents/ground_truth/docx/docx_large_formatted.txt",
+    "source": "vision"
+  }
+}