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/pdf_scanned_ocr.json
+++ b/tools/benchmark-harness/fixtures/pdf_scanned_ocr.json
@@ -0,0 +1,29 @@
+{
+  "document": "../../../test_documents/pdf/scanned.pdf",
+  "file_type": "pdf",
+  "file_size": 69966,
+  "expected_frameworks": [
+    "kreuzberg",
+    "docling",
+    "markitdown",
+    "mineru",
+    "pdfminer",
+    "pdfplumber",
+    "pdftotext",
+    "pymupdf4llm",
+    "pypdf",
+    "tika",
+    "unstructured"
+  ],
+  "metadata": {
+    "description": "Scanned PDF requiring OCR - 68KB non-searchable document",
+    "category": "pdf-scanned",
+    "size_class": "small",
+    "requires_ocr": true
+  },
+  "ground_truth": {
+    "text_file": "../../../test_documents/ground_truth/pdf/pdf_scanned_ocr.md",
+    "source": "vision",
+    "markdown_file": "../../../test_documents/ground_truth/pdf/pdf_scanned_ocr.md"
+  }
+}