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/user_report_encoding.json
+++ b/tools/benchmark-harness/fixtures/pdf/user_report_encoding.json
@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/user_reports/mp_axmp_rec_en.pdf",
+  "file_type": "pdf",
+  "file_size": 408353,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "EU health document with STX (U+0002) characters where hyphens should be. PDF font encoding issue. Community report 2026-03-25.",
+    "source": "user_report",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/pdf/mp_axmp_rec_en.txt",
+    "markdown_file": "../../../../test_documents/ground_truth/pdf/mp_axmp_rec_en.md",
+    "source": "mistral-pixtral"
+  }
+}