Nomad changes

tools/benchmark-harness/fixtures/pptx/pitch_deck_presentation.json

@@ -0,0 +1,15 @@
+{
+  "document": "../../../../test_documents/pptx/pitch_deck_presentation.pptx",
+  "file_type": "pptx",
+  "file_size": 4610862,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "pptx test: pitch_deck_presentation",
+    "source": "pandoc-generated",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "markdown_file": "../../../../test_documents/ground_truth/pptx/pitch_deck_presentation.md",
+    "source": "pandoc"
+  }
+}

tools/benchmark-harness/fixtures/pptx/powerpoint_bad_text.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/docling/pptx/powerpoint_bad_text.pptx",
+  "file_type": "pptx",
+  "file_size": 35632,
+  "expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from docling test suite",
+    "source": "docling",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/pptx/powerpoint_bad_text.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/pptx/powerpoint_bad_text.md"
+  }
+}

tools/benchmark-harness/fixtures/pptx/powerpoint_issue_2663.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/docling/pptx/powerpoint_issue_2663.pptx",
+  "file_type": "pptx",
+  "file_size": 43385,
+  "expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from docling test suite",
+    "source": "docling",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/pptx/powerpoint_issue_2663.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/pptx/powerpoint_issue_2663.md"
+  }
+}

tools/benchmark-harness/fixtures/pptx/powerpoint_sample.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/docling/pptx/powerpoint_sample.pptx",
+  "file_type": "pptx",
+  "file_size": 45849,
+  "expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from docling test suite",
+    "source": "docling",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/pptx/powerpoint_sample.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/pptx/powerpoint_sample.md"
+  }
+}

tools/benchmark-harness/fixtures/pptx/powerpoint_with_image.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/pptx/powerpoint_with_image.pptx",
+  "file_type": "pptx",
+  "file_size": 76480,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "pptx test: powerpoint_with_image",
+    "source": "pandoc-generated",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/pptx/powerpoint_with_image.txt",
+    "markdown_file": "../../../../test_documents/ground_truth/pptx/powerpoint_with_image.md",
+    "source": "pandoc"
+  }
+}

tools/benchmark-harness/fixtures/pptx/simple.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/pptx/simple.pptx",
+  "file_type": "pptx",
+  "file_size": 34865,
+  "expected_frameworks": ["kreuzberg"],
+  "metadata": {
+    "description": "PPTX test document: simple",
+    "source": "pandoc-generated",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "markdown_file": "../../../../test_documents/ground_truth/pptx/simple.md",
+    "source": "pandoc",
+    "text_file": "../../../../test_documents/ground_truth/pptx/simple.txt"
+  }
+}

tools/benchmark-harness/fixtures/pptx/test.json

@@ -0,0 +1,16 @@
+{
+  "document": "../../../../test_documents/vendored/markitdown/pptx/test.pptx",
+  "file_type": "pptx",
+  "file_size": 277515,
+  "expected_frameworks": ["kreuzberg", "docling", "markitdown", "pandoc", "tika", "unstructured"],
+  "metadata": {
+    "description": "Document from markitdown test suite",
+    "source": "markitdown",
+    "size_category": "small"
+  },
+  "ground_truth": {
+    "text_file": "../../../../test_documents/ground_truth/pptx/test.txt",
+    "source": "pandoc",
+    "markdown_file": "../../../../test_documents/ground_truth/pptx/test.md"
+  }
+}