feat(sdk.v2): Add HTML and Markdown artifact types

sdk/python/kfp/dsl/io_types.py

@@ -19,7 +19,6 @@
 import os
 from typing import Dict, Generic, List, Optional, Type, TypeVar, Union
 
-
 _GCS_LOCAL_MOUNT_PREFIX = '/gcs/'
 _MINIO_LOCAL_MOUNT_PREFIX = '/minio/'
 _S3_LOCAL_MOUNT_PREFIX = '/s3/'
@@ -399,6 +398,28 @@ def load_confusion_matrix(self, slice: str, categories: List[str],
     self._update_metadata(slice)
 
 
+class HTML(Artifact):
+  """An artifact representing an HTML file."""
+  TYPE_NAME = 'system.HTML'
+
+  def __init__(self,
+               name: Optional[str] = None,
+               uri: Optional[str] = None,
+               metadata: Optional[Dict] = None):
+    super().__init__(uri=uri, name=name, metadata=metadata)
+
+
+class Markdown(Artifact):
+  """An artifact representing an Markdown file."""
+  TYPE_NAME = 'system.Markdown'
+
+  def __init__(self,
+               name: Optional[str] = None,
+               uri: Optional[str] = None,
+               metadata: Optional[Dict] = None):
+    super().__init__(uri=uri, name=name, metadata=metadata)
+
+
 T = TypeVar('T')
 
 
@@ -407,7 +428,6 @@ class InputAnnotation():
   pass
 
 
-
 class OutputAnnotation():
   """Marker type for output artifacts."""
   pass
@@ -419,7 +439,6 @@ class OutputAnnotation():
 # Input = typing.Annotated[T, InputAnnotation]
 # Output = typing.Annotated[T, OutputAnnotation]
 
-
 # Input represents an Input artifact of type T.
 Input = Union[T, InputAnnotation]
 
@@ -430,16 +449,16 @@ class OutputAnnotation():
 def is_artifact_annotation(typ) -> bool:
   if hasattr(typ, '_subs_tree'):  # Python 3.6
     subs_tree = typ._subs_tree()
-    return len(subs_tree) == 3 and subs_tree[0] == Union and subs_tree[2] in [InputAnnotation, OutputAnnotation]
+    return len(subs_tree) == 3 and subs_tree[0] == Union and subs_tree[2] in [
+        InputAnnotation, OutputAnnotation
+    ]
 
   if not hasattr(typ, '__origin__'):
     return False
 
-
   if typ.__origin__ != Union and type(typ.__origin__) != type(Union):
     return False
 
-
   if not hasattr(typ, '__args__') or len(typ.__args__) != 2:
     return False
 
@@ -448,28 +467,31 @@ def is_artifact_annotation(typ) -> bool:
 
   return True
 
+
 def is_input_artifact(typ) -> bool:
   """Returns True if typ is of type Input[T]."""
   if not is_artifact_annotation(typ):
     return False
 
   if hasattr(typ, '_subs_tree'):  # Python 3.6
     subs_tree = typ._subs_tree()
-    return len(subs_tree) == 3 and subs_tree[2]  == InputAnnotation
+    return len(subs_tree) == 3 and subs_tree[2] == InputAnnotation
 
   return typ.__args__[1] == InputAnnotation
 
+
 def is_output_artifact(typ) -> bool:
   """Returns True if typ is of type Output[T]."""
   if not is_artifact_annotation(typ):
     return False
 
   if hasattr(typ, '_subs_tree'):  # Python 3.6
     subs_tree = typ._subs_tree()
-    return len(subs_tree) == 3 and subs_tree[2]  == OutputAnnotation
+    return len(subs_tree) == 3 and subs_tree[2] == OutputAnnotation
 
   return typ.__args__[1] == OutputAnnotation
 
+
 def get_io_artifact_class(typ):
   if not is_artifact_annotation(typ):
     return None
@@ -484,6 +506,7 @@ def get_io_artifact_class(typ):
 
   return typ.__args__[0]
 
+
 def get_io_artifact_annotation(typ):
   if not is_artifact_annotation(typ):
     return None
@@ -497,7 +520,6 @@ def get_io_artifact_annotation(typ):
   return typ.__args__[1]
 
 
-
 _SCHEMA_TITLE_TO_TYPE: Dict[str, Artifact] = {
     x.TYPE_NAME: x
     for x in [Artifact, Model, Dataset, Metrics, ClassificationMetrics]

sdk/python/kfp/dsl/type_utils.py

@@ -27,6 +27,8 @@
     'metrics': io_types.Metrics,
     'classificationmetrics': io_types.ClassificationMetrics,
     'slicedclassificationmetrics': io_types.SlicedClassificationMetrics,
+    'html': io_types.HTML,
+    'markdown': io_types.Markdown,
 }
 
 # ComponentSpec I/O types to (IR) PipelineTaskSpec I/O types mapping.

sdk/python/kfp/dsl/type_utils_test.py

@@ -129,6 +129,18 @@ def test_is_parameter_type(self):
           'expected_result':
               pb.ArtifactTypeSchema(schema_title='system.Artifact')
       },
+      {
+          'artifact_class_or_type_name':
+              io_types.HTML,
+          'expected_result':
+              pb.ArtifactTypeSchema(schema_title='system.HTML')
+      },
+      {
+          'artifact_class_or_type_name':
+              io_types.Markdown,
+          'expected_result':
+              pb.ArtifactTypeSchema(schema_title='system.Markdown')
+      },
   )
   def test_get_artifact_type_schema(self, artifact_class_or_type_name,
                                     expected_result):

sdk/python/kfp/v2/compiler_cli_tests/test_data/pipeline_with_various_io_types.json

@@ -34,6 +34,11 @@
               "artifactType": {
                 "schemaTitle": "system.Artifact"
               }
+            },
+            "input_h": {
+              "artifactType": {
+                "schemaTitle": "system.HTML"
+              }
             }
           },
           "parameters": {
@@ -92,6 +97,11 @@
               "artifactType": {
                 "schemaTitle": "system.Artifact"
               }
+            },
+            "output_8": {
+              "artifactType": {
+                "schemaTitle": "system.HTML"
+              }
             }
           },
           "parameters": {
@@ -113,7 +123,8 @@
               "{{$.inputs.artifacts['input_d'].uri}}",
               "{{$.inputs.artifacts['input_e'].uri}}",
               "{{$.inputs.artifacts['input_f'].path}}",
-              "{{$.inputs.artifacts['input_g'].path}}"
+              "{{$.inputs.artifacts['input_g'].path}}",
+              "{{$.inputs.artifacts['input_h'].path}}"
             ],
             "image": "gcr.io/image"
           }
@@ -131,7 +142,8 @@
               "{{$.outputs.artifacts['output_4'].uri}}",
               "{{$.outputs.artifacts['output_5'].uri}}",
               "{{$.outputs.artifacts['output_6'].path}}",
-              "{{$.outputs.artifacts['output_7'].path}}"
+              "{{$.outputs.artifacts['output_7'].path}}",
+              "{{$.outputs.artifacts['output_8'].path}}"
             ],
             "image": "gcr.io/image"
           }
@@ -191,6 +203,12 @@
                     "outputArtifactKey": "output_7",
                     "producerTask": "upstream"
                   }
+                },
+                "input_h": {
+                  "taskOutputArtifact": {
+                    "outputArtifactKey": "output_8",
+                    "producerTask": "upstream"
+                  }
                 }
               },
               "parameters": {

sdk/python/kfp/v2/compiler_cli_tests/test_data/pipeline_with_various_io_types.py

@@ -33,6 +33,7 @@
 - {name: output_5, type: Datasets}
 - {name: output_6, type: Some arbitrary type}
 - {name: output_7, type: {GcsPath: {data_type: TSV}}}
+- {name: output_8, type: HTML}
 implementation:
   container:
     image: gcr.io/image
@@ -48,6 +49,7 @@
     - {outputUri: output_5}
     - {outputPath: output_6}
     - {outputPath: output_7}
+    - {outputPath: output_8}
 """)
 
 component_op_2 = components.load_component_from_text("""
@@ -60,6 +62,7 @@
 - {name: input_e, type: Datasets}
 - {name: input_f, type: Some arbitrary type}
 - {name: input_g, type: {GcsPath: {data_type: TSV}}}
+- {name: input_h, type: HTML}
 implementation:
   container:
     image: gcr.io/image
@@ -71,6 +74,7 @@
     - {inputUri: input_e}
     - {inputPath: input_f}
     - {inputPath: input_g}
+    - {inputPath: input_h}
 """)
 
 
@@ -92,6 +96,7 @@ def my_pipeline(input1: str,
       input_e=component_1.outputs['output_5'],
       input_f=component_1.outputs['output_6'],
       input_g=component_1.outputs['output_7'],
+      input_h=component_1.outputs['output_8'],
   )