[DEVX-454]: Make labels optional to support Data Ingestion Pipeline (#…

…471)
Clarifai · Jan 2, 2025 · 10e3336 · 10e3336
1 parent 7938f57
commit 10e3336
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 4 deletions.
diff --git a/clarifai/datasets/upload/features.py b/clarifai/datasets/upload/features.py
@@ -7,7 +7,7 @@
 class TextFeatures:
   """Text classification datasets preprocessing output features."""
   text: str
-  labels: List[Union[str, int]]  # List[str or int] to cater for multi-class tasks
+  labels: List[Union[str, int]] = None  # List[str or int] to cater for multi-class tasks
   id: Optional[int] = None  # text_id
   metadata: Optional[dict] = None
   label_ids: Optional[List[str]] = None

diff --git a/clarifai/datasets/upload/multimodal.py b/clarifai/datasets/upload/multimodal.py
@@ -34,7 +34,8 @@ def process_data_item(id):
       metadata = Struct()
       image_bytes = data_item.image_bytes
       text = data_item.text
-      labels = data_item.labels if isinstance(data_item.labels, list) else [data_item.labels]
+      labels = data_item.labels if ((data_item.labels is None) or
+                                    isinstance(data_item.labels, list)) else [data_item.labels]
       input_id = f"{self.dataset_id}-{id}" if data_item.id is None else f"{self.dataset_id}-{str(data_item.id)}"
       if data_item.metadata is not None:
         metadata.update(data_item.metadata)

diff --git a/clarifai/datasets/upload/text.py b/clarifai/datasets/upload/text.py
@@ -34,8 +34,9 @@ def process_data_item(id):
       data_item = self.data_generator[id]
       metadata = Struct()
       text = data_item.text
-      labels = data_item.labels if isinstance(data_item.labels,
-                                              list) else [data_item.labels]  # clarifai concept
+      labels = data_item.labels if ((data_item.labels is None) or
+                                    isinstance(data_item.labels, list)) else [data_item.labels
+                                                                             ]  # clarifai concept
       label_ids = data_item.label_ids
       input_id = f"{self.dataset_id}-{get_uuid(8)}" if data_item.id is None else f"{self.dataset_id}-{str(data_item.id)}"
       if data_item.metadata is not None: