add labelbox iam integration support

deeplake/integrations/labelbox/labelbox_.py

@@ -185,6 +185,8 @@
     lb_batch_priority=5,
     data_upload_strategy="fail",
     lb_batches_name=None,
+    lb_iam_integration_id="DEFAULT",
+    lb_global_key_generator=lambda x: str(uuid.uuid4()),
 ):
     """
     Creates labelbox dataset for video annotation and sets up corresponding Labelbox project.
@@ -198,6 +200,8 @@
        lb_batch_priority (int, optional): Priority for Labelbox batches. Defaults to 5
        data_upload_strategy (str, optional): Strategy for uploading data to Labelbox. Can be 'fail', 'skip', or 'all'. Defaults to 'fail'
        lb_batches_name (str, optional): Name for Labelbox batches. Defaults to None. If None, will use lb_dataset_name + '_batch-'
+       lb_iam_integration_id (str, optional): IAM integration id for Labelbox. Defaults to 'DEFAULT'
+       lb_global_key_generator (callable, optional): Function to generate global keys for data rows. Defaults to lambda x: str(uuid.uuid4())
     """
 
     import labelbox as lb  # type: ignore
@@ -218,16 +222,40 @@
             assets = [
                 {
                     "row_data": p,
-                    "global_key": str(uuid.uuid4()),
+                    "global_key": lb_global_key_generator(p),
                     "media_type": "VIDEO",
                     "metadata_fields": [],
                     "attachments": [],
                 }
                 for p in video_paths
             ]
 
-    print("uploading videos to labelbox")
-    lb_ds = lb_client.create_dataset(name=lb_dataset_name)
+    if lb_iam_integration_id and lb_iam_integration_id != "DEFAULT":
+        lb_org = lb_client.get_organization()
+        integrations = lb_org.get_iam_integrations()
+        tmp_integration = None
+        for integration in integrations:
+            if integration.uid == lb_iam_integration_id:
+                tmp_integration = integration
+                break
+        if tmp_integration is None:
+            raise Exception(f"iam integration {lb_iam_integration_id} not found")
+        lb_iam_integration = tmp_integration
+    else:
+        lb_iam_integration = lb_iam_integration_id
+
+    print(
+        "uploading videos to labelbox",
+        (
+            f"using iam integration: {lb_iam_integration}"
+            if lb_iam_integration != "DEFAULT"
+            else ""
+        ),
+    )
+
+    lb_ds = lb_client.create_dataset(
+        iam_integration=lb_iam_integration, name=lb_dataset_name
+    )
     task = lb_ds.create_data_rows(assets)
     task.wait_till_done()
 

deeplake/integrations/labelbox/labelbox_azure_utils.py

@@ -4,6 +4,7 @@ def load_blob_file_paths_from_azure(
     parent_path,
     sas_token,
     predicate=lambda x: True,
+    sign_urls=True,
 ):
     from azure.storage.blob import BlobServiceClient
 
@@ -18,7 +19,8 @@ def load_blob_file_paths_from_azure(
     # List blobs in the directory
     blob_list = container_client.list_blobs(name_starts_with=parent_path)
     file_url_list = [
-        f"{account_url}/{container_name}/{blob.name}?{sas_token}"
+        f"{account_url}/{container_name}/{blob.name}"
+        + (f"?{sas_token}" if sign_urls else "")
         for blob in blob_list
         if predicate(blob.name)
     ]