Fix renaming from cluster_id to cloud_account

src/litdata/__about__.py

@@ -14,7 +14,7 @@
 
 import time
 
-__version__ = "0.2.36"
+__version__ = "0.2.37"
 __author__ = "Lightning AI et al."
 __author_email__ = "pytorch@lightning.ai"
 __license__ = "Apache-2.0"

src/litdata/processing/functions.py

@@ -201,6 +201,7 @@ def map(
     error_when_not_empty: bool = False,
     reader: Optional[BaseReader] = None,
     batch_size: Optional[int] = None,
+    start_method: Optional[str] = None,
 ) -> None:
     """Maps a callable over a collection of inputs, possibly in a distributed way.
 
@@ -222,7 +223,8 @@ def map(
         error_when_not_empty: Whether we should error if the output folder isn't empty.
         reader: The reader to use when reading the data. By default, it uses the `BaseReader`.
         batch_size: Group the inputs into batches of batch_size length.
-
+        start_method: The start method used by python multiprocessing package. Default to spawn unless running
+            inside an interactive shell like Ipython.
     """
     _check_version_and_prompt_upgrade(__version__)
 
@@ -286,6 +288,7 @@ def map(
             reorder_files=reorder_files,
             weights=weights,
             reader=reader,
+            start_method=start_method,
         )
         with optimize_dns_context(True):
             return data_processor.run(LambdaDataTransformRecipe(fn, inputs))

src/litdata/streaming/resolver.py

@@ -391,7 +391,7 @@ def _execute(
         num_instances=num_nodes,
         studio_id=studio._studio.id,
         teamspace_id=studio._teamspace.id,
-        cluster_id=studio._studio.cluster_id,
+        cloud_account=studio._studio.cluster_id,
         machine=machine or studio._studio_api.get_machine(studio._studio.id, studio._teamspace.id),
         interruptible=interruptible,
     )

tests/streaming/test_resolver.py

@@ -315,7 +315,7 @@ def print_fn(msg, file=None):
         "num_instances": 2,
         "studio_id": "studio_id",
         "teamspace_id": "teamspace_id",
-        "cluster_id": "cluster_id",
+        "cloud_account": "cluster_id",
         "machine": "cpu",
         "interruptible": False,
     }