Skip to content

Commit 32b85e0

Browse files
authored
Bump SDK (#783)
* update * update
1 parent 3e79da4 commit 32b85e0

File tree

4 files changed

+25
-25
lines changed

4 files changed

+25
-25
lines changed

.pre-commit-config.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -85,7 +85,7 @@ repos:
8585
args: ["--print-width=120"]
8686

8787
- repo: https://github.com/tox-dev/pyproject-fmt
88-
rev: v2.11.1
88+
rev: v2.8.0
8989
hooks:
9090
- id: pyproject-fmt
9191
additional_dependencies: [tox]

requirements/extras.txt

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2,7 +2,7 @@ pillow
22
viztracer
33
pyarrow
44
tqdm
5-
lightning-sdk==2025.9.30 # Must be pinned to ensure compatibility
5+
lightning-sdk==2025.12.17 # Must be pinned to ensure compatibility
66
google-cloud-storage
77
polars
88
fsspec

src/litdata/processing/data_processor.py

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1440,12 +1440,12 @@ def run(self, data_recipe: DataRecipe) -> None:
14401440
storage_dir=self.output_dir.path,
14411441
dataset_type=data_type,
14421442
empty=False,
1443-
size=result.size,
1443+
size=str(result.size),
14441444
num_bytes=result.num_bytes,
14451445
data_format=result.data_format,
14461446
compression=result.compression,
1447-
num_chunks=result.num_chunks,
1448-
num_bytes_per_chunk=result.num_bytes_per_chunk,
1447+
num_chunks=str(result.num_chunks),
1448+
num_bytes_per_chunk=[str(v) for v in (result.num_bytes_per_chunk or [])],
14491449
)
14501450
if self.verbose:
14511451
print("Finished data processing!")

src/litdata/processing/utilities.py

Lines changed: 20 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -33,14 +33,14 @@ def _create_dataset(
3333
storage_dir: str,
3434
dataset_type: Any,
3535
empty: bool | None = None,
36-
size: int | None = None,
36+
size: str | None = None,
3737
num_bytes: str | None = None,
3838
data_format: str | tuple[str] | None = None,
3939
compression: str | None = None,
40-
num_chunks: int | None = None,
41-
num_bytes_per_chunk: list[int] | None = None,
40+
num_chunks: str | None = None,
41+
num_bytes_per_chunk: list[str] | None = None,
4242
name: str | None = None,
43-
version: int | None = None,
43+
version: str | None = None,
4444
) -> None:
4545
"""Create a dataset with metadata information about its source and destination using the Lightning SDK.
4646
@@ -61,31 +61,31 @@ def _create_dataset(
6161
if not storage_dir:
6262
raise ValueError("The storage_dir should be defined.")
6363

64-
from lightning_sdk.lightning_cloud.openapi import ProjectIdDatasetsBody
64+
from lightning_sdk.lightning_cloud.openapi.models import DatasetServiceCreateDatasetBody
6565
from lightning_sdk.lightning_cloud.openapi.rest import ApiException
6666
from lightning_sdk.lightning_cloud.rest_client import LightningClient
6767

6868
client = LightningClient(retry=False)
6969

7070
try:
7171
client.dataset_service_create_dataset(
72-
body=ProjectIdDatasetsBody(
73-
cloud_space_id=studio_id if lightning_app_id is None else None,
74-
cluster_id=cluster_id,
75-
creator_id=user_id,
76-
empty=empty,
77-
input_dir=input_dir,
78-
lightning_app_id=lightning_app_id,
79-
name=name,
80-
size=size,
81-
num_bytes=num_bytes,
82-
data_format=str(data_format) if data_format else data_format,
83-
compression=compression,
84-
num_chunks=num_chunks,
85-
num_bytes_per_chunk=num_bytes_per_chunk,
72+
body=DatasetServiceCreateDatasetBody(
73+
cloud_space_id=(studio_id if lightning_app_id is None else None) or "",
74+
cluster_id=cluster_id or "",
75+
creator_id=user_id or "",
76+
empty=empty or True,
77+
input_dir=input_dir or "",
78+
lightning_app_id=lightning_app_id or "",
79+
name=name or "",
80+
size=size or "",
81+
num_bytes=num_bytes or "",
82+
data_format=(str(data_format) if data_format else data_format) or "",
83+
compression=compression or "",
84+
num_chunks=num_chunks or "",
85+
num_bytes_per_chunk=num_bytes_per_chunk or [],
8686
storage_dir=storage_dir,
8787
type=dataset_type,
88-
version=version,
88+
version=version or "",
8989
),
9090
project_id=project_id,
9191
)

0 commit comments

Comments
 (0)