datachain 0.20.0__py3-none-any.whl → 0.20.2__py3-none-any.whl

datachain/cli/parser/job.py

@@ -52,10 +52,10 @@ def add_jobs_parser(subparsers, parent_parser) -> None:
     )
 
     studio_run_parser.add_argument(
-        "--cluster-id",
-        type=int,
+        "--cluster",
+        type=str,
         action="store",
-        help="Compute cluster ID to run the job on",
+        help="Compute cluster to run the job on",
     )
 
     studio_run_parser.add_argument(

datachain/client/hf.py

@@ -21,6 +21,9 @@ def _wrap_class(sync_fs_class):
     asynchronous to False by default. This is similar to other Async FS
     we initialize. E.g. it means we don't break things in Jupyter where code
     run in async.
+
+    This also fixes write operations by ensuring they are properly forwarded
+    to the underlying filesystem without async buffering issues.
     """
     from fsspec.implementations.asyn_wrapper import AsyncFileSystemWrapper
 
@@ -29,6 +32,13 @@ def _wrap_class(sync_fs_class):
             sync_fs = sync_fs_class(*args, **kwargs)
             super().__init__(sync_fs, asynchronous=False)
 
+        def open(self, path, mode="rb", **kwargs):
+            # Override open to ensure write operations work correctly.
+            # It seems to be a bug in the fsspec wrapper. It avoids
+            # wrapping open() explicitly but also doesn't redirect it to
+            # sync filesystem.
+            return self.sync_fs.open(path, mode, **kwargs)
+
     GeneratedAsyncFileSystemWrapper.__name__ = f"Async{sync_fs_class.__name__}Wrapper"
     return GeneratedAsyncFileSystemWrapper
 

datachain/remote/studio.py

@@ -427,7 +427,7 @@ class StudioClient:
         requirements: Optional[str] = None,
         repository: Optional[str] = None,
         priority: Optional[int] = None,
-        cluster_id: Optional[int] = None,
+        cluster: Optional[str] = None,
     ) -> Response[JobData]:
         data = {
             "query": query,
@@ -440,7 +440,7 @@ class StudioClient:
             "requirements": requirements,
             "repository": repository,
             "priority": priority,
-            "compute_cluster_id": cluster_id,
+            "compute_cluster_name": cluster,
         }
         return self._send_request("datachain/job", data)
 

datachain/studio.py

@@ -41,7 +41,7 @@ def process_jobs_args(args: "Namespace"):
             args.req,
             args.req_file,
             args.priority,
-            args.cluster_id,
+            args.cluster,
         )
 
     if args.cmd == "cancel":
@@ -300,7 +300,7 @@ def create_job(
     req: Optional[list[str]] = None,
     req_file: Optional[str] = None,
     priority: Optional[int] = None,
-    cluster_id: Optional[int] = None,
+    cluster: Optional[str] = None,
 ):
     query_type = "PYTHON" if query_file.endswith(".py") else "SHELL"
     with open(query_file) as f:
@@ -330,7 +330,7 @@ def create_job(
         repository=repository,
         requirements=requirements,
         priority=priority,
-        cluster_id=cluster_id,
+        cluster=cluster,
     )
     if not response.ok:
         raise DataChainError(response.message)

{datachain-0.20.0.dist-info → datachain-0.20.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.20.0
+Version: 0.20.2
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.20.0.dist-info → datachain-0.20.2.dist-info}/RECORD

@@ -17,7 +17,7 @@ datachain/project.py,sha256=FobJbBJIy1-e-yemlL7M5eOcy694eceO5CWuY5H7bbw,2305
 datachain/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/script_meta.py,sha256=V-LaFOZG84pD0Zc0NvejYdzwDgzITv6yHvAHggDCnuY,4978
 datachain/semver.py,sha256=UB8GHPBtAP3UJGeiuJoInD7SK-DnB93_Xd1qy_CQ9cU,2074
-datachain/studio.py,sha256=xtuRtqokqvBEICveaQ2FNsD43duXxHTcBPrqv-C9t4M,13009
+datachain/studio.py,sha256=NMJYuWyJNLm6HS4GjcBBj7_CKjymsSBrjrLeXuEiD1M,12997
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=DNqOi-Ydb7InyWvD9m7_yailxz6-YGpZzh00biQaHNo,15305
 datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
@@ -35,7 +35,7 @@ datachain/cli/commands/misc.py,sha256=c0DmkOLwcDI2YhA8ArOuLJk6aGzSMZCiKL_E2JGibV
 datachain/cli/commands/query.py,sha256=Xzfgh14nPVH-sclqX1tpZqgfdTugw5s_44v0D33z6FA,1505
 datachain/cli/commands/show.py,sha256=Cf8wBs12h-xtdOzjU5GTDy2C8rF5HJSF0hDJYER1zH8,1606
 datachain/cli/parser/__init__.py,sha256=NPB6ssP4CCt7G1SWZ_8oNQEH2C1lktWgkyHYXDQJZNc,15073
-datachain/cli/parser/job.py,sha256=9mEkbhXFIGZxDAjZT9lWWIf3G-HiuJd1oTJNjSrEppc,5295
+datachain/cli/parser/job.py,sha256=_wqOOxGRXG_-xuQ35FaLUOwjw6w8HviWvoEpZZ7VBzI,5289
 datachain/cli/parser/studio.py,sha256=Bo__LKM7qhJGgkyX8M_bCvgZ2Gvqq6r_X4t1NdtaBIY,3881
 datachain/cli/parser/utils.py,sha256=rETdD-9Hq9A4OolgfT7jQw4aoawtbfmkdtH6E7nkhpI,2888
 datachain/client/__init__.py,sha256=1kDpCPoibMXi1gExR4lTLc5pi-k6M5TANiwtXkPoLhU,49
@@ -43,7 +43,7 @@ datachain/client/azure.py,sha256=7yyAgANHfu9Kfh187MKNTT1guvu9Q-WYsi4vYoY3aew,327
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
 datachain/client/fsspec.py,sha256=huPHNDZRGz_rSN7XnS9hKmRoS2fsSz_y2-cxUSlvsOA,13938
 datachain/client/gcs.py,sha256=8hcFhEHp8qGRsJoyfCoawfuwb1Et-MSkyQoM9AnNuXI,5204
-datachain/client/hf.py,sha256=mRBqHeBT758TJicU-Fn2L3l5AbHWwMzycWwttNUACKk,2180
+datachain/client/hf.py,sha256=n5xJZdvNLS-SqokxuBCIPfGbhIeC_XfLm_BNYtEVvg4,2677
 datachain/client/local.py,sha256=cGoCYflribzexiOe-Y1qbaE2fJRh-_EgQrfCSa0yK_E,4568
 datachain/client/s3.py,sha256=6DNVGLg-woPS1DVlYVX2rIlunNblsuxyOnI1rSzhW3k,7515
 datachain/data_storage/__init__.py,sha256=9Wit-oe5P46V7CJQTD0BJ5MhOa2Y9h3ddJ4VWTe-Lec,273
@@ -135,7 +135,7 @@ datachain/query/session.py,sha256=gKblltJAVQAVSTswAgWGDgGbpmFlFzFVkIQojDCjgXM,68
 datachain/query/udf.py,sha256=e753bDJzTNjGFQn1WGTvOAWSwjDbrFI1-_DDWkWN2ls,1343
 datachain/query/utils.py,sha256=HaSDNH_XGvp_NIcXjcB7j4vJRPi4_tbztDWclYelHY4,1208
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/remote/studio.py,sha256=jA-I6q46GEuiGLp3PlQvCaU17ylHThC0HqS73oeBKUU,15114
+datachain/remote/studio.py,sha256=aSAh7CCHrTp7U-642jHFkwY0Fer4YRAHVVpWomab3zY,15110
 datachain/sql/__init__.py,sha256=6SQRdbljO3d2hx3EAVXEZrHQKv5jth0Jh98PogT59No,262
 datachain/sql/selectable.py,sha256=cTc60qVoAwqqss0Vop8Lt5Z-ROnM1XrQmL_GLjRxhXs,1765
 datachain/sql/types.py,sha256=ASSPkmM5EzdRindqj2O7WHLXq8VHAgFYedG8lYfGvVI,14045
@@ -157,9 +157,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=ktGWzY4kyzjWyR86dhvzw-Zhl0lVk_LOX3NciTac6qo,2914
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.20.0.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.20.0.dist-info/METADATA,sha256=etcARLRHIUWT7LdqUv9Di5ZLOV3iq1HAOgiL9dsrd7c,13281
-datachain-0.20.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.20.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.20.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.20.0.dist-info/RECORD,,
+datachain-0.20.2.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.20.2.dist-info/METADATA,sha256=kHj22yPbf64WX5RAZ8tCVphhJehZsJ3cl613rtXZab0,13281
+datachain-0.20.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.20.2.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.20.2.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.20.2.dist-info/RECORD,,