datachain 0.13.0__py3-none-any.whl → 0.14.0__py3-none-any.whl

datachain/lib/dc/utils.py

@@ -0,0 +1,128 @@
+from collections.abc import Sequence
+from functools import wraps
+from typing import (
+    TYPE_CHECKING,
+    Callable,
+    Optional,
+    TypeVar,
+    Union,
+)
+
+import sqlalchemy
+from sqlalchemy.sql.functions import GenericFunction
+
+from datachain.func.base import Function
+from datachain.lib.data_model import DataModel, DataType
+from datachain.lib.utils import DataChainParamsError
+from datachain.query.schema import DEFAULT_DELIMITER
+
+if TYPE_CHECKING:
+    from typing_extensions import Concatenate, ParamSpec
+
+    from .datachain import DataChain
+
+    P = ParamSpec("P")
+
+D = TypeVar("D", bound="DataChain")
+
+
+def resolve_columns(
+    method: "Callable[Concatenate[D, P], D]",
+) -> "Callable[Concatenate[D, P], D]":
+    """Decorator that resolvs input column names to their actual DB names. This is
+    specially important for nested columns as user works with them by using dot
+    notation e.g (file.name) but are actually defined with default delimiter
+    in DB, e.g file__name.
+    If there are any sql functions in arguments, they will just be transferred as is
+    to a method.
+    """
+
+    @wraps(method)
+    def _inner(self: D, *args: "P.args", **kwargs: "P.kwargs") -> D:
+        resolved_args = self.signals_schema.resolve(
+            *[arg for arg in args if not isinstance(arg, GenericFunction)]  # type: ignore[arg-type]
+        ).db_signals()
+
+        for idx, arg in enumerate(args):
+            if isinstance(arg, GenericFunction):
+                resolved_args.insert(idx, arg)  # type: ignore[arg-type]
+
+        return method(self, *resolved_args, **kwargs)
+
+    return _inner
+
+
+class DatasetPrepareError(DataChainParamsError):
+    def __init__(self, name, msg, output=None):
+        name = f" '{name}'" if name else ""
+        output = f" output '{output}'" if output else ""
+        super().__init__(f"Dataset{name}{output} processing prepare error: {msg}")
+
+
+class DatasetFromValuesError(DataChainParamsError):
+    def __init__(self, name, msg):
+        name = f" '{name}'" if name else ""
+        super().__init__(f"Dataset{name} from values error: {msg}")
+
+
+MergeColType = Union[str, Function, sqlalchemy.ColumnElement]
+
+
+def _validate_merge_on(
+    on: Union[MergeColType, Sequence[MergeColType]],
+    ds: "DataChain",
+) -> Sequence[MergeColType]:
+    if isinstance(on, (str, sqlalchemy.ColumnElement)):
+        return [on]
+    if isinstance(on, Function):
+        return [on.get_column(table=ds._query.table)]
+    if isinstance(on, Sequence):
+        return [
+            c.get_column(table=ds._query.table) if isinstance(c, Function) else c
+            for c in on
+        ]
+
+
+def _get_merge_error_str(col: MergeColType) -> str:
+    if isinstance(col, str):
+        return col
+    if isinstance(col, Function):
+        return f"{col.name}()"
+    if isinstance(col, sqlalchemy.Column):
+        return col.name.replace(DEFAULT_DELIMITER, ".")
+    if isinstance(col, sqlalchemy.ColumnElement) and hasattr(col, "name"):
+        return f"{col.name} expression"
+    return str(col)
+
+
+class DatasetMergeError(DataChainParamsError):
+    def __init__(
+        self,
+        on: Union[MergeColType, Sequence[MergeColType]],
+        right_on: Optional[Union[MergeColType, Sequence[MergeColType]]],
+        msg: str,
+    ):
+        def _get_str(
+            on: Union[MergeColType, Sequence[MergeColType]],
+        ) -> str:
+            if not isinstance(on, Sequence):
+                return str(on)  # type: ignore[unreachable]
+            return ", ".join([_get_merge_error_str(col) for col in on])
+
+        on_str = _get_str(on)
+        right_on_str = (
+            ", right_on='" + _get_str(right_on) + "'"
+            if right_on and isinstance(right_on, Sequence)
+            else ""
+        )
+        super().__init__(f"Merge error on='{on_str}'{right_on_str}: {msg}")
+
+
+OutputType = Union[None, DataType, Sequence[str], dict[str, DataType]]
+
+
+class Sys(DataModel):
+    """Model for internal DataChain signals `id` and `rand`."""
+
+    id: int
+    rand: int

datachain/lib/dc/values.py

@@ -0,0 +1,53 @@
+from collections.abc import Iterator
+from typing import (
+    TYPE_CHECKING,
+    Optional,
+)
+
+from datachain.lib.convert.values_to_tuples import values_to_tuples
+from datachain.lib.data_model import dict_to_data_model
+from datachain.lib.dc.records import from_records
+from datachain.lib.dc.utils import OutputType
+from datachain.query import Session
+
+if TYPE_CHECKING:
+    from typing_extensions import ParamSpec
+
+    from .datachain import DataChain
+
+    P = ParamSpec("P")
+
+
+def from_values(
+    ds_name: str = "",
+    session: Optional[Session] = None,
+    settings: Optional[dict] = None,
+    in_memory: bool = False,
+    output: OutputType = None,
+    object_name: str = "",
+    **fr_map,
+) -> "DataChain":
+    """Generate chain from list of values.
+
+    Example:
+        ```py
+        import datachain as dc
+        dc.from_values(fib=[1, 2, 3, 5, 8])
+        ```
+    """
+    from .datachain import DataChain
+
+    tuple_type, output, tuples = values_to_tuples(ds_name, output, **fr_map)
+
+    def _func_fr() -> Iterator[tuple_type]:  # type: ignore[valid-type]
+        yield from tuples
+
+    chain = from_records(
+        DataChain.DEFAULT_FILE_RECORD,
+        session=session,
+        settings=settings,
+        in_memory=in_memory,
+    )
+    if object_name:
+        output = {object_name: dict_to_data_model(object_name, output)}  # type: ignore[arg-type]
+    return chain.gen(_func_fr, output=output)

datachain/lib/meta_formats.py

@@ -103,12 +103,10 @@ def read_meta(  # noqa: C901
     model_name=None,
     nrows=None,
 ) -> Callable:
-    from datachain.lib.dc import DataChain
+    from datachain import from_storage
 
     if schema_from:
-        file = next(
-            DataChain.from_storage(schema_from, type="text").limit(1).collect("file")
-        )
+        file = next(from_storage(schema_from, type="text").limit(1).collect("file"))
         model_code = gen_datamodel_code(
             file, format=format, jmespath=jmespath, model_name=model_name
         )

datachain/lib/pytorch.py

@@ -14,7 +14,7 @@ from torchvision.transforms import v2
 from datachain import Session
 from datachain.cache import get_temp_cache
 from datachain.catalog import Catalog, get_catalog
-from datachain.lib.dc import DataChain
+from datachain.lib.dc.datasets import from_dataset
 from datachain.lib.settings import Settings
 from datachain.lib.text import convert_text
 from datachain.progress import CombinedDownloadCallback
@@ -122,7 +122,7 @@ class PytorchDataset(IterableDataset):
     ) -> Generator[tuple[Any, ...], None, None]:
         catalog = self._get_catalog()
         session = Session("PyTorch", catalog=catalog)
-        ds = DataChain.from_dataset(
+        ds = from_dataset(
             name=self.name, version=self.version, session=session
         ).settings(cache=self.cache, prefetch=self.prefetch)
         ds = ds.remove_file_signals()

datachain/lib/udf.py

@@ -123,10 +123,10 @@ class UDFBase(AbstractUDF):
 
     Example:
         ```py
-        from datachain import C, DataChain, Mapper
+        import datachain as dc
         import open_clip
 
-        class ImageEncoder(Mapper):
+        class ImageEncoder(dc.Mapper):
             def __init__(self, model_name: str, pretrained: str):
                 self.model_name = model_name
                 self.pretrained = pretrained
@@ -145,7 +145,7 @@ class UDFBase(AbstractUDF):
                 return emb[0].tolist()
 
         (
-            DataChain.from_storage(
+            dc.from_storage(
                 "gs://datachain-demo/fashion-product-images/images", type="image"
             )
             .limit(5)

datachain/toolkit/split.py

@@ -37,11 +37,11 @@ def train_test_split(
     Examples:
         Train-test split:
         ```python
-        from datachain import DataChain
+        import datachain as dc
         from datachain.toolkit import train_test_split
 
         # Load a DataChain from a storage source (e.g., S3 bucket)
-        dc = DataChain.from_storage("s3://bucket/dir/")
+        dc = dc.from_storage("s3://bucket/dir/")
 
         # Perform a 70/30 train-test split
         train, test = train_test_split(dc, [0.7, 0.3])

{datachain-0.13.0.dist-info → datachain-0.14.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: datachain
-Version: 0.13.0
+Version: 0.14.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -107,6 +107,7 @@ Requires-Dist: accelerate; extra == "examples"
 Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
 Requires-Dist: ultralytics; extra == "examples"
 Requires-Dist: open_clip_torch; extra == "examples"
+Dynamic: license-file
 
 ================
 |logo| DataChain
@@ -168,16 +169,16 @@ high confidence scores.
 
 .. code:: py
 
-    from datachain import Column, DataChain
+    import datachain as dc
 
-    meta = DataChain.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
-    images = DataChain.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
+    meta = dc.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
+    images = dc.from_storage("gs://datachain-demo/dogs-and-cats/*jpg", anon=True)
 
     images_id = images.map(id=lambda file: file.path.split('.')[-2])
     annotated = images_id.merge(meta, on="id", right_on="meta.id")
 
-    likely_cats = annotated.filter((Column("meta.inference.confidence") > 0.93) \
-                                   & (Column("meta.inference.class_") == "cat"))
+    likely_cats = annotated.filter((dc.Column("meta.inference.confidence") > 0.93) \
+                                   & (dc.Column("meta.inference.class_") == "cat"))
     likely_cats.to_storage("high-confidence-cats/", signal="file")
 
 
@@ -198,11 +199,11 @@ Python code:
 
     import os
     from mistralai import Mistral
-    from datachain import File, DataChain, Column
+    import datachain as dc
 
     PROMPT = "Was this dialog successful? Answer in a single word: Success or Failure."
 
-    def eval_dialogue(file: File) -> bool:
+    def eval_dialogue(file: dc.File) -> bool:
          client = Mistral(api_key = os.environ["MISTRAL_API_KEY"])
          response = client.chat.complete(
              model="open-mixtral-8x22b",
@@ -212,13 +213,13 @@ Python code:
          return result.lower().startswith("success")
 
     chain = (
-       DataChain.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+       dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
        .settings(parallel=4, cache=True)
        .map(is_success=eval_dialogue)
        .save("mistral_files")
     )
 
-    successful_chain = chain.filter(Column("is_success") == True)
+    successful_chain = chain.filter(dc.Column("is_success") == True)
     successful_chain.to_storage("./output_mistral")
 
     print(f"{successful_chain.count()} files were exported")

{datachain-0.13.0.dist-info → datachain-0.14.0.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datachain/__init__.py,sha256=WfGQWOA05pz9haabxOjZYJMZBI1MXOEtIraDkjXaXBw,1019
+datachain/__init__.py,sha256=M_0MfSBJqlWA9hI3z47Yu36fxkxsekbpvNa-LBa1e5Q,1414
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=RH_jFwJcTXxhEFomaI9yL6S3Onau6NZ6FSKfKFGtrJE,9689
 datachain/cache.py,sha256=yQblPhOh_Mq74Ma7xT1CL1idLJ0HgrQxpGVYvRy_9Eg,3623
@@ -17,7 +17,7 @@ datachain/studio.py,sha256=9MEpFPLKI3gG4isKklcfD5BMLeNsSXhtOUboOjW4Fdc,10017
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=CLAYkI7iPbLYw3Pjh5EkWuc2UOs8wEbuXQnqIs4UyV8,14173
 datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
-datachain/catalog/catalog.py,sha256=IJSTXHFf2jqkHq2zXLvKzSUwJE9-Tu5YpY_SvcGymgI,60401
+datachain/catalog/catalog.py,sha256=6dDTbSom8JzxLD_cbFboKtsiYtGR5WIOEOQTtCQ5mws,60722
 datachain/catalog/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
 datachain/catalog/loader.py,sha256=AhSQR_-S-9lY3DcXn3PVZv9UtarHOMlDy2x75iDwUjo,6035
 datachain/cli/__init__.py,sha256=YPVkuQ7IezNhtzo5xrfca1hEIiZtFxOlJCOzAOEuxmA,8335
@@ -26,10 +26,10 @@ datachain/cli/commands/__init__.py,sha256=zp3bYIioO60x_X04A4-IpZqSYVnpwOa1AdERQa
 datachain/cli/commands/datasets.py,sha256=865ui6q4UVPbL_-jk18C-lYi_bGMlh7XhfRaHbbNyhk,5796
 datachain/cli/commands/du.py,sha256=9edEzDEs98K2VYk8Wf-ZMpUzALcgm9uD6YtoqbvtUGU,391
 datachain/cli/commands/index.py,sha256=eglNaIe1yyIadUHHumjtNbgIjht6kme7SS7xE3YHR88,198
-datachain/cli/commands/ls.py,sha256=7yVSRzhmocnnaAXgim4NzrzEymwpLTJjhXq5EATFwsU,5286
+datachain/cli/commands/ls.py,sha256=dSD2_MHng4t9HRFJZWMOCjPL4XU3qaBV3piNl8UXP08,5275
 datachain/cli/commands/misc.py,sha256=c0DmkOLwcDI2YhA8ArOuLJk6aGzSMZCiKL_E2JGibVE,600
 datachain/cli/commands/query.py,sha256=2S7hQxialt1fkbocxi6JXZI6jS5QnFrD1aOjKgZkzfI,1471
-datachain/cli/commands/show.py,sha256=0ITkA7wvBPfEKM1K6uE0aage38WVsy1QXi6NS8VeSJw,1643
+datachain/cli/commands/show.py,sha256=pn8jQ5HqUpzZE3KE-iydflp8LGgfVIKR8eKwVKv6A-8,1604
 datachain/cli/parser/__init__.py,sha256=rtjlqSsDd4LZH9WdgvluO27M4sID1wD7YkQ4cKhNXzw,15721
 datachain/cli/parser/job.py,sha256=kvQkSfieyUmvJpOK8p78UgS8sygHhQXztRlOtVcgtaU,3449
 datachain/cli/parser/studio.py,sha256=Y-1OlQGecLVi9QofvWUfSlPd2ISyaESf7QFGZqGsrdw,3609
@@ -50,7 +50,7 @@ datachain/data_storage/schema.py,sha256=qSukry2kINhVw8aj5lQrpe7N90DFeatKIKmDh6jA
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
 datachain/data_storage/sqlite.py,sha256=KJ8hI0Hrwv9eAA-nLUlw2AYCQxiAAZ12a-ftUBtroNQ,24545
 datachain/data_storage/warehouse.py,sha256=GGtgHcOKjnvHN6CFkGGB8m4CFgPPJBo3f-KHEFEJmDc,30730
-datachain/diff/__init__.py,sha256=xSbJtmj-oawXQ2qfdGtfnVsfXV7KhdkQKC9bG_5lA2k,9256
+datachain/diff/__init__.py,sha256=YkGdiDbZIMhAZ2SJ4eSe00HU67VP1P6SL2L_t0ODYMs,9425
 datachain/fs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/fs/reference.py,sha256=A8McpXF0CqbXPqanXuvpKu50YLB3a2ZXA3YAPxtBXSM,914
 datachain/fs/utils.py,sha256=s-FkTOCGBk-b6TT3toQH51s9608pofoFjUSTc1yy7oE,825
@@ -70,20 +70,19 @@ datachain/lib/arrow.py,sha256=9UBCF-lftQaz0yxdsjbLKbyzVSmrF_QSWdhp2oBDPqs,9486
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=ZwBXELtqROEdLL4DmxTipnwUZmhQvMz_UVDzyf7nQ9Y,2899
 datachain/lib/dataset_info.py,sha256=IjdF1E0TQNOq9YyynfWiCFTeZpbyGfyJvxgJY4YN810,2493
-datachain/lib/dc.py,sha256=fNIVsAU5_uPbjQhIjoXfEDEF7eImh0cqtIl39CI5sKs,99457
 datachain/lib/file.py,sha256=HLQXS_WULm7Y-fkHMy0WpibVAcrkLPRS6CrZy6rwFe0,30450
 datachain/lib/hf.py,sha256=gjxuStZBlKtNk3-4yYSlWZDv9zBGblOdvEy_Lwap5hA,5882
 datachain/lib/image.py,sha256=butvUY_33PVEYPKX2nVCPeJjJVcBaptZwsE9REQsTS8,3247
 datachain/lib/listing.py,sha256=xrgsd1_YLLiA69LnwK56oZwe0RXTBCDicGzhavF_2AQ,6665
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
-datachain/lib/meta_formats.py,sha256=xEYlfN6XgiOgrqhY2kVlvK3xlo5nT3nuVrH111XMOrg,6385
+datachain/lib/meta_formats.py,sha256=f-irPQH_acIYT5gzjqoOvGrGOQrm-E_0wN-4lqZF_j8,6349
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
-datachain/lib/pytorch.py,sha256=QxXBhrn2-D0RiFA2rdxZ7wKMxyuQ0WWHKfiFEWAA760,7710
+datachain/lib/pytorch.py,sha256=FFCZoVkoG_FY_vJ4v_DgzijEEcTozuddlPz1uAa5tyg,7712
 datachain/lib/settings.py,sha256=ZELRCTLbi5vzRPiDX6cQ9LLg9TefJ_A05gIGni0lll8,2535
 datachain/lib/signal_schema.py,sha256=DRatqSG7OVtCUCWyZvMXe4m7r7XFO6NCfzsJRDErMtg,35185
 datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=4_mdcWNkyukbDjqBNszlIrZLQyl_dPVQxhKwb_iDtQQ,16192
+datachain/lib/udf.py,sha256=6ZCn9qIAVwQA4zEyWiTb1jaSLkpkBXeGeaH8EB7Im3I,16168
 datachain/lib/udf_signature.py,sha256=2EtsOPDNSPqcOlYwqbCdy6RF5MldI-7smii8aLy8p7Y,7543
 datachain/lib/utils.py,sha256=QrjVs_oLRXEotOPUYurBJypBFi_ReTJmxcnJeH4j2Uk,1596
 datachain/lib/video.py,sha256=suH_8Mi8VYk4-IVb1vjSduF_njs64ji1WGKHxDLnGYw,6629
@@ -95,6 +94,19 @@ datachain/lib/convert/python_to_sql.py,sha256=wg-O5FRKX3x3Wh8ZL1b9ntMlgf1zRO4djM
 datachain/lib/convert/sql_to_python.py,sha256=XXCBYDQFUXJIBNWkjEP944cnCfJ8GF2Tji0DLF3A_zQ,315
 datachain/lib/convert/unflatten.py,sha256=ysMkstwJzPMWUlnxn-Z-tXJR3wmhjHeSN_P-sDcLS6s,2010
 datachain/lib/convert/values_to_tuples.py,sha256=EFfIGBiVVltJQG8blzsQ1dGXneh4D3wdLfSUeoK10OI,3931
+datachain/lib/dc/__init__.py,sha256=QKjTAYrigSoy74RQHmNS_86SEOisKk-BLDREYaJ_olY,743
+datachain/lib/dc/csv.py,sha256=OaVHYnOZiYEfsUcispXuGcIYQKF03u4XrRf6Fgce6Kk,4401
+datachain/lib/dc/datachain.py,sha256=NdGCRNk3NZCGQHs-sq0jiKkvsXiowiqDQTY_X4AbL6o,76390
+datachain/lib/dc/datasets.py,sha256=0vdgNpA_xakFgnfm78I1yU98u2hvOawOXS872pg2F48,4329
+datachain/lib/dc/hf.py,sha256=F_ME1IpUlQfhqVGe__Uz7jLwd-fp-O7pu50OLhkaG0w,2170
+datachain/lib/dc/json.py,sha256=gVH69oP8b5FR1YX3c_4Z_G1nFsAQ_xFz6fBg0J-U9ak,2719
+datachain/lib/dc/listings.py,sha256=c2ASPhwRhPDMbA5esYp3kMVw6sQ7vsWEflHWh9x7tkw,1044
+datachain/lib/dc/pandas.py,sha256=eteVB6DqRGAU2tDF_Bep7JRU4nny3uyVPbGKOZ6PVq0,1249
+datachain/lib/dc/parquet.py,sha256=tO0rDL3XZ24rqkUJYAYn_yAyZgIYV5N6r28MTlPE0Z0,1809
+datachain/lib/dc/records.py,sha256=zV4vPJvCEd5mBv-E_q-VfrSXNjcfu74QY884z3QuftM,2524
+datachain/lib/dc/storage.py,sha256=PIz6K2VOtrVV7XUNd3BESp3P5WovgaG1RgBYut0OBNA,3789
+datachain/lib/dc/utils.py,sha256=Ct-0FqCaDhNWHx09gJFcCXJGPjMI-VZr4t-GJyqTi44,3984
+datachain/lib/dc/values.py,sha256=PLBZew0BYO3mv7W3n8OF5Ad-5tp5eWPqlbiVxG5pJ30,1409
 datachain/model/__init__.py,sha256=R9faX5OHV1xh2EW-g2MPedwbtEqt3LodJRyluB-QylI,189
 datachain/model/bbox.py,sha256=cQNHuQuVsh6bW3n3Hj40F2Cc20cExQ9Lg_q7R2jxUMI,9324
 datachain/model/pose.py,sha256=rjquA6M-I-Y30Xm6YSkGv1OY52hJZmR2AuxbIpE5uD0,3865
@@ -136,11 +148,11 @@ datachain/sql/sqlite/base.py,sha256=N-cQT0Hpu9ROWe4OiKlkkn_YP1NKCRZZ3xSfTzpyaDA,
 datachain/sql/sqlite/types.py,sha256=cH6oge2E_YWFy22wY-txPJH8gxoQFSpCthtZR8PZjpo,1849
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
-datachain/toolkit/split.py,sha256=z3zRJNzjWrpPuRw-zgFbCOBKInyYxJew8ygrYQRQLNc,2930
+datachain/toolkit/split.py,sha256=VdcP_zVLqAxuSrze3BaR-dBzTmyKkCUAiAremw3OEPU,2914
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.13.0.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.13.0.dist-info/METADATA,sha256=4pdyj_HTlLLYZXfamUuBrMipFviwUfZ3vjzAvEOI-10,11351
-datachain-0.13.0.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
-datachain-0.13.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.13.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.13.0.dist-info/RECORD,,
+datachain-0.14.0.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.14.0.dist-info/METADATA,sha256=lC1I5lSWJX7a9oNpsRnEOM_L1W3hfnY8Op7iGWaNNcM,11324
+datachain-0.14.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+datachain-0.14.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.14.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.14.0.dist-info/RECORD,,

{datachain-0.13.0.dist-info → datachain-0.14.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.1.0)
+Generator: setuptools (78.1.0)
 Root-Is-Purelib: true
 Tag: py3-none-any