datachain 0.14.1__py3-none-any.whl → 0.14.2__py3-none-any.whl

datachain/__init__.py

@@ -5,16 +5,16 @@ from datachain.lib.dc import (
     DataChain,
     Sys,
     datasets,
-    from_csv,
-    from_dataset,
-    from_hf,
-    from_json,
-    from_pandas,
-    from_parquet,
-    from_records,
-    from_storage,
-    from_values,
     listings,
+    read_csv,
+    read_dataset,
+    read_hf,
+    read_json,
+    read_pandas,
+    read_parquet,
+    read_records,
+    read_storage,
+    read_values,
 )
 from datachain.lib.file import (
     ArrowRow,
@@ -61,17 +61,17 @@ __all__ = [
     "VideoFragment",
     "VideoFrame",
     "datasets",
-    "from_csv",
-    "from_dataset",
-    "from_hf",
-    "from_json",
-    "from_pandas",
-    "from_parquet",
-    "from_records",
-    "from_storage",
-    "from_values",
     "is_chain_type",
     "listings",
     "metrics",
     "param",
+    "read_csv",
+    "read_dataset",
+    "read_hf",
+    "read_json",
+    "read_pandas",
+    "read_parquet",
+    "read_records",
+    "read_storage",
+    "read_values",
 ]

datachain/catalog/catalog.py

@@ -583,10 +583,10 @@ class Catalog:
         object_name="file",
         skip_indexing=False,
     ) -> tuple[Optional["Listing"], "Client", str]:
-        from datachain import from_storage
+        from datachain import read_storage
         from datachain.listing import Listing
 
-        from_storage(
+        read_storage(
             source, session=self.session, update=update, object_name=object_name
         ).exec()
 
@@ -994,14 +994,14 @@ class Catalog:
         if not sources:
             raise ValueError("Sources needs to be non empty list")
 
-        from datachain import from_dataset, from_storage
+        from datachain import read_dataset, read_storage
 
         chains = []
         for source in sources:
             if source.startswith(DATASET_PREFIX):
-                dc = from_dataset(source[len(DATASET_PREFIX) :], session=self.session)
+                dc = read_dataset(source[len(DATASET_PREFIX) :], session=self.session)
             else:
-                dc = from_storage(source, session=self.session, recursive=recursive)
+                dc = read_storage(source, session=self.session, recursive=recursive)
 
             chains.append(dc)
 

datachain/cli/commands/show.py

@@ -18,7 +18,7 @@ def show(
     schema: bool = False,
     include_hidden: bool = False,
 ) -> None:
-    from datachain import Session, from_dataset
+    from datachain import Session, read_dataset
     from datachain.query.dataset import DatasetQuery
     from datachain.utils import show_records
 
@@ -51,5 +51,5 @@ def show(
     if schema and dataset_version.feature_schema:
         print("\nSchema:")
         session = Session.get(catalog=catalog)
-        dc = from_dataset(name=name, version=version, session=session)
+        dc = read_dataset(name=name, version=version, session=session)
         dc.print_schema()

datachain/lib/dc/__init__.py

@@ -1,15 +1,15 @@
-from .csv import from_csv
+from .csv import read_csv
 from .datachain import C, Column, DataChain
-from .datasets import datasets, from_dataset
-from .hf import from_hf
-from .json import from_json
+from .datasets import datasets, read_dataset
+from .hf import read_hf
+from .json import read_json
 from .listings import listings
-from .pandas import from_pandas
-from .parquet import from_parquet
-from .records import from_records
-from .storage import from_storage
+from .pandas import read_pandas
+from .parquet import read_parquet
+from .records import read_records
+from .storage import read_storage
 from .utils import DatasetMergeError, DatasetPrepareError, Sys
-from .values import from_values
+from .values import read_values
 
 __all__ = [
     "C",
@@ -19,14 +19,14 @@ __all__ = [
     "DatasetPrepareError",
     "Sys",
     "datasets",
-    "from_csv",
-    "from_dataset",
-    "from_hf",
-    "from_json",
-    "from_pandas",
-    "from_parquet",
-    "from_records",
-    "from_storage",
-    "from_values",
     "listings",
+    "read_csv",
+    "read_dataset",
+    "read_hf",
+    "read_json",
+    "read_pandas",
+    "read_parquet",
+    "read_records",
+    "read_storage",
+    "read_values",
 ]

datachain/lib/dc/csv.py

@@ -16,7 +16,7 @@ if TYPE_CHECKING:
     from .datachain import DataChain
 
 
-def from_csv(
+def read_csv(
     path,
     delimiter: Optional[str] = None,
     header: bool = True,
@@ -58,13 +58,13 @@ def from_csv(
         Reading a csv file:
         ```py
         import datachain as dc
-        chain = dc.from_csv("s3://mybucket/file.csv")
+        chain = dc.read_csv("s3://mybucket/file.csv")
         ```
 
         Reading csv files from a directory as a combined dataset:
         ```py
         import datachain as dc
-        chain = dc.from_csv("s3://mybucket/dir")
+        chain = dc.read_csv("s3://mybucket/dir")
         ```
     """
     from pandas.io.parsers.readers import STR_NA_VALUES
@@ -72,7 +72,7 @@ def from_csv(
     from pyarrow.dataset import CsvFileFormat
     from pyarrow.lib import type_for_alias
 
-    from .storage import from_storage
+    from .storage import read_storage
 
     parse_options = parse_options or {}
     if "delimiter" not in parse_options:
@@ -88,7 +88,7 @@ def from_csv(
     else:
         column_types = {}
 
-    chain = from_storage(path, session=session, settings=settings, **kwargs)
+    chain = read_storage(path, session=session, settings=settings, **kwargs)
 
     column_names = None
     if not header:

datachain/lib/dc/datachain.py

@@ -84,22 +84,22 @@ class DataChain:
     underlyind library `Pydantic`.
 
     See Also:
-        `from_storage("s3://my-bucket/my-dir/")` - reading unstructured
+        `read_storage("s3://my-bucket/my-dir/")` - reading unstructured
             data files from storages such as S3, gs or Azure ADLS.
 
         `DataChain.save("name")` - saving to a dataset.
 
-        `from_dataset("name")` - reading from a dataset.
+        `read_dataset("name")` - reading from a dataset.
 
-        `from_values(fib=[1, 2, 3, 5, 8])` - generating from values.
+        `read_values(fib=[1, 2, 3, 5, 8])` - generating from values.
 
-        `from_pandas(pd.DataFrame(...))` - generating from pandas.
+        `read_pandas(pd.DataFrame(...))` - generating from pandas.
 
-        `from_json("file.json")` - generating from json.
+        `read_json("file.json")` - generating from json.
 
-        `from_csv("file.csv")` - generating from csv.
+        `read_csv("file.csv")` - generating from csv.
 
-        `from_parquet("file.parquet")` - generating from parquet.
+        `read_parquet("file.parquet")` - generating from parquet.
 
     Example:
         ```py
@@ -118,7 +118,7 @@ class DataChain:
         api_key = os.environ["MISTRAL_API_KEY"]
 
         chain = (
-            dc.from_storage("gs://datachain-demo/chatbot-KiT/")
+            dc.read_storage("gs://datachain-demo/chatbot-KiT/")
             .limit(5)
             .settings(cache=True, parallel=5)
             .map(
@@ -315,27 +315,27 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .storage import from_storage
+        from .storage import read_storage
 
         warnings.warn(
             "Class method `from_storage` is deprecated. "
-            "Use `from_storage` function instead from top_module.",
+            "Use `read_storage` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_storage(*args, **kwargs)
+        return read_storage(*args, **kwargs)
 
     @classmethod
     def from_dataset(cls, *args, **kwargs) -> "DataChain":
-        from .datasets import from_dataset
+        from .datasets import read_dataset
 
         warnings.warn(
             "Class method `from_dataset` is deprecated. "
-            "Use `from_dataset` function instead from top_module.",
+            "Use `read_dataset` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_dataset(*args, **kwargs)
+        return read_dataset(*args, **kwargs)
 
     @classmethod
     def from_json(
@@ -343,15 +343,15 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .json import from_json
+        from .json import read_json
 
         warnings.warn(
             "Class method `from_json` is deprecated. "
-            "Use `from_json` function instead from top_module.",
+            "Use `read_json` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_json(*args, **kwargs)
+        return read_json(*args, **kwargs)
 
     def explode(
         self,
@@ -487,7 +487,7 @@ class DataChain:
                 )
 
             chain = (
-                dc.from_storage("s3://my-bucket")
+                dc.read_storage("s3://my-bucket")
                 .apply(parse_stem)
                 .filter(C("stem").glob("*cat*"))
             )
@@ -727,7 +727,7 @@ class DataChain:
 
         Note:
             Order is not guaranteed when steps are added after an `order_by` statement.
-            I.e. when using `from_dataset` an `order_by` statement should be used if
+            I.e. when using `read_dataset` an `order_by` statement should be used if
             the order of the records in the chain is important.
             Using `order_by` directly before `limit`, `collect` and `collect_flatten`
             will give expected results.
@@ -1466,15 +1466,15 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .values import from_values
+        from .values import read_values
 
         warnings.warn(
             "Class method `from_values` is deprecated. "
-            "Use `from_values` function instead from top_module.",
+            "Use `read_values` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_values(*args, **kwargs)
+        return read_values(*args, **kwargs)
 
     @classmethod
     def from_pandas(
@@ -1482,15 +1482,15 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .pandas import from_pandas
+        from .pandas import read_pandas
 
         warnings.warn(
             "Class method `from_pandas` is deprecated. "
-            "Use `from_pandas` function instead from top_module.",
+            "Use `read_pandas` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_pandas(*args, **kwargs)
+        return read_pandas(*args, **kwargs)
 
     def to_pandas(self, flatten=False, include_hidden=True) -> "pd.DataFrame":
         """Return a pandas DataFrame from the chain.
@@ -1575,15 +1575,15 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .hf import from_hf
+        from .hf import read_hf
 
         warnings.warn(
             "Class method `from_hf` is deprecated. "
-            "Use `from_hf` function instead from top_module.",
+            "Use `read_hf` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_hf(*args, **kwargs)
+        return read_hf(*args, **kwargs)
 
     def parse_tabular(
         self,
@@ -1610,7 +1610,7 @@ class DataChain:
             Reading a json lines file:
             ```py
             import datachain as dc
-            chain = dc.from_storage("s3://mybucket/file.jsonl")
+            chain = dc.read_storage("s3://mybucket/file.jsonl")
             chain = chain.parse_tabular(format="json")
             ```
 
@@ -1618,7 +1618,7 @@ class DataChain:
             ```py
             import datachain as dc
 
-            chain = dc.from_storage("s3://mybucket")
+            chain = dc.read_storage("s3://mybucket")
             chain = chain.filter(dc.C("file.name").glob("*.jsonl"))
             chain = chain.parse_tabular(format="json")
             ```
@@ -1680,15 +1680,15 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .csv import from_csv
+        from .csv import read_csv
 
         warnings.warn(
             "Class method `from_csv` is deprecated. "
-            "Use `from_csv` function instead from top_module.",
+            "Use `read_csv` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_csv(*args, **kwargs)
+        return read_csv(*args, **kwargs)
 
     @classmethod
     def from_parquet(
@@ -1696,15 +1696,15 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .parquet import from_parquet
+        from .parquet import read_parquet
 
         warnings.warn(
             "Class method `from_parquet` is deprecated. "
-            "Use `from_parquet` function instead from top_module.",
+            "Use `read_parquet` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_parquet(*args, **kwargs)
+        return read_parquet(*args, **kwargs)
 
     def to_parquet(
         self,
@@ -1930,15 +1930,15 @@ class DataChain:
         *args,
         **kwargs,
     ) -> "DataChain":
-        from .records import from_records
+        from .records import read_records
 
         warnings.warn(
             "Class method `from_records` is deprecated. "
-            "Use `from_records` function instead from top_module.",
+            "Use `read_records` function instead from top_module.",
             DeprecationWarning,
             stacklevel=2,
         )
-        return from_records(*args, **kwargs)
+        return read_records(*args, **kwargs)
 
     def sum(self, fr: DataType):  # type: ignore[override]
         """Compute the sum of a column."""
@@ -1969,7 +1969,7 @@ class DataChain:
             import datachain as dc
 
             (
-                dc.from_storage(DATA, type="text")
+                dc.read_storage(DATA, type="text")
                 .settings(parallel=4, cache=True)
                 .setup(client=lambda: anthropic.Anthropic(api_key=API_KEY))
                 .map(
@@ -2021,7 +2021,7 @@ class DataChain:
             ```py
             import datachain as dc
 
-            ds = dc.from_storage("s3://mybucket")
+            ds = dc.read_storage("s3://mybucket")
             ds.to_storage("gs://mybucket", placement="filename")
             ```
         """
@@ -2139,7 +2139,7 @@ class DataChain:
             ```py
             import datachain as dc
 
-            chain = dc.from_storage(...)
+            chain = dc.read_storage(...)
             chunk_1 = query._chunk(0, 2)
             chunk_2 = query._chunk(1, 2)
             ```

datachain/lib/dc/datasets.py

@@ -13,7 +13,7 @@ from datachain.query import Session
 from datachain.query.dataset import DatasetQuery
 
 from .utils import Sys
-from .values import from_values
+from .values import read_values
 
 if TYPE_CHECKING:
     from typing_extensions import ParamSpec
@@ -23,7 +23,7 @@ if TYPE_CHECKING:
     P = ParamSpec("P")
 
 
-def from_dataset(
+def read_dataset(
     name: str,
     version: Optional[int] = None,
     session: Optional[Session] = None,
@@ -44,15 +44,15 @@ def from_dataset(
     Example:
         ```py
         import datachain as dc
-        chain = dc.from_dataset("my_cats")
+        chain = dc.read_dataset("my_cats")
         ```
 
         ```py
-        chain = dc.from_dataset("my_cats", fallback_to_studio=False)
+        chain = dc.read_dataset("my_cats", fallback_to_studio=False)
         ```
 
         ```py
-        chain = dc.from_dataset("my_cats", version=1)
+        chain = dc.read_dataset("my_cats", version=1)
         ```
 
         ```py
@@ -64,7 +64,7 @@ def from_dataset(
             "min_task_size": 1000,
             "prefetch": 10,
         }
-        chain = dc.from_dataset(
+        chain = dc.read_dataset(
             name="my_cats",
             version=1,
             session=session,
@@ -140,7 +140,7 @@ def datasets(
         )
     ]
 
-    return from_values(
+    return read_values(
         session=session,
         settings=settings,
         in_memory=in_memory,

datachain/lib/dc/hf.py

@@ -18,7 +18,7 @@ if TYPE_CHECKING:
     P = ParamSpec("P")
 
 
-def from_hf(
+def read_hf(
     dataset: Union[str, "HFDatasetType"],
     *args,
     session: Optional[Session] = None,
@@ -42,7 +42,7 @@ def from_hf(
         Load from Hugging Face Hub:
         ```py
         import datachain as dc
-        chain = dc.from_hf("beans", split="train")
+        chain = dc.read_hf("beans", split="train")
         ```
 
         Generate chain from loaded dataset:
@@ -50,12 +50,12 @@ def from_hf(
         from datasets import load_dataset
         ds = load_dataset("beans", split="train")
         import datachain as dc
-        chain = dc.from_hf(ds)
+        chain = dc.read_hf(ds)
         ```
     """
     from datachain.lib.hf import HFGenerator, get_output_schema, stream_splits
 
-    from .values import from_values
+    from .values import read_values
 
     output: dict[str, DataType] = {}
     ds_dict = stream_splits(dataset, *args, **kwargs)
@@ -69,5 +69,5 @@ def from_hf(
     if object_name:
         output = {object_name: model}
 
-    chain = from_values(split=list(ds_dict.keys()), session=session, settings=settings)
+    chain = read_values(split=list(ds_dict.keys()), session=session, settings=settings)
     return chain.gen(HFGenerator(dataset, model, *args, **kwargs), output=output)

datachain/lib/dc/json.py

@@ -22,7 +22,7 @@ if TYPE_CHECKING:
     P = ParamSpec("P")
 
 
-def from_json(
+def read_json(
     path: Union[str, os.PathLike[str]],
     type: FileType = "text",
     spec: Optional[DataType] = None,
@@ -52,16 +52,16 @@ def from_json(
         infer JSON schema from data, reduce using JMESPATH
         ```py
         import datachain as dc
-        chain = dc.from_json("gs://json", jmespath="key1.key2")
+        chain = dc.read_json("gs://json", jmespath="key1.key2")
         ```
 
         infer JSON schema from a particular path
         ```py
         import datachain as dc
-        chain = dc.from_json("gs://json_ds", schema_from="gs://json/my.json")
+        chain = dc.read_json("gs://json_ds", schema_from="gs://json/my.json")
         ```
     """
-    from .storage import from_storage
+    from .storage import read_storage
 
     if schema_from == "auto":
         schema_from = os.fspath(path)
@@ -74,7 +74,7 @@ def from_json(
         object_name = jmespath_to_name(jmespath)
     if not object_name:
         object_name = format
-    chain = from_storage(uri=path, type=type, **kwargs)
+    chain = read_storage(uri=path, type=type, **kwargs)
     signal_dict = {
         object_name: read_meta(
             schema_from=schema_from,

datachain/lib/dc/listings.py

@@ -6,7 +6,7 @@ from typing import (
 from datachain.lib.listing_info import ListingInfo
 from datachain.query import Session
 
-from .values import from_values
+from .values import read_values
 
 if TYPE_CHECKING:
     from typing_extensions import ParamSpec
@@ -35,7 +35,7 @@ def listings(
     session = Session.get(session, in_memory=in_memory)
     catalog = kwargs.get("catalog") or session.catalog
 
-    return from_values(
+    return read_values(
         session=session,
         in_memory=in_memory,
         output={object_name: ListingInfo},

datachain/lib/dc/pandas.py

@@ -5,7 +5,7 @@ from typing import (
 
 from datachain.query import Session
 
-from .values import from_values
+from .values import read_values
 
 if TYPE_CHECKING:
     import pandas as pd
@@ -16,7 +16,7 @@ if TYPE_CHECKING:
     P = ParamSpec("P")
 
 
-def from_pandas(  # type: ignore[override]
+def read_pandas(  # type: ignore[override]
     df: "pd.DataFrame",
     name: str = "",
     session: Optional[Session] = None,
@@ -32,7 +32,7 @@ def from_pandas(  # type: ignore[override]
         import datachain as dc
 
         df = pd.DataFrame({"fib": [1, 2, 3, 5, 8]})
-        dc.from_pandas(df)
+        dc.read_pandas(df)
         ```
     """
     from .utils import DatasetPrepareError
@@ -46,7 +46,7 @@ def from_pandas(  # type: ignore[override]
                 f"import from pandas error - '{column}' cannot be a column name",
             )
 
-    return from_values(
+    return read_values(
         name,
         session,
         settings=settings,

datachain/lib/dc/parquet.py

@@ -15,7 +15,7 @@ if TYPE_CHECKING:
     P = ParamSpec("P")
 
 
-def from_parquet(
+def read_parquet(
     path,
     partitioning: Any = "hive",
     output: Optional[dict[str, DataType]] = None,
@@ -43,18 +43,18 @@ def from_parquet(
         Reading a single file:
         ```py
         import datachain as dc
-        dc.from_parquet("s3://mybucket/file.parquet")
+        dc.read_parquet("s3://mybucket/file.parquet")
         ```
 
         Reading a partitioned dataset from a directory:
         ```py
         import datachain as dc
-        dc.from_parquet("s3://mybucket/dir")
+        dc.read_parquet("s3://mybucket/dir")
         ```
     """
-    from .storage import from_storage
+    from .storage import read_storage
 
-    chain = from_storage(path, session=session, settings=settings, **kwargs)
+    chain = read_storage(path, session=session, settings=settings, **kwargs)
     return chain.parse_tabular(
         output=output,
         object_name=object_name,

datachain/lib/dc/records.py

@@ -21,7 +21,7 @@ if TYPE_CHECKING:
     P = ParamSpec("P")
 
 
-def from_records(
+def read_records(
     to_insert: Optional[Union[dict, list[dict]]],
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
@@ -40,10 +40,10 @@ def from_records(
     Example:
         ```py
         import datachain as dc
-        single_record = dc.from_records(dc.DEFAULT_FILE_RECORD)
+        single_record = dc.read_records(dc.DEFAULT_FILE_RECORD)
         ```
     """
-    from .datasets import from_dataset
+    from .datasets import read_dataset
 
     session = Session.get(session, in_memory=in_memory)
     catalog = session.catalog
@@ -87,4 +87,4 @@ def from_records(
     insert_q = dr.get_table().insert()
     for record in to_insert:
         db.execute(insert_q.values(**record))
-    return from_dataset(name=dsr.name, session=session, settings=settings)
+    return read_dataset(name=dsr.name, session=session, settings=settings)

datachain/lib/dc/storage.py

@@ -21,7 +21,7 @@ if TYPE_CHECKING:
     from .datachain import DataChain
 
 
-def from_storage(
+def read_storage(
     uri: Union[str, os.PathLike[str], list[str], list[os.PathLike[str]]],
     *,
     type: FileType = "binary",
@@ -55,12 +55,12 @@ def from_storage(
         Simple call from s3:
         ```python
         import datachain as dc
-        chain = dc.from_storage("s3://my-bucket/my-dir")
+        chain = dc.read_storage("s3://my-bucket/my-dir")
         ```
 
         Multiple URIs:
         ```python
-        chain = dc.from_storage([
+        chain = dc.read_storage([
             "s3://bucket1/dir1",
             "s3://bucket2/dir2"
         ])
@@ -68,7 +68,7 @@ def from_storage(
 
         With AWS S3-compatible storage:
         ```python
-        chain = dc.from_storage(
+        chain = dc.read_storage(
             "s3://my-bucket/my-dir",
             client_config = {"aws_endpoint_url": "<minio-endpoint-url>"}
         )
@@ -77,7 +77,7 @@ def from_storage(
         Pass existing session
         ```py
         session = Session.get()
-        chain = dc.from_storage([
+        chain = dc.read_storage([
             "path/to/dir1",
             "path/to/dir2"
         ], session=session, recursive=True)
@@ -88,9 +88,9 @@ def from_storage(
         avoiding redundant updates for URIs pointing to the same storage location.
     """
     from .datachain import DataChain
-    from .datasets import from_dataset
-    from .records import from_records
-    from .values import from_values
+    from .datasets import read_dataset
+    from .records import read_records
+    from .values import read_values
 
     file_type = get_file_type(type)
 
@@ -122,7 +122,8 @@ def from_storage(
             )
             continue
 
-        dc = from_dataset(list_ds_name, session=session, settings=settings)
+        dc = read_dataset(list_ds_name, session=session, settings=settings)
+        dc._query.update = update
         dc.signals_schema = dc.signals_schema.mutate({f"{object_name}": file_type})
 
         if update or not list_ds_exists:
@@ -130,7 +131,7 @@ def from_storage(
             def lst_fn(ds_name, lst_uri):
                 # disable prefetch for listing, as it pre-downloads all files
                 (
-                    from_records(
+                    read_records(
                         DataChain.DEFAULT_FILE_RECORD,
                         session=session,
                         settings=settings,
@@ -144,7 +145,7 @@ def from_storage(
                     .save(ds_name, listing=True)
                 )
 
-            dc._query.add_before_steps(
+            dc._query.set_listing_fn(
                 lambda ds_name=list_ds_name, lst_uri=list_uri: lst_fn(ds_name, lst_uri)
             )
 
@@ -154,7 +155,7 @@ def from_storage(
         listed_ds_name.add(list_ds_name)
 
     if file_values:
-        file_chain = from_values(
+        file_chain = read_values(
             session=session,
             settings=settings,
             in_memory=in_memory,

datachain/lib/dc/values.py

@@ -6,7 +6,7 @@ from typing import (
 
 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.records import read_records
 from datachain.lib.dc.utils import OutputType
 from datachain.query import Session
 
@@ -18,7 +18,7 @@ if TYPE_CHECKING:
     P = ParamSpec("P")
 
 
-def from_values(
+def read_values(
     ds_name: str = "",
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
@@ -32,7 +32,7 @@ def from_values(
     Example:
         ```py
         import datachain as dc
-        dc.from_values(fib=[1, 2, 3, 5, 8])
+        dc.read_values(fib=[1, 2, 3, 5, 8])
         ```
     """
     from .datachain import DataChain
@@ -42,7 +42,7 @@ def from_values(
     def _func_fr() -> Iterator[tuple_type]:  # type: ignore[valid-type]
         yield from tuples
 
-    chain = from_records(
+    chain = read_records(
         DataChain.DEFAULT_FILE_RECORD,
         session=session,
         settings=settings,

datachain/lib/listing.py

@@ -4,6 +4,7 @@ import os
 import posixpath
 from collections.abc import Iterator
 from contextlib import contextmanager
+from datetime import datetime, timedelta, timezone
 from typing import TYPE_CHECKING, Callable, Optional, TypeVar, Union
 
 from fsspec.asyn import get_loop
@@ -32,6 +33,16 @@ logging.getLogger("aiobotocore.credentials").setLevel(logging.CRITICAL)
 logging.getLogger("gcsfs").setLevel(logging.CRITICAL)
 
 
+def listing_dataset_expired(lst_ds) -> bool:
+    """Function that checks if listing dataset is expired or not"""
+    lst_version = lst_ds.versions[-1]
+    if not lst_version.finished_at:
+        return False
+
+    expires = lst_version.finished_at + timedelta(seconds=LISTING_TTL)
+    return datetime.now(timezone.utc) > expires
+
+
 def list_bucket(uri: str, cache, client_config=None) -> Callable:
     """
     Function that returns another generator function that yields File objects

datachain/lib/meta_formats.py

@@ -103,10 +103,10 @@ def read_meta(  # noqa: C901
     model_name=None,
     nrows=None,
 ) -> Callable:
-    from datachain import from_storage
+    from datachain import read_storage
 
     if schema_from:
-        file = next(from_storage(schema_from, type="text").limit(1).collect("file"))
+        file = next(read_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.datasets import from_dataset
+from datachain.lib.dc.datasets import read_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 = from_dataset(
+        ds = read_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

@@ -145,7 +145,7 @@ class UDFBase(AbstractUDF):
                 return emb[0].tolist()
 
         (
-            dc.from_storage(
+            dc.read_storage(
                 "gs://datachain-demo/fashion-product-images/images", type="image"
             )
             .limit(5)

datachain/query/dataset.py

@@ -47,7 +47,10 @@ from datachain.error import (
     QueryScriptCancelError,
 )
 from datachain.func.base import Function
-from datachain.lib.listing import is_listing_dataset
+from datachain.lib.listing import (
+    is_listing_dataset,
+    listing_dataset_expired,
+)
 from datachain.lib.udf import UDFAdapter, _get_cache
 from datachain.progress import CombinedDownloadCallback, TqdmCombinedDownloadCallback
 from datachain.query.schema import C, UDFParamSpec, normalize_param
@@ -1080,6 +1083,7 @@ class DatasetQuery:
         indexing_column_types: Optional[dict[str, Any]] = None,
         in_memory: bool = False,
         fallback_to_studio: bool = True,
+        update: bool = False,
     ) -> None:
         from datachain.remote.studio import is_token_set
 
@@ -1097,6 +1101,8 @@ class DatasetQuery:
         self.feature_schema: Optional[dict] = None
         self.column_types: Optional[dict[str, Any]] = None
         self.before_steps: list[Callable] = []
+        self.listing_fn: Optional[Callable] = None
+        self.update = update
 
         self.list_ds_name: Optional[str] = None
 
@@ -1190,23 +1196,30 @@ class DatasetQuery:
         col.table = self.table
         return col
 
-    def add_before_steps(self, fn: Callable) -> None:
-        """
-        Setting custom function to be run before applying steps
-        """
-        self.before_steps.append(fn)
+    def set_listing_fn(self, fn: Callable) -> None:
+        """Setting listing function to be run if needed"""
+        self.listing_fn = fn
 
     def apply_steps(self) -> QueryGenerator:
         """
         Apply the steps in the query and return the resulting
         sqlalchemy.SelectBase.
         """
-        for fn in self.before_steps:
-            fn()
+        if self.list_ds_name and not self.starting_step:
+            listing_ds = None
+            try:
+                listing_ds = self.catalog.get_dataset(self.list_ds_name)
+            except DatasetNotFoundError:
+                pass
+
+            if not listing_ds or self.update or listing_dataset_expired(listing_ds):
+                assert self.listing_fn
+                self.listing_fn()
+                listing_ds = self.catalog.get_dataset(self.list_ds_name)
 
-        if self.list_ds_name:
             # at this point we know what is our starting listing dataset name
-            self._set_starting_step(self.catalog.get_dataset(self.list_ds_name))  # type: ignore [arg-type]
+            self._set_starting_step(listing_ds)  # type: ignore [arg-type]
+
         query = self.clone()
 
         index = os.getenv("DATACHAIN_QUERY_CHUNK_INDEX", self._chunk_index)

datachain/toolkit/split.py

@@ -41,7 +41,7 @@ def train_test_split(
         from datachain.toolkit import train_test_split
 
         # Load a DataChain from a storage source (e.g., S3 bucket)
-        dc = dc.from_storage("s3://bucket/dir/")
+        dc = dc.read_storage("s3://bucket/dir/")
 
         # Perform a 70/30 train-test split
         train, test = train_test_split(dc, [0.7, 0.3])

{datachain-0.14.1.dist-info → datachain-0.14.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.14.1
+Version: 0.14.2
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -38,7 +38,7 @@ Requires-Dist: sqlalchemy>=2
 Requires-Dist: multiprocess==0.70.16
 Requires-Dist: cloudpickle
 Requires-Dist: orjson>=3.10.5
-Requires-Dist: pydantic<3,>=2
+Requires-Dist: pydantic<2.11,>=2
 Requires-Dist: jmespath>=1.0
 Requires-Dist: datamodel-code-generator>=0.25
 Requires-Dist: Pillow<12,>=10.0.0
@@ -171,8 +171,8 @@ high confidence scores.
 
     import datachain as dc
 
-    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)
+    meta = dc.read_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
+    images = dc.read_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")
@@ -213,7 +213,7 @@ Python code:
          return result.lower().startswith("success")
 
     chain = (
-       dc.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+       dc.read_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
        .settings(parallel=4, cache=True)
        .map(is_success=eval_dialogue)
        .save("mistral_files")

{datachain-0.14.1.dist-info → datachain-0.14.2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datachain/__init__.py,sha256=M_0MfSBJqlWA9hI3z47Yu36fxkxsekbpvNa-LBa1e5Q,1414
+datachain/__init__.py,sha256=h3W0agyTcpXOfMA26jZyHo-Gs7vLXhbR-9uEkzK8Szk,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=FGW2cEOysgVMyokqIFAJ1PB-RYJrqDEFGfHP5qLYO-k,60729
+datachain/catalog/catalog.py,sha256=k-okQ4aqoyWrsNlDeCz6jP6TNRiZCUENbGV9Sz6EEtw,60729
 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
@@ -29,7 +29,7 @@ datachain/cli/commands/index.py,sha256=eglNaIe1yyIadUHHumjtNbgIjht6kme7SS7xE3YHR
 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=pn8jQ5HqUpzZE3KE-iydflp8LGgfVIKR8eKwVKv6A-8,1604
+datachain/cli/commands/show.py,sha256=P6e6bYiRCyVKO0ggnoFkLkwGmBWlrlm8W5c_sBNxBBw,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
@@ -73,16 +73,16 @@ datachain/lib/dataset_info.py,sha256=IjdF1E0TQNOq9YyynfWiCFTeZpbyGfyJvxgJY4YN810
 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.py,sha256=O29s7H-2rqjHHGKWkKGNNXlo2zynv4pygVTKImpV8fo,7046
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
-datachain/lib/meta_formats.py,sha256=f-irPQH_acIYT5gzjqoOvGrGOQrm-E_0wN-4lqZF_j8,6349
+datachain/lib/meta_formats.py,sha256=Epydbdch1g4CojK8wd_ePzmwmljC4fVWlJtZ16jsX-A,6349
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
-datachain/lib/pytorch.py,sha256=FFCZoVkoG_FY_vJ4v_DgzijEEcTozuddlPz1uAa5tyg,7712
+datachain/lib/pytorch.py,sha256=YS6yR13iVlrAXo5wzJswFFUHwWOql9KTdWIa86DXB-k,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=6ZCn9qIAVwQA4zEyWiTb1jaSLkpkBXeGeaH8EB7Im3I,16168
+datachain/lib/udf.py,sha256=h38a457xg-4wO2XcxPs4pzDq8JxTmYm4N84iAf0HRzY,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
@@ -94,19 +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=mlrqsmxLDYNP7dmde3IDYP01QlbUzP8Pj5UDqlqJcZ0,2725
-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=mIAlNEYRJ8r3yHA2sJyt8duwuSfehbPro7WqMQvezIc,5295
+datachain/lib/dc/__init__.py,sha256=6rKKHS6MA3mS6UJXiysrv4TURs4R_UWAQK2tJ2t1QMs,743
+datachain/lib/dc/csv.py,sha256=d0ULzpsTTeqp_eM-2jVHb1kYHQN2lJFf4O6LWd5tOJw,4401
+datachain/lib/dc/datachain.py,sha256=hwuAElfEhRLyh-Uvuc7YIpFx6nsI_B90xwnMqgkkgrI,76390
+datachain/lib/dc/datasets.py,sha256=hTzq18Ij9kpOAJOU-VN4-VyThTTxLSWLfVIk3bgzAPs,4329
+datachain/lib/dc/hf.py,sha256=I1vFNOa1C87lBuBj5FHENLY2jTaQ8erngiX0cyBmOp4,2170
+datachain/lib/dc/json.py,sha256=9ei9ZNzWVXZWD4HNGTfBhcoLPnXBBDywKV-3Wi1mT28,2725
+datachain/lib/dc/listings.py,sha256=qPy1DTvYkbNICT1ujo8LwezzMEW8E3dln1knw7Jwl0I,1044
+datachain/lib/dc/pandas.py,sha256=jJvgNPPjiSLAjdYlhI4fvGKNWRh-hbMgZyBlURS633E,1249
+datachain/lib/dc/parquet.py,sha256=lXCSr_S7bQsPUWq1pJ-Ur8R8RxArjyFpCpBXK-aorQw,1809
+datachain/lib/dc/records.py,sha256=DOFkQV7A7kZnMiCS4mHOzee2ibWIhz-mWQpgVsU78SE,2524
+datachain/lib/dc/storage.py,sha256=kM3Ix2L0j01a4XcXPZpdDxvici9yu-Ks-Cd3uf_qESA,5327
 datachain/lib/dc/utils.py,sha256=Ct-0FqCaDhNWHx09gJFcCXJGPjMI-VZr4t-GJyqTi44,3984
-datachain/lib/dc/values.py,sha256=PLBZew0BYO3mv7W3n8OF5Ad-5tp5eWPqlbiVxG5pJ30,1409
+datachain/lib/dc/values.py,sha256=HaABQKmhgW-N1pcBn7CQuTIiOFXYVjU1H9LbupGM3WQ,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
@@ -118,7 +118,7 @@ datachain/model/ultralytics/pose.py,sha256=gXAWfAk4OWZl93hKcQPKZvqJa3nIrECB4RM8K
 datachain/model/ultralytics/segment.py,sha256=koq1HASo29isf0in6oSlzmU4IzsmOXe87F1ajQQVfh4,2911
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=6w8gzLTmLeylststu-gT5jIqEfi4-djS7_yTYyeo-fw,4190
-datachain/query/dataset.py,sha256=Em5vfKkZygzXCiWRYUBGLSh3eWlIamMBvh328YNnmww,58201
+datachain/query/dataset.py,sha256=G_fyt3vwifY5Usnp8pvkho543innrcDOImKLqG3W3YU,58665
 datachain/query/dispatch.py,sha256=_1vjeQ1wjUoxlik55k0JkWqQCUfMjgVWmEOyWRkx0dU,12437
 datachain/query/metrics.py,sha256=r5b0ygYhokbXp8Mg3kCH8iFSRw0jxzyeBe-C-J_bKFc,938
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
@@ -148,11 +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=VdcP_zVLqAxuSrze3BaR-dBzTmyKkCUAiAremw3OEPU,2914
+datachain/toolkit/split.py,sha256=ktGWzY4kyzjWyR86dhvzw-Zhl0lVk_LOX3NciTac6qo,2914
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.14.1.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.14.1.dist-info/METADATA,sha256=UPk0v7fsYz_eTsJf5YpexjD4jrjpWsKEyAVNSXN3KvE,11335
-datachain-0.14.1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-datachain-0.14.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.14.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.14.1.dist-info/RECORD,,
+datachain-0.14.2.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.14.2.dist-info/METADATA,sha256=hvPp9rvpa2p9FnopnOrd4DvJE1Rugef5YHe8vViSPyI,11338
+datachain-0.14.2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+datachain-0.14.2.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.14.2.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.14.2.dist-info/RECORD,,