datachain 0.14.3__py3-none-any.whl → 0.14.5__py3-none-any.whl

datachain/catalog/catalog.py

@@ -580,15 +580,13 @@ class Catalog:
         source: str,
         update=False,
         client_config=None,
-        object_name="file",
+        column="file",
         skip_indexing=False,
     ) -> tuple[Optional["Listing"], "Client", str]:
         from datachain import read_storage
         from datachain.listing import Listing
 
-        read_storage(
-            source, session=self.session, update=update, object_name=object_name
-        ).exec()
+        read_storage(source, session=self.session, update=update, column=column).exec()
 
         list_ds_name, list_uri, list_path, _ = get_listing(
             source, self.session, update=update
@@ -602,7 +600,7 @@ class Catalog:
                 self.warehouse.clone(),
                 client,
                 dataset_name=list_ds_name,
-                object_name=object_name,
+                column=column,
             )
 
         return lst, client, list_path

datachain/data_storage/schema.py

@@ -30,8 +30,8 @@ if TYPE_CHECKING:
 DEFAULT_DELIMITER = "__"
 
 
-def col_name(name: str, object_name: str = "file") -> str:
-    return f"{object_name}{DEFAULT_DELIMITER}{name}"
+def col_name(name: str, column: str = "file") -> str:
+    return f"{column}{DEFAULT_DELIMITER}{name}"
 
 
 def dedup_columns(columns: Iterable[sa.Column]) -> list[sa.Column]:
@@ -84,19 +84,19 @@ def convert_rows_custom_column_types(
 
 
 class DirExpansion:
-    def __init__(self, object_name: str):
-        self.object_name = object_name
+    def __init__(self, column: str):
+        self.column = column
 
-    def col_name(self, name: str, object_name: Optional[str] = None) -> str:
-        object_name = object_name or self.object_name
-        return col_name(name, object_name)
+    def col_name(self, name: str, column: Optional[str] = None) -> str:
+        column = column or self.column
+        return col_name(name, column)
 
-    def c(self, query, name: str, object_name: Optional[str] = None) -> str:
-        return getattr(query.c, self.col_name(name, object_name=object_name))
+    def c(self, query, name: str, column: Optional[str] = None) -> str:
+        return getattr(query.c, self.col_name(name, column=column))
 
     def base_select(self, q):
         return sa.select(
-            self.c(q, "id", object_name="sys"),
+            self.c(q, "id", column="sys"),
             false().label(self.col_name("is_dir")),
             self.c(q, "source"),
             self.c(q, "path"),
@@ -153,12 +153,12 @@ class DataTable:
         name: str,
         engine: "DatabaseEngine",
         column_types: Optional[dict[str, SQLType]] = None,
-        object_name: str = "file",
+        column: str = "file",
     ):
         self.name: str = name
         self.engine = engine
         self.column_types: dict[str, SQLType] = column_types or {}
-        self.object_name = object_name
+        self.column = column
 
     @staticmethod
     def copy_column(
@@ -224,18 +224,16 @@ class DataTable:
     def columns(self) -> "ReadOnlyColumnCollection[str, sa.Column[Any]]":
         return self.table.columns
 
-    def col_name(self, name: str, object_name: Optional[str] = None) -> str:
-        object_name = object_name or self.object_name
-        return col_name(name, object_name)
+    def col_name(self, name: str, column: Optional[str] = None) -> str:
+        column = column or self.column
+        return col_name(name, column)
 
-    def without_object(
-        self, column_name: str, object_name: Optional[str] = None
-    ) -> str:
-        object_name = object_name or self.object_name
-        return column_name.removeprefix(f"{object_name}{DEFAULT_DELIMITER}")
+    def without_object(self, column_name: str, column: Optional[str] = None) -> str:
+        column = column or self.column
+        return column_name.removeprefix(f"{column}{DEFAULT_DELIMITER}")
 
-    def c(self, name: str, object_name: Optional[str] = None):
-        return getattr(self.columns, self.col_name(name, object_name=object_name))
+    def c(self, name: str, column: Optional[str] = None):
+        return getattr(self.columns, self.col_name(name, column=column))
 
     @property
     def table(self) -> "sa.Table":
@@ -275,7 +273,7 @@ class DataTable:
         ]
 
     def dir_expansion(self):
-        return DirExpansion(self.object_name)
+        return DirExpansion(self.column)
 
 
 PARTITION_COLUMN_ID = "partition_id"

datachain/data_storage/sqlite.py

@@ -489,7 +489,7 @@ class SQLiteWarehouse(AbstractWarehouse):
         self, dataset: DatasetRecord, version: int
     ) -> list[StorageURI]:
         dr = self.dataset_rows(dataset, version)
-        query = dr.select(dr.c("source", object_name="file")).distinct()
+        query = dr.select(dr.c("source", column="file")).distinct()
         cur = self.db.cursor()
         cur.row_factory = sqlite3.Row  # type: ignore[assignment]
 

datachain/data_storage/warehouse.py

@@ -179,7 +179,7 @@ class AbstractWarehouse(ABC, Serializable):
         self,
         dataset: DatasetRecord,
         version: Optional[int] = None,
-        object_name: str = "file",
+        column: str = "file",
     ):
         version = version or dataset.latest_version
 
@@ -188,7 +188,7 @@ class AbstractWarehouse(ABC, Serializable):
             table_name,
             self.db,
             dataset.get_schema(version),
-            object_name=object_name,
+            column=column,
         )
 
     @property
@@ -487,7 +487,7 @@ class AbstractWarehouse(ABC, Serializable):
         dataset_rows: "DataTable",
         path_list: list[str],
         glob_name: str,
-        object_name="file",
+        column="file",
     ) -> Iterator[Node]:
         """Finds all Nodes that correspond to GLOB like path pattern."""
         dr = dataset_rows
@@ -521,7 +521,7 @@ class AbstractWarehouse(ABC, Serializable):
         de = dr.dir_expansion()
         q = de.query(
             dr.select().where(dr.c("is_latest") == true()).subquery(),
-            object_name=dr.object_name,
+            column=dr.column,
         ).subquery()
         q = self.expand_query(de, q, dr)
 
@@ -597,12 +597,10 @@ class AbstractWarehouse(ABC, Serializable):
             with_default(dr.c("is_latest")),
             dr.c("last_modified"),
             with_default(dr.c("size")),
-            with_default(dr.c("rand", object_name="sys")),
+            with_default(dr.c("rand", column="sys")),
             dr.c("location"),
             de.c(q, "source"),
-        ).select_from(
-            q.outerjoin(dr.table, q.c.sys__id == dr.c("id", object_name="sys"))
-        )
+        ).select_from(q.outerjoin(dr.table, q.c.sys__id == dr.c("id", column="sys")))
 
     def get_node_by_path(self, dataset_rows: "DataTable", path: str) -> Node:
         """Gets node that corresponds to some path"""

datachain/lib/dataset_info.py

@@ -12,6 +12,7 @@ from datachain.dataset import (
 )
 from datachain.job import Job
 from datachain.lib.data_model import DataModel
+from datachain.query.session import Session
 from datachain.utils import TIME_ZERO
 
 if TYPE_CHECKING:
@@ -32,6 +33,10 @@ class DatasetInfo(DataModel):
     error_message: str = Field(default="")
     error_stack: str = Field(default="")
 
+    @property
+    def is_temp(self) -> bool:
+        return Session.is_temp_dataset(self.name)
+
     @staticmethod
     def _validate_dict(
         v: Optional[Union[str, dict]],

datachain/lib/dc/csv.py

@@ -21,7 +21,7 @@ def read_csv(
     delimiter: Optional[str] = None,
     header: bool = True,
     output: OutputType = None,
-    object_name: str = "",
+    column: str = "",
     model_name: str = "",
     source: bool = True,
     nrows=None,
@@ -42,7 +42,7 @@ def read_csv(
         output : Dictionary or feature class defining column names and their
             corresponding types. List of column names is also accepted, in which
             case types will be inferred.
-        object_name : Created object column name.
+        column : Created column name.
         model_name : Generated model name.
         source : Whether to include info about the source file.
         nrows : Optional row limit.
@@ -119,7 +119,7 @@ def read_csv(
     )
     return chain.parse_tabular(
         output=output,
-        object_name=object_name,
+        column=column,
         model_name=model_name,
         source=source,
         nrows=nrows,

datachain/lib/dc/datachain.py

@@ -357,7 +357,7 @@ class DataChain:
         self,
         col: str,
         model_name: Optional[str] = None,
-        object_name: Optional[str] = None,
+        column: Optional[str] = None,
         schema_sample_size: int = 1,
     ) -> "DataChain":
         """Explodes a column containing JSON objects (dict or str DataChain type) into
@@ -368,7 +368,7 @@ class DataChain:
             col: the name of the column containing JSON to be exploded.
             model_name: optional generated model name.  By default generates the name
                 automatically.
-            object_name: optional generated object column name. By default generates the
+            column: optional generated column name. By default generates the
                 name automatically.
             schema_sample_size: the number of rows to use for inferring the schema of
                 the JSON (in case some fields are optional and it's not enough to
@@ -406,10 +406,10 @@ class DataChain:
             )
             return model.model_validate(json_dict)
 
-        if not object_name:
-            object_name = f"{col}_expl"
+        if not column:
+            column = f"{col}_expl"
 
-        return self.map(json_to_model, params=col, output={object_name: model})
+        return self.map(json_to_model, params=col, output={column: model})
 
     @classmethod
     def datasets(
@@ -1588,7 +1588,7 @@ class DataChain:
     def parse_tabular(
         self,
         output: OutputType = None,
-        object_name: str = "",
+        column: str = "",
         model_name: str = "",
         source: bool = True,
         nrows: Optional[int] = None,
@@ -1600,7 +1600,7 @@ class DataChain:
             output : Dictionary or feature class defining column names and their
                 corresponding types. List of column names is also accepted, in which
                 case types will be inferred.
-            object_name : Generated object column name.
+            column : Generated column name.
             model_name : Generated model name.
             source : Whether to include info about the source file.
             nrows : Optional row limit.
@@ -1651,14 +1651,14 @@ class DataChain:
                 raise DatasetPrepareError(self.name, e) from e
 
         if isinstance(output, dict):
-            model_name = model_name or object_name or ""
+            model_name = model_name or column or ""
             model = dict_to_data_model(model_name, output)
             output = model
         else:
             model = output  # type: ignore[assignment]
 
-        if object_name:
-            output = {object_name: model}  # type: ignore[dict-item]
+        if column:
+            output = {column: model}  # type: ignore[dict-item]
         elif isinstance(output, type(BaseModel)):
             output = {
                 name: info.annotation  # type: ignore[misc]

datachain/lib/dc/datasets.py

@@ -1,7 +1,4 @@
-from typing import (
-    TYPE_CHECKING,
-    Optional,
-)
+from typing import TYPE_CHECKING, Optional, get_origin, get_type_hints
 
 from datachain.lib.dataset_info import DatasetInfo
 from datachain.lib.file import (
@@ -102,7 +99,7 @@ def datasets(
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
     in_memory: bool = False,
-    object_name: str = "dataset",
+    column: Optional[str] = None,
     include_listing: bool = False,
     studio: bool = False,
 ) -> "DataChain":
@@ -112,7 +109,8 @@ def datasets(
         session: Optional session instance. If not provided, uses default session.
         settings: Optional dictionary of settings to configure the chain.
         in_memory: If True, creates an in-memory session. Defaults to False.
-        object_name: Name of the output object in the chain. Defaults to "dataset".
+        column: Name of the output column in the chain. Defaults to None which
+            means no top level column will be created.
         include_listing: If True, includes listing datasets. Defaults to False.
         studio: If True, returns datasets from Studio only,
             otherwise returns all local datasets. Defaults to False.
@@ -124,7 +122,7 @@ def datasets(
         ```py
         import datachain as dc
 
-        chain = dc.datasets()
+        chain = dc.datasets(column="dataset")
         for ds in chain.collect("dataset"):
             print(f"{ds.name}@v{ds.version}")
         ```
@@ -139,11 +137,32 @@ def datasets(
             include_listing=include_listing, studio=studio
         )
     ]
+    datasets_values = [d for d in datasets_values if not d.is_temp]
+
+    if not column:
+        # flattening dataset fields
+        schema = {
+            k: get_origin(v) if get_origin(v) is dict else v
+            for k, v in get_type_hints(DatasetInfo).items()
+            if k in DatasetInfo.model_fields
+        }
+        data = {k: [] for k in DatasetInfo.model_fields}  # type: ignore[var-annotated]
+        for d in [d.model_dump() for d in datasets_values]:
+            for field, value in d.items():
+                data[field].append(value)
+
+        return read_values(
+            session=session,
+            settings=settings,
+            in_memory=in_memory,
+            output=schema,
+            **data,  # type: ignore[arg-type]
+        )
 
     return read_values(
         session=session,
         settings=settings,
         in_memory=in_memory,
-        output={object_name: DatasetInfo},
-        **{object_name: datasets_values},  # type: ignore[arg-type]
+        output={column: DatasetInfo},
+        **{column: datasets_values},  # type: ignore[arg-type]
     )

datachain/lib/dc/hf.py

@@ -23,7 +23,7 @@ def read_hf(
     *args,
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
-    object_name: str = "",
+    column: str = "",
     model_name: str = "",
     **kwargs,
 ) -> "DataChain":
@@ -34,7 +34,7 @@ def read_hf(
             or an instance of `datasets.Dataset`-like object.
         session : Session to use for the chain.
         settings : Settings to use for the chain.
-        object_name : Generated object column name.
+        column : Generated object column name.
         model_name : Generated model name.
         kwargs : Parameters to pass to datasets.load_dataset.
 
@@ -62,12 +62,12 @@ def read_hf(
     if len(ds_dict) > 1:
         output = {"split": str}
 
-    model_name = model_name or object_name or ""
+    model_name = model_name or column or ""
     hf_features = next(iter(ds_dict.values())).features
     output = output | get_output_schema(hf_features)
     model = dict_to_data_model(model_name, output)
-    if object_name:
-        output = {object_name: model}
+    if column:
+        output = {column: model}
 
     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

@@ -28,7 +28,7 @@ def read_json(
     spec: Optional[DataType] = None,
     schema_from: Optional[str] = "auto",
     jmespath: Optional[str] = None,
-    object_name: Optional[str] = "",
+    column: Optional[str] = "",
     model_name: Optional[str] = None,
     format: Optional[str] = "json",
     nrows=None,
@@ -42,7 +42,7 @@ def read_json(
         type : read file as "binary", "text", or "image" data. Default is "text".
         spec : optional Data Model
         schema_from : path to sample to infer spec (if schema not provided)
-        object_name : generated object column name
+        column : generated column name
         model_name : optional generated model name
         format: "json", "jsonl"
         jmespath : optional JMESPATH expression to reduce JSON
@@ -70,13 +70,13 @@ def read_json(
         name_end = re.search(r"\W", s).start() if re.search(r"\W", s) else len(s)  # type: ignore[union-attr]
         return s[:name_end]
 
-    if (not object_name) and jmespath:
-        object_name = jmespath_to_name(jmespath)
-    if not object_name:
-        object_name = format
+    if (not column) and jmespath:
+        column = jmespath_to_name(jmespath)
+    if not column:
+        column = format
     chain = read_storage(uri=path, type=type, **kwargs)
     signal_dict = {
-        object_name: read_meta(
+        column: read_meta(
             schema_from=schema_from,
             format=format,
             spec=spec,

datachain/lib/dc/listings.py

@@ -19,7 +19,7 @@ if TYPE_CHECKING:
 def listings(
     session: Optional[Session] = None,
     in_memory: bool = False,
-    object_name: str = "listing",
+    column: str = "listing",
     **kwargs,
 ) -> "DataChain":
     """Generate chain with list of cached listings.
@@ -38,6 +38,6 @@ def listings(
     return read_values(
         session=session,
         in_memory=in_memory,
-        output={object_name: ListingInfo},
-        **{object_name: catalog.listings()},  # type: ignore[arg-type]
+        output={column: ListingInfo},
+        **{column: catalog.listings()},  # type: ignore[arg-type]
     )

datachain/lib/dc/pandas.py

@@ -22,7 +22,7 @@ def read_pandas(  # type: ignore[override]
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
     in_memory: bool = False,
-    object_name: str = "",
+    column: str = "",
 ) -> "DataChain":
     """Generate chain from pandas data-frame.
 
@@ -39,18 +39,18 @@ def read_pandas(  # type: ignore[override]
 
     fr_map = {col.lower(): df[col].tolist() for col in df.columns}
 
-    for column in fr_map:
-        if not column.isidentifier():
+    for c in fr_map:
+        if not c.isidentifier():
             raise DatasetPrepareError(
                 name,
-                f"import from pandas error - '{column}' cannot be a column name",
+                f"import from pandas error - '{c}' cannot be a column name",
             )
 
     return read_values(
         name,
         session,
         settings=settings,
-        object_name=object_name,
+        column=column,
         in_memory=in_memory,
         **fr_map,
     )

datachain/lib/dc/parquet.py

@@ -19,7 +19,7 @@ def read_parquet(
     path,
     partitioning: Any = "hive",
     output: Optional[dict[str, DataType]] = None,
-    object_name: str = "",
+    column: str = "",
     model_name: str = "",
     source: bool = True,
     session: Optional[Session] = None,
@@ -33,7 +33,7 @@ def read_parquet(
             as `s3://`, `gs://`, `az://` or "file:///".
         partitioning : Any pyarrow partitioning schema.
         output : Dictionary defining column names and their corresponding types.
-        object_name : Created object column name.
+        column : Created column name.
         model_name : Generated model name.
         source : Whether to include info about the source file.
         session : Session to use for the chain.
@@ -57,7 +57,7 @@ def read_parquet(
     chain = read_storage(path, session=session, settings=settings, **kwargs)
     return chain.parse_tabular(
         output=output,
-        object_name=object_name,
+        column=column,
         model_name=model_name,
         source=source,
         format="parquet",

datachain/lib/dc/storage.py

@@ -29,7 +29,7 @@ def read_storage(
     settings: Optional[dict] = None,
     in_memory: bool = False,
     recursive: Optional[bool] = True,
-    object_name: str = "file",
+    column: str = "file",
     update: bool = False,
     anon: bool = False,
     client_config: Optional[dict] = None,
@@ -43,7 +43,7 @@ def read_storage(
             as `s3://`, `gs://`, `az://` or "file:///"
         type : read file as "binary", "text", or "image" data. Default is "binary".
         recursive : search recursively for the given path.
-        object_name : Created object column name.
+        column : Created column name.
         update : force storage reindexing. Default is False.
         anon : If True, we will treat cloud bucket as public one
         client_config : Optional client configuration for the storage client.
@@ -124,7 +124,7 @@ def read_storage(
 
         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})
+        dc.signals_schema = dc.signals_schema.mutate({f"{column}": file_type})
 
         if update or not list_ds_exists:
 
@@ -140,7 +140,7 @@ def read_storage(
                     .settings(prefetch=0)
                     .gen(
                         list_bucket(lst_uri, cache, client_config=client_config),
-                        output={f"{object_name}": file_type},
+                        output={f"{column}": file_type},
                     )
                     .save(ds_name, listing=True)
                 )
@@ -149,7 +149,7 @@ def read_storage(
                 lambda ds_name=list_ds_name, lst_uri=list_uri: lst_fn(ds_name, lst_uri)
             )
 
-        chain = ls(dc, list_path, recursive=recursive, object_name=object_name)
+        chain = ls(dc, list_path, recursive=recursive, column=column)
 
         storage_chain = storage_chain.union(chain) if storage_chain else chain
         listed_ds_name.add(list_ds_name)
@@ -162,7 +162,7 @@ def read_storage(
             file=file_values,
         )
         file_chain.signals_schema = file_chain.signals_schema.mutate(
-            {f"{object_name}": file_type}
+            {f"{column}": file_type}
         )
         storage_chain = storage_chain.union(file_chain) if storage_chain else file_chain
 

datachain/lib/dc/values.py

@@ -24,7 +24,7 @@ def read_values(
     settings: Optional[dict] = None,
     in_memory: bool = False,
     output: OutputType = None,
-    object_name: str = "",
+    column: str = "",
     **fr_map,
 ) -> "DataChain":
     """Generate chain from list of values.
@@ -48,6 +48,6 @@ def read_values(
         settings=settings,
         in_memory=in_memory,
     )
-    if object_name:
-        output = {object_name: dict_to_data_model(object_name, output)}  # type: ignore[arg-type]
+    if column:
+        output = {column: dict_to_data_model(column, output)}  # type: ignore[arg-type]
     return chain.gen(_func_fr, output=output)

datachain/lib/listing.py

@@ -72,7 +72,7 @@ def ls(
     dc: D,
     path: str,
     recursive: Optional[bool] = True,
-    object_name="file",
+    column="file",
 ) -> D:
     """
     Return files by some path from DataChain instance which contains bucket listing.
@@ -82,7 +82,7 @@ def ls(
     """
 
     def _file_c(name: str) -> Column:
-        return Column(f"{object_name}.{name}")
+        return Column(f"{column}.{name}")
 
     dc = dc.filter(_file_c("is_latest") == true())
 

datachain/lib/signal_schema.py

@@ -87,6 +87,12 @@ class SignalResolvingTypeError(SignalResolvingError):
         )
 
 
+class SignalRemoveError(SignalSchemaError):
+    def __init__(self, path: Optional[list[str]], msg: str):
+        name = " '" + ".".join(path) + "'" if path else ""
+        super().__init__(f"cannot remove signal name{name}: {msg}")
+
+
 class CustomType(BaseModel):
     schema_version: int = Field(ge=1, le=2, strict=True)
     name: str
@@ -620,18 +626,27 @@ class SignalSchema:
         return curr_type
 
     def select_except_signals(self, *args: str) -> "SignalSchema":
-        schema = copy.deepcopy(self.values)
-        for field in args:
-            if not isinstance(field, str):
-                raise SignalResolvingTypeError("select_except()", field)
+        def has_signal(signal: str):
+            signal = signal.replace(".", DEFAULT_DELIMITER)
+            return any(signal == s for s in self.db_signals())
 
-            if field not in self.values:
+        schema = copy.deepcopy(self.values)
+        for signal in args:
+            if not isinstance(signal, str):
+                raise SignalResolvingTypeError("select_except()", signal)
+
+            if signal not in self.values:
+                if has_signal(signal):
+                    raise SignalRemoveError(
+                        signal.split("."),
+                        "select_except() error - removing nested signal would"
+                        " break parent schema, which isn't supported.",
+                    )
                 raise SignalResolvingError(
-                    field.split("."),
-                    "select_except() error - the feature name does not exist or "
-                    "inside of feature (not supported)",
+                    signal.split("."),
+                    "select_except() error - the signal does not exist",
                 )
-            del schema[field]
+            del schema[signal]
 
         return SignalSchema(schema)
 

datachain/lib/udf.py

@@ -16,7 +16,6 @@ from datachain.lib.convert.flatten import flatten
 from datachain.lib.data_model import DataValue
 from datachain.lib.file import File
 from datachain.lib.utils import AbstractUDF, DataChainError, DataChainParamsError
-from datachain.progress import CombinedDownloadCallback
 from datachain.query.batch import (
     Batch,
     BatchingStrategy,
@@ -327,8 +326,9 @@ def _prefetch_inputs(
 
     if after_prefetch is None:
         after_prefetch = noop
-        if isinstance(download_cb, CombinedDownloadCallback):
-            after_prefetch = download_cb.increment_file_count
+        if download_cb and hasattr(download_cb, "increment_file_count"):
+            increment_file_count: Callable[[], None] = download_cb.increment_file_count
+            after_prefetch = increment_file_count
 
     f = partial(_prefetch_input, download_cb=download_cb, after_prefetch=after_prefetch)
     mapper = AsyncMapper(f, prepared_inputs, workers=prefetch)

datachain/listing.py

@@ -27,14 +27,14 @@ class Listing:
         client: "Client",
         dataset_name: Optional["str"] = None,
         dataset_version: Optional[int] = None,
-        object_name: str = "file",
+        column: str = "file",
     ):
         self.metastore = metastore
         self.warehouse = warehouse
         self.client = client
         self.dataset_name = dataset_name  # dataset representing bucket listing
         self.dataset_version = dataset_version  # dataset representing bucket listing
-        self.object_name = object_name
+        self.column = column
 
     def clone(self) -> "Listing":
         return self.__class__(
@@ -43,7 +43,7 @@ class Listing:
             self.client,
             self.dataset_name,
             self.dataset_version,
-            self.object_name,
+            self.column,
         )
 
     def __enter__(self) -> "Listing":
@@ -74,7 +74,7 @@ class Listing:
         return self.warehouse.dataset_rows(
             dataset,
             self.dataset_version or dataset.latest_version,
-            object_name=self.object_name,
+            column=self.column,
         )
 
     def expand_path(self, path, use_glob=True) -> list[Node]:

datachain/query/dispatch.py

@@ -4,9 +4,8 @@ from itertools import chain
 from multiprocessing import cpu_count
 from sys import stdin
 from threading import Timer
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING, Literal, Optional
 
-import attrs
 import multiprocess
 from cloudpickle import load, loads
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback
@@ -60,6 +59,7 @@ def udf_entrypoint() -> int:
     query = udf_info["query"]
     rows_total = udf_info["rows_total"]
     batching = udf_info["batching"]
+    is_generator = udf_info["is_generator"]
     n_workers = udf_info["processes"]
     if n_workers is True:
         n_workers = None  # Use default number of CPUs (cores)
@@ -72,17 +72,20 @@ def udf_entrypoint() -> int:
     ) as udf_inputs:
         download_cb = get_download_callback()
         processed_cb = get_processed_callback()
+        generated_cb = get_generated_callback(is_generator)
         try:
             dispatch.run_udf_parallel(
                 udf_inputs,
                 rows_total=rows_total,
                 n_workers=n_workers,
-                processed_cb=processed_cb,
                 download_cb=download_cb,
+                processed_cb=processed_cb,
+                generated_cb=generated_cb,
             )
         finally:
             download_cb.close()
             processed_cb.close()
+            generated_cb.close()
 
     return 0
 
@@ -128,7 +131,6 @@ class UDFDispatcher:
             self.done_queue,
             self.query,
             self.table,
-            self.is_generator,
             self.is_batching,
             self.cache,
             self.udf_fields,
@@ -152,16 +154,14 @@ class UDFDispatcher:
         for _ in range(n_workers):
             put_into_queue(task_queue, STOP_SIGNAL)
 
-    def create_input_queue(self):
-        return self.ctx.Queue()
-
     def run_udf_parallel(  # noqa: C901, PLR0912
         self,
         input_rows: Iterable[RowsOutput],
         rows_total: int,
         n_workers: Optional[int] = None,
-        processed_cb: Callback = DEFAULT_CALLBACK,
         download_cb: Callback = DEFAULT_CALLBACK,
+        processed_cb: Callback = DEFAULT_CALLBACK,
+        generated_cb: Callback = DEFAULT_CALLBACK,
     ) -> None:
         n_workers = get_n_workers_from_arg(n_workers)
 
@@ -214,6 +214,8 @@ class UDFDispatcher:
                     download_cb.relative_update(downloaded)
                 if processed := result.get("processed"):
                     processed_cb.relative_update(processed)
+                if generated := result.get("generated"):
+                    generated_cb.relative_update(generated)
 
                 status = result["status"]
                 if status in (OK_STATUS, NOTIFY_STATUS):
@@ -260,46 +262,61 @@ class UDFDispatcher:
                 p.join()
 
 
-class WorkerCallback(Callback):
-    def __init__(self, queue: "multiprocess.Queue"):
+class DownloadCallback(Callback):
+    def __init__(self, queue: "multiprocess.Queue") -> None:
         self.queue = queue
         super().__init__()
 
     def relative_update(self, inc: int = 1) -> None:
+        # This callback is used to notify the size of the downloaded files
+        pass
+
+    def increment_file_count(self, inc: int = 1) -> None:
         put_into_queue(self.queue, {"status": NOTIFY_STATUS, "downloaded": inc})
 
 
 class ProcessedCallback(Callback):
-    def __init__(self):
-        self.processed_rows: Optional[int] = None
+    def __init__(
+        self,
+        name: Literal["processed", "generated"],
+        queue: "multiprocess.Queue",
+    ) -> None:
+        self.name = name
+        self.queue = queue
         super().__init__()
 
     def relative_update(self, inc: int = 1) -> None:
-        self.processed_rows = inc
+        put_into_queue(self.queue, {"status": NOTIFY_STATUS, self.name: inc})
 
 
-@attrs.define
 class UDFWorker:
-    catalog: "Catalog"
-    udf: "UDFAdapter"
-    task_queue: "multiprocess.Queue"
-    done_queue: "multiprocess.Queue"
-    query: "Select"
-    table: "Table"
-    is_generator: bool
-    is_batching: bool
-    cache: bool
-    udf_fields: Sequence[str]
-    cb: Callback = attrs.field()
-
-    @cb.default
-    def _default_callback(self) -> WorkerCallback:
-        return WorkerCallback(self.done_queue)
+    def __init__(
+        self,
+        catalog: "Catalog",
+        udf: "UDFAdapter",
+        task_queue: "multiprocess.Queue",
+        done_queue: "multiprocess.Queue",
+        query: "Select",
+        table: "Table",
+        is_batching: bool,
+        cache: bool,
+        udf_fields: Sequence[str],
+    ) -> None:
+        self.catalog = catalog
+        self.udf = udf
+        self.task_queue = task_queue
+        self.done_queue = done_queue
+        self.query = query
+        self.table = table
+        self.is_batching = is_batching
+        self.cache = cache
+        self.udf_fields = udf_fields
+
+        self.download_cb = DownloadCallback(self.done_queue)
+        self.processed_cb = ProcessedCallback("processed", self.done_queue)
+        self.generated_cb = ProcessedCallback("generated", self.done_queue)
 
     def run(self) -> None:
-        processed_cb = ProcessedCallback()
-        generated_cb = get_generated_callback(self.is_generator)
-
         prefetch = self.udf.prefetch
         with _get_cache(self.catalog.cache, prefetch, use_cache=self.cache) as _cache:
             catalog = clone_catalog_with_cache(self.catalog, _cache)
@@ -308,29 +325,22 @@ class UDFWorker:
                 self.get_inputs(),
                 catalog,
                 self.cache,
-                download_cb=self.cb,
-                processed_cb=processed_cb,
+                download_cb=self.download_cb,
+                processed_cb=self.processed_cb,
             )
             with safe_closing(udf_results):
                 process_udf_outputs(
                     catalog.warehouse,
                     self.table,
-                    self.notify_and_process(udf_results, processed_cb),
+                    self.notify_and_process(udf_results),
                     self.udf,
-                    cb=generated_cb,
+                    cb=self.generated_cb,
                 )
+        put_into_queue(self.done_queue, {"status": FINISHED_STATUS})
 
-        put_into_queue(
-            self.done_queue,
-            {"status": FINISHED_STATUS, "processed": processed_cb.processed_rows},
-        )
-
-    def notify_and_process(self, udf_results, processed_cb):
+    def notify_and_process(self, udf_results):
         for row in udf_results:
-            put_into_queue(
-                self.done_queue,
-                {"status": OK_STATUS, "processed": processed_cb.processed_rows},
-            )
+            put_into_queue(self.done_queue, {"status": OK_STATUS})
             yield row
 
     def get_inputs(self):

datachain/query/session.py

@@ -100,6 +100,10 @@ class Session:
     def get_temp_prefix(self) -> str:
         return f"{self.DATASET_PREFIX}{self.name}_"
 
+    @classmethod
+    def is_temp_dataset(cls, name) -> bool:
+        return name.startswith(cls.DATASET_PREFIX)
+
     def _cleanup_temp_datasets(self) -> None:
         prefix = self.get_temp_prefix()
         try:

{datachain-0.14.3.dist-info → datachain-0.14.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.14.3
+Version: 0.14.5
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -171,7 +171,7 @@ high confidence scores.
 
     import datachain as dc
 
-    meta = dc.read_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta", anon=True)
+    meta = dc.read_json("gs://datachain-demo/dogs-and-cats/*json", column="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])
@@ -213,7 +213,7 @@ Python code:
          return result.lower().startswith("success")
 
     chain = (
-       dc.read_storage("gs://datachain-demo/chatbot-KiT/", object_name="file", anon=True)
+       dc.read_storage("gs://datachain-demo/chatbot-KiT/", column="file", anon=True)
        .settings(parallel=4, cache=True)
        .map(is_success=eval_dialogue)
        .save("mistral_files")

{datachain-0.14.3.dist-info → datachain-0.14.5.dist-info}/RECORD

@@ -6,7 +6,7 @@ datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
 datachain/dataset.py,sha256=ZfgsGlddTXsSqCohNSRSChdH6Jjw7wrkso1Am166k-M,19391
 datachain/error.py,sha256=bxAAL32lSeMgzsQDEHbGTGORj-mPzzpCRvWDPueJNN4,1092
 datachain/job.py,sha256=x5PB6d5sqx00hePNNkirESlOVAvnmkEM5ygUgQmAhsk,1262
-datachain/listing.py,sha256=HNB-xeKA6aUA-HTWr--H22S6jVOxP2OVQ-3d07ISqAk,7109
+datachain/listing.py,sha256=kNSCFYWo2iM1wWg1trwq4WpYZxYqz4RKxkTtsppEzAw,7079
 datachain/node.py,sha256=KWDT0ClYXB7FYI-QOvzAa-UDkLJErUI2eWm5FBteYuU,5577
 datachain/nodes_fetcher.py,sha256=_wgaKyqEjkqdwJ_Hj6D8vUYz7hnU7g6xhm0H6ZnYxmE,1095
 datachain/nodes_thread_pool.py,sha256=mdo0s-VybuSZkRUARcUO4Tjh8KFfZr9foHqmupx2SmM,3989
@@ -17,7 +17,7 @@ datachain/studio.py,sha256=9MEpFPLKI3gG4isKklcfD5BMLeNsSXhtOUboOjW4Fdc,10017
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=8Qz8lRrX0bUTGvwYd-OR-l6ElVRsQBdBO5QMvwt56T4,15190
 datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
-datachain/catalog/catalog.py,sha256=k-okQ4aqoyWrsNlDeCz6jP6TNRiZCUENbGV9Sz6EEtw,60729
+datachain/catalog/catalog.py,sha256=05_JplTuoyqDWtxUeu324ogaHVqXGPSaPxtUXtuMljk,60682
 datachain/catalog/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
 datachain/catalog/loader.py,sha256=wCOWeDwuFNKr_frZRkqTZhkCAiB0CBCRJio3LF2zKPA,5765
 datachain/cli/__init__.py,sha256=YPVkuQ7IezNhtzo5xrfca1hEIiZtFxOlJCOzAOEuxmA,8335
@@ -46,10 +46,10 @@ datachain/data_storage/__init__.py,sha256=9Wit-oe5P46V7CJQTD0BJ5MhOa2Y9h3ddJ4VWT
 datachain/data_storage/db_engine.py,sha256=n8ojCbvVMPY2e3SG8fUaaD0b9GkVfpl_Naa_6EiHfWg,3788
 datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s,383
 datachain/data_storage/metastore.py,sha256=19LP15xT2Fmz0aIZ1sIajq8i1-KnFgCBEZeU2Ka9-mc,37780
-datachain/data_storage/schema.py,sha256=qSukry2kINhVw8aj5lQrpe7N90DFeatKIKmDh6jAzR8,9515
+datachain/data_storage/schema.py,sha256=asZYz1cg_WKfe2Q-k5W51E2z2CzHU5B4QEDZDMFr8yo,9346
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=KJ8hI0Hrwv9eAA-nLUlw2AYCQxiAAZ12a-ftUBtroNQ,24545
-datachain/data_storage/warehouse.py,sha256=7awrmqBgcqKfJFuZG4WRpjZLdRCTBwbNDvtL3XakR8c,31145
+datachain/data_storage/sqlite.py,sha256=f4tvq0gzYQP7aYGnfL3j4IBUNvctpBxI_ioFU-B1LFc,24540
+datachain/data_storage/warehouse.py,sha256=0GQdf7BwGav783zhB-RBKwjUqkLf2JW2lS-KXTqimnQ,31083
 datachain/diff/__init__.py,sha256=YkGdiDbZIMhAZ2SJ4eSe00HU67VP1P6SL2L_t0ODYMs,9425
 datachain/fs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/fs/reference.py,sha256=A8McpXF0CqbXPqanXuvpKu50YLB3a2ZXA3YAPxtBXSM,914
@@ -69,20 +69,20 @@ datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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/dataset_info.py,sha256=Jnjy7vq4iNVkq1e-SYjqxdojlxIDXvZ352NCLLZg59k,2633
 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=O29s7H-2rqjHHGKWkKGNNXlo2zynv4pygVTKImpV8fo,7046
+datachain/lib/listing.py,sha256=qmie3z8UR5bdXiZnMo3Qy5IpT76vFu5gn0x2ksMi-y8,7036
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
 datachain/lib/meta_formats.py,sha256=Epydbdch1g4CojK8wd_ePzmwmljC4fVWlJtZ16jsX-A,6349
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
 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/signal_schema.py,sha256=uIBHYXtu_XpLbOUVC-kq-GduEOCfz9hQORi9ZG3JFqo,35820
 datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=h38a457xg-4wO2XcxPs4pzDq8JxTmYm4N84iAf0HRzY,16168
+datachain/lib/udf.py,sha256=JJwjvy41N65PtWGUAq7TYnhdOOR6RiMDUJEKl5xtwLc,16199
 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
@@ -95,18 +95,18 @@ datachain/lib/convert/sql_to_python.py,sha256=XXCBYDQFUXJIBNWkjEP944cnCfJ8GF2Tji
 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=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/csv.py,sha256=asWPAxhMgIoLAdD2dObDlnGL8CTSD3TAuFuM4ci89bQ,4374
+datachain/lib/dc/datachain.py,sha256=PDkB1fvmokJr-Tmyn0CuFGgZSxPn25FMjjUVHbrx6-c,76326
+datachain/lib/dc/datasets.py,sha256=K-GCTZ6Ps_XNpzKz19my8VijXb-b0b3eZASoavKk1Uc,5157
+datachain/lib/dc/hf.py,sha256=PJl2wiLjdRsMz0SYbLT-6H8b-D5i2WjeH7li8HHOk_0,2145
+datachain/lib/dc/json.py,sha256=ZUThPDAaP2gBFIL5vsQTwKBcuN_dhvC_O44wdDv0jEc,2683
+datachain/lib/dc/listings.py,sha256=2na9v63xO1vPUNaoBSzA-TSN49V7zQAb-4iS1wOPLFE,1029
+datachain/lib/dc/pandas.py,sha256=mM2y44s1-3dwkxjVe6RdfT6PVoeRHS9OgsGaSz4YsqQ,1219
+datachain/lib/dc/parquet.py,sha256=zYcSgrWwyEDW9UxGUSVdIVsCu15IGEf0xL8KfWQqK94,1782
 datachain/lib/dc/records.py,sha256=DOFkQV7A7kZnMiCS4mHOzee2ibWIhz-mWQpgVsU78SE,2524
-datachain/lib/dc/storage.py,sha256=kM3Ix2L0j01a4XcXPZpdDxvici9yu-Ks-Cd3uf_qESA,5327
+datachain/lib/dc/storage.py,sha256=QLf3-xMV2Gmy3AA8qF9WqAsb7R8Rk87l4s5hBoiCH98,5285
 datachain/lib/dc/utils.py,sha256=Ct-0FqCaDhNWHx09gJFcCXJGPjMI-VZr4t-GJyqTi44,3984
-datachain/lib/dc/values.py,sha256=HaABQKmhgW-N1pcBn7CQuTIiOFXYVjU1H9LbupGM3WQ,1409
+datachain/lib/dc/values.py,sha256=cBQubhmPNEDMJldUXzGh-UKbdim4P6O2B91Gp39roKw,1389
 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
@@ -119,12 +119,12 @@ datachain/model/ultralytics/segment.py,sha256=koq1HASo29isf0in6oSlzmU4IzsmOXe87F
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=6w8gzLTmLeylststu-gT5jIqEfi4-djS7_yTYyeo-fw,4190
 datachain/query/dataset.py,sha256=caUsFzaVZXOz8NmeTMeOdyRQLQP8KCnxYMxF-pG4yFQ,58712
-datachain/query/dispatch.py,sha256=T4vdJE0k3Ff1osaQzYTC_2gOOkT0mXwKzNy-5aZcrTE,12300
+datachain/query/dispatch.py,sha256=ErdK-biHYhRLDsm7on6vAHSjX-hAHgEHsBRHmuMS_4E,12979
 datachain/query/metrics.py,sha256=r5b0ygYhokbXp8Mg3kCH8iFSRw0jxzyeBe-C-J_bKFc,938
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
 datachain/query/queue.py,sha256=waqM_KzavU8C-G95-4211Nd4GXna_u2747Chgwtgz2w,3839
 datachain/query/schema.py,sha256=b_KnVy6B26Ol4nYG0LqNNpeQ1QYPk95YRGUjXfdaQWs,6606
-datachain/query/session.py,sha256=I1KG8jDIaxGAfRfDRucMx8DqsANf_VYWtwtXjeD19lI,6399
+datachain/query/session.py,sha256=wNdOHAi4HrsEihfzdcTlfB5i1xyj0dw6rlUz84StOoU,6512
 datachain/query/udf.py,sha256=ljAYaF-J77t7iS4zc1-g1ssYd4c6Q-ccKGEc3VQQmeM,1322
 datachain/query/utils.py,sha256=u0A_BwG9PNs0DxoDcvSWgWLpj3ByTUv8CqH13CIuGag,1293
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -150,9 +150,9 @@ 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-0.14.3.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.14.3.dist-info/METADATA,sha256=hTVICGrF_sALHSr7uuAipFr5HVrgydiP2JcDlZ-Q_w0,11338
-datachain-0.14.3.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-datachain-0.14.3.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.14.3.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.14.3.dist-info/RECORD,,
+datachain-0.14.5.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.14.5.dist-info/METADATA,sha256=y6sL0tB9tFRXF_LnjkPLM7cmtBBhXWxTvtNWRnmgfb4,11328
+datachain-0.14.5.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+datachain-0.14.5.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.14.5.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.14.5.dist-info/RECORD,,