datachain 0.12.0__py3-none-any.whl → 0.13.1__py3-none-any.whl

datachain/catalog/catalog.py

@@ -777,6 +777,8 @@ class Catalog:
         validate_version: Optional[bool] = True,
         listing: Optional[bool] = False,
         uuid: Optional[str] = None,
+        description: Optional[str] = None,
+        labels: Optional[list[str]] = None,
     ) -> "DatasetRecord":
         """
         Creates new dataset of a specific version.
@@ -793,6 +795,19 @@ class Catalog:
         try:
             dataset = self.get_dataset(name)
             default_version = dataset.next_version
+
+            if (description or labels) and (
+                dataset.description != description or dataset.labels != labels
+            ):
+                description = description or dataset.description
+                labels = labels or dataset.labels
+
+                self.update_dataset(
+                    dataset,
+                    description=description,
+                    labels=labels,
+                )
+
         except DatasetNotFoundError:
             schema = {
                 c.name: c.type.to_dict() for c in columns if isinstance(c.type, SQLType)
@@ -803,6 +818,8 @@ class Catalog:
                 query_script=query_script,
                 schema=schema,
                 ignore_if_exists=True,
+                description=description,
+                labels=labels,
             )
 
         version = version or default_version
@@ -1608,7 +1625,7 @@ class Catalog:
             except TerminationSignal as exc:
                 signal.signal(signal.SIGTERM, orig_sigterm_handler)
                 signal.signal(signal.SIGINT, orig_sigint_handler)
-                logging.info("Shutting down process %s, received %r", proc.pid, exc)
+                logger.info("Shutting down process %s, received %r", proc.pid, exc)
                 # Rather than forwarding the signal to the child, we try to shut it down
                 # gracefully. This is because we consider the script to be interactive
                 # and special, so we give it time to cleanup before exiting.
@@ -1623,7 +1640,7 @@ class Catalog:
                 if thread:
                     thread.join()  # wait for the reader thread
 
-        logging.info("Process %s exited with return code %s", proc.pid, proc.returncode)
+        logger.info("Process %s exited with return code %s", proc.pid, proc.returncode)
         if proc.returncode == QUERY_SCRIPT_CANCELED_EXIT_CODE:
             raise QueryScriptCancelError(
                 "Query script was canceled by user",

datachain/cli/commands/ls.py

@@ -38,11 +38,12 @@ def ls_local(
 ):
     from datachain import DataChain
 
-    if catalog is None:
-        from datachain.catalog import get_catalog
-
-        catalog = get_catalog(client_config=client_config)
     if sources:
+        if catalog is None:
+            from datachain.catalog import get_catalog
+
+            catalog = get_catalog(client_config=client_config)
+
         actual_sources = list(ls_urls(sources, catalog=catalog, long=long, **kwargs))
         if len(actual_sources) == 1:
             for _, entries in actual_sources:
@@ -61,8 +62,9 @@ def ls_local(
                 for entry in entries:
                     print(format_ls_entry(entry))
     else:
-        chain = DataChain.listings()
-        for ls in chain.collect("listing"):
+        # Collect results in a list here to prevent interference from `tqdm` and `print`
+        listing = list(DataChain.listings().collect("listing"))
+        for ls in listing:
             print(format_ls_entry(f"{ls.uri}@v{ls.version}"))  # type: ignore[union-attr]
 
 

datachain/cli/commands/show.py

@@ -40,6 +40,13 @@ def show(
         .offset(offset)
     )
     records = query.to_db_records()
+    print("Name: ", name)
+    if dataset.description:
+        print("Description: ", dataset.description)
+    if dataset.labels:
+        print("Labels: ", ",".join(dataset.labels))
+    print("\n")
+
     show_records(records, collapse_columns=not no_collapse, hidden_fields=hidden_fields)
 
     if schema and dataset_version.feature_schema:

datachain/client/gcs.py

@@ -30,7 +30,7 @@ class GCSClient(Client):
         if kwargs.pop("anon", False):
             kwargs["token"] = "anon"  # noqa: S105
 
-        return cast(GCSFileSystem, super().create_fs(**kwargs))
+        return cast("GCSFileSystem", super().create_fs(**kwargs))
 
     def url(self, path: str, expires: int = 3600, **kwargs) -> str:
         """

datachain/client/s3.py

@@ -55,7 +55,7 @@ class ClientS3(Client):
             except NotImplementedError:
                 pass
 
-        return cast(S3FileSystem, super().create_fs(**kwargs))
+        return cast("S3FileSystem", super().create_fs(**kwargs))
 
     def url(self, path: str, expires: int = 3600, **kwargs) -> str:
         """

datachain/data_storage/metastore.py

@@ -119,6 +119,8 @@ class AbstractMetastore(ABC, Serializable):
         query_script: str = "",
         schema: Optional[dict[str, Any]] = None,
         ignore_if_exists: bool = False,
+        description: Optional[str] = None,
+        labels: Optional[list[str]] = None,
     ) -> DatasetRecord:
         """Creates new dataset."""
 
@@ -518,6 +520,8 @@ class AbstractDBMetastore(AbstractMetastore):
         query_script: str = "",
         schema: Optional[dict[str, Any]] = None,
         ignore_if_exists: bool = False,
+        description: Optional[str] = None,
+        labels: Optional[list[str]] = None,
         **kwargs,  # TODO registered = True / False
     ) -> DatasetRecord:
         """Creates new dataset."""
@@ -533,6 +537,8 @@ class AbstractDBMetastore(AbstractMetastore):
             sources="\n".join(sources) if sources else "",
             query_script=query_script,
             schema=json.dumps(schema or {}),
+            description=description,
+            labels=json.dumps(labels or []),
         )
         if ignore_if_exists and hasattr(query, "on_conflict_do_nothing"):
             # SQLite and PostgreSQL both support 'on_conflict_do_nothing',

datachain/diff/__init__.py

@@ -74,6 +74,7 @@ def _compare(  # noqa: C901
     # all left and right columns
     cols = left.signals_schema.clone_without_sys_signals().db_signals()
     right_cols = right.signals_schema.clone_without_sys_signals().db_signals()
+    cols_select = list(left.signals_schema.clone_without_sys_signals().values.keys())
 
     # getting correct on and right_on column names
     on = left.signals_schema.resolve(*on).db_signals()  # type: ignore[assignment]
@@ -131,10 +132,12 @@ def _compare(  # noqa: C901
         # when the row is deleted, we need to take column values from the right chain
         .mutate(
             **{
-                f"{c}": ifelse(
-                    C(diff_col) == CompareStatus.DELETED, C(f"{rname}{c}"), C(c)
+                f"{l_on}": ifelse(
+                    C(diff_col) == CompareStatus.DELETED,
+                    C(f"{rname + l_on if on == right_on else r_on}"),
+                    C(l_on),
                 )
-                for c in [c for c in cols if c in right_cols]
+                for l_on, r_on in zip(on, right_on)  # type: ignore[arg-type]
             }
         )
         .select_except(ldiff_col, rdiff_col)
@@ -150,9 +153,9 @@ def _compare(  # noqa: C901
         dc_diff = dc_diff.filter(C(diff_col) != CompareStatus.DELETED)
 
     if status_col:
-        cols.append(diff_col)  # type: ignore[arg-type]
+        cols_select.append(diff_col)
 
-    dc_diff = dc_diff.select(*cols)
+    dc_diff = dc_diff.select(*cols_select)
 
     # final schema is schema from the left chain with status column added if needed
     dc_diff.signals_schema = (

datachain/lib/dc.py

@@ -6,6 +6,7 @@ import sys
 from collections.abc import Iterator, Sequence
 from functools import wraps
 from typing import (
+    IO,
     TYPE_CHECKING,
     Any,
     BinaryIO,
@@ -270,6 +271,18 @@ class DataChain:
         self._setup: dict = setup or {}
         self._sys = _sys
 
+    def __repr__(self) -> str:
+        """Return a string representation of the chain."""
+        classname = self.__class__.__name__
+        if not self._effective_signals_schema.values:
+            return f"Empty {classname}"
+
+        import io
+
+        file = io.StringIO()
+        self.print_schema(file=file)
+        return file.getvalue()
+
     @property
     def schema(self) -> dict[str, DataType]:
         """Get schema of the chain."""
@@ -323,9 +336,9 @@ class DataChain:
         """Return `self.union(other)`."""
         return self.union(other)
 
-    def print_schema(self) -> None:
+    def print_schema(self, file: Optional[IO] = None) -> None:
         """Print schema of the chain."""
-        self._effective_signals_schema.print_tree()
+        self._effective_signals_schema.print_tree(file=file)
 
     def clone(self) -> "Self":
         """Make a copy of the chain in a new table."""
@@ -629,7 +642,8 @@ class DataChain:
                 model_name=model_name,
                 jmespath=jmespath,
                 nrows=nrows,
-            )
+            ),
+            "params": {"file": File},
         }
         # disable prefetch if nrows is set
         settings = {"prefetch": 0} if nrows else {}
@@ -773,7 +787,12 @@ class DataChain:
         )
 
     def save(  # type: ignore[override]
-        self, name: Optional[str] = None, version: Optional[int] = None, **kwargs
+        self,
+        name: Optional[str] = None,
+        version: Optional[int] = None,
+        description: Optional[str] = None,
+        labels: Optional[list[str]] = None,
+        **kwargs,
     ) -> "Self":
         """Save to a Dataset. It returns the chain itself.
 
@@ -781,11 +800,18 @@ class DataChain:
             name : dataset name. Empty name saves to a temporary dataset that will be
                 removed after process ends. Temp dataset are useful for optimization.
             version : version of a dataset. Default - the last version that exist.
+            description : description of a dataset.
+            labels : labels of a dataset.
         """
         schema = self.signals_schema.clone_without_sys_signals().serialize()
         return self._evolve(
             query=self._query.save(
-                name=name, version=version, feature_schema=schema, **kwargs
+                name=name,
+                version=version,
+                description=description,
+                labels=labels,
+                feature_schema=schema,
+                **kwargs,
             )
         )
 
@@ -1003,8 +1029,9 @@ class DataChain:
         func: Optional[Union[Callable, UDFObjT]],
         params: Union[None, str, Sequence[str]],
         output: OutputType,
-        signal_map,
+        signal_map: dict[str, Callable],
     ) -> UDFObjT:
+        is_batch = target_class.is_input_batched
         is_generator = target_class.is_output_batched
         name = self.name or ""
 
@@ -1015,7 +1042,9 @@ class DataChain:
         if self._sys:
             signals_schema = SignalSchema({"sys": Sys}) | signals_schema
 
-        params_schema = signals_schema.slice(sign.params, self._setup)
+        params_schema = signals_schema.slice(
+            sign.params, self._setup, is_batch=is_batch
+        )
 
         return target_class._create(sign, params_schema)
 

datachain/lib/file.py

@@ -193,7 +193,14 @@ class File(DataModel):
         "last_modified": DateTime,
         "location": JSON,
     }
-    _hidden_fields: ClassVar[list[str]] = ["version", "source"]
+    _hidden_fields: ClassVar[list[str]] = [
+        "source",
+        "version",
+        "etag",
+        "is_latest",
+        "last_modified",
+        "location",
+    ]
 
     _unique_id_keys: ClassVar[list[str]] = [
         "source",

datachain/lib/meta_formats.py

@@ -10,7 +10,7 @@ import jmespath as jsp
 from pydantic import BaseModel, ConfigDict, Field, ValidationError  # noqa: F401
 
 from datachain.lib.data_model import DataModel  # noqa: F401
-from datachain.lib.file import File
+from datachain.lib.file import TextFile
 
 
 class UserModel(BaseModel):
@@ -130,7 +130,7 @@ def read_meta(  # noqa: C901
     #
 
     def parse_data(
-        file: File,
+        file: TextFile,
         data_model=spec,
         format=format,
         jmespath=jmespath,

datachain/lib/signal_schema.py

@@ -5,6 +5,7 @@ from dataclasses import dataclass
 from datetime import datetime
 from inspect import isclass
 from typing import (  # noqa: UP035
+    IO,
     TYPE_CHECKING,
     Annotated,
     Any,
@@ -154,9 +155,9 @@ class SignalSchema:
             if not callable(func):
                 raise SetupError(key, "value must be function or callable class")
 
-    def _init_setup_values(self):
+    def _init_setup_values(self) -> None:
         if self.setup_values is not None:
-            return self.setup_values
+            return
 
         res = {}
         for key, func in self.setup_func.items():
@@ -398,7 +399,7 @@ class SignalSchema:
         return SignalSchema(signals)
 
     @staticmethod
-    def get_flatten_hidden_fields(schema):
+    def get_flatten_hidden_fields(schema: dict):
         custom_types = schema.get("_custom_types", {})
         if not custom_types:
             return []
@@ -464,19 +465,61 @@ class SignalSchema:
         return False
 
     def slice(
-        self, keys: Sequence[str], setup: Optional[dict[str, Callable]] = None
+        self,
+        params: dict[str, Union[DataType, Any]],
+        setup: Optional[dict[str, Callable]] = None,
+        is_batch: bool = False,
     ) -> "SignalSchema":
-        # Make new schema that combines current schema and setup signals
-        setup = setup or {}
-        setup_no_types = dict.fromkeys(setup.keys(), str)
-        union = SignalSchema(self.values | setup_no_types)
-        # Slice combined schema by keys
-        schema = {}
-        for k in keys:
-            try:
-                schema[k] = union._find_in_tree(k.split("."))
-            except SignalResolvingError:
-                pass
+        """
+        Returns new schema that combines current schema and setup signals.
+        """
+        setup_params = setup.keys() if setup else []
+        schema: dict[str, DataType] = {}
+
+        for param, param_type in params.items():
+            # This is special case for setup params, they are always treated as strings
+            if param in setup_params:
+                schema[param] = str
+                continue
+
+            schema_type = self._find_in_tree(param.split("."))
+
+            if param_type is Any:
+                schema[param] = schema_type
+                continue
+
+            schema_origin = get_origin(schema_type)
+            param_origin = get_origin(param_type)
+
+            if schema_origin is Union and type(None) in get_args(schema_type):
+                schema_type = get_args(schema_type)[0]
+                if param_origin is Union and type(None) in get_args(param_type):
+                    param_type = get_args(param_type)[0]
+
+            if is_batch:
+                if param_type is list:
+                    schema[param] = schema_type
+                    continue
+
+                if param_origin is not list:
+                    raise SignalResolvingError(param.split("."), "is not a list")
+
+                param_type = get_args(param_type)[0]
+
+            if param_type == schema_type or (
+                isclass(param_type)
+                and isclass(schema_type)
+                and issubclass(param_type, File)
+                and issubclass(schema_type, File)
+            ):
+                schema[param] = schema_type
+                continue
+
+            raise SignalResolvingError(
+                param.split("."),
+                f"types mismatch: {param_type} != {schema_type}",
+            )
+
         return SignalSchema(schema, setup)
 
     def row_to_features(
@@ -696,16 +739,20 @@ class SignalSchema:
                     substree, new_prefix, depth + 1, include_hidden
                 )
 
-    def print_tree(self, indent: int = 4, start_at: int = 0):
+    def print_tree(self, indent: int = 2, start_at: int = 0, file: Optional[IO] = None):
         for path, type_, _, depth in self.get_flat_tree():
             total_indent = start_at + depth * indent
-            print(" " * total_indent, f"{path[-1]}:", SignalSchema._type_to_str(type_))
+            col_name = " " * total_indent + path[-1]
+            col_type = SignalSchema._type_to_str(type_)
+            print(col_name, col_type, sep=": ", file=file)
 
             if get_origin(type_) is list:
                 args = get_args(type_)
                 if len(args) > 0 and ModelStore.is_pydantic(args[0]):
                     sub_schema = SignalSchema({"* list of": args[0]})
-                    sub_schema.print_tree(indent=indent, start_at=total_indent + indent)
+                    sub_schema.print_tree(
+                        indent=indent, start_at=total_indent + indent, file=file
+                    )
 
     def get_headers_with_length(self, include_hidden: bool = True):
         paths = [

datachain/lib/udf.py

@@ -159,6 +159,7 @@ class UDFBase(AbstractUDF):
         ```
     """
 
+    is_input_batched = False
     is_output_batched = False
     prefetch: int = 0
 
@@ -395,6 +396,7 @@ class Mapper(UDFBase):
 class BatchMapper(UDFBase):
     """Inherit from this class to pass to `DataChain.batch_map()`."""
 
+    is_input_batched = True
     is_output_batched = True
 
     def run(
@@ -481,6 +483,7 @@ class Generator(UDFBase):
 class Aggregator(UDFBase):
     """Inherit from this class to pass to `DataChain.agg()`."""
 
+    is_input_batched = True
     is_output_batched = True
 
     def run(

datachain/lib/udf_signature.py

@@ -1,7 +1,7 @@
 import inspect
 from collections.abc import Generator, Iterator, Sequence
 from dataclasses import dataclass
-from typing import Callable, Union, get_args, get_origin
+from typing import Any, Callable, Union, get_args, get_origin
 
 from datachain.lib.data_model import DataType, DataTypeNames, is_chain_type
 from datachain.lib.signal_schema import SignalSchema
@@ -18,7 +18,7 @@ class UdfSignatureError(DataChainParamsError):
 @dataclass
 class UdfSignature:
     func: Union[Callable, UDFBase]
-    params: Sequence[str]
+    params: dict[str, Union[DataType, Any]]
     output_schema: SignalSchema
 
     DEFAULT_RETURN_TYPE = str
@@ -58,15 +58,23 @@ class UdfSignature:
         if not isinstance(udf_func, UDFBase) and not callable(udf_func):
             raise UdfSignatureError(chain, f"UDF '{udf_func}' is not callable")
 
-        func_params_map_sign, func_outs_sign, is_iterator = (
-            UdfSignature._func_signature(chain, udf_func)
+        func_params_map_sign, func_outs_sign, is_iterator = cls._func_signature(
+            chain, udf_func
         )
+
+        udf_params: dict[str, Union[DataType, Any]] = {}
         if params:
-            udf_params = [params] if isinstance(params, str) else params
-        elif not func_params_map_sign:
-            udf_params = []
-        else:
-            udf_params = list(func_params_map_sign.keys())
+            udf_params = (
+                {params: Any} if isinstance(params, str) else dict.fromkeys(params, Any)
+            )
+        elif func_params_map_sign:
+            udf_params = {
+                param: (
+                    param_type if param_type is not inspect.Parameter.empty else Any
+                )
+                for param, param_type in func_params_map_sign.items()
+            }
+
         if output:
             udf_output_map = UdfSignature._validate_output(
                 chain, signal_name, func, func_outs_sign, output

datachain/query/dataset.py

@@ -1646,6 +1646,8 @@ class DatasetQuery:
         name: Optional[str] = None,
         version: Optional[int] = None,
         feature_schema: Optional[dict] = None,
+        description: Optional[str] = None,
+        labels: Optional[list[str]] = None,
         **kwargs,
     ) -> "Self":
         """Save the query as a dataset."""
@@ -1678,6 +1680,8 @@ class DatasetQuery:
                 version=version,
                 feature_schema=feature_schema,
                 columns=columns,
+                description=description,
+                labels=labels,
                 **kwargs,
             )
             version = version or dataset.latest_version

datachain/sql/sqlite/base.py

@@ -290,9 +290,9 @@ def adapt_datetime(val: datetime) -> str:
             val = val.astimezone(timezone.utc)
         except (OverflowError, ValueError, OSError):
             if val.year == MAXYEAR:
-                val = datetime.max
+                val = datetime.max.replace(tzinfo=timezone.utc)
             elif val.year == MINYEAR:
-                val = datetime.min
+                val = datetime.min.replace(tzinfo=timezone.utc)
             else:
                 raise
     return val.replace(tzinfo=None).isoformat(" ")

{datachain-0.12.0.dist-info → datachain-0.13.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: datachain
-Version: 0.12.0
+Version: 0.13.1
 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

{datachain-0.12.0.dist-info → datachain-0.13.1.dist-info}/RECORD

@@ -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=3CGnGuQpFRi-BmPoq-0HeXntZcFG3sh7UhuRNClwYX4,60244
+datachain/catalog/catalog.py,sha256=C9FmhIDlTePiFZFJ4Yq7pfchNs1nciAVlkijtFLPZy4,60822
 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=Wb8hXyBwyhb62Zk6ZhNFPFrj2lJhdbRcnBQQkgL_qyw,5174
+datachain/cli/commands/ls.py,sha256=7yVSRzhmocnnaAXgim4NzrzEymwpLTJjhXq5EATFwsU,5286
 datachain/cli/commands/misc.py,sha256=c0DmkOLwcDI2YhA8ArOuLJk6aGzSMZCiKL_E2JGibVE,600
 datachain/cli/commands/query.py,sha256=2S7hQxialt1fkbocxi6JXZI6jS5QnFrD1aOjKgZkzfI,1471
-datachain/cli/commands/show.py,sha256=d-DDw4hA3TWA2vqIS-FkEXrzqvttcTdh2QPaahtLdy0,1445
+datachain/cli/commands/show.py,sha256=0ITkA7wvBPfEKM1K6uE0aage38WVsy1QXi6NS8VeSJw,1643
 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
@@ -38,19 +38,19 @@ datachain/client/__init__.py,sha256=1kDpCPoibMXi1gExR4lTLc5pi-k6M5TANiwtXkPoLhU,
 datachain/client/azure.py,sha256=ma6fJcnveG8wpNy1PSrN5hgvmRdCj8Sf3RKjfd3qCyM,3221
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
 datachain/client/fsspec.py,sha256=VutCpF8MDisDwdnJvJpiTuDU9BRRAa0Km3ZkD0sKaI0,13834
-datachain/client/gcs.py,sha256=TY5K5INORKknTnoWDYv0EUztVLmuY1hHmdf2wUB_9uE,5114
+datachain/client/gcs.py,sha256=tepsstv-6WkkJ16SVXIPKPlWdNyFlTqrUlDwulWlWGQ,5116
 datachain/client/hf.py,sha256=posnI5WOKOMG1yY_ZiV9Orcd24QsUPKZlOXgJVLxxrM,1558
 datachain/client/local.py,sha256=cGoCYflribzexiOe-Y1qbaE2fJRh-_EgQrfCSa0yK_E,4568
-datachain/client/s3.py,sha256=l2A4J086ZROKKHNVXnoBky0OgYYKB0EAr8Y3lObo8GY,7284
+datachain/client/s3.py,sha256=YCtDhKVO_jGsMPeyqe3xk5QsF5lqMabqkt0tPFWUHOM,7286
 datachain/data_storage/__init__.py,sha256=9Wit-oe5P46V7CJQTD0BJ5MhOa2Y9h3ddJ4VWTe-Lec,273
 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=hfTITcesE9XlUTxcCcdDyWGGep-QSjJL9DUxko5QCeI,37524
+datachain/data_storage/metastore.py,sha256=19LP15xT2Fmz0aIZ1sIajq8i1-KnFgCBEZeU2Ka9-mc,37780
 datachain/data_storage/schema.py,sha256=qSukry2kINhVw8aj5lQrpe7N90DFeatKIKmDh6jAzR8,9515
 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
@@ -70,21 +70,21 @@ 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=qk6R8D1Snf3yuJ-y2PVbSjkpEllKVJ7TDkC7I2GpBHY,98590
-datachain/lib/file.py,sha256=o4napoPLP_BZYc05ktE9GcF1VlTj3s4lrGvbhxpDeX8,30345
+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=hDPfEkcmiLZOjhBBXuareMdnq65Wj8vZvxjmum6cROM,6377
+datachain/lib/meta_formats.py,sha256=xEYlfN6XgiOgrqhY2kVlvK3xlo5nT3nuVrH111XMOrg,6385
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
 datachain/lib/pytorch.py,sha256=QxXBhrn2-D0RiFA2rdxZ7wKMxyuQ0WWHKfiFEWAA760,7710
 datachain/lib/settings.py,sha256=ZELRCTLbi5vzRPiDX6cQ9LLg9TefJ_A05gIGni0lll8,2535
-datachain/lib/signal_schema.py,sha256=WyVTXUsa4DVTIZRAX2-MdjOe4deat_Fufsd9n8ycrXQ,33629
+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=TlvikKTFvkIKaqqSkSriOyXhQ0rwRHV2ZRs1LHZOCmo,16107
-datachain/lib/udf_signature.py,sha256=GXw24A-Olna6DWCdgy2bC-gZh_gLGPQ-KvjuI6pUjC0,7281
+datachain/lib/udf.py,sha256=4_mdcWNkyukbDjqBNszlIrZLQyl_dPVQxhKwb_iDtQQ,16192
+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
 datachain/lib/webdataset.py,sha256=o7SHk5HOUWsZ5Ln04xOM04eQqiBHiJNO7xLgyVBrwo8,6924
@@ -106,7 +106,7 @@ 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=jRMclCOKUblMb-OGGUHq59Zk0d3M2eHkqIh14F7jyY4,57097
+datachain/query/dataset.py,sha256=J3NgcrzSP2dFg8JVqDodyBh1QEia_B-alcyfI3xKlZE,57256
 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
@@ -132,15 +132,15 @@ datachain/sql/functions/path.py,sha256=zixpERotTFP6LZ7I4TiGtyRA8kXOoZmH1yzH9oRW0
 datachain/sql/functions/random.py,sha256=vBwEEj98VH4LjWixUCygQ5Bz1mv1nohsCG0-ZTELlVg,271
 datachain/sql/functions/string.py,sha256=E-T9OIzUR-GKaLgjZsEtg5CJrY_sLf1lt1awTvY7w2w,1426
 datachain/sql/sqlite/__init__.py,sha256=TAdJX0Bg28XdqPO-QwUVKy8rg78cgMileHvMNot7d04,166
-datachain/sql/sqlite/base.py,sha256=Rfemu8pj7V0aWhWwryDghhnbiMFfQS5X9FCihGuplb8,19593
+datachain/sql/sqlite/base.py,sha256=N-cQT0Hpu9ROWe4OiKlkkn_YP1NKCRZZ3xSfTzpyaDA,19651
 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/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.12.0.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.12.0.dist-info/METADATA,sha256=yHNtv5QzGI6O2TJcGTgFszXBANJHjQibgj_sq_00vy0,11351
-datachain-0.12.0.dist-info/WHEEL,sha256=52BFRY2Up02UkjOa29eZOS2VxUrpPORXg1pkohGGUS8,91
-datachain-0.12.0.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.12.0.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.12.0.dist-info/RECORD,,
+datachain-0.13.1.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.13.1.dist-info/METADATA,sha256=FUW59zu58aHCBMYTtC_K6DkXYQZXaRQRc1L4wJFcGtc,11373
+datachain-0.13.1.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
+datachain-0.13.1.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.13.1.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.13.1.dist-info/RECORD,,

{datachain-0.12.0.dist-info → datachain-0.13.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (76.0.0)
+Generator: setuptools (77.0.3)
 Root-Is-Purelib: true
 Tag: py3-none-any