datachain 0.3.17__py3-none-any.whl → 0.3.18__py3-none-any.whl

datachain/nodes_thread_pool.py

@@ -20,7 +20,7 @@ class NodeChunk:
     def next_downloadable(self):
         node = next(self.nodes, None)
         while node and (
-            not node.is_downloadable or self.cache.contains(node.as_uid(self.storage))
+            not node.is_downloadable or self.cache.contains(node.to_file(self.storage))
         ):
             node = next(self.nodes, None)
         return node

datachain/progress.py

@@ -1,8 +1,6 @@
 """Manages progress bars."""
 
 import logging
-import os
-import re
 import sys
 from threading import RLock
 from typing import Any, ClassVar
@@ -10,20 +8,12 @@ from typing import Any, ClassVar
 from fsspec.callbacks import TqdmCallback
 from tqdm import tqdm
 
+from datachain.utils import env2bool
+
 logger = logging.getLogger(__name__)
 tqdm.set_lock(RLock())
 
 
-def env2bool(var, undefined=False):
-    """
-    undefined: return value if env var is unset
-    """
-    var = os.getenv(var, None)
-    if var is None:
-        return undefined
-    return bool(re.search("1|y|yes|true", var, flags=re.IGNORECASE))
-
-
 class Tqdm(tqdm):
     """
     maximum-compatibility tqdm-based progressbars

datachain/query/dataset.py

@@ -53,7 +53,7 @@ from datachain.utils import (
 
 from .schema import C, UDFParamSpec, normalize_param
 from .session import Session
-from .udf import UDFBase, UDFClassWrapper, UDFFactory, UDFType
+from .udf import UDFBase
 
 if TYPE_CHECKING:
     from sqlalchemy.sql.elements import ClauseElement
@@ -364,7 +364,7 @@ def get_generated_callback(is_generator: bool = False) -> Callback:
 
 @frozen
 class UDFStep(Step, ABC):
-    udf: UDFType
+    udf: UDFBase
     catalog: "Catalog"
     partition_by: Optional[PartitionByType] = None
     parallel: Optional[int] = None
@@ -470,12 +470,6 @@ class UDFStep(Step, ABC):
 
             else:
                 # Otherwise process single-threaded (faster for smaller UDFs)
-                # Optionally instantiate the UDF instance if a class is provided.
-                if isinstance(self.udf, UDFFactory):
-                    udf: UDFBase = self.udf()
-                else:
-                    udf = self.udf
-
                 warehouse = self.catalog.warehouse
 
                 with contextlib.closing(
@@ -485,7 +479,7 @@ class UDFStep(Step, ABC):
                     processed_cb = get_processed_callback()
                     generated_cb = get_generated_callback(self.is_generator)
                     try:
-                        udf_results = udf.run(
+                        udf_results = self.udf.run(
                             udf_fields,
                             udf_inputs,
                             self.catalog,
@@ -498,7 +492,7 @@ class UDFStep(Step, ABC):
                             warehouse,
                             udf_table,
                             udf_results,
-                            udf,
+                            self.udf,
                             cb=generated_cb,
                         )
                     finally:
@@ -1471,7 +1465,7 @@ class DatasetQuery:
     @detach
     def add_signals(
         self,
-        udf: UDFType,
+        udf: UDFBase,
         parallel: Optional[int] = None,
         workers: Union[bool, int] = False,
         min_task_size: Optional[int] = None,
@@ -1492,9 +1486,6 @@ class DatasetQuery:
         at least that minimum number of rows to each distributed worker, mostly useful
         if there are a very large number of small tasks to process.
         """
-        if isinstance(udf, UDFClassWrapper):  # type: ignore[unreachable]
-            # This is a bare decorated class, "instantiate" it now.
-            udf = udf()  # type: ignore[unreachable]
         query = self.clone()
         query.steps.append(
             UDFSignal(
@@ -1518,16 +1509,13 @@ class DatasetQuery:
     @detach
     def generate(
         self,
-        udf: UDFType,
+        udf: UDFBase,
         parallel: Optional[int] = None,
         workers: Union[bool, int] = False,
         min_task_size: Optional[int] = None,
         partition_by: Optional[PartitionByType] = None,
         cache: bool = False,
     ) -> "Self":
-        if isinstance(udf, UDFClassWrapper):  # type: ignore[unreachable]
-            # This is a bare decorated class, "instantiate" it now.
-            udf = udf()  # type: ignore[unreachable]
         query = self.clone()
         steps = query.steps
         steps.append(

datachain/query/dispatch.py

@@ -27,7 +27,7 @@ from datachain.query.queue import (
     put_into_queue,
     unmarshal,
 )
-from datachain.query.udf import UDFBase, UDFFactory, UDFResult
+from datachain.query.udf import UDFBase, UDFResult
 from datachain.utils import batched_it
 
 DEFAULT_BATCH_SIZE = 10000
@@ -156,8 +156,6 @@ class UDFDispatcher:
 
     @property
     def batch_size(self):
-        if not self.udf:
-            self.udf = self.udf_factory()
         if self._batch_size is None:
             if hasattr(self.udf, "properties") and hasattr(
                 self.udf.properties, "batch"
@@ -181,18 +179,7 @@ class UDFDispatcher:
             self.catalog = Catalog(
                 id_generator, metastore, warehouse, **self.catalog_init_params
             )
-        udf = loads(self.udf_data)
-        # isinstance cannot be used here, as cloudpickle packages the entire class
-        # definition, and so these two types are not considered exactly equal,
-        # even if they have the same import path.
-        if full_module_type_path(type(udf)) != full_module_type_path(UDFFactory):
-            self.udf = udf
-        else:
-            self.udf = None
-            self.udf_factory = udf
-        if not self.udf:
-            self.udf = self.udf_factory()
-
+        self.udf = loads(self.udf_data)
         return UDFWorker(
             self.catalog,
             self.udf,

datachain/query/schema.py

@@ -9,6 +9,7 @@ import attrs
 import sqlalchemy as sa
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback
 
+from datachain.lib.file import File
 from datachain.sql.types import JSON, Boolean, DateTime, Int64, SQLType, String
 
 if TYPE_CHECKING:
@@ -97,11 +98,11 @@ class Object(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["file__source"])
-        uid = catalog._get_row_uid(file_signals(row))
+        file = File._from_row(file_signals(row))
+        client = catalog.get_client(file.source)
         if cache:
-            client.download(uid, callback=cb)
-        with client.open_object(uid, use_cache=cache, cb=cb) as f:
+            client.download(file, callback=cb)
+        with client.open_object(file, use_cache=cache, cb=cb) as f:
             return self.reader(f)
 
     async def get_value_async(
@@ -114,12 +115,12 @@ class Object(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["file__source"])
-        uid = catalog._get_row_uid(file_signals(row))
+        file = File._from_row(file_signals(row))
+        client = catalog.get_client(file.source)
         if cache:
-            await client._download(uid, callback=cb)
+            await client._download(file, callback=cb)
         obj = await mapper.to_thread(
-            functools.partial(client.open_object, uid, use_cache=cache, cb=cb)
+            functools.partial(client.open_object, file, use_cache=cache, cb=cb)
         )
         with obj:
             return await mapper.to_thread(self.reader, obj)
@@ -140,11 +141,11 @@ class Stream(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["file__source"])
-        uid = catalog._get_row_uid(file_signals(row))
+        file = File._from_row(file_signals(row))
+        client = catalog.get_client(file.source)
         if cache:
-            client.download(uid, callback=cb)
-        return client.open_object(uid, use_cache=cache, cb=cb)
+            client.download(file, callback=cb)
+        return client.open_object(file, use_cache=cache, cb=cb)
 
     async def get_value_async(
         self,
@@ -156,12 +157,12 @@ class Stream(UDFParameter):
         cb: Callback = DEFAULT_CALLBACK,
         **kwargs,
     ) -> Any:
-        client = catalog.get_client(row["file__source"])
-        uid = catalog._get_row_uid(file_signals(row))
+        file = File._from_row(file_signals(row))
+        client = catalog.get_client(file.source)
         if cache:
-            await client._download(uid, callback=cb)
+            await client._download(file, callback=cb)
         return await mapper.to_thread(
-            functools.partial(client.open_object, uid, use_cache=cache, cb=cb)
+            functools.partial(client.open_object, file, use_cache=cache, cb=cb)
         )
 
 
@@ -189,10 +190,10 @@ class LocalFilename(UDFParameter):
             # If the glob pattern is specified and the row filename
             # does not match it, then return None
             return None
-        client = catalog.get_client(row["file__source"])
-        uid = catalog._get_row_uid(file_signals(row))
-        client.download(uid, callback=cb)
-        return client.cache.get_path(uid)
+        file = File._from_row(file_signals(row))
+        client = catalog.get_client(file.source)
+        client.download(file, callback=cb)
+        return client.cache.get_path(file)
 
     async def get_value_async(
         self,
@@ -208,10 +209,10 @@ class LocalFilename(UDFParameter):
             # If the glob pattern is specified and the row filename
             # does not match it, then return None
             return None
-        client = catalog.get_client(row["file__source"])
-        uid = catalog._get_row_uid(file_signals(row))
-        await client._download(uid, callback=cb)
-        return client.cache.get_path(uid)
+        file = File._from_row(file_signals(row))
+        client = catalog.get_client(file.source)
+        await client._download(file, callback=cb)
+        return client.cache.get_path(file)
 
 
 UDFParamSpec = Union[str, Column, UDFParameter]

datachain/query/udf.py

@@ -1,13 +1,9 @@
 import typing
 from collections.abc import Iterable, Iterator, Sequence
 from dataclasses import dataclass
-from functools import WRAPPER_ASSIGNMENTS
 from typing import (
     TYPE_CHECKING,
     Any,
-    Callable,
-    Optional,
-    Union,
 )
 
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback
@@ -128,105 +124,3 @@ class UDFBase:
             for row_id, signals in zip(row_ids, results)
             if signals is not None  # skip rows with no output
         ]
-
-
-class UDFClassWrapper:
-    """
-    A wrapper for class-based (stateful) UDFs.
-    """
-
-    def __init__(
-        self,
-        udf_class: type,
-        properties: UDFProperties,
-        method: Optional[str] = None,
-    ):
-        self.udf_class = udf_class
-        self.udf_method = method
-        self.properties = properties
-        self.output = properties.output
-
-    def __call__(self, *args, **kwargs) -> "UDFFactory":
-        return UDFFactory(
-            self.udf_class,
-            args,
-            kwargs,
-            self.properties,
-            self.udf_method,
-        )
-
-
-class UDFWrapper(UDFBase):
-    """A wrapper class for function UDFs to be used in custom signal generation."""
-
-    def __init__(
-        self,
-        func: Callable,
-        properties: UDFProperties,
-    ):
-        self.func = func
-        super().__init__(properties)
-        # This emulates the behavior of functools.wraps for a class decorator
-        for attr in WRAPPER_ASSIGNMENTS:
-            if hasattr(func, attr):
-                setattr(self, attr, getattr(func, attr))
-
-    def run_once(
-        self,
-        catalog: "Catalog",
-        arg: "UDFInput",
-        is_generator: bool = False,
-        cache: bool = False,
-        cb: Callback = DEFAULT_CALLBACK,
-    ) -> Iterable[UDFResult]:
-        if isinstance(arg, UDFInputBatch):
-            udf_inputs = [
-                self.bind_parameters(catalog, row, cache=cache, cb=cb)
-                for row in arg.rows
-            ]
-            udf_outputs = self.func(udf_inputs)
-            return self._process_results(arg.rows, udf_outputs, is_generator)
-        if isinstance(arg, RowDict):
-            udf_inputs = self.bind_parameters(catalog, arg, cache=cache, cb=cb)
-            udf_outputs = self.func(*udf_inputs)
-            if not is_generator:
-                # udf_outputs is generator already if is_generator=True
-                udf_outputs = [udf_outputs]
-            return self._process_results([arg], udf_outputs, is_generator)
-        raise ValueError(f"Unexpected UDF argument: {arg}")
-
-    # This emulates the behavior of functools.wraps for a class decorator
-    def __repr__(self):
-        return repr(self.func)
-
-
-class UDFFactory:
-    """
-    A wrapper for late instantiation of UDF classes, primarily for use in parallelized
-    execution.
-    """
-
-    def __init__(
-        self,
-        udf_class: type,
-        args,
-        kwargs,
-        properties: UDFProperties,
-        method: Optional[str] = None,
-    ):
-        self.udf_class = udf_class
-        self.udf_method = method
-        self.args = args
-        self.kwargs = kwargs
-        self.properties = properties
-        self.output = properties.output
-
-    def __call__(self) -> UDFWrapper:
-        udf_func = self.udf_class(*self.args, **self.kwargs)
-        if self.udf_method:
-            udf_func = getattr(udf_func, self.udf_method)
-
-        return UDFWrapper(udf_func, self.properties)
-
-
-UDFType = Union[UDFBase, UDFFactory]

datachain/sql/types.py

@@ -12,11 +12,11 @@ for sqlite we can use `sqlite.register_converter`
 ( https://docs.python.org/3/library/sqlite3.html#sqlite3.register_converter )
 """
 
-import json
 from datetime import datetime
 from types import MappingProxyType
 from typing import Any, Union
 
+import orjson
 import sqlalchemy as sa
 from sqlalchemy import TypeDecorator, types
 
@@ -312,7 +312,7 @@ class Array(SQLType):
     def on_read_convert(self, value, dialect):
         r = read_converter(dialect).array(value, self.item_type, dialect)
         if isinstance(self.item_type, JSON):
-            r = [json.loads(item) if isinstance(item, str) else item for item in r]
+            r = [orjson.loads(item) if isinstance(item, str) else item for item in r]
         return r
 
 
@@ -420,6 +420,8 @@ class TypeReadConverter:
         return [item_type.on_read_convert(x, dialect) for x in value]
 
     def json(self, value):
+        if isinstance(value, str):
+            return orjson.loads(value)
         return value
 
     def datetime(self, value):

datachain/telemetry.py

@@ -0,0 +1,37 @@
+import logging
+import os
+from importlib.metadata import PackageNotFoundError, version
+
+from iterative_telemetry import IterativeTelemetryLogger
+
+from datachain.utils import env2bool
+
+logger = logging.getLogger(__name__)
+
+
+def is_enabled():
+    """
+    Determine if telemetry is enabled based on environment variables and configuration.
+    """
+    # Disable telemetry if running in test mode
+    if env2bool("DATACHAIN_TEST"):
+        return False
+
+    # Check if telemetry is disabled by environment variable
+    disabled = bool(os.getenv("DATACHAIN_NO_ANALYTICS"))
+    if disabled:
+        logger.debug("Telemetry is disabled by environment variable.")
+        return False
+
+    logger.debug("Telemetry is enabled.")
+    return True
+
+
+# Try to get the version of the datachain package
+try:
+    __version__ = version("datachain")
+except PackageNotFoundError:
+    __version__ = "unknown"
+
+# Initialize telemetry logger
+telemetry = IterativeTelemetryLogger("datachain", __version__, is_enabled)

datachain/utils.py

@@ -4,6 +4,7 @@ import json
 import os
 import os.path as osp
 import random
+import re
 import stat
 import sys
 import time
@@ -410,3 +411,13 @@ def get_datachain_executable() -> list[str]:
 def uses_glob(path: str) -> bool:
     """Checks if some URI path has glob syntax in it"""
     return glob.has_magic(os.path.basename(os.path.normpath(path)))
+
+
+def env2bool(var, undefined=False):
+    """
+    undefined: return value if env var is unset
+    """
+    var = os.getenv(var, None)
+    if var is None:
+        return undefined
+    return bool(re.search("1|y|yes|true", var, flags=re.IGNORECASE))

{datachain-0.3.17.dist-info → datachain-0.3.18.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.3.17
+Version: 0.3.18
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -43,6 +43,7 @@ Requires-Dist: Pillow <11,>=10.0.0
 Requires-Dist: msgpack <2,>=1.0.4
 Requires-Dist: psutil
 Requires-Dist: huggingface-hub
+Requires-Dist: iterative-telemetry >=0.0.9
 Requires-Dist: numpy <2,>=1 ; sys_platform == "win32"
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests] ; extra == 'dev'
@@ -63,9 +64,10 @@ Requires-Dist: datachain[tests] ; extra == 'examples'
 Requires-Dist: numpy <2,>=1 ; extra == 'examples'
 Requires-Dist: defusedxml ; extra == 'examples'
 Requires-Dist: accelerate ; extra == 'examples'
-Requires-Dist: unstructured[pdf] ; extra == 'examples'
+Requires-Dist: unstructured[embed-huggingface,pdf] ; extra == 'examples'
 Requires-Dist: pdfplumber ==0.11.4 ; extra == 'examples'
 Requires-Dist: huggingface-hub[hf_transfer] ; extra == 'examples'
+Requires-Dist: onnx ==1.16.1 ; extra == 'examples'
 Provides-Extra: hf
 Requires-Dist: numba >=0.60.0 ; extra == 'hf'
 Requires-Dist: datasets[audio,vision] >=2.21.0 ; extra == 'hf'
@@ -78,7 +80,7 @@ Requires-Dist: pytest <9,>=8 ; extra == 'tests'
 Requires-Dist: pytest-sugar >=0.9.6 ; extra == 'tests'
 Requires-Dist: pytest-cov >=4.1.0 ; extra == 'tests'
 Requires-Dist: pytest-mock >=3.12.0 ; extra == 'tests'
-Requires-Dist: pytest-servers[all] >=0.5.5 ; extra == 'tests'
+Requires-Dist: pytest-servers[all] >=0.5.7 ; extra == 'tests'
 Requires-Dist: pytest-benchmark[histogram] ; extra == 'tests'
 Requires-Dist: pytest-xdist >=3.3.1 ; extra == 'tests'
 Requires-Dist: virtualenv ; extra == 'tests'

{datachain-0.3.17.dist-info → datachain-0.3.18.dist-info}/RECORD

@@ -1,32 +1,33 @@
 datachain/__init__.py,sha256=GeyhE-5LgfJav2OKYGaieP2lBvf2Gm-ihj7thnK9zjI,800
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=Lg3Ck1PQLjQziMx9KU4atzbEnJXTE0924WMYkhgWtGU,8247
-datachain/cache.py,sha256=WP-ktH_bRn3w2g1JOOQ7rCPsZyR4OM6K1Kb7yZsSSns,4056
-datachain/cli.py,sha256=zObcD5W8dzUJKk2RGQ1MxQLEr3jnox6bybU8WyDaIqE,29941
+datachain/cache.py,sha256=s0YHN7qurmQv-eC265TjeureK84TebWWAnL07cxchZQ,2997
+datachain/cli.py,sha256=tRuUvlFey5zYE0UVkGylqGiG5t89gUBo2SJ_yPsvu1I,30129
 datachain/cli_utils.py,sha256=jrn9ejGXjybeO1ur3fjdSiAyCHZrX0qsLLbJzN9ErPM,2418
 datachain/config.py,sha256=PfC7W5yO6HFO6-iMB4YB-0RR88LPiGmD6sS_SfVbGso,1979
 datachain/dataset.py,sha256=sHnsmKfMg2bK88gZH1izk8jlbmJDEhQpyOemdaPQVFo,14761
 datachain/error.py,sha256=OnZ8OaBtDdTZPy8XQiy29SAjqdQArQeorYbP5ju7ldc,1199
 datachain/job.py,sha256=Jt4sNutMHJReaGsj3r3scueN5aESLGfhimAa8pUP7Is,1271
-datachain/listing.py,sha256=vfjOlcb98A7xkGGKWEYON6l7lfrOqNv6kldmdVnlJn4,8178
-datachain/node.py,sha256=-Y8O7q7NtIm_jX0HgjhjvdFwm73TrO5QBslxvFVwTJE,5208
-datachain/nodes_fetcher.py,sha256=kca19yvu11JxoVY1t4_ydp1FmchiV88GnNicNBQ9NIA,831
-datachain/nodes_thread_pool.py,sha256=ZyzBvUImIPmi4WlKC2SW2msA0UhtembbTdcs2nx29A0,3191
-datachain/progress.py,sha256=7_8FtJs770ITK9sMq-Lt4k4k18QmYl4yIG_kCoWID3o,4559
+datachain/listing.py,sha256=TkMmBzCiru26x4RaZiagWJTmTGbiy6yGrAsSJMr8cFE,8213
+datachain/node.py,sha256=ThE6Ue4BqpaBvrkFFJW_ljLxchixUX2aWz3l_nbwY54,5195
+datachain/nodes_fetcher.py,sha256=F-73-h19HHNGtHFBGKk7p3mc0ALm4a9zGnzhtuUjnp4,1107
+datachain/nodes_thread_pool.py,sha256=uPo-xl8zG5m9YgODjPFBpbcqqHjI-dcxH87yAbj_qco,3192
+datachain/progress.py,sha256=5KotcvvzAUL_RF0GEj4JY0IB1lyImnmHxe89YkT1XO4,4330
 datachain/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/storage.py,sha256=RiSJLYdHUjnrEWkLBKPcETHpAxld_B2WxLg711t0aZI,3733
-datachain/utils.py,sha256=VGAcTWjGF0e2qB3Se77shhpiqGMo-ol0QAwf3MH5b7c,11857
+datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
+datachain/utils.py,sha256=KeFSRHsiYthnTu4a6bH-rw04mX1m8krTX0f2NqfQGFI,12114
 datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=IAaaSVFxtJxVlIGEbu8sHinmYyeDGY6dg7APrtOchVk,68278
+datachain/catalog/catalog.py,sha256=tICInYEeCRJow9hNSFnlA50hCOjFPN7fyGgoN5shcf8,67985
 datachain/catalog/datasource.py,sha256=D-VWIVDCM10A8sQavLhRXdYSCG7F4o4ifswEF80_NAQ,1412
 datachain/catalog/loader.py,sha256=-6VelNfXUdgUnwInVyA8g86Boxv2xqhTh9xNS-Zlwig,8242
 datachain/client/__init__.py,sha256=T4wiYL9KIM0ZZ_UqIyzV8_ufzYlewmizlV4iymHNluE,86
 datachain/client/azure.py,sha256=ffxs26zm6KLAL1aUWJm-vtzuZP3LSNha7UDGXynMBKo,2234
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
-datachain/client/fsspec.py,sha256=0i4EJIwdx_UNZlbSsUeohWjgVg4B5xoGxTYZKwXS22U,13459
+datachain/client/fsspec.py,sha256=CO5LfxlZF58UAywLfMYeZRXDLIzcJepnQyPZfZk0Ies,12236
 datachain/client/gcs.py,sha256=cnTIr5GS6dbYOEYfqehhyQu3dr6XNjPHSg5U3FkivUk,4124
 datachain/client/hf.py,sha256=k24bpa6FEKNQn9zhoNC9kCigDwFSqobLsCnN_Nuzwh4,922
-datachain/client/local.py,sha256=LTyISV4oNSOPUdsai5eNZYCGXNCn8rNGuAI0bdgbtnU,5006
+datachain/client/local.py,sha256=5OT3yf9QHi0If_dlqKYIYs-if-3oWhfAztMvsSa3YRA,4969
 datachain/client/s3.py,sha256=CVHBUZ1Ic2Q3370nl-Bbe69phuWjFlrVv9dTJKBpRT0,6019
 datachain/data_storage/__init__.py,sha256=cEOJpyu1JDZtfUupYucCDNFI6e5Wmp_Oyzq6rZv32Y8,398
 datachain/data_storage/db_engine.py,sha256=81Ol1of9TTTzD97ORajCnP366Xz2mEJt6C-kTUCaru4,3406
@@ -38,15 +39,15 @@ datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2kru
 datachain/data_storage/sqlite.py,sha256=EBKJncuzcyQfcKFm2mUjvHjHRTODsteM-k_zndunBrw,28834
 datachain/data_storage/warehouse.py,sha256=Vwhu_OfcNAoTtg1BHui80VCzlPeTUjZQL0QWziu8awY,32186
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/lib/arrow.py,sha256=voY9KuJ2uhPxw_DS6rIjwfKjWXi84T3LFJ7kGFcDQuk,7272
+datachain/lib/arrow.py,sha256=uYn9RQwJy4MsMkhu18_6cgtVO3HkniBcB1NdFmkwtvo,7292
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=gHIjlow84GMRDa78yLL1Ud-N18or21fnTyPEwsatpXY,2045
 datachain/lib/dataset_info.py,sha256=srPPhI2UHf6hFPBecyFEVw2SS5aPisIIMsvGgKqi7ss,2366
-datachain/lib/dc.py,sha256=DkzuKS14kgAEax47Gi9w_XJXV3dbboW85A0YOxwNjKY,68869
-datachain/lib/file.py,sha256=elQLorLbIkusuQSVfiuC_KrGSZI8cGm-iT8fHmckJlo,13774
+datachain/lib/dc.py,sha256=oc9tPf5G9X3DmVCPaTuuwp8LlLogoYuEHpOkq_W7h6Y,68984
+datachain/lib/file.py,sha256=flKGvmrotXWZqQQafaZQEeSQlqUVTSVWB7JIkEsr0MM,14255
 datachain/lib/hf.py,sha256=cPnmLuprr0pYABH7KqA5FARQ1JGlywdDwD3yDzVAm4k,5920
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
-datachain/lib/listing.py,sha256=NrKb7_6jwp1vEqp5TavSvx3SbLJdvuBzSEclPvbQr30,4013
+datachain/lib/listing.py,sha256=cHPN5-Fq8yb0gP6DARImhmZWxykDDNqhhJujDxEp53A,4104
 datachain/lib/listing_info.py,sha256=36NZ-tXY5Y118wurkajuWWbcE8UCjkRwZlacDtN9F3g,954
 datachain/lib/meta_formats.py,sha256=3f-0vpMTesagS9iMd3y9-u9r-7g0eqYsxmK4fVfNWlw,6635
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
@@ -69,19 +70,19 @@ datachain/lib/convert/unflatten.py,sha256=Ogvh_5wg2f38_At_1lN0D_e2uZOOpYEvwvB2xd
 datachain/lib/convert/values_to_tuples.py,sha256=YOdbjzHq-uj6-cV2Qq43G72eN2avMNDGl4x5t6yQMl8,3931
 datachain/query/__init__.py,sha256=0NBOZVgIDpCcj1Ci883dQ9A0iiwe03xzmotkOCFbxYc,293
 datachain/query/batch.py,sha256=-vlpINJiertlnaoUVv1C95RatU0F6zuhpIYRufJRo1M,3660
-datachain/query/dataset.py,sha256=27QCFhwz4hK-pqTY0hvfFqwxNIH5yxuSjWRl1ZfELd0,55004
-datachain/query/dispatch.py,sha256=GBh3EZHDp5AaXxrjOpfrpfsuy7Umnqxu-MAXcK9X3gc,12945
+datachain/query/dataset.py,sha256=k2jU0uZ86i9vr3On-o7GzHrubK5bCJjZEvz9P8extmw,54347
+datachain/query/dispatch.py,sha256=CFAc09O6UllcyUSSEY1GUlEMPzeO8RYhXinNN4HBl9M,12405
 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=A-Btmu-rR00841PNcs9CjcppfTUc176wT6-m3BOaSgo,8049
+datachain/query/schema.py,sha256=I8zLWJuWl5N332ni9mAzDYtcxMJupVPgWkSDe8spNEk,8019
 datachain/query/session.py,sha256=UPH5Z4fzCDsvj81ji0e8GA6Mgra3bOAEpVq4htqOtis,4317
-datachain/query/udf.py,sha256=QRDcSgJ_zrY63dyMVD8nq4ky9Q2kaKSoM6bsDqpXOvQ,6682
+datachain/query/udf.py,sha256=HB2hbEuiGA4ch9P2mh9iLA5Jj9mRj-4JFy9VfjTLJ8U,3622
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/remote/studio.py,sha256=f5s6qSZ9uB4URGUoU_8_W1KZRRQQVSm6cgEBkBUEfuE,7226
 datachain/sql/__init__.py,sha256=A2djrbQwSMUZZEIKGnm-mnRA-NDSbiDJNpAmmwGNyIo,303
 datachain/sql/selectable.py,sha256=fBM-wS1TUA42kVEAAiwqGtibIevyZAEritwt8PZGyLQ,1589
-datachain/sql/types.py,sha256=1ofJjgzKTxFLl1WaMSI9pLvdHGZ1U24I0z5i-gChqDI,13305
+datachain/sql/types.py,sha256=3aXpoxkmCYbw0Dlta5J1enwS8_FuvjfSqyrNZO-dWj4,13383
 datachain/sql/utils.py,sha256=rzlJw08etivdrcuQPqNVvVWhuVSyUPUQEEc6DOhu258,818
 datachain/sql/default/__init__.py,sha256=XQ2cEZpzWiABqjV-6yYHUBGI9vN_UHxbxZENESmVAWw,45
 datachain/sql/default/base.py,sha256=QD-31C6JnyOXzogyDx90sUhm7QvgXIYpeHEASH84igU,628
@@ -96,9 +97,9 @@ datachain/sql/sqlite/base.py,sha256=WLPHBhZbXbiqPoRV1VgDrXJqku4UuvJpBhYeQ0k5rI8,
 datachain/sql/sqlite/types.py,sha256=yzvp0sXSEoEYXs6zaYC_2YubarQoZH-MiUNXcpuEP4s,1573
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.3.17.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.3.17.dist-info/METADATA,sha256=bPMIQkvQjnflmMQhJa3BH3Mi4DpHTAI8KQ5Vd2ur8Mo,17073
-datachain-0.3.17.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-datachain-0.3.17.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.3.17.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.3.17.dist-info/RECORD,,
+datachain-0.3.18.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.3.18.dist-info/METADATA,sha256=_LpwSHtaSTA-rz4rG9nHIbO2mLlrlI4mCnlxKx8vePo,17185
+datachain-0.3.18.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+datachain-0.3.18.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.3.18.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.3.18.dist-info/RECORD,,