datachain 0.8.10__py3-none-any.whl → 0.8.12__py3-none-any.whl

datachain/lib/dc.py

@@ -25,6 +25,7 @@ from sqlalchemy.sql.functions import GenericFunction
 from sqlalchemy.sql.sqltypes import NullType
 
 from datachain.dataset import DatasetRecord
+from datachain.func import literal
 from datachain.func.base import Function
 from datachain.func.func import Func
 from datachain.lib.convert.python_to_sql import python_to_sql
@@ -1129,8 +1130,12 @@ class DataChain:
         )
         ```
         """
+        primitives = (bool, str, int, float)
+
         for col_name, expr in kwargs.items():
-            if not isinstance(expr, (Column, Func)) and isinstance(expr.type, NullType):
+            if not isinstance(expr, (*primitives, Column, Func)) and isinstance(
+                expr.type, NullType
+            ):
                 raise DataChainColumnError(
                     col_name, f"Cannot infer type with expression {expr}"
                 )
@@ -1145,6 +1150,11 @@ class DataChain:
             elif isinstance(value, Func):
                 # adding new signal
                 mutated[name] = value.get_column(schema)
+            elif isinstance(value, primitives):
+                # adding simple python constant primitives like str, int, float, bool
+                val = literal(value)
+                val.type = python_to_sql(type(value))()
+                mutated[name] = val  # type: ignore[assignment]
             else:
                 # adding new signal
                 mutated[name] = value
@@ -1942,7 +1952,7 @@ class DataChain:
     def from_csv(
         cls,
         path,
-        delimiter: str = ",",
+        delimiter: Optional[str] = None,
         header: bool = True,
         output: OutputType = None,
         object_name: str = "",
@@ -1952,6 +1962,7 @@ class DataChain:
         session: Optional[Session] = None,
         settings: Optional[dict] = None,
         column_types: Optional[dict[str, "Union[str, ArrowDataType]"]] = None,
+        parse_options: Optional[dict[str, "Union[str, Union[bool, Callable]]"]] = None,
         **kwargs,
     ) -> "DataChain":
         """Generate chain from csv files.
@@ -1959,7 +1970,8 @@ class DataChain:
         Parameters:
             path : Storage URI with directory. URI must start with storage prefix such
                 as `s3://`, `gs://`, `az://` or "file:///".
-            delimiter : Character for delimiting columns.
+            delimiter : Character for delimiting columns. Takes precedence if also
+                specified in `parse_options`. Defaults to ",".
             header : Whether the files include a header row.
             output : Dictionary or feature class defining column names and their
                 corresponding types. List of column names is also accepted, in which
@@ -1973,6 +1985,8 @@ class DataChain:
             column_types : Dictionary of column names and their corresponding types.
                 It is passed to CSV reader and for each column specified type auto
                 inference is disabled.
+            parse_options: Tells the parser how to process lines.
+                See https://arrow.apache.org/docs/python/generated/pyarrow.csv.ParseOptions.html
 
         Example:
             Reading a csv file:
@@ -1990,6 +2004,12 @@ class DataChain:
         from pyarrow.dataset import CsvFileFormat
         from pyarrow.lib import type_for_alias
 
+        parse_options = parse_options or {}
+        if "delimiter" not in parse_options:
+            parse_options["delimiter"] = ","
+        if delimiter:
+            parse_options["delimiter"] = delimiter
+
         if column_types:
             column_types = {
                 name: type_for_alias(typ) if isinstance(typ, str) else typ
@@ -2017,7 +2037,7 @@ class DataChain:
                 msg = f"error parsing csv - incompatible output type {type(output)}"
                 raise DatasetPrepareError(chain.name, msg)
 
-        parse_options = ParseOptions(delimiter=delimiter)
+        parse_options = ParseOptions(**parse_options)
         read_options = ReadOptions(column_names=column_names)
         convert_options = ConvertOptions(
             strings_can_be_null=True,

datachain/lib/file.py

@@ -190,6 +190,22 @@ class File(DataModel):
         self._catalog = None
         self._caching_enabled: bool = False
 
+    @classmethod
+    def upload(
+        cls, data: bytes, path: str, catalog: Optional["Catalog"] = None
+    ) -> "File":
+        if catalog is None:
+            from datachain.catalog.loader import get_catalog
+
+            catalog = get_catalog()
+
+        parent, name = posixpath.split(path)
+
+        client = catalog.get_client(parent)
+        file = client.upload(data, name)
+        file._set_stream(catalog)
+        return file
+
     @classmethod
     def _from_row(cls, row: "RowDict") -> "Self":
         return cls(**{key: row[key] for key in cls._datachain_column_types})

datachain/lib/listing.py

@@ -1,3 +1,5 @@
+import logging
+import os
 import posixpath
 from collections.abc import Iterator
 from typing import TYPE_CHECKING, Callable, Optional, TypeVar
@@ -7,6 +9,7 @@ from sqlalchemy.sql.expression import true
 
 from datachain.asyn import iter_over_async
 from datachain.client import Client
+from datachain.error import REMOTE_ERRORS, ClientError
 from datachain.lib.file import File
 from datachain.query.schema import Column
 from datachain.sql.functions import path as pathfunc
@@ -22,6 +25,10 @@ LISTING_PREFIX = "lst__"  # listing datasets start with this name
 
 D = TypeVar("D", bound="DataChain")
 
+# Disable warnings for remote errors in clients
+logging.getLogger("aiobotocore.credentials").setLevel(logging.CRITICAL)
+logging.getLogger("gcsfs").setLevel(logging.CRITICAL)
+
 
 def list_bucket(uri: str, cache, client_config=None) -> Callable:
     """
@@ -90,6 +97,15 @@ def _isfile(client: "Client", path: str) -> bool:
     Returns True if uri points to a file
     """
     try:
+        if "://" in path:
+            # This makes sure that the uppercase scheme is converted to lowercase
+            scheme, path = path.split("://", 1)
+            path = f"{scheme.lower()}://{path}"
+
+        if os.name == "nt" and "*" in path:
+            # On Windows, the glob pattern "*" is not supported
+            return False
+
         info = client.fs.info(path)
         name = info.get("name")
         # case for special simulated directories on some clouds
@@ -99,21 +115,21 @@ def _isfile(client: "Client", path: str) -> bool:
             return False
 
         return info["type"] == "file"
-    except:  # noqa: E722
+    except FileNotFoundError:
         return False
+    except REMOTE_ERRORS as e:
+        raise ClientError(
+            message=str(e),
+            error_code=getattr(e, "code", None),
+        ) from e
 
 
-def parse_listing_uri(uri: str, cache, client_config) -> tuple[Optional[str], str, str]:
+def parse_listing_uri(uri: str, client_config) -> tuple[str, str, str]:
     """
     Parsing uri and returns listing dataset name, listing uri and listing path
     """
     client_config = client_config or {}
-    client = Client.get_client(uri, cache, **client_config)
     storage_uri, path = Client.parse_url(uri)
-    telemetry.log_param("client", client.PREFIX)
-
-    if not uri.endswith("/") and _isfile(client, uri):
-        return None, f"{storage_uri}/{path.lstrip('/')}", path
     if uses_glob(path):
         lst_uri_path = posixpath.dirname(path)
     else:
@@ -157,13 +173,15 @@ def get_listing(
     client_config = catalog.client_config
 
     client = Client.get_client(uri, cache, **client_config)
-    ds_name, list_uri, list_path = parse_listing_uri(uri, cache, client_config)
-    listing = None
+    telemetry.log_param("client", client.PREFIX)
 
-    # if we don't want to use cached dataset (e.g. for a single file listing)
-    if not ds_name:
-        return None, list_uri, list_path, False
+    # we don't want to use cached dataset (e.g. for a single file listing)
+    if not uri.endswith("/") and _isfile(client, uri):
+        storage_uri, path = Client.parse_url(uri)
+        return None, f"{storage_uri}/{path.lstrip('/')}", path, False
 
+    ds_name, list_uri, list_path = parse_listing_uri(uri, client_config)
+    listing = None
     listings = [
         ls for ls in catalog.listings() if not ls.is_expired and ls.contains(ds_name)
     ]

datachain/lib/pytorch.py

@@ -23,7 +23,7 @@ from datachain.query.dataset import get_download_callback
 if TYPE_CHECKING:
     from torchvision.transforms.v2 import Transform
 
-    from datachain.cache import DataChainCache as Cache
+    from datachain.cache import Cache
 
 
 logger = logging.getLogger("datachain")

datachain/lib/udf.py

@@ -32,7 +32,7 @@ if TYPE_CHECKING:
 
     from typing_extensions import Self
 
-    from datachain.cache import DataChainCache as Cache
+    from datachain.cache import Cache
     from datachain.catalog import Catalog
     from datachain.lib.signal_schema import SignalSchema
     from datachain.lib.udf_signature import UdfSignature

datachain/listing.py

@@ -2,7 +2,6 @@ import glob
 import os
 from collections.abc import Iterable, Iterator
 from functools import cached_property
-from itertools import zip_longest
 from typing import TYPE_CHECKING, Optional
 
 from sqlalchemy import Column
@@ -101,11 +100,8 @@ class Listing:
         copy_to_filename: Optional[str],
         recursive=False,
         copy_dir_contents=False,
-        relative_path=None,
-        from_edatachain=False,
         from_dataset=False,
     ) -> list[NodeWithPath]:
-        rel_path_elements = relative_path.split("/") if relative_path else []
         all_nodes: list[NodeWithPath] = []
         for src in sources:
             node = src.node
@@ -119,15 +115,7 @@ class Listing:
                 )
             else:
                 node_path = []
-                if from_edatachain:
-                    for rpe, npe in zip_longest(
-                        rel_path_elements, node.path.split("/")
-                    ):
-                        if rpe == npe:
-                            continue
-                        if npe:
-                            node_path.append(npe)
-                elif copy_to_filename:
+                if copy_to_filename:
                     node_path = [os.path.basename(copy_to_filename)]
                 elif from_dataset:
                     node_path = [

datachain/node.py

@@ -84,18 +84,6 @@ class Node:
         fd.write(f"  size: {self.size}\n")
         return size
 
-    def get_metafile_data(self, path: str):
-        data: dict[str, Any] = {
-            "name": path,
-            "etag": self.etag,
-        }
-        version = self.version
-        if version:
-            data["version"] = version
-        data["last_modified"] = time_to_str(self.last_modified)
-        data["size"] = self.size
-        return data
-
     @property
     def full_path(self) -> str:
         if self.is_dir and self.path:
@@ -181,9 +169,6 @@ class NodeWithPath:
     def append_to_file(self, fd):
         return self.n.append_to_file(fd, "/".join(self.path))
 
-    def get_metafile_data(self):
-        return self.n.get_metafile_data("/".join(self.path))
-
     @property
     def full_path(self) -> str:
         path = "/".join(self.path)

datachain/nodes_fetcher.py

@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING
 from datachain.nodes_thread_pool import NodesThreadPool
 
 if TYPE_CHECKING:
-    from datachain.cache import DataChainCache
+    from datachain.cache import Cache
     from datachain.client.fsspec import Client
     from datachain.node import Node
 
@@ -13,7 +13,7 @@ logger = logging.getLogger("datachain")
 
 
 class NodesFetcher(NodesThreadPool):
-    def __init__(self, client: "Client", max_threads: int, cache: "DataChainCache"):
+    def __init__(self, client: "Client", max_threads: int, cache: "Cache"):
         super().__init__(max_threads)
         self.client = client
         self.cache = cache

datachain/remote/studio.py

@@ -16,14 +16,12 @@ from urllib.parse import urlparse, urlunparse
 import websockets
 
 from datachain.config import Config
-from datachain.dataset import DatasetStats
 from datachain.error import DataChainError
 from datachain.utils import STUDIO_URL, retry_with_backoff
 
 T = TypeVar("T")
 LsData = Optional[list[dict[str, Any]]]
 DatasetInfoData = Optional[dict[str, Any]]
-DatasetStatsData = Optional[DatasetStats]
 DatasetRowsData = Optional[Iterable[dict[str, Any]]]
 DatasetJobVersionsData = Optional[dict[str, Any]]
 DatasetExportStatus = Optional[dict[str, Any]]
@@ -309,7 +307,7 @@ class StudioClient:
             "datachain/datasets",
             {
                 "dataset_name": name,
-                "version": version,
+                "dataset_version": version,
                 "force": force,
             },
             method="DELETE",
@@ -347,16 +345,6 @@ class StudioClient:
             method="GET",
         )
 
-    def dataset_stats(self, name: str, version: int) -> Response[DatasetStatsData]:
-        response = self._send_request(
-            "datachain/datasets/stats",
-            {"dataset_name": name, "dataset_version": version},
-            method="GET",
-        )
-        if response.ok:
-            response.data = DatasetStats(**response.data)
-        return response
-
     def export_dataset_table(
         self, name: str, version: int
     ) -> Response[DatasetExportSignedUrls]:
@@ -375,7 +363,7 @@ class StudioClient:
             method="GET",
         )
 
-    def upload_file(self, file_name: str, content: bytes) -> Response[FileUploadData]:
+    def upload_file(self, content: bytes, file_name: str) -> Response[FileUploadData]:
         data = {
             "file_content": base64.b64encode(content).decode("utf-8"),
             "file_name": file_name,

datachain/studio.py

@@ -282,7 +282,7 @@ def upload_files(client: StudioClient, files: list[str]) -> list[str]:
         file_name = os.path.basename(file)
         with open(file, "rb") as f:
             file_content = f.read()
-        response = client.upload_file(file_name, file_content)
+        response = client.upload_file(file_content, file_name)
         if not response.ok:
             raise_remote_error(response.message)
 

{datachain-0.8.10.dist-info → datachain-0.8.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: datachain
-Version: 0.8.10
+Version: 0.8.12
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -78,7 +78,6 @@ Requires-Dist: pytest-xdist>=3.3.1; extra == "tests"
 Requires-Dist: virtualenv; extra == "tests"
 Requires-Dist: dulwich; extra == "tests"
 Requires-Dist: hypothesis; extra == "tests"
-Requires-Dist: open_clip_torch; extra == "tests"
 Requires-Dist: aiotools>=1.7.0; extra == "tests"
 Requires-Dist: requests-mock; extra == "tests"
 Requires-Dist: scipy; extra == "tests"
@@ -94,12 +93,9 @@ Provides-Extra: examples
 Requires-Dist: datachain[tests]; extra == "examples"
 Requires-Dist: defusedxml; extra == "examples"
 Requires-Dist: accelerate; extra == "examples"
-Requires-Dist: unstructured_ingest[embed-huggingface]; extra == "examples"
-Requires-Dist: unstructured[pdf]<0.16.12; extra == "examples"
-Requires-Dist: pdfplumber==0.11.5; extra == "examples"
 Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
-Requires-Dist: onnx==1.16.1; extra == "examples"
-Requires-Dist: ultralytics==8.3.61; extra == "examples"
+Requires-Dist: ultralytics==8.3.68; extra == "examples"
+Requires-Dist: open_clip_torch; extra == "examples"
 
 ================
 |logo| DataChain

{datachain-0.8.10.dist-info → datachain-0.8.12.dist-info}/RECORD

@@ -1,61 +1,61 @@
 datachain/__init__.py,sha256=ofPJ6B-d-ybSDRrE7J6wqF_ZRAB2W9U8l-eeuBtqPLg,865
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=RH_jFwJcTXxhEFomaI9yL6S3Onau6NZ6FSKfKFGtrJE,9689
-datachain/cache.py,sha256=8BdTklwLOsDicVXUfriIXsheiYVLxgrC-ElkRhPoHxI,3659
+datachain/cache.py,sha256=yQblPhOh_Mq74Ma7xT1CL1idLJ0HgrQxpGVYvRy_9Eg,3623
 datachain/config.py,sha256=g8qbNV0vW2VEKpX-dGZ9pAn0DAz6G2ZFcr7SAV3PoSM,4272
-datachain/dataset.py,sha256=5HtqZBRaaToa_C74g62bACjBaCRf2Y6BDgIACLhK1ZA,19161
-datachain/error.py,sha256=bxAAL32lSeMgzsQDEHbGTGORj-mPzzpCRvWDPueJNN4,1092
+datachain/dataset.py,sha256=uqP6gtVFcVMVUFyB9Twr6Uk2onx-aBurbli8_VZu4-s,18993
+datachain/error.py,sha256=P1VI-etraA08ZrXHUEg1-xnOa2MkONd7vV0qA5uxBig,1314
 datachain/job.py,sha256=Jt4sNutMHJReaGsj3r3scueN5aESLGfhimAa8pUP7Is,1271
-datachain/listing.py,sha256=kTjZq3XUBmReh_P3sBP2n87F87h30FJwGSRgs6S_0TE,7612
-datachain/node.py,sha256=HSpjBUBQBWXUUpbUEq839dsSc5KR2O8ww1Udl4jQemY,6023
-datachain/nodes_fetcher.py,sha256=ILMzUW5o4_6lUOVrLDC9gJPCXfcgKnMG68plrc7dAOA,1113
+datachain/listing.py,sha256=HNB-xeKA6aUA-HTWr--H22S6jVOxP2OVQ-3d07ISqAk,7109
+datachain/node.py,sha256=KWDT0ClYXB7FYI-QOvzAa-UDkLJErUI2eWm5FBteYuU,5577
+datachain/nodes_fetcher.py,sha256=_wgaKyqEjkqdwJ_Hj6D8vUYz7hnU7g6xhm0H6ZnYxmE,1095
 datachain/nodes_thread_pool.py,sha256=uPo-xl8zG5m9YgODjPFBpbcqqHjI-dcxH87yAbj_qco,3192
 datachain/progress.py,sha256=lRzxoYP4Qv2XBwD78sOkmYRzHFpZ2ExVNJF8wAeICtY,770
 datachain/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/studio.py,sha256=k4QcFmzJ8rBVJIz27BfexmH6lxqpY6VFRgSTJ1Y90Gw,9408
+datachain/studio.py,sha256=iMVDm9wfc86_G02N2p7qF4sdmKDGUkGz7kTOKc9m3Ao,9408
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
 datachain/utils.py,sha256=LBeg-9n48saBTHSPk7u_j-kjJnPUAq5Oyps_peSaqlM,14128
-datachain/catalog/__init__.py,sha256=g2iAAFx_gEIrqshXlhSEbrc8qDaEH11cjU40n3CHDz4,409
-datachain/catalog/catalog.py,sha256=1jtwHVxCRQWJSTz1GjP6qvB2bDo2AosBjouQh3neKaM,60516
+datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
+datachain/catalog/catalog.py,sha256=Kg5JBfuf-e7QoiHx1wLKRq4h3KmWEMpCHpHLd-WBX9E,58611
 datachain/catalog/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
 datachain/catalog/loader.py,sha256=HA_mBC7q_My8j2WnSvIjUGuJpl6SIdg5vvy_lagxJlA,5733
-datachain/cli/__init__.py,sha256=c5iTf37zCeyJfKbJeFyseVCH9tj-zxlYlCUZWWZCy3s,8432
+datachain/cli/__init__.py,sha256=B6xw0qTcBgrICPqeWOhVXPaWJcxdKKg0Os6j2_IGAIc,8219
 datachain/cli/utils.py,sha256=wrLnAh7Wx8O_ojZE8AE4Lxn5WoxHbOj7as8NWlLAA74,3036
-datachain/cli/commands/__init__.py,sha256=uc77ggTRWrq-w1AVsH3Muy6v1ATkNsXUBPIRaOFgNus,533
-datachain/cli/commands/datasets.py,sha256=q1FkvFfeBCkuIuaA8pick0y51ZQuQK89ULUFse5xsu0,3583
+datachain/cli/commands/__init__.py,sha256=zp3bYIioO60x_X04A4-IpZqSYVnpwOa1AdERQaRlIhI,493
+datachain/cli/commands/datasets.py,sha256=k_CwJ_wYX-Jcc_Z8t9a8vX5jFHVt7qDQ0dehaA94iKs,3140
 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/misc.py,sha256=c0DmkOLwcDI2YhA8ArOuLJk6aGzSMZCiKL_E2JGibVE,600
 datachain/cli/commands/query.py,sha256=2S7hQxialt1fkbocxi6JXZI6jS5QnFrD1aOjKgZkzfI,1471
 datachain/cli/commands/show.py,sha256=RVb_7Kjd1kzqTxRKYFvmD04LaJHOtrCc4FYMyc-ZEYw,1149
-datachain/cli/parser/__init__.py,sha256=dgTUS0SjkT01imPG-EcXP0k_juornFh360wsWhdT1fY,14893
+datachain/cli/parser/__init__.py,sha256=mfOf3tbN4xGr4WQND1B5qMQ4LXoqEU9OhYac7wI-WBc,14393
 datachain/cli/parser/job.py,sha256=Zpi_bEsMp71YCr8xay0I93Taz8zS0_jHbxtvvTzXj6c,3197
-datachain/cli/parser/studio.py,sha256=NTymVNu0vnRgNDWSqE22fRsMDlCFNZLcWJ7SsLDs2sE,2917
-datachain/cli/parser/utils.py,sha256=8dybCL0Tce9-3IQntCiEY0t_q2-YGBxZeMqnq_es8vI,1607
+datachain/cli/parser/studio.py,sha256=CwmfdnsDNvDTOEbhLmjun18s4yo8zCgrtGTpF67qf8Q,2968
+datachain/cli/parser/utils.py,sha256=7ZtzGXfBAjVthnc-agz7R9rplnxqFan0LT6x2tq-6Fk,2007
 datachain/client/__init__.py,sha256=1kDpCPoibMXi1gExR4lTLc5pi-k6M5TANiwtXkPoLhU,49
 datachain/client/azure.py,sha256=ma6fJcnveG8wpNy1PSrN5hgvmRdCj8Sf3RKjfd3qCyM,3221
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
-datachain/client/fsspec.py,sha256=7gysN8NjFXKEgu1-gy_PCiupByV-UGh3AEkz-jF1hVI,13912
+datachain/client/fsspec.py,sha256=whQWKD0tGQUjc8FpA0irxc31wiJuQS4x2arHc98-Lv0,13966
 datachain/client/gcs.py,sha256=TY5K5INORKknTnoWDYv0EUztVLmuY1hHmdf2wUB_9uE,5114
 datachain/client/hf.py,sha256=XeVJVbiNViZCpn3sfb90Fr8SYO3BdLmfE3hOWMoqInE,951
-datachain/client/local.py,sha256=_twL9v9vM2q7hyWeETZ9qLJOlG4FhZ0cGg7RteEXHQA,4708
+datachain/client/local.py,sha256=Pv67SYdkNkkNExBoKJF9AnNu0FSrt4JqLRkSVsUnveU,4672
 datachain/client/s3.py,sha256=l2A4J086ZROKKHNVXnoBky0OgYYKB0EAr8Y3lObo8GY,7284
 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/schema.py,sha256=8np_S6Ltq7WXfcqpoSeFPryPS7cipdbiSP6UnKJkAac,9516
+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=ovdH9LmOWLfCrvf0UvXnrNC-CrdAjns3EmXEgFdz4KM,30824
 datachain/diff/__init__.py,sha256=OapNRBsyGDOQHelefUEoXoFHRWCJuBnhvD0ibebKvBc,10486
-datachain/func/__init__.py,sha256=8WWvzWYtOzXmAC1fOMegyoJ-rFnpAca_5UW4gy8BVsk,1077
+datachain/func/__init__.py,sha256=qaSjakSaTsRtnU7Hcb4lJk71tbwk7M0oWmjRqXExCLA,1099
 datachain/func/aggregate.py,sha256=7_IPrIwb2XSs3zG4iOr1eTvzn6kNVe2mkzvNzjusDHk,10942
 datachain/func/array.py,sha256=zHDNWuWLA7HVa9FEvQeHhVi00_xqenyleTqcLwkXWBI,5477
 datachain/func/base.py,sha256=wA0sBQAVyN9LPxoo7Ox83peS0zUVnyuKxukwAcjGLfY,534
-datachain/func/conditional.py,sha256=AfvGQKBFOJ-wkmDTH0P7pmq42Zf1DRcYRsLGurdAiJE,4766
-datachain/func/func.py,sha256=4FJYMqeGD6xNe5ahrFgfthi0DTFb5w3QDLlXxbpHZjU,15371
+datachain/func/conditional.py,sha256=g46zwW-i87uA45zWJnPHtHaqr6qOXSg6xLb4p9W3Gtk,6400
+datachain/func/func.py,sha256=PnwTRAiEJUus3e4NYdQ-hldqLzKS9hY0FjiyBMZhsSo,16183
 datachain/func/numeric.py,sha256=gMe1Ks0dqQKHkjcpvj7I5S-neECzQ_gltPQLNoaWOyo,5632
 datachain/func/path.py,sha256=mqN_mfkwv44z2II7DMTp_fGGw95hmTCNls_TOFNpr4k,3155
 datachain/func/random.py,sha256=pENOLj9rSmWfGCnOsUIaCsVC5486zQb66qfQvXaz9Z4,452
@@ -66,20 +66,20 @@ datachain/lib/arrow.py,sha256=sU6cbjz2W1UuTfez6tCYPfVPJXlmfMDbnaVWPhMu0XU,9906
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=zS4lmXHVBXc9ntcyea2a1CRLXGSAN_0glXcF88CohgY,2685
 datachain/lib/dataset_info.py,sha256=IjdF1E0TQNOq9YyynfWiCFTeZpbyGfyJvxgJY4YN810,2493
-datachain/lib/dc.py,sha256=l1iKnT6wplndIgfMsVMbbKL-etlj2TdHPKJ6kIwqK88,92398
-datachain/lib/file.py,sha256=7posvEFSb7gsLKAiid75dOJRyHTRKOmBAkmBw6RiZyg,16307
+datachain/lib/dc.py,sha256=hJR0rxP4mQozYubERiw35mkTpsm2J0nvB7dJIAWEQ30,93367
+datachain/lib/file.py,sha256=SLgaE5sJJu0-c981Ux1OsR4-IbULD17wGO7fttbCcXU,16743
 datachain/lib/hf.py,sha256=DvoI8fv-WkL3FDEuIT80T9WrRs6fXesjbU0bmIDDsNE,5882
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
-datachain/lib/listing.py,sha256=MSr07Xn2yjIKazbAtRIyVamK8GImcxMeVMChDu2vXrA,6621
+datachain/lib/listing.py,sha256=auodM0HitYZsL0DybdgQUYhne_LgkVW-LKGYYOACP90,7272
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
 datachain/lib/meta_formats.py,sha256=hDPfEkcmiLZOjhBBXuareMdnq65Wj8vZvxjmum6cROM,6377
 datachain/lib/model_store.py,sha256=DNIv8Y6Jtk1_idNLzIpsThOsdW2BMAudyUCbPUcgcxk,2515
-datachain/lib/pytorch.py,sha256=sIm8ITBSGzw08zJMV9mm4nIqDLqbwb4AAmqhuW4_bzU,7728
+datachain/lib/pytorch.py,sha256=QxXBhrn2-D0RiFA2rdxZ7wKMxyuQ0WWHKfiFEWAA760,7710
 datachain/lib/settings.py,sha256=ZELRCTLbi5vzRPiDX6cQ9LLg9TefJ_A05gIGni0lll8,2535
 datachain/lib/signal_schema.py,sha256=ps5od6zhWtdX3Khx2fwArl2xlGkK8SKi6vCQ6QmbaR0,27404
 datachain/lib/tar.py,sha256=3WIzao6yD5fbLqXLTt9GhPGNonbFIs_fDRu-9vgLgsA,1038
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
-datachain/lib/udf.py,sha256=XYu0KN3vlreMcpfUDXuOT325fNwem3UHYPlbyEShdLw,16125
+datachain/lib/udf.py,sha256=TlvikKTFvkIKaqqSkSriOyXhQ0rwRHV2ZRs1LHZOCmo,16107
 datachain/lib/udf_signature.py,sha256=GXw24A-Olna6DWCdgy2bC-gZh_gLGPQ-KvjuI6pUjC0,7281
 datachain/lib/utils.py,sha256=QrjVs_oLRXEotOPUYurBJypBFi_ReTJmxcnJeH4j2Uk,1596
 datachain/lib/vfile.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -111,7 +111,7 @@ datachain/query/session.py,sha256=fQAtl5zRESRDfRS2d5J9KgrWauunCtrd96vP4Ns1KlE,59
 datachain/query/udf.py,sha256=GY8E9pnzPE7ZKl_jvetZpn9R2rlUtMlhoYj4UmrzFzw,594
 datachain/query/utils.py,sha256=u0A_BwG9PNs0DxoDcvSWgWLpj3ByTUv8CqH13CIuGag,1293
 datachain/remote/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/remote/studio.py,sha256=DfW2Iej858tWkKQMg_fvp1cvsvgGX3Z07VXhv_sI3GY,13362
+datachain/remote/studio.py,sha256=3v4ZqP06BwBMLXQ4mbcTS95oUodYgBv9A5XisL6ffWo,12915
 datachain/sql/__init__.py,sha256=6SQRdbljO3d2hx3EAVXEZrHQKv5jth0Jh98PogT59No,262
 datachain/sql/selectable.py,sha256=cTc60qVoAwqqss0Vop8Lt5Z-ROnM1XrQmL_GLjRxhXs,1765
 datachain/sql/types.py,sha256=ASSPkmM5EzdRindqj2O7WHLXq8VHAgFYedG8lYfGvVI,14045
@@ -133,9 +133,9 @@ datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=z3zRJNzjWrpPuRw-zgFbCOBKInyYxJew8ygrYQRQLNc,2930
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.8.10.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.8.10.dist-info/METADATA,sha256=pOueDLv5huX86frgB9ihIuydK_1-t_PHDUvTpabvLuE,11118
-datachain-0.8.10.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-datachain-0.8.10.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.8.10.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.8.10.dist-info/RECORD,,
+datachain-0.8.12.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.8.12.dist-info/METADATA,sha256=C1vaFTVw44GIVe32CcfLthfCi5nbbqTgS7HL61iSFGg,10880
+datachain-0.8.12.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+datachain-0.8.12.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.8.12.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.8.12.dist-info/RECORD,,