datachain 0.8.9__py3-none-any.whl → 0.8.10__py3-none-any.whl

datachain/cli/__init__.py

@@ -48,7 +48,6 @@ def main(argv: Optional[list[str]] = None) -> int:
     logger.setLevel(logging_level)
 
     client_config = {
-        "aws_endpoint_url": args.aws_endpoint_url,
         "anon": args.anon,
     }
 
@@ -73,7 +72,7 @@ def main(argv: Optional[list[str]] = None) -> int:
 
 def handle_command(args, catalog, client_config) -> int:
     """Handle the different CLI commands."""
-    from datachain.studio import process_jobs_args, process_studio_cli_args
+    from datachain.studio import process_auth_cli_args, process_jobs_args
 
     command_handlers = {
         "cp": lambda: handle_cp_command(args, catalog),
@@ -89,7 +88,7 @@ def handle_command(args, catalog, client_config) -> int:
         "query": lambda: handle_query_command(args, catalog),
         "clear-cache": lambda: clear_cache(catalog),
         "gc": lambda: garbage_collect(catalog),
-        "studio": lambda: process_studio_cli_args(args),
+        "auth": lambda: process_auth_cli_args(args),
         "job": lambda: process_jobs_args(args),
     }
 

datachain/cli/parser/__init__.py

@@ -7,7 +7,7 @@ import shtab
 from datachain.cli.utils import BooleanOptionalAction, KeyValueArgs
 
 from .job import add_jobs_parser
-from .studio import add_studio_parser
+from .studio import add_auth_parser
 from .utils import FIND_COLUMNS, add_show_args, add_sources_arg, find_columns_type
 
 
@@ -26,24 +26,25 @@ def get_parser() -> ArgumentParser:  # noqa: PLR0915
 
     parent_parser = ArgumentParser(add_help=False)
     parent_parser.add_argument(
-        "--aws-endpoint-url",
-        type=str,
-        help="AWS endpoint URL",
-    )
-    parent_parser.add_argument(
-        "--anon",
-        action="store_true",
-        help="anon flag for remote storage (like awscli's --no-sign-request)",
+        "-v", "--verbose", action="count", default=0, help="Be verbose"
     )
     parent_parser.add_argument(
-        "-u", "--update", action="count", default=0, help="Update cache"
+        "-q", "--quiet", action="count", default=0, help="Be quiet"
     )
+
     parent_parser.add_argument(
-        "-v", "--verbose", action="count", default=0, help="Be verbose"
+        "--anon",
+        action="store_true",
+        help="Use anonymous access to storage",
     )
     parent_parser.add_argument(
-        "-q", "--quiet", action="count", default=0, help="Be quiet"
+        "-u",
+        "--update",
+        action="count",
+        default=0,
+        help="Update cached list of files for the sources",
     )
+
     parent_parser.add_argument(
         "--debug-sql",
         action="store_true",
@@ -67,7 +68,9 @@ def get_parser() -> ArgumentParser:  # noqa: PLR0915
         "cp", parents=[parent_parser], description="Copy data files from the cloud."
     )
     add_sources_arg(parse_cp).complete = shtab.DIR  # type: ignore[attr-defined]
-    parse_cp.add_argument("output", type=str, help="Output")
+    parse_cp.add_argument(
+        "output", type=str, help="Path to a directory or file to put data to"
+    )
     parse_cp.add_argument(
         "-f",
         "--force",
@@ -94,7 +97,9 @@ def get_parser() -> ArgumentParser:  # noqa: PLR0915
         "clone", parents=[parent_parser], description="Copy data files from the cloud."
     )
     add_sources_arg(parse_clone).complete = shtab.DIR  # type: ignore[attr-defined]
-    parse_clone.add_argument("output", type=str, help="Output")
+    parse_clone.add_argument(
+        "output", type=str, help="Path to a directory or file to put data to"
+    )
     parse_clone.add_argument(
         "-f",
         "--force",
@@ -123,7 +128,7 @@ def get_parser() -> ArgumentParser:  # noqa: PLR0915
         help="Do not copy files, just create a dataset",
     )
 
-    add_studio_parser(subp, parent_parser)
+    add_auth_parser(subp, parent_parser)
     add_jobs_parser(subp, parent_parser)
 
     datasets_parser = subp.add_parser(

datachain/cli/parser/job.py

@@ -6,7 +6,7 @@ def add_jobs_parser(subparsers, parent_parser) -> None:
     )
     jobs_subparser = jobs_parser.add_subparsers(
         dest="cmd",
-        help="Use `datachain studio CMD --help` to display command-specific help",
+        help="Use `datachain auth CMD --help` to display command-specific help",
     )
 
     studio_run_help = "Run a job in Studio"

datachain/cli/parser/studio.py

@@ -1,31 +1,31 @@
-def add_studio_parser(subparsers, parent_parser) -> None:
-    studio_help = "Manage Studio authentication"
-    studio_description = (
+def add_auth_parser(subparsers, parent_parser) -> None:
+    auth_help = "Manage Studio authentication"
+    auth_description = (
         "Manage authentication and settings for Studio. "
         "Configure tokens for sharing datasets and using Studio features."
     )
 
-    studio_parser = subparsers.add_parser(
-        "studio",
+    auth_parser = subparsers.add_parser(
+        "auth",
         parents=[parent_parser],
-        description=studio_description,
-        help=studio_help,
+        description=auth_description,
+        help=auth_help,
     )
-    studio_subparser = studio_parser.add_subparsers(
+    auth_subparser = auth_parser.add_subparsers(
         dest="cmd",
-        help="Use `datachain studio CMD --help` to display command-specific help",
+        help="Use `datachain auth CMD --help` to display command-specific help",
     )
 
-    studio_login_help = "Authenticate with Studio"
-    studio_login_description = (
+    auth_login_help = "Authenticate with Studio"
+    auth_login_description = (
         "Authenticate with Studio using default scopes. "
         "A random name will be assigned as the token name if not specified."
     )
-    login_parser = studio_subparser.add_parser(
+    login_parser = auth_subparser.add_parser(
         "login",
         parents=[parent_parser],
-        description=studio_login_description,
-        help=studio_login_help,
+        description=auth_login_description,
+        help=auth_login_help,
     )
 
     login_parser.add_argument(
@@ -58,26 +58,26 @@ def add_studio_parser(subparsers, parent_parser) -> None:
         help="Use code-based authentication without browser",
     )
 
-    studio_logout_help = "Log out from Studio"
-    studio_logout_description = (
+    auth_logout_help = "Log out from Studio"
+    auth_logout_description = (
         "Remove the Studio authentication token from global config."
     )
 
-    studio_subparser.add_parser(
+    auth_subparser.add_parser(
         "logout",
         parents=[parent_parser],
-        description=studio_logout_description,
-        help=studio_logout_help,
+        description=auth_logout_description,
+        help=auth_logout_help,
     )
 
-    studio_team_help = "Set default team for Studio operations"
-    studio_team_description = "Set the default team for Studio operations."
+    auth_team_help = "Set default team for Studio operations"
+    auth_team_description = "Set the default team for Studio operations."
 
-    team_parser = studio_subparser.add_parser(
+    team_parser = auth_subparser.add_parser(
         "team",
         parents=[parent_parser],
-        description=studio_team_description,
-        help=studio_team_help,
+        description=auth_team_description,
+        help=auth_team_help,
     )
     team_parser.add_argument(
         "team_name",
@@ -91,12 +91,12 @@ def add_studio_parser(subparsers, parent_parser) -> None:
         help="Set team globally for all projects",
     )
 
-    studio_token_help = "View Studio authentication token"  # noqa: S105
-    studio_token_description = "Display the current authentication token for Studio."  # noqa: S105
+    auth_token_help = "View Studio authentication token"  # noqa: S105
+    auth_token_description = "Display the current authentication token for Studio."  # noqa: S105
 
-    studio_subparser.add_parser(
+    auth_subparser.add_parser(
         "token",
         parents=[parent_parser],
-        description=studio_token_description,
-        help=studio_token_help,
+        description=auth_token_description,
+        help=auth_token_help,
     )

datachain/cli/parser/utils.py

@@ -30,7 +30,7 @@ def add_sources_arg(parser: ArgumentParser, nargs: Union[str, int] = "+") -> Act
         "sources",
         type=str,
         nargs=nargs,
-        help="Data sources - paths to cloud storage directories",
+        help="Data sources - paths to source storage directories or files",
     )
 
 

datachain/cli/utils.py

@@ -87,7 +87,7 @@ def get_logging_level(args: Namespace) -> int:
 def determine_flavors(studio: bool, local: bool, all: bool, token: Optional[str]):
     if studio and not token:
         raise DataChainError(
-            "Not logged in to Studio. Log in with 'datachain studio login'."
+            "Not logged in to Studio. Log in with 'datachain auth login'."
         )
 
     if local or studio:

datachain/data_storage/sqlite.py

@@ -19,6 +19,7 @@ from sqlalchemy import MetaData, Table, UniqueConstraint, exists, select
 from sqlalchemy.dialects import sqlite
 from sqlalchemy.schema import CreateIndex, CreateTable, DropTable
 from sqlalchemy.sql import func
+from sqlalchemy.sql.elements import BinaryExpression, BooleanClauseList
 from sqlalchemy.sql.expression import bindparam, cast
 from sqlalchemy.sql.selectable import Select
 from tqdm.auto import tqdm
@@ -40,7 +41,6 @@ if TYPE_CHECKING:
     from sqlalchemy.schema import SchemaItem
     from sqlalchemy.sql._typing import _FromClauseArgument, _OnClauseArgument
     from sqlalchemy.sql.elements import ColumnElement
-    from sqlalchemy.sql.selectable import Join
     from sqlalchemy.types import TypeEngine
 
     from datachain.lib.file import File
@@ -654,16 +654,47 @@ class SQLiteWarehouse(AbstractWarehouse):
         right: "_FromClauseArgument",
         onclause: "_OnClauseArgument",
         inner: bool = True,
-    ) -> "Join":
+        full: bool = False,
+        columns=None,
+    ) -> "Select":
         """
         Join two tables together.
         """
-        return sqlalchemy.join(
-            left,
-            right,
-            onclause,
-            isouter=not inner,
+        if not full:
+            join_query = sqlalchemy.join(
+                left,
+                right,
+                onclause,
+                isouter=not inner,
+            )
+            return sqlalchemy.select(*columns).select_from(join_query)
+
+        left_right_join = sqlalchemy.select(*columns).select_from(
+            sqlalchemy.join(left, right, onclause, isouter=True)
         )
+        right_left_join = sqlalchemy.select(*columns).select_from(
+            sqlalchemy.join(right, left, onclause, isouter=True)
+        )
+
+        def add_left_rows_filter(exp: BinaryExpression):
+            """
+            Adds filter to right_left_join to remove unmatched left table rows by
+            getting column names that need to be NULL from BinaryExpressions in onclause
+            """
+            return right_left_join.where(
+                getattr(left.c, exp.left.name) == None  # type: ignore[union-attr] # noqa: E711
+            )
+
+        if isinstance(onclause, BinaryExpression):
+            right_left_join = add_left_rows_filter(onclause)
+
+        if isinstance(onclause, BooleanClauseList):
+            for c in onclause.get_children():
+                if isinstance(c, BinaryExpression):
+                    right_left_join = add_left_rows_filter(c)
+
+        union = sqlalchemy.union(left_right_join, right_left_join).subquery()
+        return sqlalchemy.select(*union.c).select_from(union)
 
     def create_pre_udf_table(self, query: "Select") -> "Table":
         """

datachain/data_storage/warehouse.py

@@ -31,7 +31,7 @@ if TYPE_CHECKING:
         _FromClauseArgument,
         _OnClauseArgument,
     )
-    from sqlalchemy.sql.selectable import Join, Select
+    from sqlalchemy.sql.selectable import Select
     from sqlalchemy.types import TypeEngine
 
     from datachain.data_storage import schema
@@ -873,7 +873,7 @@ class AbstractWarehouse(ABC, Serializable):
         right: "_FromClauseArgument",
         onclause: "_OnClauseArgument",
         inner: bool = True,
-    ) -> "Join":
+    ) -> "Select":
         """
         Join two tables together.
         """

datachain/lib/convert/python_to_sql.py

@@ -52,15 +52,15 @@ def python_to_sql(typ):  # noqa: PLR0911
 
     args = get_args(typ)
     if inspect.isclass(orig) and (issubclass(list, orig) or issubclass(tuple, orig)):
-        if args is None or len(args) != 1:
+        if args is None:
             raise TypeError(f"Cannot resolve type '{typ}' for flattening features")
 
         args0 = args[0]
         if ModelStore.is_pydantic(args0):
             return Array(JSON())
 
-        next_type = python_to_sql(args0)
-        return Array(next_type)
+        list_type = list_of_args_to_type(args)
+        return Array(list_type)
 
     if orig is Annotated:
         # Ignoring annotations
@@ -82,6 +82,18 @@ def python_to_sql(typ):  # noqa: PLR0911
     raise TypeError(f"Cannot recognize type {typ}")
 
 
+def list_of_args_to_type(args) -> SQLType:
+    first_type = python_to_sql(args[0])
+    for next_arg in args[1:]:
+        try:
+            next_type = python_to_sql(next_arg)
+            if next_type != first_type:
+                return JSON()
+        except TypeError:
+            return JSON()
+    return first_type
+
+
 def _is_json_inside_union(orig, args) -> bool:
     if orig == Union and len(args) >= 2:
         # List in JSON: Union[dict, list[dict]]

datachain/lib/dc.py

@@ -1332,6 +1332,7 @@ class DataChain:
         on: Union[MergeColType, Sequence[MergeColType]],
         right_on: Optional[Union[MergeColType, Sequence[MergeColType]]] = None,
         inner=False,
+        full=False,
         rname="right_",
     ) -> "Self":
         """Merge two chains based on the specified criteria.
@@ -1345,6 +1346,7 @@ class DataChain:
             right_on: Optional predicate or list of Predicates for the `right_ds`
                 to join.
             inner (bool): Whether to run inner join or outer join.
+            full (bool): Whether to run full outer join.
             rname (str): Name prefix for conflicting signal names.
 
         Examples:
@@ -1419,7 +1421,7 @@ class DataChain:
             )
 
         query = self._query.join(
-            right_ds._query, sqlalchemy.and_(*ops), inner, rname + "{name}"
+            right_ds._query, sqlalchemy.and_(*ops), inner, full, rname + "{name}"
         )
         query.feature_schema = None
         ds = self._evolve(query=query)

datachain/query/dataset.py

@@ -875,6 +875,7 @@ class SQLJoin(Step):
     query2: "DatasetQuery"
     predicates: Union[JoinPredicateType, tuple[JoinPredicateType, ...]]
     inner: bool
+    full: bool
     rname: str
 
     def get_query(self, dq: "DatasetQuery", temp_tables: list[str]) -> sa.Subquery:
@@ -977,14 +978,14 @@ class SQLJoin(Step):
         self.validate_expression(join_expression, q1, q2)
 
         def q(*columns):
-            join_query = self.catalog.warehouse.join(
+            return self.catalog.warehouse.join(
                 q1,
                 q2,
                 join_expression,
                 inner=self.inner,
+                full=self.full,
+                columns=columns,
             )
-            return sqlalchemy.select(*columns).select_from(join_query)
-            # return sqlalchemy.select(*subquery.c).select_from(subquery)
 
         return step_result(
             q,
@@ -1489,6 +1490,7 @@ class DatasetQuery:
         dataset_query: "DatasetQuery",
         predicates: Union[JoinPredicateType, Sequence[JoinPredicateType]],
         inner=False,
+        full=False,
         rname="{name}_right",
     ) -> "Self":
         left = self.clone(new_table=False)
@@ -1504,7 +1506,9 @@ class DatasetQuery:
             if isinstance(predicates, (str, ColumnClause, ColumnElement))
             else tuple(predicates)
         )
-        new_query.steps = [SQLJoin(self.catalog, left, right, predicates, inner, rname)]
+        new_query.steps = [
+            SQLJoin(self.catalog, left, right, predicates, inner, full, rname)
+        ]
         return new_query
 
     @detach

datachain/remote/studio.py

@@ -75,7 +75,7 @@ class StudioClient:
 
         if not token:
             raise DataChainError(
-                "Studio token is not set. Use `datachain studio login` "
+                "Studio token is not set. Use `datachain auth login` "
                 "or environment variable `DVC_STUDIO_TOKEN` to set it."
             )
 
@@ -105,7 +105,7 @@ class StudioClient:
         if not team:
             raise DataChainError(
                 "Studio team is not set. "
-                "Use `datachain studio team <team_name>` "
+                "Use `datachain auth team <team_name>` "
                 "or environment variable `DVC_STUDIO_TEAM` to set it."
                 "You can also set it in the config file as team under studio."
             )

datachain/sql/sqlite/base.py

@@ -4,6 +4,7 @@ import sqlite3
 import warnings
 from collections.abc import Iterable
 from datetime import MAXYEAR, MINYEAR, datetime, timezone
+from functools import cache
 from types import MappingProxyType
 from typing import Callable, Optional
 
@@ -526,24 +527,44 @@ def compile_collect(element, compiler, **kwargs):
     return compiler.process(func.json_group_array(*element.clauses.clauses), **kwargs)
 
 
-def load_usearch_extension(conn: sqlite3.Connection) -> bool:
+@cache
+def usearch_sqlite_path() -> Optional[str]:
     try:
-        # usearch is part of the vector optional dependencies
-        # we use the extension's cosine and euclidean distance functions
-        from usearch import sqlite_path
+        import usearch
+    except ImportError:
+        return None
 
-        conn.enable_load_extension(True)
+    with warnings.catch_warnings():
+        # usearch binary is not available for Windows, see: https://github.com/unum-cloud/usearch/issues/427.
+        # and, sometimes fail to download the binary in other platforms
+        # triggering UserWarning.
 
-        with warnings.catch_warnings():
-            # usearch binary is not available for Windows, see: https://github.com/unum-cloud/usearch/issues/427.
-            # and, sometimes fail to download the binary in other platforms
-            # triggering UserWarning.
+        warnings.filterwarnings("ignore", category=UserWarning, module="usearch")
 
-            warnings.filterwarnings("ignore", category=UserWarning, module="usearch")
-            conn.load_extension(sqlite_path())
+        try:
+            return usearch.sqlite_path()
+        except FileNotFoundError:
+            return None
 
-        conn.enable_load_extension(False)
-        return True
 
-    except Exception:  # noqa: BLE001
+def load_usearch_extension(conn: sqlite3.Connection) -> bool:
+    # usearch is part of the vector optional dependencies
+    # we use the extension's cosine and euclidean distance functions
+    ext_path = usearch_sqlite_path()
+    if ext_path is None:
+        return False
+
+    try:
+        conn.enable_load_extension(True)
+    except AttributeError:
+        # sqlite3 module is not built with loadable extension support by default.
+        return False
+
+    try:
+        conn.load_extension(ext_path)
+    except sqlite3.OperationalError:
         return False
+    else:
+        return True
+    finally:
+        conn.enable_load_extension(False)

datachain/studio.py

@@ -47,7 +47,7 @@ def process_jobs_args(args: "Namespace"):
     raise DataChainError(f"Unknown command '{args.cmd}'.")
 
 
-def process_studio_cli_args(args: "Namespace"):
+def process_auth_cli_args(args: "Namespace"):
     if args.cmd is None:
         print(
             f"Use 'datachain {args.command} --help' to see available options",
@@ -95,7 +95,7 @@ def login(args: "Namespace"):
         raise DataChainError(
             "Token already exists. "
             "To login with a different token, "
-            "logout using `datachain studio logout`."
+            "logout using `datachain auth logout`."
         )
 
     open_browser = not args.no_open
@@ -121,12 +121,12 @@ def logout():
         token = conf.get("studio", {}).get("token")
         if not token:
             raise DataChainError(
-                "Not logged in to Studio. Log in with 'datachain studio login'."
+                "Not logged in to Studio. Log in with 'datachain auth login'."
             )
 
         del conf["studio"]["token"]
 
-    print("Logged out from Studio. (you can log back in with 'datachain studio login')")
+    print("Logged out from Studio. (you can log back in with 'datachain auth login')")
 
 
 def token():
@@ -134,7 +134,7 @@ def token():
     token = config.get("token")
     if not token:
         raise DataChainError(
-            "Not logged in to Studio. Log in with 'datachain studio login'."
+            "Not logged in to Studio. Log in with 'datachain auth login'."
         )
 
     print(token)
@@ -299,7 +299,7 @@ def cancel_job(job_id: str, team_name: Optional[str]):
     token = Config().read().get("studio", {}).get("token")
     if not token:
         raise DataChainError(
-            "Not logged in to Studio. Log in with 'datachain studio login'."
+            "Not logged in to Studio. Log in with 'datachain auth login'."
         )
 
     client = StudioClient(team=team_name)
@@ -314,7 +314,7 @@ def show_job_logs(job_id: str, team_name: Optional[str]):
     token = Config().read().get("studio", {}).get("token")
     if not token:
         raise DataChainError(
-            "Not logged in to Studio. Log in with 'datachain studio login'."
+            "Not logged in to Studio. Log in with 'datachain auth login'."
         )
 
     client = StudioClient(team=team_name)

{datachain-0.8.9.dist-info → datachain-0.8.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: datachain
-Version: 0.8.9
+Version: 0.8.10
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0

{datachain-0.8.9.dist-info → datachain-0.8.10.dist-info}/RECORD

@@ -12,15 +12,15 @@ datachain/nodes_fetcher.py,sha256=ILMzUW5o4_6lUOVrLDC9gJPCXfcgKnMG68plrc7dAOA,11
 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=5LTzr7jNxapQk4aF4ob8ax9zNQ0ShZ26nQtOi4gKToc,9422
+datachain/studio.py,sha256=k4QcFmzJ8rBVJIz27BfexmH6lxqpY6VFRgSTJ1Y90Gw,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/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
 datachain/catalog/loader.py,sha256=HA_mBC7q_My8j2WnSvIjUGuJpl6SIdg5vvy_lagxJlA,5733
-datachain/cli/__init__.py,sha256=jnmSov-UIvgz3p-YclkKEhVpvawPVtsd8o5uq7hrRfc,8489
-datachain/cli/utils.py,sha256=jEoqY0agU3AZ-VQBpyieDKIlk7j3sumtlHE3OgbAzdU,3038
+datachain/cli/__init__.py,sha256=c5iTf37zCeyJfKbJeFyseVCH9tj-zxlYlCUZWWZCy3s,8432
+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/du.py,sha256=9edEzDEs98K2VYk8Wf-ZMpUzALcgm9uD6YtoqbvtUGU,391
@@ -29,10 +29,10 @@ datachain/cli/commands/ls.py,sha256=Wb8hXyBwyhb62Zk6ZhNFPFrj2lJhdbRcnBQQkgL_qyw,
 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=xBvS6FDkD-0TrME9t56C00jCFHD5Ly4SIQLe9JGHlpE,14881
-datachain/cli/parser/job.py,sha256=m_w6DZBMvQu0pu5LHxBVnh9gENPf02jxhwtLqjfhEGU,3199
-datachain/cli/parser/studio.py,sha256=AxCK8Oz5psj3jtl6XFSkGjDoSXuek3nBpPttvNFov9U,2977
-datachain/cli/parser/utils.py,sha256=gDaRll8CugmdFdx9mhdSPVKW3oBoQOVlg6WmNeMgyd8,1597
+datachain/cli/parser/__init__.py,sha256=dgTUS0SjkT01imPG-EcXP0k_juornFh360wsWhdT1fY,14893
+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/client/__init__.py,sha256=1kDpCPoibMXi1gExR4lTLc5pi-k6M5TANiwtXkPoLhU,49
 datachain/client/azure.py,sha256=ma6fJcnveG8wpNy1PSrN5hgvmRdCj8Sf3RKjfd3qCyM,3221
 datachain/client/fileslice.py,sha256=bT7TYco1Qe3bqoc8aUkUZcPdPofJDHlryL5BsTn9xsY,3021
@@ -47,8 +47,8 @@ datachain/data_storage/job.py,sha256=w-7spowjkOa1P5fUVtJou3OltT0L48P0RYWZ9rSJ9-s
 datachain/data_storage/metastore.py,sha256=hfTITcesE9XlUTxcCcdDyWGGep-QSjJL9DUxko5QCeI,37524
 datachain/data_storage/schema.py,sha256=8np_S6Ltq7WXfcqpoSeFPryPS7cipdbiSP6UnKJkAac,9516
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=kSUvChn3bugyh5qUN8cEE6Rvornwh_6fd94ZKKTxLpk,23181
-datachain/data_storage/warehouse.py,sha256=ASKD0mMB8eTvXhMLoUroUypWpN1fVaynSB6k1NZX8lE,30828
+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/aggregate.py,sha256=7_IPrIwb2XSs3zG4iOr1eTvzn6kNVe2mkzvNzjusDHk,10942
@@ -66,7 +66,7 @@ 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=673Mu2Pqu63o7wrpdvujOmWJhJNbXfnyCSWLS93mJpw,92315
+datachain/lib/dc.py,sha256=l1iKnT6wplndIgfMsVMbbKL-etlj2TdHPKJ6kIwqK88,92398
 datachain/lib/file.py,sha256=7posvEFSb7gsLKAiid75dOJRyHTRKOmBAkmBw6RiZyg,16307
 datachain/lib/hf.py,sha256=DvoI8fv-WkL3FDEuIT80T9WrRs6fXesjbU0bmIDDsNE,5882
 datachain/lib/image.py,sha256=AMXYwQsmarZjRbPCZY3M1jDsM2WAB_b3cTY4uOIuXNU,2675
@@ -87,7 +87,7 @@ datachain/lib/webdataset.py,sha256=o7SHk5HOUWsZ5Ln04xOM04eQqiBHiJNO7xLgyVBrwo8,6
 datachain/lib/webdataset_laion.py,sha256=xvT6m_r5y0KbOx14BUe7UC5mOgrktJq53Mh-H0EVlUE,2525
 datachain/lib/convert/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/lib/convert/flatten.py,sha256=IZFiUYbgXSxXhPSG5Cqf5IjnJ4ZDZKXMr4o_yCR1NY4,1505
-datachain/lib/convert/python_to_sql.py,sha256=40SAOdoOgikZRhn8iomCPDRoxC3RFxjJLivEAA9MHDU,2880
+datachain/lib/convert/python_to_sql.py,sha256=wg-O5FRKX3x3Wh8ZL1b9ntMlgf1zRO4djMP3t8CHJLo,3188
 datachain/lib/convert/sql_to_python.py,sha256=XXCBYDQFUXJIBNWkjEP944cnCfJ8GF2Tji0DLF3A_zQ,315
 datachain/lib/convert/unflatten.py,sha256=ysMkstwJzPMWUlnxn-Z-tXJR3wmhjHeSN_P-sDcLS6s,2010
 datachain/lib/convert/values_to_tuples.py,sha256=EFfIGBiVVltJQG8blzsQ1dGXneh4D3wdLfSUeoK10OI,3931
@@ -101,7 +101,7 @@ datachain/model/ultralytics/pose.py,sha256=71KBTcoST2wcEtsyGXqLVpvUtqbp9gwZGA15p
 datachain/model/ultralytics/segment.py,sha256=Z1ab0tZRJubSYNH4KkFlzhYeGNTfAyC71KmkQcToHDQ,2760
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=6w8gzLTmLeylststu-gT5jIqEfi4-djS7_yTYyeo-fw,4190
-datachain/query/dataset.py,sha256=iupWhXBxbBDuihqyidztXWhTAD7wAli3FLFkf8_neUA,56351
+datachain/query/dataset.py,sha256=Su4axlm8ShxUzalYYA7UKU11Pm9cmYi88kUI9FKScew,56328
 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
@@ -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=3DlgESETzxm3dgb6zzjjGxsddSkacT2dARnteLAfMxQ,13366
+datachain/remote/studio.py,sha256=DfW2Iej858tWkKQMg_fvp1cvsvgGX3Z07VXhv_sI3GY,13362
 datachain/sql/__init__.py,sha256=6SQRdbljO3d2hx3EAVXEZrHQKv5jth0Jh98PogT59No,262
 datachain/sql/selectable.py,sha256=cTc60qVoAwqqss0Vop8Lt5Z-ROnM1XrQmL_GLjRxhXs,1765
 datachain/sql/types.py,sha256=ASSPkmM5EzdRindqj2O7WHLXq8VHAgFYedG8lYfGvVI,14045
@@ -127,15 +127,15 @@ 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=E2PK3hoGlHey1eEjcReXRrI-c_ASr3AmAXaNYKDY_o8,18634
+datachain/sql/sqlite/base.py,sha256=bPrYfj2ZF9hFZFs0chgH7J5l_tdXI4VMZMgkuBjf7Ng,19070
 datachain/sql/sqlite/types.py,sha256=lPXS1XbkmUtlkkiRxy_A_UzsgpPv2VSkXYOD4zIHM4w,1734
 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-0.8.9.dist-info/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.8.9.dist-info/METADATA,sha256=fXC2bFkpYNoMmWo8a1m4NYgdCsH4HfLy9ufR89u0PHY,11117
-datachain-0.8.9.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-datachain-0.8.9.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.8.9.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.8.9.dist-info/RECORD,,
+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,,