datachain 0.30.3__py3-none-any.whl → 0.30.5__py3-none-any.whl

datachain/__init__.py

@@ -6,6 +6,7 @@ from datachain.lib.dc import (
     Sys,
     datasets,
     delete_dataset,
+    is_studio,
     listings,
     move_dataset,
     read_csv,
@@ -74,6 +75,7 @@ __all__ = [
     "datasets",
     "delete_dataset",
     "is_chain_type",
+    "is_studio",
     "listings",
     "metrics",
     "move_dataset",

datachain/catalog/__init__.py

@@ -3,6 +3,7 @@ from .catalog import (
     QUERY_SCRIPT_CANCELED_EXIT_CODE,
     QUERY_SCRIPT_INVALID_LAST_STATEMENT_EXIT_CODE,
     Catalog,
+    is_namespace_local,
 )
 from .loader import get_catalog
 
@@ -12,4 +13,5 @@ __all__ = [
     "QUERY_SCRIPT_INVALID_LAST_STATEMENT_EXIT_CODE",
     "Catalog",
     "get_catalog",
+    "is_namespace_local",
 ]

datachain/catalog/catalog.py

@@ -113,6 +113,11 @@ else:
     SIGINT = signal.SIGINT
 
 
+def is_namespace_local(namespace_name) -> bool:
+    """Checks if namespace is from local environment, i.e. is `local`"""
+    return namespace_name == "local"
+
+
 def shutdown_process(
     proc: subprocess.Popen,
     interrupt_timeout: Optional[int] = None,
@@ -1121,6 +1126,8 @@ class Catalog:
         pull_dataset: bool = False,
         update: bool = False,
     ) -> DatasetRecord:
+        from datachain.lib.dc.utils import is_studio
+
         # Intentionally ignore update flag is version is provided. Here only exact
         # version can be provided and update then doesn't make sense.
         # It corresponds to a query like this for example:
@@ -1129,7 +1136,12 @@ class Catalog:
         if version:
             update = False
 
-        if self.metastore.is_local_dataset(namespace_name) or not update:
+        # we don't do Studio fallback is script is already ran in Studio, or if we try
+        # to fetch dataset with local namespace as that one cannot
+        # exist in Studio in the first place
+        no_fallback = is_studio() or is_namespace_local(namespace_name)
+
+        if no_fallback or not update:
             try:
                 ds = self.get_dataset(
                     name,
@@ -1141,7 +1153,7 @@ class Catalog:
             except (NamespaceNotFoundError, ProjectNotFoundError, DatasetNotFoundError):
                 pass
 
-        if self.metastore.is_local_dataset(namespace_name):
+        if no_fallback:
             raise DatasetNotFoundError(
                 f"Dataset {name}"
                 + (f" version {version} " if version else " ")

datachain/catalog/loader.py

@@ -127,7 +127,8 @@ def get_udf_distributor_class() -> Optional[type["AbstractUDFDistributor"]]:
 
 
 def get_catalog(
-    client_config: Optional[dict[str, Any]] = None, in_memory: bool = False
+    client_config: Optional[dict[str, Any]] = None,
+    in_memory: bool = False,
 ) -> "Catalog":
     """
     Function that creates Catalog instance with appropriate metastore
@@ -142,8 +143,9 @@ def get_catalog(
     """
     from datachain.catalog import Catalog
 
+    metastore = get_metastore(in_memory=in_memory)
     return Catalog(
-        metastore=get_metastore(in_memory=in_memory),
+        metastore=metastore,
         warehouse=get_warehouse(in_memory=in_memory),
         client_config=client_config,
         in_memory=in_memory,

datachain/cli/__init__.py

@@ -6,6 +6,7 @@ from multiprocessing import freeze_support
 from typing import Optional
 
 from datachain.cli.utils import get_logging_level
+from datachain.error import DataChainError as DataChainError
 
 from .commands import (
     clear_cache,

datachain/cli/commands/datasets.py

@@ -6,6 +6,7 @@ from tabulate import tabulate
 if TYPE_CHECKING:
     from datachain.catalog import Catalog
 
+from datachain.catalog import is_namespace_local
 from datachain.cli.utils import determine_flavors
 from datachain.config import Config
 from datachain.error import DataChainError, DatasetNotFoundError
@@ -138,15 +139,18 @@ def rm_dataset(
 ):
     namespace_name, project_name, name = catalog.get_full_dataset_name(name)
 
-    if not catalog.metastore.is_local_dataset(namespace_name) and studio:
+    if studio:
+        # removing Studio dataset from CLI
         from datachain.studio import remove_studio_dataset
 
-        token = Config().read().get("studio", {}).get("token")
-        if not token:
+        if Config().read().get("studio", {}).get("token"):
+            remove_studio_dataset(
+                team, name, namespace_name, project_name, version, force
+            )
+        else:
             raise DataChainError(
                 "Not logged in to Studio. Log in with 'datachain auth login'."
             )
-        remove_studio_dataset(team, name, namespace_name, project_name, version, force)
     else:
         try:
             project = catalog.metastore.get_project(project_name, namespace_name)
@@ -163,9 +167,11 @@ def edit_dataset(
     attrs: Optional[list[str]] = None,
     team: Optional[str] = None,
 ):
+    from datachain.lib.dc.utils import is_studio
+
     namespace_name, project_name, name = catalog.get_full_dataset_name(name)
 
-    if catalog.metastore.is_local_dataset(namespace_name):
+    if is_studio() or is_namespace_local(namespace_name):
         try:
             catalog.edit_dataset(
                 name, catalog.metastore.default_project, new_name, description, attrs
@@ -175,11 +181,11 @@ def edit_dataset(
     else:
         from datachain.studio import edit_studio_dataset
 
-        token = Config().read().get("studio", {}).get("token")
-        if not token:
+        if Config().read().get("studio", {}).get("token"):
+            edit_studio_dataset(
+                team, name, namespace_name, project_name, new_name, description, attrs
+            )
+        else:
             raise DataChainError(
                 "Not logged in to Studio. Log in with 'datachain auth login'."
             )
-        edit_studio_dataset(
-            team, name, namespace_name, project_name, new_name, description, attrs
-        )

datachain/data_storage/metastore.py

@@ -145,23 +145,6 @@ class AbstractMetastore(ABC, Serializable):
     def list_namespaces(self, conn=None) -> list[Namespace]:
         """Gets a list of all namespaces"""
 
-    @property
-    @abstractmethod
-    def is_studio(self) -> bool:
-        """Returns True if this code is ran in Studio"""
-
-    def is_local_dataset(self, dataset_namespace: str) -> bool:
-        """
-        Returns True if this is local dataset i.e. not pulled from Studio but
-        created locally. This is False if we ran code in CLI mode but using dataset
-        names that are present in Studio.
-        """
-        return self.is_studio or dataset_namespace == Namespace.default()
-
-    @property
-    def namespace_allowed_to_create(self):
-        return self.is_studio
-
     #
     # Projects
     #
@@ -215,10 +198,6 @@ class AbstractMetastore(ABC, Serializable):
     def list_projects(self, namespace_id: Optional[int], conn=None) -> list[Project]:
         """Gets list of projects in some namespace or in general (in all namespaces)"""
 
-    @property
-    def project_allowed_to_create(self):
-        return self.is_studio
-
     #
     # Datasets
     #

datachain/data_storage/sqlite.py

@@ -542,10 +542,6 @@ class SQLiteMetastore(AbstractDBMetastore):
     def _jobs_insert(self) -> "Insert":
         return sqlite.insert(self._jobs)
 
-    @property
-    def is_studio(self) -> bool:
-        return False
-
     #
     # Namespaces
     #

datachain/data_storage/warehouse.py

@@ -1,5 +1,4 @@
 import glob
-import json
 import logging
 import posixpath
 import random
@@ -11,6 +10,7 @@ from urllib.parse import urlparse
 
 import attrs
 import sqlalchemy as sa
+import ujson as json
 from sqlalchemy.sql.expression import true
 
 from datachain.client import Client
@@ -122,7 +122,7 @@ class AbstractWarehouse(ABC, Serializable):
                 if value_type is str:
                     return val
                 if value_type in (dict, list):
-                    return json.dumps(val)
+                    return json.dumps(val, ensure_ascii=False)
                 raise ValueError(
                     f"Cannot convert value {val!r} with type {value_type} to JSON"
                 )

datachain/lib/arrow.py

@@ -2,8 +2,8 @@ from collections.abc import Sequence
 from itertools import islice
 from typing import TYPE_CHECKING, Any, Optional
 
-import orjson
 import pyarrow as pa
+import ujson as json
 from pyarrow._csv import ParseOptions
 from pyarrow.dataset import CsvFileFormat, dataset
 from tqdm.auto import tqdm
@@ -269,7 +269,7 @@ def _get_hf_schema(
 def _get_datachain_schema(schema: "pa.Schema") -> Optional[SignalSchema]:
     """Return a restored SignalSchema from parquet metadata, if any is found."""
     if schema.metadata and DATACHAIN_SIGNAL_SCHEMA_PARQUET_KEY in schema.metadata:
-        serialized_signal_schema = orjson.loads(
+        serialized_signal_schema = json.loads(
             schema.metadata[DATACHAIN_SIGNAL_SCHEMA_PARQUET_KEY]
         )
         return SignalSchema.deserialize(serialized_signal_schema)

datachain/lib/dc/__init__.py

@@ -9,7 +9,7 @@ from .pandas import read_pandas
 from .parquet import read_parquet
 from .records import read_records
 from .storage import read_storage
-from .utils import DatasetMergeError, DatasetPrepareError, Sys
+from .utils import DatasetMergeError, DatasetPrepareError, Sys, is_studio
 from .values import read_values
 
 __all__ = [
@@ -21,6 +21,7 @@ __all__ = [
     "Sys",
     "datasets",
     "delete_dataset",
+    "is_studio",
     "listings",
     "move_dataset",
     "read_csv",

datachain/lib/dc/datachain.py

@@ -19,8 +19,8 @@ from typing import (
     overload,
 )
 
-import orjson
 import sqlalchemy
+import ujson as json
 from pydantic import BaseModel
 from sqlalchemy.sql.elements import ColumnElement
 from tqdm import tqdm
@@ -67,6 +67,7 @@ from .utils import (
     Sys,
     _get_merge_error_str,
     _validate_merge_on,
+    is_studio,
     resolve_columns,
 )
 
@@ -461,8 +462,6 @@ class DataChain:
         Returns:
             DataChain: A new DataChain instance with the new set of columns.
         """
-        import json
-
         import pyarrow as pa
 
         from datachain.lib.arrow import schema_to_output
@@ -609,7 +608,7 @@ class DataChain:
             project = self.session.catalog.metastore.get_project(
                 project_name,
                 namespace_name,
-                create=self.session.catalog.metastore.project_allowed_to_create,
+                create=is_studio(),
             )
         except ProjectNotFoundError as e:
             # not being able to create it as creation is not allowed
@@ -1184,17 +1183,13 @@ class DataChain:
         )
 
     def mutate(self, **kwargs) -> "Self":
-        """Create new signals based on existing signals.
-
-        This method cannot modify existing columns. If you need to modify an
-        existing column, use a different name for the new column and then use
-        `select()` to choose which columns to keep.
+        """Create or modify signals based on existing signals.
 
         This method is vectorized and more efficient compared to map(), and it does not
         extract or download any data from the internal database. However, it can only
         utilize predefined built-in functions and their combinations.
 
-        The supported functions:
+        Supported functions:
            Numerical:   +, -, *, /, rand(), avg(), count(), func(),
                         greatest(), least(), max(), min(), sum()
            String:      length(), split(), replace(), regexp_replace()
@@ -1221,13 +1216,20 @@ class DataChain:
         ```
 
         This method can be also used to rename signals. If the Column("name") provided
-        as value for the new signal - the old column will be dropped. Otherwise a new
-        column is created.
+        as value for the new signal - the old signal will be dropped. Otherwise a new
+        signal is created. Exception, if the old signal is nested one (e.g.
+        `C("file.path")`), it will be kept to keep the object intact.
 
         Example:
         ```py
          dc.mutate(
-            newkey=Column("oldkey")
+            newkey=Column("oldkey") # drops oldkey
+        )
+        ```
+
+        ```py
+         dc.mutate(
+            size=Column("file.size") # keeps `file.size`
         )
         ```
         """
@@ -1262,8 +1264,10 @@ class DataChain:
                 # adding new signal
                 mutated[name] = value
 
+        new_schema = schema.mutate(kwargs)
         return self._evolve(
-            query=self._query.mutate(**mutated), signal_schema=schema.mutate(kwargs)
+            query=self._query.mutate(new_schema=new_schema, **mutated),
+            signal_schema=new_schema,
         )
 
     @property
@@ -2123,9 +2127,9 @@ class DataChain:
             fsspec_fs = client.create_fs(**fs_kwargs)
 
         _partition_cols = list(partition_cols) if partition_cols else None
-        signal_schema_metadata = orjson.dumps(
-            self._effective_signals_schema.serialize()
-        )
+        signal_schema_metadata = json.dumps(
+            self._effective_signals_schema.serialize(), ensure_ascii=False
+        ).encode("utf-8")
 
         column_names, column_chunks = self.to_columnar_data_with_names(chunk_size)
 
@@ -2272,7 +2276,11 @@ class DataChain:
                         f.write(b"\n")
                 else:
                     is_first = False
-                f.write(orjson.dumps(row_to_nested_dict(headers, row)))
+                f.write(
+                    json.dumps(
+                        row_to_nested_dict(headers, row), ensure_ascii=False
+                    ).encode("utf-8")
+                )
             if include_outer_list:
                 # This makes the file JSON instead of JSON lines.
                 f.write(b"\n]\n")

datachain/lib/dc/datasets.py

@@ -13,7 +13,7 @@ from datachain.lib.signal_schema import SignalSchema
 from datachain.query import Session
 from datachain.query.dataset import DatasetQuery
 
-from .utils import Sys
+from .utils import Sys, is_studio
 from .values import read_values
 
 if TYPE_CHECKING:
@@ -343,7 +343,7 @@ def delete_dataset(
         namespace_name=namespace,
     )
 
-    if not catalog.metastore.is_local_dataset(namespace_name) and studio:
+    if not is_studio() and studio:
         return remove_studio_dataset(
             None, name, namespace_name, project_name, version=version, force=force
         )
@@ -418,6 +418,6 @@ def move_dataset(
         project_id=catalog.metastore.get_project(
             dest_project,
             dest_namespace,
-            create=catalog.metastore.project_allowed_to_create,
+            create=is_studio(),
         ).id,
     )

datachain/lib/dc/utils.py

@@ -15,6 +15,7 @@ from datachain.func.base import Function
 from datachain.lib.data_model import DataModel, DataType
 from datachain.lib.utils import DataChainParamsError
 from datachain.query.schema import DEFAULT_DELIMITER
+from datachain.utils import getenv_bool
 
 if TYPE_CHECKING:
     from typing_extensions import Concatenate, ParamSpec
@@ -26,6 +27,10 @@ if TYPE_CHECKING:
 D = TypeVar("D", bound="DataChain")
 
 
+def is_studio() -> bool:
+    return getenv_bool("DATACHAIN_IS_STUDIO", default=False)
+
+
 def resolve_columns(
     method: "Callable[Concatenate[D, P], D]",
 ) -> "Callable[Concatenate[D, P], D]":

datachain/lib/model_store.py

@@ -89,3 +89,15 @@ class ModelStore:
             and ModelStore.is_pydantic(parent_type)
             and "@" in ModelStore.get_name(parent_type)
         )
+
+    @classmethod
+    def rebuild_all(cls) -> None:
+        """Ensure pydantic schemas are (re)built for all registered models.
+
+        Uses ``force=True`` to avoid subtle cases where a deserialized class
+        (e.g. from by-value cloudpickle in workers) reports built state but
+        nested model field schemas aren't fully resolved yet.
+        """
+        for versions in cls.store.values():
+            for model in versions.values():
+                model.model_rebuild(force=True)

datachain/lib/namespaces.py

@@ -28,7 +28,9 @@ def create(
     """
     session = Session.get(session)
 
-    if not session.catalog.metastore.namespace_allowed_to_create:
+    from datachain.lib.dc.utils import is_studio
+
+    if not is_studio():
         raise NamespaceCreateNotAllowedError("Creating namespace is not allowed")
 
     Namespace.validate_name(name)

datachain/lib/projects.py

@@ -32,7 +32,9 @@ def create(
     """
     session = Session.get(session)
 
-    if not session.catalog.metastore.project_allowed_to_create:
+    from datachain.lib.dc.utils import is_studio
+
+    if not is_studio():
         raise ProjectCreateNotAllowedError("Creating project is not allowed")
 
     Project.validate_name(name)

datachain/lib/signal_schema.py

@@ -34,7 +34,7 @@ from datachain.lib.data_model import DataModel, DataType, DataValue
 from datachain.lib.file import File
 from datachain.lib.model_store import ModelStore
 from datachain.lib.utils import DataChainParamsError
-from datachain.query.schema import DEFAULT_DELIMITER, Column, ColumnMeta
+from datachain.query.schema import DEFAULT_DELIMITER, C, Column, ColumnMeta
 from datachain.sql.types import SQLType
 
 if TYPE_CHECKING:
@@ -680,35 +680,46 @@ class SignalSchema:
         primitives = (bool, str, int, float)
 
         for name, value in args_map.items():
+            current_type = None
+
+            if C.is_nested(name):
+                try:
+                    current_type = self.get_column_type(name)
+                except SignalResolvingError as err:
+                    msg = f"Creating new nested columns directly is not allowed: {name}"
+                    raise ValueError(msg) from err
+
             if isinstance(value, Column) and value.name in self.values:
                 # renaming existing signal
+                # Note: it won't touch nested signals here (e.g. file__path)
+                # we don't allow removing nested columns to keep objects consistent
                 del new_values[value.name]
                 new_values[name] = self.values[value.name]
-                continue
-            if isinstance(value, Column):
+            elif isinstance(value, Column):
                 # adding new signal from existing signal field
-                try:
-                    new_values[name] = self.get_column_type(
-                        value.name, with_subtree=True
-                    )
-                    continue
-                except SignalResolvingError:
-                    pass
-            if isinstance(value, Func):
+                new_values[name] = self.get_column_type(value.name, with_subtree=True)
+            elif isinstance(value, Func):
                 # adding new signal with function
                 new_values[name] = value.get_result_type(self)
-                continue
-            if isinstance(value, primitives):
+            elif isinstance(value, primitives):
                 # For primitives, store the type, not the value
                 val = literal(value)
                 val.type = python_to_sql(type(value))()
                 new_values[name] = sql_to_python(val)
-                continue
-            if isinstance(value, ColumnElement):
+            elif isinstance(value, ColumnElement):
                 # adding new signal
                 new_values[name] = sql_to_python(value)
-                continue
-            new_values[name] = value
+            else:
+                new_values[name] = value
+
+            if C.is_nested(name):
+                if current_type != new_values[name]:
+                    msg = (
+                        f"Altering nested column type is not allowed: {name}, "
+                        f"current type: {current_type}, new type: {new_values[name]}"
+                    )
+                    raise ValueError(msg)
+                del new_values[name]
 
         return SignalSchema(new_values)
 

datachain/query/dataset.py

@@ -10,7 +10,6 @@ from abc import ABC, abstractmethod
 from collections.abc import Generator, Iterable, Iterator, Sequence
 from copy import copy
 from functools import wraps
-from secrets import token_hex
 from types import GeneratorType
 from typing import (
     TYPE_CHECKING,
@@ -29,7 +28,7 @@ from attrs import frozen
 from fsspec.callbacks import DEFAULT_CALLBACK, Callback, TqdmCallback
 from sqlalchemy import Column
 from sqlalchemy.sql import func as f
-from sqlalchemy.sql.elements import ColumnClause, ColumnElement
+from sqlalchemy.sql.elements import ColumnClause, ColumnElement, Label
 from sqlalchemy.sql.expression import label
 from sqlalchemy.sql.schema import TableClause
 from sqlalchemy.sql.selectable import Select
@@ -46,6 +45,7 @@ from datachain.dataset import DatasetDependency, DatasetStatus, RowDict
 from datachain.error import DatasetNotFoundError, QueryScriptCancelError
 from datachain.func.base import Function
 from datachain.lib.listing import is_listing_dataset, listing_dataset_expired
+from datachain.lib.signal_schema import SignalSchema
 from datachain.lib.udf import UDFAdapter, _get_cache
 from datachain.progress import CombinedDownloadCallback, TqdmCombinedDownloadCallback
 from datachain.project import Project
@@ -795,28 +795,32 @@ class SQLSelectExcept(SQLClause):
 
 @frozen
 class SQLMutate(SQLClause):
-    args: tuple[Union[Function, ColumnElement], ...]
+    args: tuple[Label, ...]
+    new_schema: SignalSchema
 
     def apply_sql_clause(self, query: Select) -> Select:
         original_subquery = query.subquery()
-        args = [
-            original_subquery.c[str(c)] if isinstance(c, (str, C)) else c
-            for c in self.parse_cols(self.args)
-        ]
-        to_mutate = {c.name for c in args}
+        to_mutate = {c.name for c in self.args}
 
-        prefix = f"mutate{token_hex(8)}_"
-        cols = [
-            c.label(prefix + c.name) if c.name in to_mutate else c
+        # Drop the original versions to avoid name collisions, exclude renamed
+        # columns. Always keep system columns (sys__*) if they exist in original query
+        new_schema_columns = set(self.new_schema.db_signals())
+        base_cols = [
+            c
             for c in original_subquery.c
+            if c.name not in to_mutate
+            and (c.name in new_schema_columns or c.name.startswith("sys__"))
         ]
-        # this is needed for new column to be used in clauses
-        # like ORDER BY, otherwise new column is not recognized
-        subquery = (
-            sqlalchemy.select(*cols, *args).select_from(original_subquery).subquery()
+
+        # Create intermediate subquery to properly handle window functions
+        intermediate_query = sqlalchemy.select(*base_cols, *self.args).select_from(
+            original_subquery
         )
+        intermediate_subquery = intermediate_query.subquery()
 
-        return sqlalchemy.select(*subquery.c).select_from(subquery)
+        return sqlalchemy.select(*intermediate_subquery.c).select_from(
+            intermediate_subquery
+        )
 
 
 @frozen
@@ -1470,7 +1474,7 @@ class DatasetQuery:
         return query
 
     @detach
-    def mutate(self, *args, **kwargs) -> "Self":
+    def mutate(self, *args, new_schema, **kwargs) -> "Self":
         """
         Add new columns to this query.
 
@@ -1482,7 +1486,7 @@ class DatasetQuery:
         """
         query_args = [v.label(k) for k, v in dict(args, **kwargs).items()]
         query = self.clone()
-        query.steps.append(SQLMutate((*query_args,)))
+        query.steps.append(SQLMutate((*query_args,), new_schema))
         return query
 
     @detach

datachain/query/dispatch.py

@@ -13,6 +13,7 @@ from multiprocess import get_context
 from datachain.catalog import Catalog
 from datachain.catalog.catalog import clone_catalog_with_cache
 from datachain.catalog.loader import DISTRIBUTED_IMPORT_PATH, get_udf_distributor_class
+from datachain.lib.model_store import ModelStore
 from datachain.lib.udf import _get_cache
 from datachain.query.dataset import (
     get_download_callback,
@@ -130,6 +131,8 @@ class UDFDispatcher:
 
     def _create_worker(self) -> "UDFWorker":
         udf: UDFAdapter = loads(self.udf_data)
+        # Ensure all registered DataModels have rebuilt schemas in worker processes.
+        ModelStore.rebuild_all()
         return UDFWorker(
             self.catalog,
             udf,
@@ -196,6 +199,8 @@ class UDFDispatcher:
         generated_cb: Callback = DEFAULT_CALLBACK,
     ) -> None:
         udf: UDFAdapter = loads(self.udf_data)
+        # Rebuild schemas in single process too for consistency (cheap, idempotent).
+        ModelStore.rebuild_all()
 
         if ids_only and not self.is_batching:
             input_rows = flatten(input_rows)

datachain/query/schema.py

@@ -36,6 +36,10 @@ class ColumnMeta(type):
     def __getattr__(cls, name: str):
         return cls(ColumnMeta.to_db_name(name))
 
+    @staticmethod
+    def is_nested(name: str) -> bool:
+        return DEFAULT_DELIMITER in name
+
 
 class Column(sa.ColumnClause, metaclass=ColumnMeta):
     inherit_cache: Optional[bool] = True

datachain/sql/sqlite/base.py

@@ -8,8 +8,8 @@ from functools import cache
 from types import MappingProxyType
 from typing import Callable, Optional
 
-import orjson
 import sqlalchemy as sa
+import ujson as json
 from sqlalchemy.dialects import sqlite
 from sqlalchemy.ext.compiler import compiles
 from sqlalchemy.sql.elements import literal
@@ -182,7 +182,7 @@ def missing_vector_function(name, exc):
 
 
 def sqlite_string_split(string: str, sep: str, maxsplit: int = -1) -> str:
-    return orjson.dumps(string.split(sep, maxsplit)).decode("utf-8")
+    return json.dumps(string.split(sep, maxsplit), ensure_ascii=False)
 
 
 def sqlite_int_hash_64(x: int) -> int:
@@ -453,17 +453,17 @@ def compile_byte_hamming_distance(element, compiler, **kwargs):
 
 
 def py_json_array_length(arr):
-    return len(orjson.loads(arr))
+    return len(json.loads(arr))
 
 
 def py_json_array_contains(arr, value, is_json):
     if is_json:
-        value = orjson.loads(value)
-    return value in orjson.loads(arr)
+        value = json.loads(value)
+    return value in json.loads(arr)
 
 
 def py_json_array_get_element(val, idx):
-    arr = orjson.loads(val)
+    arr = json.loads(val)
     try:
         return arr[idx]
     except IndexError:
@@ -471,17 +471,18 @@ def py_json_array_get_element(val, idx):
 
 
 def py_json_array_slice(val, offset: int, length: Optional[int] = None):
-    arr = orjson.loads(val)
+    arr = json.loads(val)
     try:
-        return orjson.dumps(
-            list(arr[offset : offset + length] if length is not None else arr[offset:])
-        ).decode("utf-8")
+        return json.dumps(
+            list(arr[offset : offset + length] if length is not None else arr[offset:]),
+            ensure_ascii=False,
+        )
     except IndexError:
         return None
 
 
 def py_json_array_join(val, sep: str):
-    return sep.join(orjson.loads(val))
+    return sep.join(json.loads(val))
 
 
 def compile_array_get_element(element, compiler, **kwargs):

datachain/sql/sqlite/types.py

@@ -1,6 +1,6 @@
 import sqlite3
 
-import orjson
+import ujson as json
 from sqlalchemy import types
 
 from datachain.sql.types import TypeConverter, TypeReadConverter
@@ -28,26 +28,21 @@ class Array(types.UserDefinedType):
 
 
 def adapt_array(arr):
-    return orjson.dumps(arr).decode("utf-8")
+    return json.dumps(arr, ensure_ascii=False)
 
 
 def adapt_dict(dct):
-    return orjson.dumps(dct).decode("utf-8")
+    return json.dumps(dct, ensure_ascii=False)
 
 
 def convert_array(arr):
-    return orjson.loads(arr)
+    return json.loads(arr)
 
 
 def adapt_np_array(arr):
-    def _json_serialize(obj):
-        if isinstance(obj, np.ndarray):
-            return obj.tolist()
-        return obj
-
-    return orjson.dumps(
-        arr, option=orjson.OPT_SERIALIZE_NUMPY, default=_json_serialize
-    ).decode("utf-8")
+    # Primarily needed for UDF numpy results (e.g. WDS)
+    # tolist() gives nested Python lists + native scalars; ujson.dumps handles NaN/Inf.
+    return json.dumps(arr.tolist(), ensure_ascii=False)
 
 
 def adapt_np_generic(val):
@@ -74,5 +69,5 @@ class SQLiteTypeConverter(TypeConverter):
 class SQLiteTypeReadConverter(TypeReadConverter):
     def array(self, value, item_type, dialect):
         if isinstance(value, str):
-            value = orjson.loads(value)
+            value = json.loads(value)
         return super().array(value, item_type, dialect)

datachain/sql/types.py

@@ -16,8 +16,8 @@ from datetime import datetime
 from types import MappingProxyType
 from typing import Any, Union
 
-import orjson
 import sqlalchemy as sa
+import ujson as jsonlib
 from sqlalchemy import TypeDecorator, types
 
 from datachain.lib.data_model import StandardType
@@ -352,7 +352,7 @@ 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 = [orjson.loads(item) if isinstance(item, str) else item for item in r]
+            r = [jsonlib.loads(item) if isinstance(item, str) else item for item in r]
         return r
 
 
@@ -466,7 +466,7 @@ class TypeReadConverter:
         if isinstance(value, str):
             if value == "":
                 return {}
-            return orjson.loads(value)
+            return jsonlib.loads(value)
         return value
 
     def datetime(self, value):

datachain/utils.py

@@ -417,7 +417,7 @@ class JSONSerialize(json.JSONEncoder):
 
 def inside_colab() -> bool:
     try:
-        from google import colab  # noqa: F401
+        from google import colab  # type: ignore[attr-defined]  # noqa: F401
     except ImportError:
         return False
     return True
@@ -531,3 +531,10 @@ def safe_closing(thing: T) -> Iterator[T]:
     finally:
         if hasattr(thing, "close"):
             thing.close()
+
+
+def getenv_bool(name: str, default: bool = False) -> bool:
+    val = os.getenv(name)
+    if val is None:
+        return default
+    return val.lower() in ("1", "true", "yes", "on")

{datachain-0.30.3.dist-info → datachain-0.30.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.30.3
+Version: 0.30.5
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0
@@ -22,6 +22,7 @@ Requires-Dist: tomlkit
 Requires-Dist: tqdm
 Requires-Dist: numpy<3,>=1
 Requires-Dist: pandas>=2.0.0
+Requires-Dist: ujson>=5.10.0
 Requires-Dist: packaging
 Requires-Dist: pyarrow
 Requires-Dist: typing-extensions
@@ -38,7 +39,6 @@ Requires-Dist: shtab<2,>=1.3.4
 Requires-Dist: sqlalchemy>=2
 Requires-Dist: multiprocess==0.70.16
 Requires-Dist: cloudpickle
-Requires-Dist: orjson>=3.10.5
 Requires-Dist: pydantic
 Requires-Dist: jmespath>=1.0
 Requires-Dist: datamodel-code-generator>=0.25
@@ -92,7 +92,7 @@ Requires-Dist: pytest-mock>=3.12.0; extra == "tests"
 Requires-Dist: pytest-servers[all]>=0.5.9; extra == "tests"
 Requires-Dist: pytest-benchmark[histogram]; extra == "tests"
 Requires-Dist: pytest-xdist>=3.3.1; extra == "tests"
-Requires-Dist: pytest-env>=1.1.0; extra == "tests"
+Requires-Dist: pytest-dotenv; extra == "tests"
 Requires-Dist: virtualenv; extra == "tests"
 Requires-Dist: dulwich; extra == "tests"
 Requires-Dist: hypothesis; extra == "tests"

{datachain-0.30.3.dist-info → datachain-0.30.5.dist-info}/RECORD

@@ -1,4 +1,4 @@
-datachain/__init__.py,sha256=2TZ8ptSB9BtnYF31mDEhWG9N16EQ5pf9vNqQaFr2txs,1712
+datachain/__init__.py,sha256=Ze-u6SSNsTFBRFw0lVPCdoP0kt8ybKxJIhO8jfC22Cw,1744
 datachain/__main__.py,sha256=hG3Y4ARGEqe1AWwNMd259rBlqtphx1Wk39YbueQ0yV8,91
 datachain/asyn.py,sha256=RH_jFwJcTXxhEFomaI9yL6S3Onau6NZ6FSKfKFGtrJE,9689
 datachain/cache.py,sha256=ESVRaCJXEThMIfGEFVHx6wJPOZA7FYk9V6WxjyuqUBY,3626
@@ -19,15 +19,15 @@ datachain/script_meta.py,sha256=V-LaFOZG84pD0Zc0NvejYdzwDgzITv6yHvAHggDCnuY,4978
 datachain/semver.py,sha256=UB8GHPBtAP3UJGeiuJoInD7SK-DnB93_Xd1qy_CQ9cU,2074
 datachain/studio.py,sha256=27750qCSNxIChEzhV02damIFreLMfr7UdiWqMFyk8AA,15361
 datachain/telemetry.py,sha256=0A4IOPPp9VlP5pyW9eBfaTK3YhHGzHl7dQudQjUAx9A,994
-datachain/utils.py,sha256=Gp5JVr_m7nVWQGDOjrGnZjRXF9-Ai-MBxiPJIcpPvWQ,15451
-datachain/catalog/__init__.py,sha256=cMZzSz3VoUi-6qXSVaHYN-agxQuAcz2XSqnEPZ55crE,353
-datachain/catalog/catalog.py,sha256=vy5k0ME9FxDnpV5D9Ry0YT8eRAKZglUDdyePslJSBpk,67174
+datachain/utils.py,sha256=RKe1-VuC9juQSIbIpMnELJ7QrsKQggj8l7Q8_FiCZHE,15664
+datachain/catalog/__init__.py,sha256=9NBaywvAOaXdkyqiHjbBEiXs7JImR1OJsY9r8D5Q16g,403
+datachain/catalog/catalog.py,sha256=a1AN6eDHWWzII1wi46T_1JvTsW1AeMudwR_6sVQ4f7I,67588
 datachain/catalog/datasource.py,sha256=IkGMh0Ttg6Q-9DWfU_H05WUnZepbGa28HYleECi6K7I,1353
-datachain/catalog/loader.py,sha256=B2cps5coFE4MBttM-j8cs7JgNVPjnHKF4Gx1s2fJrxw,6119
-datachain/cli/__init__.py,sha256=migILaB4-dSSlxEoi6MYOGhOg2jpZo3a2AhS3mSuN8o,8237
+datachain/catalog/loader.py,sha256=53VnuSRkt_CO9RdlHWkzQsPF55qMxcXvEm3ecsZREw8,6150
+datachain/cli/__init__.py,sha256=so3WxEQF03KdGvjav15Sw7a6-lriiE24uDSGbBDBp8o,8298
 datachain/cli/utils.py,sha256=wrLnAh7Wx8O_ojZE8AE4Lxn5WoxHbOj7as8NWlLAA74,3036
 datachain/cli/commands/__init__.py,sha256=zp3bYIioO60x_X04A4-IpZqSYVnpwOa1AdERQaRlIhI,493
-datachain/cli/commands/datasets.py,sha256=m8aTlUMpYCZmfSwhp7Lb_UFaQRQm_kOWXh71bNBn7qQ,6461
+datachain/cli/commands/datasets.py,sha256=Q2zYbiWXYPjg6e_YHyUKaYRg1L6-lxv0L214bogwsUY,6565
 datachain/cli/commands/du.py,sha256=9edEzDEs98K2VYk8Wf-ZMpUzALcgm9uD6YtoqbvtUGU,391
 datachain/cli/commands/index.py,sha256=eglNaIe1yyIadUHHumjtNbgIjht6kme7SS7xE3YHR88,198
 datachain/cli/commands/ls.py,sha256=CBmk838Q-EQp04lE2Qdnpsc1GXAkC4-I-b-a_828n1E,5272
@@ -49,11 +49,11 @@ datachain/client/s3.py,sha256=6DNVGLg-woPS1DVlYVX2rIlunNblsuxyOnI1rSzhW3k,7515
 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=ZkeXCNUj_VCkoKYx29hqB4AcfVUielnRjY-GYUcUxt4,426
-datachain/data_storage/metastore.py,sha256=0-myih2VtUm_gcwz8bNgnP2h0rBkBl6v1IEhduShb4w,54517
+datachain/data_storage/metastore.py,sha256=aSeTRh43hmrOhULi9YD2VlgCj8B4bjE3jqCOvnb_HQs,53851
 datachain/data_storage/schema.py,sha256=o3JbURKXRg3IJyIVA4QjHHkn6byRuz7avbydU2FlvNY,9897
 datachain/data_storage/serializer.py,sha256=6G2YtOFqqDzJf1KbvZraKGXl2XHZyVml2krunWUum5o,927
-datachain/data_storage/sqlite.py,sha256=TTQjdDXUaZSr3MEaxZjDhsVIkIJqxFNA-sD25TO3m_4,30228
-datachain/data_storage/warehouse.py,sha256=66PETLzfkgSmj-EF604m62xmFMQBXaRZSw8sdKGMam8,32613
+datachain/data_storage/sqlite.py,sha256=edcTegzEoAEdEp62Rg9oERvHWXDcpg8d4onrD-P2xKM,30159
+datachain/data_storage/warehouse.py,sha256=sEbNiWKdB7yuLt88FuIfRur7U7WiOZrcHWhnBS_eMAg,32642
 datachain/diff/__init__.py,sha256=-OFZzgOplqO84iWgGY7kfe60NXaWR9JRIh9T-uJboAM,9668
 datachain/fs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datachain/fs/reference.py,sha256=A8McpXF0CqbXPqanXuvpKu50YLB3a2ZXA3YAPxtBXSM,914
@@ -70,7 +70,7 @@ datachain/func/random.py,sha256=t7jwXsI8-hy0qAdvjAntgzy-AHtTAfozlZ1CpKR-QZE,458
 datachain/func/string.py,sha256=6-fZM7wHv0JZ2ZzpLFPLLYW15K_CT5VfYsmx56zBrpA,7419
 datachain/func/window.py,sha256=ImyRpc1QI8QUSPO7KdD60e_DPVo7Ja0G5kcm6BlyMcw,1584
 datachain/lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datachain/lib/arrow.py,sha256=geoLvyDd5uMqS3D9Ec1ODlShCUAdtwHUwl8FqbUX_hg,10776
+datachain/lib/arrow.py,sha256=aedsosbFNjIBa6LQIxR2zhIVcA4pVw1p5hCVmrDhWsQ,10781
 datachain/lib/audio.py,sha256=fQmIBq-9hrUZtkgeJdPHYA_D8Wfe9D4cQZk4_ijxpNc,7580
 datachain/lib/clip.py,sha256=lm5CzVi4Cj1jVLEKvERKArb-egb9j1Ls-fwTItT6vlI,6150
 datachain/lib/data_model.py,sha256=Rjah76GHwIV6AZQk4rsdg6JLre5D8Kb9T4PS5SXzsPA,3740
@@ -81,12 +81,12 @@ datachain/lib/image.py,sha256=erWvZW5M3emnbl6_fGAOPyKm-1EKbt3vOdWPfe3Oo7U,3265
 datachain/lib/listing.py,sha256=U-2stsTEwEsq4Y80dqGfktGzkmB5-ZntnL1_rzXlH0k,7089
 datachain/lib/listing_info.py,sha256=9ua40Hw0aiQByUw3oAEeNzMavJYfW0Uhe8YdCTK-m_g,1110
 datachain/lib/meta_formats.py,sha256=zdyg6XLk3QIsSk3I7s0Ez5kaCJSlE3uq7JiGxf7UwtU,6348
-datachain/lib/model_store.py,sha256=dkL2rcT5ag-kbgkhQPL_byEs-TCYr29qvdltroL5NxM,2734
-datachain/lib/namespaces.py,sha256=it52UbbwB8dzhesO2pMs_nThXiPQ1Ph9sD9I3GQkg5s,2099
-datachain/lib/projects.py,sha256=8lN0qV8czX1LGtWURCUvRlSJk-RpO9w9Rra_pOZus6g,2595
+datachain/lib/model_store.py,sha256=A0pSVQ7uaZ9RvANapzirF8Cqq9N6ysosPpMSkzdRPkU,3226
+datachain/lib/namespaces.py,sha256=I6gLC4ZzgyatFtHL85MWR4ml7-yuQOzxHE7IQNbt_ac,2107
+datachain/lib/projects.py,sha256=VJgmzHzKjmNPZD1tm0a1RNHmUQwn6WLWCLpKyc4UrSk,2605
 datachain/lib/pytorch.py,sha256=S-st2SAczYut13KMf6eSqP_OQ8otWI5TRmzhK5fN3k0,7828
 datachain/lib/settings.py,sha256=n0YYhCVdgCdMkCSLY7kscJF9mUhlQ0a4ENWBsJFynkw,3809
-datachain/lib/signal_schema.py,sha256=FmsfEAdRDeAzv1ApQnRXzkkyNeY9fTaXpjMzSMhDh7M,38574
+datachain/lib/signal_schema.py,sha256=YMMcc9gHIzBz88zfsreGa1nOoO_56HBtZlT6jf3V1WE,39224
 datachain/lib/tar.py,sha256=MLcVjzIgBqRuJacCNpZ6kwSZNq1i2tLyROc8PVprHsA,999
 datachain/lib/text.py,sha256=UNHm8fhidk7wdrWqacEWaA6I9ykfYqarQ2URby7jc7M,1261
 datachain/lib/udf.py,sha256=IB1IKF5KyA-NiyfhVzmBPpF_aITPS3zSlrt24f_Ofjo,17956
@@ -101,11 +101,11 @@ datachain/lib/convert/python_to_sql.py,sha256=wg-O5FRKX3x3Wh8ZL1b9ntMlgf1zRO4djM
 datachain/lib/convert/sql_to_python.py,sha256=Gxc4FylWC_Pvvuawuc2MKZIiuAWI7wje8pyeN1MxRrU,670
 datachain/lib/convert/unflatten.py,sha256=ysMkstwJzPMWUlnxn-Z-tXJR3wmhjHeSN_P-sDcLS6s,2010
 datachain/lib/convert/values_to_tuples.py,sha256=j5yZMrVUH6W7b-7yUvdCTGI7JCUAYUOzHUGPoyZXAB0,4360
-datachain/lib/dc/__init__.py,sha256=TFci5HTvYGjBesNUxDAnXaX36PnzPEUSn5a6JxB9o0U,872
+datachain/lib/dc/__init__.py,sha256=UrUzmDH6YyVl8fxM5iXTSFtl5DZTUzEYm1MaazK4vdQ,900
 datachain/lib/dc/csv.py,sha256=q6a9BpapGwP6nwy6c5cklxQumep2fUp9l2LAjtTJr6s,4411
 datachain/lib/dc/database.py,sha256=F6EOjPKwSdp26kJsOKGq49D9OxqyKEalINHEwLQav2s,14716
-datachain/lib/dc/datachain.py,sha256=sfLT_iMGkNsPh5JAPzRATyC4hsotp34bDS0rSu2NQ10,99244
-datachain/lib/dc/datasets.py,sha256=jRwfHUUESlNdK1heUNxb-V10ZobRJYPbvCqYYkz2FYI,15240
+datachain/lib/dc/datachain.py,sha256=cJ0lbFteO5ync08M1QbriRrSAATOmU-nDkbxSH6SYgA,99462
+datachain/lib/dc/datasets.py,sha256=HKQXnCpIGFsYQ9ociLAUm8cwg2H0GaUmgWCF4FkKpbk,15180
 datachain/lib/dc/hf.py,sha256=AP_MUHg6HJWae10PN9hD_beQVjrl0cleZ6Cvhtl1yoI,2901
 datachain/lib/dc/json.py,sha256=dNijfJ-H92vU3soyR7X1IiDrWhm6yZIGG3bSnZkPdAE,2733
 datachain/lib/dc/listings.py,sha256=V379Cb-7ZyquM0w7sWArQZkzInZy4GB7QQ1ZfowKzQY,4544
@@ -113,7 +113,7 @@ datachain/lib/dc/pandas.py,sha256=ObueUXDUFKJGu380GmazdG02ARpKAHPhSaymfmOH13E,14
 datachain/lib/dc/parquet.py,sha256=zYcSgrWwyEDW9UxGUSVdIVsCu15IGEf0xL8KfWQqK94,1782
 datachain/lib/dc/records.py,sha256=4N1Fq-j5r4GK-PR5jIO-9B2u_zTNX9l-6SmcRhQDAsw,3136
 datachain/lib/dc/storage.py,sha256=FXroEdxOZfbuEBIWfWTkbGwrI0D4_mrLZSRsIQm0WFE,7693
-datachain/lib/dc/utils.py,sha256=VawOAlJSvAtZbsMg33s5tJe21TRx1Km3QggI1nN6tnw,3984
+datachain/lib/dc/utils.py,sha256=9OMiFu2kXIbtMqzJTEr1qbCoCBGpOmTnkWImVgFTKgo,4112
 datachain/lib/dc/values.py,sha256=7l1n352xWrEdql2NhBcZ3hj8xyPglWiY4qHjFPjn6iw,1428
 datachain/model/__init__.py,sha256=R9faX5OHV1xh2EW-g2MPedwbtEqt3LodJRyluB-QylI,189
 datachain/model/bbox.py,sha256=cQNHuQuVsh6bW3n3Hj40F2Cc20cExQ9Lg_q7R2jxUMI,9324
@@ -126,12 +126,12 @@ datachain/model/ultralytics/pose.py,sha256=pvoXrWWUSWT_UBaMwUb5MBHAY57Co2HFDPigF
 datachain/model/ultralytics/segment.py,sha256=v9_xDxd5zw_I8rXsbl7yQXgEdTs2T38zyY_Y4XGN8ok,3194
 datachain/query/__init__.py,sha256=7DhEIjAA8uZJfejruAVMZVcGFmvUpffuZJwgRqNwe-c,263
 datachain/query/batch.py,sha256=-goxLpE0EUvaDHu66rstj53UnfHpYfBUGux8GSpJ93k,4306
-datachain/query/dataset.py,sha256=qMVySOlyDm3b-zpF7z_DGeeCfltH7YSGwB7HYYmNhBU,63081
-datachain/query/dispatch.py,sha256=A0nPxn6mEN5d9dDo6S8m16Ji_9IvJLXrgF2kqXdi4fs,15546
+datachain/query/dataset.py,sha256=OaGRBNSWYNaRbYn6avij0fiFN5DT-nwdM-wJ4yTfaYs,63317
+datachain/query/dispatch.py,sha256=f8IIvuLBJaCEwSRv7bWPMy1uXyc28W0LGqrBffjYf98,15831
 datachain/query/metrics.py,sha256=DOK5HdNVaRugYPjl8qnBONvTkwjMloLqAr7Mi3TjCO0,858
 datachain/query/params.py,sha256=O_j89mjYRLOwWNhYZl-z7mi-rkdP7WyFmaDufsdTryE,863
 datachain/query/queue.py,sha256=v0UeK4ilmdiRoJ5OdjB5qpnHTYDxRP4vhVp5Iw_toaI,3512
-datachain/query/schema.py,sha256=b_KnVy6B26Ol4nYG0LqNNpeQ1QYPk95YRGUjXfdaQWs,6606
+datachain/query/schema.py,sha256=qLpEyvnzKlNCOrThQiTNpUKTUEsVIHT9trt-0UMt6ko,6704
 datachain/query/session.py,sha256=gKblltJAVQAVSTswAgWGDgGbpmFlFzFVkIQojDCjgXM,6809
 datachain/query/udf.py,sha256=e753bDJzTNjGFQn1WGTvOAWSwjDbrFI1-_DDWkWN2ls,1343
 datachain/query/utils.py,sha256=a2PTBZ3qsG6XlUcp9XsoGiQfKkca4Q3m-VzFgiGQPAc,1230
@@ -141,7 +141,7 @@ datachain/sql/__init__.py,sha256=8D2omsBiATt8bjLjGo6jBEtaKEkOlnlNFWhVryHMDv0,388
 datachain/sql/postgresql_dialect.py,sha256=pDTfH8xaXz5xZsq8O1aQUvWLRIv_ogYeAqtmKlPp3Rw,280
 datachain/sql/postgresql_types.py,sha256=ryb_0lzuA9UOJ_B6nW9Yb8nJjzeSmEItAL_Ceue65lc,627
 datachain/sql/selectable.py,sha256=cTc60qVoAwqqss0Vop8Lt5Z-ROnM1XrQmL_GLjRxhXs,1765
-datachain/sql/types.py,sha256=RWOghtYFx14K-e71QOGg5yfKb-A4-4JgFjaJ0wCZ17Y,15006
+datachain/sql/types.py,sha256=2XbNaQTTc2BGJ6qL7RcwrBByIEbf9PXcsElIz6q9Mkg,15018
 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
@@ -154,15 +154,15 @@ 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=PsLaDSij9a03VxGSpagpNl7NQsGtgm72ArUeALZONoc,183
-datachain/sql/sqlite/base.py,sha256=6aoQHeggY3hs31_YZ-wlYKA1Lto4MFOpgfgRspH6IMc,21498
-datachain/sql/sqlite/types.py,sha256=cH6oge2E_YWFy22wY-txPJH8gxoQFSpCthtZR8PZjpo,1849
+datachain/sql/sqlite/base.py,sha256=WzRxJ8lHAeBCQlh4Z_NmX0CCkxeOt10M_vudCQzY4gE,21510
+datachain/sql/sqlite/types.py,sha256=DCK7q-Zdc_m1o1T33xrKjYX1zRg1231gw3o3ACO_qho,1815
 datachain/sql/sqlite/vector.py,sha256=ncW4eu2FlJhrP_CIpsvtkUabZlQdl2D5Lgwy_cbfqR0,469
 datachain/toolkit/__init__.py,sha256=eQ58Q5Yf_Fgv1ZG0IO5dpB4jmP90rk8YxUWmPc1M2Bo,68
 datachain/toolkit/split.py,sha256=ktGWzY4kyzjWyR86dhvzw-Zhl0lVk_LOX3NciTac6qo,2914
 datachain/torch/__init__.py,sha256=gIS74PoEPy4TB3X6vx9nLO0Y3sLJzsA8ckn8pRWihJM,579
-datachain-0.30.3.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
-datachain-0.30.3.dist-info/METADATA,sha256=TataasDxkiKnymsMaLxda_Cp0DhYE_FhUMA8CKBXCgg,13903
-datachain-0.30.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-datachain-0.30.3.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
-datachain-0.30.3.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
-datachain-0.30.3.dist-info/RECORD,,
+datachain-0.30.5.dist-info/licenses/LICENSE,sha256=8DnqK5yoPI_E50bEg_zsHKZHY2HqPy4rYN338BHQaRA,11344
+datachain-0.30.5.dist-info/METADATA,sha256=90OhCbSbqZn245Dm4-9zgbyBxI6N2NF8jsIdEiw6PUs,13898
+datachain-0.30.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+datachain-0.30.5.dist-info/entry_points.txt,sha256=0GMJS6B_KWq0m3VT98vQI2YZodAMkn4uReZ_okga9R4,49
+datachain-0.30.5.dist-info/top_level.txt,sha256=lZPpdU_2jJABLNIg2kvEOBi8PtsYikbN1OdMLHk8bTg,10
+datachain-0.30.5.dist-info/RECORD,,