datachain 0.14.5__tar.gz → 0.15.0__tar.gz

{datachain-0.14.5 → datachain-0.15.0}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.11.4'
+    rev: 'v0.11.5'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.14.5/src/datachain.egg-info → datachain-0.15.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.14.5
+Version: 0.15.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.14.5 → datachain-0.15.0}/docs/references/datachain.md

@@ -31,6 +31,10 @@ for examples of how to create a chain.
 
 ::: datachain.lib.dc.values.read_values
 
+::: datachain.lib.dc.database.read_database
+
+::: datachain.lib.dc.database.ConnectionType
+
 ::: datachain.lib.dc.DataChain
 
 ::: datachain.lib.utils.DataChainError

{datachain-0.14.5 → datachain-0.15.0}/examples/multimodal/wds_filtered.py

@@ -27,7 +27,7 @@ filtered = (
         / func.least("laion.json.original_width", "laion.json.original_height")
         < 3.0
     )
-    .save()
+    .persist()
 )
 
 filtered.show(3)

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/__init__.py

@@ -5,8 +5,10 @@ from datachain.lib.dc import (
     DataChain,
     Sys,
     datasets,
+    delete_dataset,
     listings,
     read_csv,
+    read_database,
     read_dataset,
     read_hf,
     read_json,
@@ -61,11 +63,13 @@ __all__ = [
     "VideoFragment",
     "VideoFrame",
     "datasets",
+    "delete_dataset",
     "is_chain_type",
     "listings",
     "metrics",
     "param",
     "read_csv",
+    "read_database",
     "read_dataset",
     "read_hf",
     "read_json",

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/catalog/catalog.py

@@ -1299,7 +1299,17 @@ class Catalog:
         name: str,
         version: Optional[int] = None,
         force: Optional[bool] = False,
+        studio: Optional[bool] = False,
     ):
+        from datachain.remote.studio import StudioClient
+
+        if studio:
+            client = StudioClient()
+            response = client.rm_dataset(name, version=version, force=force)
+            if not response.ok:
+                raise DataChainError(response.message)
+            return
+
         dataset = self.get_dataset(name)
         if not version and not force:
             raise ValueError(f"Missing dataset version from input for dataset {name}")

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/catalog/loader.py

@@ -1,4 +1,5 @@
 import os
+import sys
 from importlib import import_module
 from typing import TYPE_CHECKING, Any, Optional
 
@@ -15,6 +16,7 @@ METASTORE_ARG_PREFIX = "DATACHAIN_METASTORE_ARG_"
 WAREHOUSE_SERIALIZED = "DATACHAIN__WAREHOUSE"
 WAREHOUSE_IMPORT_PATH = "DATACHAIN_WAREHOUSE"
 WAREHOUSE_ARG_PREFIX = "DATACHAIN_WAREHOUSE_ARG_"
+DISTRIBUTED_IMPORT_PYTHONPATH = "DATACHAIN_DISTRIBUTED_PYTHONPATH"
 DISTRIBUTED_IMPORT_PATH = "DATACHAIN_DISTRIBUTED"
 
 IN_MEMORY_ERROR_MESSAGE = "In-memory is only supported on SQLite"
@@ -100,19 +102,21 @@ def get_warehouse(in_memory: bool = False) -> "AbstractWarehouse":
     return warehouse_class(**warehouse_args)
 
 
-def get_udf_distributor_class() -> type["AbstractUDFDistributor"]:
-    distributed_import_path = os.environ.get(DISTRIBUTED_IMPORT_PATH)
+def get_udf_distributor_class() -> Optional[type["AbstractUDFDistributor"]]:
+    if not (distributed_import_path := os.environ.get(DISTRIBUTED_IMPORT_PATH)):
+        return None
 
-    if not distributed_import_path:
-        raise RuntimeError(
-            f"{DISTRIBUTED_IMPORT_PATH} import path is required "
-            "for distributed UDF processing."
-        )
     # Distributed class paths are specified as (for example): module.classname
     if "." not in distributed_import_path:
         raise RuntimeError(
             f"Invalid {DISTRIBUTED_IMPORT_PATH} import path: {distributed_import_path}"
         )
+
+    # Optional: set the Python path to look for the module
+    distributed_import_pythonpath = os.environ.get(DISTRIBUTED_IMPORT_PYTHONPATH)
+    if distributed_import_pythonpath and distributed_import_pythonpath not in sys.path:
+        sys.path.insert(0, distributed_import_pythonpath)
+
     module_name, _, class_name = distributed_import_path.rpartition(".")
     distributed = import_module(module_name)
     return getattr(distributed, class_name)

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/lib/convert/values_to_tuples.py

@@ -1,5 +1,6 @@
+import itertools
 from collections.abc import Sequence
-from typing import Any, Union
+from typing import Any, Optional, Union
 
 from datachain.lib.data_model import (
     DataType,
@@ -66,21 +67,29 @@ def values_to_tuples(  # noqa: C901, PLR0912
                     f"signal '{k}' is not present in the output",
                 )
         else:
-            if len_ == 0:
-                raise ValuesToTupleError(ds_name, f"signal '{k}' is empty list")
-
-            first_element = next(iter(v))
-            typ = type(first_element)
-            if not is_chain_type(typ):
-                raise ValuesToTupleError(
-                    ds_name,
-                    f"signal '{k}' has unsupported type '{typ.__name__}'."
-                    f" Please use DataModel types: {DataTypeNames}",
+            # FIXME: Stops as soon as it finds the first non-None value.
+            # If a non-None value appears early, it won't check the remaining items for
+            # `None` values.
+            try:
+                pos, first_not_none_element = next(
+                    itertools.dropwhile(lambda pair: pair[1] is None, enumerate(v))
                 )
-            if isinstance(first_element, list):
-                types_map[k] = list[type(first_element[0])]  # type: ignore[assignment, misc]
+            except StopIteration:
+                typ = str  # default to str if all values are None or has length 0
+                nullable = True
             else:
-                types_map[k] = typ
+                nullable = pos > 0
+                typ = type(first_not_none_element)  # type: ignore[assignment]
+                if not is_chain_type(typ):
+                    raise ValuesToTupleError(
+                        ds_name,
+                        f"signal '{k}' has unsupported type '{typ.__name__}'."
+                        f" Please use DataModel types: {DataTypeNames}",
+                    )
+                if isinstance(first_not_none_element, list):
+                    typ = list[type(first_not_none_element[0])]  # type: ignore[assignment, misc]
+
+            types_map[k] = Optional[typ] if nullable else typ  # type: ignore[assignment]
 
         if length < 0:
             length = len_

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/lib/dc/__init__.py

@@ -1,6 +1,7 @@
 from .csv import read_csv
+from .database import read_database
 from .datachain import C, Column, DataChain
-from .datasets import datasets, read_dataset
+from .datasets import datasets, delete_dataset, read_dataset
 from .hf import read_hf
 from .json import read_json
 from .listings import listings
@@ -19,8 +20,10 @@ __all__ = [
     "DatasetPrepareError",
     "Sys",
     "datasets",
+    "delete_dataset",
     "listings",
     "read_csv",
+    "read_database",
     "read_dataset",
     "read_hf",
     "read_json",

datachain-0.15.0/src/datachain/lib/dc/database.py

@@ -0,0 +1,151 @@
+import contextlib
+import itertools
+import os
+import sqlite3
+from typing import TYPE_CHECKING, Any, Optional, Union
+
+import sqlalchemy
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator, Mapping, Sequence
+
+    import sqlalchemy.orm  # noqa: TC004
+
+    from datachain.lib.data_model import DataType
+    from datachain.query import Session
+
+    from .datachain import DataChain
+
+    ConnectionType = Union[
+        str,
+        sqlalchemy.engine.URL,
+        sqlalchemy.engine.interfaces.Connectable,
+        sqlalchemy.engine.Engine,
+        sqlalchemy.engine.Connection,
+        sqlalchemy.orm.Session,
+        sqlite3.Connection,
+    ]
+
+
+@contextlib.contextmanager
+def _connect(
+    connection: "ConnectionType",
+) -> "Iterator[Union[sqlalchemy.engine.Connection, sqlalchemy.orm.Session]]":
+    import sqlalchemy.orm
+
+    with contextlib.ExitStack() as stack:
+        engine_kwargs = {"echo": bool(os.environ.get("DEBUG_SHOW_SQL_QUERIES"))}
+        if isinstance(connection, (str, sqlalchemy.URL)):
+            engine = sqlalchemy.create_engine(connection, **engine_kwargs)
+            stack.callback(engine.dispose)
+            yield stack.enter_context(engine.connect())
+        elif isinstance(connection, sqlite3.Connection):
+            engine = sqlalchemy.create_engine(
+                "sqlite://", creator=lambda: connection, **engine_kwargs
+            )
+            # do not close the connection, as it is managed by the caller
+            yield engine.connect()
+        elif isinstance(connection, sqlalchemy.Engine):
+            yield stack.enter_context(connection.connect())
+        elif isinstance(connection, (sqlalchemy.Connection, sqlalchemy.orm.Session)):
+            # do not close the connection, as it is managed by the caller
+            yield connection
+        else:
+            raise TypeError(f"Unsupported connection type: {type(connection).__name__}")
+
+
+def _infer_schema(
+    result: "sqlalchemy.engine.Result",
+    to_infer: list[str],
+    infer_schema_length: Optional[int] = 100,
+) -> tuple[list["sqlalchemy.Row"], dict[str, "DataType"]]:
+    from datachain.lib.convert.values_to_tuples import values_to_tuples
+
+    if not to_infer:
+        return [], {}
+
+    rows = list(itertools.islice(result, infer_schema_length))
+    values = {col: [row._mapping[col] for row in rows] for col in to_infer}
+    _, output_schema, _ = values_to_tuples("", **values)
+    return rows, output_schema
+
+
+def read_database(
+    query: Union[str, "sqlalchemy.sql.expression.Executable"],
+    connection: "ConnectionType",
+    params: Union["Sequence[Mapping[str, Any]]", "Mapping[str, Any]", None] = None,
+    *,
+    output: Optional["dict[str, DataType]"] = None,
+    session: Optional["Session"] = None,
+    settings: Optional[dict] = None,
+    in_memory: bool = False,
+    infer_schema_length: Optional[int] = 100,
+) -> "DataChain":
+    """
+    Read the results of a SQL query into a DataChain, using a given database connection.
+
+    Args:
+        query:
+            The SQL query to execute. Can be a raw SQL string or a SQLAlchemy
+            `Executable` object.
+        connection: SQLAlchemy connectable, str, or a sqlite3 connection
+            Using SQLAlchemy makes it possible to use any DB supported by that
+            library. If a DBAPI2 object, only sqlite3 is supported. The user is
+            responsible for engine disposal and connection closure for the
+            SQLAlchemy connectable; str connections are closed automatically.
+        params: Parameters to pass to execute method.
+        output: A dictionary mapping column names to types, used to override the
+            schema inferred from the query results.
+        session: Session to use for the chain.
+        settings: Settings to use for the chain.
+        in_memory: If True, creates an in-memory session. Defaults to False.
+        infer_schema_length:
+            The maximum number of rows to scan for inferring schema.
+            If set to `None`, the full data may be scanned.
+            The rows used for schema inference are stored in memory,
+            so large values can lead to high memory usage.
+            Only applies if the `output` parameter is not set for the given column.
+
+    Examples:
+        Reading from a SQL query against a user-supplied connection:
+        ```python
+        query = "SELECT key, value FROM tbl"
+        chain = dc.read_database(query, connection, output={"value": float})
+        ```
+
+        Load data from a SQLAlchemy driver/engine:
+        ```python
+        from sqlalchemy import create_engine
+        engine = create_engine("postgresql+psycopg://myuser:mypassword@localhost:5432/mydb")
+        chain = dc.read_database("select * from tbl", engine)
+        ```
+
+        Load data from a parameterized SQLAlchemy query:
+        ```python
+        query = "SELECT key, value FROM tbl WHERE value > :value"
+        dc.read_database(query, engine, params={"value": 50})
+        ```
+
+    Notes:
+        This function works with a variety of databases — including, but not limited to,
+        SQLite, DuckDB, PostgreSQL, and Snowflake, provided the appropriate driver is
+        installed.
+    """
+    from datachain.lib.dc.records import read_records
+
+    output = output or {}
+    if isinstance(query, str):
+        query = sqlalchemy.text(query)
+    kw = {"execution_options": {"stream_results": True}}  # use server-side cursors
+    with _connect(connection) as conn, conn.execute(query, params, **kw) as result:
+        cols = result.keys()
+        to_infer = [k for k in cols if k not in output]  # preserve the order
+        rows, inferred_schema = _infer_schema(result, to_infer, infer_schema_length)
+        records = (row._asdict() for row in itertools.chain(rows, result))
+        return read_records(
+            records,
+            session=session,
+            settings=settings,
+            in_memory=in_memory,
+            schema=inferred_schema | output,
+        )

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/lib/dc/datachain.py

@@ -133,7 +133,7 @@ class DataChain:
                 .choices[0]
                 .message.content,
             )
-            .save()
+            .persist()
         )
 
         try:
@@ -443,9 +443,20 @@ class DataChain:
         )
         return listings(*args, **kwargs)
 
+    def persist(self) -> "Self":
+        """Saves temporary chain that will be removed after the process ends.
+        Temporary datasets are useful for optimization, for example when we have
+        multiple chains starting with identical sub-chain. We can then persist that
+        common chain and use it to calculate other chains, to avoid re-calculation
+        every time.
+        It returns the chain itself.
+        """
+        schema = self.signals_schema.clone_without_sys_signals().serialize()
+        return self._evolve(query=self._query.save(feature_schema=schema))
+
     def save(  # type: ignore[override]
         self,
-        name: Optional[str] = None,
+        name: str,
         version: Optional[int] = None,
         description: Optional[str] = None,
         labels: Optional[list[str]] = None,
@@ -454,8 +465,7 @@ class DataChain:
         """Save to a Dataset. It returns the chain itself.
 
         Parameters:
-            name : dataset name. Empty name saves to a temporary dataset that will be
-                removed after process ends. Temp dataset are useful for optimization.
+            name : dataset name.
             version : version of a dataset. Default - the last version that exist.
             description : description of a dataset.
             labels : labels of a dataset.
@@ -1112,7 +1122,7 @@ class DataChain:
         if self._query.attached:
             chain = self
         else:
-            chain = self.save()
+            chain = self.persist()
         assert chain.name is not None  # for mypy
         return PytorchDataset(
             chain.name,

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/lib/dc/datasets.py

@@ -166,3 +166,46 @@ def datasets(
         output={column: DatasetInfo},
         **{column: datasets_values},  # type: ignore[arg-type]
     )
+
+
+def delete_dataset(
+    name: str,
+    version: Optional[int] = None,
+    force: Optional[bool] = False,
+    studio: Optional[bool] = False,
+    session: Optional[Session] = None,
+    in_memory: bool = False,
+) -> None:
+    """Removes specific dataset version or all dataset versions, depending on
+    a force flag.
+
+    Args:
+        name : Dataset name
+        version : Optional dataset version
+        force: If true, all datasets versions will be removed. Defaults to False.
+        studio: If True, removes dataset from Studio only,
+            otherwise remove from local. Defaults to False.
+        session: Optional session instance. If not provided, uses default session.
+        in_memory: If True, creates an in-memory session. Defaults to False.
+
+    Returns: None
+
+    Example:
+        ```py
+        import datachain as dc
+        dc.delete_dataset("cats")
+        ```
+
+        ```py
+        import datachain as dc
+        dc.delete_dataset("cats", version=1)
+        ```
+    """
+
+    session = Session.get(session, in_memory=in_memory)
+    catalog = session.catalog
+    if not force:
+        version = version or catalog.get_dataset(name).latest_version
+    else:
+        version = None
+    catalog.remove_dataset(name, version=version, force=force, studio=studio)

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/lib/dc/pandas.py

@@ -37,7 +37,14 @@ def read_pandas(  # type: ignore[override]
     """
     from .utils import DatasetPrepareError
 
-    fr_map = {col.lower(): df[col].tolist() for col in df.columns}
+    def get_col_name(col):
+        if isinstance(col, tuple):
+            # Join tuple elements with underscore for MultiIndex columns
+            return "_".join(map(str, col)).lower()
+        # Handle regular string column names
+        return str(col).lower()
+
+    fr_map = {get_col_name(col): df[col].tolist() for col in df.columns}
 
     for c in fr_map:
         if not c.isidentifier():

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/lib/dc/records.py

@@ -1,8 +1,5 @@
-from typing import (
-    TYPE_CHECKING,
-    Optional,
-    Union,
-)
+from collections.abc import Iterable
+from typing import TYPE_CHECKING, Optional, Union
 
 import sqlalchemy
 
@@ -12,6 +9,7 @@ from datachain.lib.file import (
 )
 from datachain.lib.signal_schema import SignalSchema
 from datachain.query import Session
+from datachain.query.schema import Column
 
 if TYPE_CHECKING:
     from typing_extensions import ParamSpec
@@ -22,7 +20,7 @@ if TYPE_CHECKING:
 
 
 def read_records(
-    to_insert: Optional[Union[dict, list[dict]]],
+    to_insert: Optional[Union[dict, Iterable[dict]]],
     session: Optional[Session] = None,
     settings: Optional[dict] = None,
     in_memory: bool = False,
@@ -54,10 +52,11 @@ def read_records(
 
     if schema:
         signal_schema = SignalSchema(schema)
-        columns = [
-            sqlalchemy.Column(c.name, c.type)  # type: ignore[union-attr]
-            for c in signal_schema.db_signals(as_columns=True)  # type: ignore[assignment]
-        ]
+        columns = []
+        for c in signal_schema.db_signals(as_columns=True):
+            assert isinstance(c, Column)
+            kw = {"nullable": c.nullable} if c.nullable is not None else {}
+            columns.append(sqlalchemy.Column(c.name, c.type, **kw))
     else:
         columns = [
             sqlalchemy.Column(name, typ)
@@ -83,8 +82,7 @@ def read_records(
 
     warehouse = catalog.warehouse
     dr = warehouse.dataset_rows(dsr)
-    db = warehouse.db
-    insert_q = dr.get_table().insert()
-    for record in to_insert:
-        db.execute(insert_q.values(**record))
+    table = dr.get_table()
+    warehouse.insert_rows(table, to_insert)
+    warehouse.insert_rows_done(table)
     return read_dataset(name=dsr.name, session=session, settings=settings)

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/lib/signal_schema.py

@@ -581,7 +581,11 @@ class SignalSchema:
         signals = [
             DEFAULT_DELIMITER.join(path)
             if not as_columns
-            else Column(DEFAULT_DELIMITER.join(path), python_to_sql(_type))
+            else Column(
+                DEFAULT_DELIMITER.join(path),
+                python_to_sql(_type),
+                nullable=is_optional(_type),
+            )
             for path, _type, has_subtree, _ in self.get_flat_tree(
                 include_hidden=include_hidden
             )
@@ -990,3 +994,8 @@ class SignalSchema:
             }
 
         return SignalSchema.deserialize(schema)
+
+
+def is_optional(type_: Any) -> bool:
+    """Check if a type is Optional."""
+    return get_origin(type_) is Union and type(None) in get_args(type_)

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/query/dataset.py

@@ -437,9 +437,17 @@ class UDFStep(Step, ABC):
                             "distributed processing."
                         )
 
-                    from datachain.catalog.loader import get_udf_distributor_class
+                    from datachain.catalog.loader import (
+                        DISTRIBUTED_IMPORT_PATH,
+                        get_udf_distributor_class,
+                    )
+
+                    if not (udf_distributor_class := get_udf_distributor_class()):
+                        raise RuntimeError(
+                            f"{DISTRIBUTED_IMPORT_PATH} import path is required "
+                            "for distributed UDF processing."
+                        )
 
-                    udf_distributor_class = get_udf_distributor_class()
                     udf_distributor = udf_distributor_class(
                         catalog=catalog,
                         table=udf_table,
@@ -1162,16 +1170,6 @@ class DatasetQuery:
         )
         return sqlalchemy.table(table_name)
 
-    @staticmethod
-    def delete(
-        name: str, version: Optional[int] = None, catalog: Optional["Catalog"] = None
-    ) -> None:
-        from datachain.catalog import get_catalog
-
-        catalog = catalog or get_catalog()
-        version = version or catalog.get_dataset(name).latest_version
-        catalog.remove_dataset(name, version)
-
     @property
     def attached(self) -> bool:
         """

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/query/dispatch.py

@@ -13,7 +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 get_udf_distributor_class
+from datachain.catalog.loader import DISTRIBUTED_IMPORT_PATH, get_udf_distributor_class
 from datachain.lib.udf import _get_cache
 from datachain.query.batch import RowsOutput, RowsOutputBatch
 from datachain.query.dataset import (
@@ -91,7 +91,12 @@ def udf_entrypoint() -> int:
 
 
 def udf_worker_entrypoint() -> int:
-    return get_udf_distributor_class().run_worker()
+    if not (udf_distributor_class := get_udf_distributor_class()):
+        raise RuntimeError(
+            f"{DISTRIBUTED_IMPORT_PATH} import path is required "
+            "for distributed UDF processing."
+        )
+    return udf_distributor_class.run_worker()
 
 
 class UDFDispatcher:

{datachain-0.14.5 → datachain-0.15.0}/src/datachain/query/schema.py

@@ -40,12 +40,15 @@ class ColumnMeta(type):
 class Column(sa.ColumnClause, metaclass=ColumnMeta):
     inherit_cache: Optional[bool] = True
 
-    def __init__(self, text, type_=None, is_literal=False, _selectable=None):
+    def __init__(
+        self, text, type_=None, is_literal=False, nullable=None, _selectable=None
+    ):
         """Dataset column."""
         self.name = ColumnMeta.to_db_name(text)
         super().__init__(
             self.name, type_=type_, is_literal=is_literal, _selectable=_selectable
         )
+        self.nullable = nullable
 
     def __getattr__(self, name: str):
         return Column(self.name + DEFAULT_DELIMITER + name)

{datachain-0.14.5 → datachain-0.15.0/src/datachain.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datachain
-Version: 0.14.5
+Version: 0.15.0
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License-Expression: Apache-2.0

{datachain-0.14.5 → datachain-0.15.0}/src/datachain.egg-info/SOURCES.txt

@@ -168,6 +168,7 @@ src/datachain/lib/convert/unflatten.py
 src/datachain/lib/convert/values_to_tuples.py
 src/datachain/lib/dc/__init__.py
 src/datachain/lib/dc/csv.py
+src/datachain/lib/dc/database.py
 src/datachain/lib/dc/datachain.py
 src/datachain/lib/dc/datasets.py
 src/datachain/lib/dc/hf.py
@@ -267,6 +268,7 @@ tests/func/test_metrics.py
 tests/func/test_pull.py
 tests/func/test_pytorch.py
 tests/func/test_query.py
+tests/func/test_read_database.py
 tests/func/test_session.py
 tests/func/test_toolkit.py
 tests/func/test_video.py

{datachain-0.14.5 → datachain-0.15.0}/tests/conftest.py

@@ -631,10 +631,13 @@ def dataset_rows():
 
 
 @pytest.fixture
-def studio_datasets(requests_mock):
+def studio_token():
     with Config(ConfigLevel.GLOBAL).edit() as conf:
         conf["studio"] = {"token": "isat_access_token", "team": "team_name"}
 
+
+@pytest.fixture
+def studio_datasets(requests_mock, studio_token):
     common_version_info = {
         "status": 1,
         "created_at": "2024-02-23T10:42:31.842944+00:00",