v4.2.14 Release.

Author: khustup2

python/deeplake/__init__.py

@@ -16,7 +16,7 @@ def progress_bar(iterable, *args, **kwargs):
 from deeplake.ingestion import from_coco
 
 
-__version__ = "4.2.12"
+__version__ = "4.2.14"
 
 __all__ = [
     "__version__",
@@ -143,6 +143,7 @@ def progress_bar(iterable, *args, **kwargs):
     "create_async",
     "_create_global_cache",
     "delete",
+    "delete_async",
     "disconnect",
     "exists",
     "explain_query",

python/deeplake/__init__.pyi

@@ -131,6 +131,7 @@ __all__ = [
     "create_async",
     "_create_global_cache",
     "delete",
+    "delete_async",
     "disconnect",
     "exists",
     "explain_query",
@@ -2521,19 +2522,6 @@ class Dataset(DatasetView):
         The history of the dataset.
         """
 
-    @property
-    def _reader(self) -> storage.Reader:
-        """
-        A [reader][deeplake.storage.Reader] that can be used to directly access files from the dataset's storage.
-
-        Primarily used for debugging purposes.
-        """
-        ...
-
-    @property
-    def _datafiles(self) -> list[tuple[str, int]]:
-        ...
-
     @property
     def id(self) -> str:
         """
@@ -2640,12 +2628,7 @@ class Dataset(DatasetView):
             arg0 (dict): The pickled state used to restore the dataset.
         """
 
-    def add_column(
-        self,
-        name: str,
-        dtype: types.DataType | str | types.Type | type | typing.Callable,
-        default_value: typing.Any = None,
-    ) -> None:
+    def add_column(self, name: str, dtype: typing.Any, default_value: typing.Any = None) -> None:
         """
         Add a new column to the dataset.
 
@@ -3023,19 +3006,6 @@ class ReadOnlyDataset(DatasetView):
         """
         ...
 
-    @property
-    def _reader(self) -> storage.Reader:
-        """
-        A [reader][deeplake.storage.Reader] that can be used to directly access files from the dataset's storage.
-
-        Primarily used for debugging purposes.
-        """
-        ...
-
-    @property
-    def _datafiles(self) -> list[tuple[str, int]]:
-        ...
-
     @property
     def id(self) -> str:
         """
@@ -3447,7 +3417,7 @@ def create(
     url: str,
     creds: dict[str, str] | None = None,
     token: str | None = None,
-    schema: dict[str, types.DataType | str | types.Type] | None = None,
+    schema: dict[str, typing.Any] | typing.Any | None = None,
 ) -> Dataset:
     """
     Creates a new dataset at the given URL.
@@ -3527,7 +3497,7 @@ def create_async(
     url: str,
     creds: dict[str, str] | None = None,
     token: str | None = None,
-    schema: dict[str, types.DataType | str | types.Type] | None = None,
+    schema: dict[str, typing.Any] | typing.Any | None = None,
 ) -> Future:
     """
     Asynchronously creates a new dataset at the given URL.
@@ -3641,6 +3611,19 @@ def delete(
         It's recommended to use this operation with caution.
     """
 
+def delete_async(
+    url: str, creds: dict[str, str] | None = None, token: str | None = None
+) -> FutureVoid:
+    """
+    Asynchronously deletes an existing dataset.
+
+    !!! warning
+        This operation is irreversible. All data will be lost.
+
+        If concurrent processes are attempting to write to the dataset while it's being deleted, it may lead to data inconsistency.
+        It's recommended to use this operation with caution.
+    """
+
 def exists(
     url: str, creds: dict[str, str] | None = None, token: str | None = None
 ) -> bool:

python/deeplake/types.py

@@ -2,6 +2,7 @@
 
 __all__ = [
     "Array",
+    "Audio",
     "BM25",
     "Binary",
     "BinaryMask",
@@ -15,8 +16,8 @@
     "Dict",
     "Embedding",
     "EmbeddingIndex",
-    "EmbeddingIndexType",
     "EmbeddingIndexEnumType",
+    "EmbeddingIndexType",
     "EmbeddingsMatrixIndex",
     "EmbeddingsMatrixIndexType",
     "Exact",
@@ -31,21 +32,22 @@
     "Int8",
     "Inverted",
     "Link",
-    "Polygon",
+    "Medical",
     "Point",
+    "Polygon",
     "QuantizationType",
     "SegmentMask",
-    "Medical",
     "Sequence",
     "Struct",
     "Text",
     "TextIndex",
-    "TextIndexType",
     "TextIndexEnumType",
+    "TextIndexType",
     "Type",
     "TypeKind",
     "UInt16",
     "UInt32",
     "UInt64",
     "UInt8"
 ]
+

python/deeplake/types.pyi

@@ -2,8 +2,8 @@ from __future__ import annotations
 
 import typing
 
-__all__ = [
-    "Array",
+__all__ = ["Array",
+    "Audio",
     "BM25",
     "Binary",
     "BinaryMask",
@@ -17,8 +17,8 @@ __all__ = [
     "Dict",
     "Embedding",
     "EmbeddingIndex",
-    "EmbeddingIndexType",
     "EmbeddingIndexEnumType",
+    "EmbeddingIndexType",
     "EmbeddingsMatrixIndex",
     "EmbeddingsMatrixIndexType",
     "Exact",
@@ -33,17 +33,17 @@ __all__ = [
     "Int8",
     "Inverted",
     "Link",
-    "Polygon",
+    "Medical",
     "Point",
+    "Polygon",
     "QuantizationType",
     "SegmentMask",
-    "Medical",
     "Sequence",
     "Struct",
     "Text",
     "TextIndex",
-    "TextIndexType",
     "TextIndexEnumType",
+    "TextIndexType",
     "Type",
     "TypeKind",
     "UInt16",
@@ -336,7 +336,7 @@ class TypeKind:
         Medical: Medical data type
         Link: Link data type
     """
-
+    Audio: typing.ClassVar[TypeKind]
     BinaryMask: typing.ClassVar[TypeKind]
     BoundingBox: typing.ClassVar[TypeKind]
     ClassLabel: typing.ClassVar[TypeKind]
@@ -422,6 +422,38 @@ def Array(
     """
     ...
 
+def Audio(dtype: DataType | str = "uint8", sample_compression: str = "mp3") -> Type:
+    """
+    Creates an audio data type.
+
+    Parameters:
+        dtype: DataType | str
+            The datatype of the audio samples. Defaults to "uint8".
+        sample_compression: str
+            The compression format for the audio samples wav or mp3. Defaults to "mp3".
+
+    Returns:
+        Type: A new audio data type.
+
+    <!--
+    ```python
+    ds = deeplake.create("tmp://")
+    ```
+    -->
+
+    Examples:
+        Create an audio column with default settings:
+        ```python
+        ds.add_column("col1", types.Audio())
+        ```
+
+        Create an audio column with specific sample compression:
+        ```python
+        ds.add_column("col2", types.Audio(sample_compression="wav"))
+        ```
+    """
+    ...
+
 def Bool() -> DataType:
     """
     Creates a boolean value type.
@@ -1175,4 +1207,4 @@ def UInt8() -> DataType:
         ds.add_column("col1", types.UInt16)
         ```
     """
-    ...
+    ...