v4.1.16 Release (#3047)

Author: khustup2

python/deeplake/__init__.py

@@ -16,7 +16,7 @@ def progress_bar(iterable, *args, **kwargs):
 from deeplake.ingestion import from_coco
 
 
-__version__ = "4.1.12"
+__version__ = "4.1.16"
 
 __all__ = [
     "__version__",
@@ -27,7 +27,6 @@ def progress_bar(iterable, *args, **kwargs):
     "BadRequestError",
     "Branch",
     "BranchExistsError",
-    "BranchHasChildrenError",
     "BranchNotFoundError",
     "BranchView",
     "Branches",
@@ -36,7 +35,6 @@ def progress_bar(iterable, *args, **kwargs):
     "CanNotCreateTensorWithProvidedCompressions",
     "CannotDeleteMainBranchError",
     "CannotRenameMainBranchError",
-    "CannotTagUncommittedDatasetError",
     "Client",
     "Column",
     "ColumnAlreadyExistsError",
@@ -89,6 +87,8 @@ def progress_bar(iterable, *args, **kwargs):
     "NotLoggedInAgreementError",
     "PushError",
     "QuantizationType",
+    "Random",
+    "random",
     "ReadOnlyDataset",
     "ReadOnlyDatasetModificationError",
     "ReadOnlyMetadata",
@@ -152,6 +152,8 @@ def progress_bar(iterable, *args, **kwargs):
     "storage",
     "tql",
     "types",
+    "TelemetryClient",
+    "telemetry_client"
 ]
 
 

python/deeplake/__init__.pyi

@@ -15,7 +15,6 @@ __all__ = [
     "BadRequestError",
     "Branch",
     "BranchExistsError",
-    "BranchHasChildrenError",
     "BranchNotFoundError",
     "BranchView",
     "Branches",
@@ -24,7 +23,6 @@ __all__ = [
     "CanNotCreateTensorWithProvidedCompressions",
     "CannotDeleteMainBranchError",
     "CannotRenameMainBranchError",
-    "CannotTagUncommittedDatasetError",
     "Client",
     "Column",
     "ColumnAlreadyExistsError",
@@ -77,6 +75,8 @@ __all__ = [
     "NotLoggedInAgreementError",
     "PushError",
     "QuantizationType",
+    "Random",
+    "random",
     "ReadOnlyDataset",
     "ReadOnlyDatasetModificationError",
     "ReadOnlyMetadata",
@@ -140,6 +140,8 @@ __all__ = [
     "storage",
     "tql",
     "types",
+    "TelemetryClient",
+    "telemetry_client"
 ]
 
 class Future:
@@ -739,6 +741,14 @@ class Client:
     """
     endpoint: str
 
+class Random:
+    """
+    A pseudorandom number generator class that allows for deterministic random number generation
+    through seed control.
+    """
+
+    seed: int | None
+
 class Branch:
     """
     Describes a branch within the dataset.
@@ -2152,6 +2162,38 @@ class Dataset(DatasetView):
         """
         ...
 
+    def merge(self, branch_name: str, version: str | None = None) -> None:
+        """
+        Merge the given branch into the current branch. If no version is given, the current version will be picked up.
+
+        Parameters:
+            name: The name of the branch
+            version: The version of the dataset
+
+        <!-- test-context
+        ```python
+        import deeplake
+        ```
+        -->
+
+        Examples:
+            ```python
+            ds = deeplake.create("mem://merge_branch")
+            ds.add_column("c1", deeplake.types.Int64())
+            ds.append({"c1": [1, 2, 3]})
+            ds.commit()
+
+            b = ds.branch("Branch1")
+            branch_ds = b.open()
+            branch_ds.append({"c1": [4, 5, 6]})
+            branch_ds.commit()
+
+            ds.merge("Branch1")
+            print(len(ds))
+            ```
+        """
+        ...
+
     def tag(self, name: str, version: str | None = None) -> Tag:
         """
         Tags a version of the dataset. If no version is given, the current version is tagged.
@@ -2879,18 +2921,12 @@ class BranchExistsError(Exception):
 class BranchNotFoundError(Exception):
     pass
 
-class BranchHasChildrenError(Exception):
-    pass
-
 class TagNotFoundError(Exception):
     pass
 
 class TagExistsError(Exception):
     pass
 
-class CannotTagUncommittedDatasetError(Exception):
-    pass
-
 class PushError(Exception):
     pass
 
@@ -3176,7 +3212,7 @@ def create(
         ```
 
     Raises:
-        ValueError: if a dataset already exists at the given URL
+        LogExistsError: if a dataset already exists at the given URL
     """
 
 def create_async(
@@ -3239,7 +3275,7 @@ def create_async(
         ```
 
     Raises:
-        ValueError: if a dataset already exists at the given URL (will be raised when the future is awaited)
+        RuntimeError: if a dataset already exists at the given URL (will be raised when the future is awaited)
     """
 
 def copy(
@@ -3661,3 +3697,10 @@ def from_coco(
     """
 
 def __prepare_atfork() -> None: ...
+
+class TelemetryClient:
+    """
+    Client for logging deeplake messages to telemetry.
+    """
+    endpoint: str
+    api_key: str

python/deeplake/storage.py

@@ -1,3 +1,3 @@
 from ._deeplake.types import *
 
-__all__ = ["Reader", "Writer"]
+__all__ = ["Reader", "Writer", "ResourceMeta"]

python/deeplake/storage.pyi

@@ -3,10 +3,11 @@ Storage readers and writers - s3, gcs, azure, filesystem, etc.
 """
 
 from __future__ import annotations
+import datetime
 import deeplake._deeplake.core
 import typing
 
-__all__ = ["Reader", "Writer"]
+__all__ = ["Reader", "Writer", "ResourceMeta"]
 
 class Reader:
     def __getstate__(self) -> tuple: ...
@@ -15,7 +16,7 @@ class Reader:
         self, path: str, start_bytes: int | None = None, end_bytes: int | None = None
     ) -> deeplake._deeplake.core.MemoryBuffer: ...
     def length(self, path: str) -> int: ...
-    def list(self, path: str) -> list: ...
+    def list(self, path: str) -> list[ResourceMeta]: ...
     def subdir(self, subpath: str) -> Reader: ...
     @property
     def original_path(self) -> str: ...
@@ -37,3 +38,24 @@ class Writer:
     def path(self) -> str: ...
     @property
     def token(self) -> str: ...
+
+class ResourceMeta:
+    __hash__: typing.ClassVar[None] = None
+    def __eq__(self, other: ResourceMeta) -> bool:
+        ...
+    def __lt__(self, other: ResourceMeta) -> bool:
+        ...
+    def __repr__(self) -> str:
+        ...
+    @property
+    def etag(self) -> str:
+        ...
+    @property
+    def last_modified(self) -> datetime.datetime:
+        ...
+    @property
+    def path(self) -> str:
+        ...
+    @property
+    def size(self) -> int:
+        ...

python/deeplake/types.py

@@ -19,6 +19,7 @@
     "EmbeddingIndexEnumType",
     "EmbeddingsMatrixIndex",
     "EmbeddingsMatrixIndexType",
+    "Float16",
     "Float32",
     "Float64",
     "Image",

python/deeplake/types.pyi

@@ -21,6 +21,7 @@ __all__ = [
     "EmbeddingIndexEnumType",
     "EmbeddingsMatrixIndex",
     "EmbeddingsMatrixIndexType",
+    "Float16",
     "Float32",
     "Float64",
     "Image",
@@ -643,6 +644,27 @@ def EmbeddingsMatrixIndex() -> EmbeddingsMatrixIndexType:
     """
     ...
 
+def Float16() -> DataType:
+    """
+    Creates a 16-bit (half) float value type.
+
+    Returns:
+        DataType: A new 16-bit float data type.
+
+    <!--
+    ```python
+    ds = deeplake.create("tmp://")
+    ```
+    -->
+
+    Examples:
+        Create a column with 16-bit float type:
+        ```python
+        ds.add_column("col1", types.Float16)
+        ```
+    """
+    ...
+
 def Float32() -> DataType:
     """
     Creates a 32-bit float value type.