v4.0.3 Release

python/deeplake/__init__.py

@@ -6,7 +6,7 @@
 import deeplake
 from ._deeplake import *
 
-__version__ = "4.0.2"
+__version__ = "4.0.3"
 
 __all__ = [
     "__version__",
@@ -34,6 +34,7 @@
     "ColumnAlreadyExistsError",
     "ColumnDoesNotExistError",
     "InvalidColumnValueError",
+    "PushError",
     "GcsStorageProviderFailed",
     "History",
     "InvalidType",

python/deeplake/__init__.pyi

@@ -32,6 +32,7 @@ __all__ = [
     "ColumnAlreadyExistsError",
     "ColumnDoesNotExistError",
     "InvalidColumnValueError",
+    "PushError",
     "GcsStorageProviderFailed",
     "History",
     "InvalidType",
@@ -380,6 +381,9 @@ class TagExistsError(Exception):
 class CannotTagUncommittedDatasetError(Exception):
     pass
 
+class PushError(Exception):
+    pass
+
 class Tags:
     """
     Provides access to the tags within a dataset.
@@ -1155,7 +1159,7 @@ class Dataset(DatasetView):
         """Restores dataset from a pickled state.
 
         Args:
-            state (dict): The pickled state used to restore the dataset.
+            arg0 (dict): The pickled state used to restore the dataset.
         """
 
     def add_column(
@@ -1331,6 +1335,57 @@ class Dataset(DatasetView):
         Asynchronously reverts any in-progress changes to the dataset you have made. Does not revert any changes that have been committed.
         """
 
+    def push(self, url: str, creds: dict[str, str] | None = None, token: str | None = None) -> None:
+        """
+        Pushes any new history from this dataset to the dataset at the given url
+
+        Similar to [deeplake.Dataset.pull][] but the other direction.
+
+        Parameters:
+            url: The URL of the destination dataset
+            creds: Optional credentials needed to connect to the dataset
+            token: Optional deeplake token
+        """
+        ...
+    def push_async(self, url: str, creds: dict[str, str] | None = None, token: str | None = None) -> FutureVoid:
+        """
+        Asynchronously Pushes new any history from this dataset to the dataset at the given url
+
+        Similar to [deeplake.Dataset.pull_async][] but the other direction.
+
+        Parameters:
+            url: The URL of the destination dataset
+            creds: Optional credentials needed to connect to the dataset
+            token: Optional deeplake token
+        """
+        ...
+
+    def pull(self, url: str, creds: dict[str, str] | None = None, token: str | None = None) -> None:
+        """
+        Pulls any new history from the dataset at the passed url into this dataset.
+
+        Similar to [deeplake.Dataset.push][] but the other direction.
+
+        Parameters:
+            url: The URL of the destination dataset
+            creds: Optional credentials needed to connect to the dataset
+            token: Optional deeplake token
+        """
+        ...
+    def pull_async(self, url: str, creds: dict[str, str] | None = None, token: str | None = None) -> FutureVoid:
+        """
+        Asynchronously pulls any new history from the dataset at the passed url into this dataset.
+
+        Similar to [deeplake.Dataset.push_async][] but the other direction.
+
+        Parameters:
+            url: The URL of the destination dataset
+            creds: Optional credentials needed to connect to the dataset
+            token: Optional deeplake token
+        """
+        ...
+
+
     @property
     def history(self) -> History:
         """
@@ -1406,7 +1461,7 @@ class ReadOnlyDataset(DatasetView):
     @property
     def tags(self) -> TagsView:
         """
-        The collection of [deeplake.TagsView][] within the dataset
+        The collection of [deeplake.TagView][]s within the dataset
         """
         ...
 
@@ -1474,6 +1529,27 @@ class ReadOnlyDataset(DatasetView):
         """
         ...
 
+    def push(self, url: str, creds: dict[str, str] | None = None, token: str | None = None) -> None:
+        """
+        Pushes any history from this dataset to the dataset at the given url
+
+        Parameters:
+            url: The URL of the destination dataset
+            creds: Optional credentials needed to connect to the dataset
+            token: Optional deeplake token
+        """
+        ...
+    def push_async(self, url: str, creds: dict[str, str] | None = None, token: str | None = None) -> FutureVoid:
+        """
+        Asynchronously Pushes any history from this dataset to the dataset at the given url
+
+        Parameters:
+            url: The URL of the destination dataset
+            creds: Optional credentials needed to connect to the dataset
+            token: Optional deeplake token
+        """
+        ...
+
     def __getstate__(self) -> tuple:
         """Returns a dict that can be pickled and used to restore this dataset.
 
@@ -1803,7 +1879,7 @@ def create(url: str, creds: dict[str, str] | None = None, token: str | None = No
             - To use credentials managed in your Activeloop organization, use they key 'creds_key': 'managed_key_name'. This requires the org_id dataset argument to be set.
             - If nothing is given is, credentials are fetched from the environment variables. This is also the case when creds is not passed for cloud datasets
         token (str, optional): Activeloop token, used for fetching credentials to the dataset at path if it is a Deep Lake dataset. This is optional, tokens are normally autogenerated.
-        schema (dict): The initial schema to use for the dataset. See `deeplake.schema` such as [deeplake.schemas.TextDocuments][] for common starting schemas.
+        schema (dict): The initial schema to use for the dataset. See `deeplake.schema` such as [deeplake.schemas.TextEmbeddings][] for common starting schemas.
 
     Examples:
         >>> import deeplake