From 8db6d02b2e15ecc4d33c200b13de5567bf517ad9 Mon Sep 17 00:00:00 2001 From: Nathan Voxland Date: Mon, 6 Nov 2023 15:06:16 -0600 Subject: [PATCH 1/3] Removed pip install deeplake[enterprise] references in docs --- deeplake/core/dataset/dataset.py | 6 ++---- deeplake/core/dataset/deeplake_query_dataset.py | 2 +- deeplake/integrations/pytorch/pytorch.py | 2 +- docs/source/Tensor-Query-Language.rst | 2 +- 4 files changed, 5 insertions(+), 7 deletions(-) diff --git a/deeplake/core/dataset/dataset.py b/deeplake/core/dataset/dataset.py index 465630e230..b087196ede 100644 --- a/deeplake/core/dataset/dataset.py +++ b/deeplake/core/dataset/dataset.py @@ -2137,7 +2137,7 @@ def pytorch( return dataloader def dataloader(self, ignore_errors: bool = False, verbose: bool = False): - """Returns a :class:`~deeplake.enterprise.DeepLakeDataLoader` object. To use this, install deeplake with ``pip install deeplake[enterprise]``. + """Returns a :class:`~deeplake.enterprise.DeepLakeDataLoader` object. Args: ignore_errors (bool): If ``True``, the data loader will ignore errors appeared during data iteration otherwise it will collect the statistics and report appeared errors. Default value is ``False`` @@ -2271,7 +2271,7 @@ def query( runtime: Optional[Dict] = None, return_data: bool = False, ): - """Returns a sliced :class:`~deeplake.core.dataset.Dataset` with given query results. To use this, install deeplake with ``pip install deeplake[enterprise]``. + """Returns a sliced :class:`~deeplake.core.dataset.Dataset` with given query results. It allows to run SQL like queries on dataset and extract results. See supported keywords and the Tensor Query Language documentation :ref:`here `. @@ -2349,7 +2349,6 @@ def sample_by( size: Optional[int] = None, ): """Returns a sliced :class:`~deeplake.core.dataset.Dataset` with given weighted sampler applied. - To use this, install deeplake with ``pip install deeplake[enterprise]``. Args: weights: (Union[str, list, tuple]): If it's string then tql will be run to calculate the weights based on the expression. list and tuple will be treated as the list of the weights per sample. @@ -4764,7 +4763,6 @@ def max_view(self): def random_split(self, lengths: Sequence[Union[int, float]]): """Splits the dataset into non-overlapping :class:`~deeplake.core.dataset.Dataset` objects of given lengths. If a list of fractions that sum up to 1 is given, the lengths will be computed automatically as floor(frac * len(dataset)) for each fraction provided. - The split generated is only performant with enterprise dataloader which can be installed with ``pip install deeplake[enterprise]``. After computing the lengths, if there are any remainders, 1 count will be distributed in round-robin fashion to the lengths until there are no remainders left. diff --git a/deeplake/core/dataset/deeplake_query_dataset.py b/deeplake/core/dataset/deeplake_query_dataset.py index 66a7d9767c..8429caa330 100644 --- a/deeplake/core/dataset/deeplake_query_dataset.py +++ b/deeplake/core/dataset/deeplake_query_dataset.py @@ -199,7 +199,7 @@ def __len__(self): @deeplake_reporter.record_call def dataloader(self, ignore_errors: bool = False, verbose: bool = False): - """Returns a :class:`~deeplake.enterprise.DeepLakeDataLoader` object. To use this, install deeplake with ``pip install deeplake[enterprise]``. + """Returns a :class:`~deeplake.enterprise.DeepLakeDataLoader` object. Args: ignore_errors (bool): If ``True``, the data loader will ignore errors appeared during data iteration otherwise it will collect the statistics and report appeared errors. Default value is ``False`` diff --git a/deeplake/integrations/pytorch/pytorch.py b/deeplake/integrations/pytorch/pytorch.py index 558a249f35..5e1121a3d3 100644 --- a/deeplake/integrations/pytorch/pytorch.py +++ b/deeplake/integrations/pytorch/pytorch.py @@ -99,7 +99,7 @@ def dataset_to_pytorch( for t in tensors: if dataset[t].is_sequence: raise NotImplementedError( - f"Deep Lake’s OSS pure-python dataloader is not compatible with tensor `{t}` with htype = sequence[…]. Please use the C++ dataloader via ds.dataloader(…), which can be installed using ‘pip install deeplake[enterprise]’." + f"Deep Lake’s OSS pure-python dataloader is not compatible with tensor `{t}` with htype = sequence[…]. Please use the C++ dataloader via ds.dataloader(…)" ) tensors = map_tensor_keys(dataset, tensors) diff --git a/docs/source/Tensor-Query-Language.rst b/docs/source/Tensor-Query-Language.rst index 8ced3664bf..7ea432423c 100644 --- a/docs/source/Tensor-Query-Language.rst +++ b/docs/source/Tensor-Query-Language.rst @@ -7,7 +7,7 @@ Tensor Query Language :language: sql This page describes the Tensor Query Language (TQL), an SQL-like language used for `Querying in Activeloop Platform `_ -as well as in :meth:`ds.query ` in our Python API. To use queries, install deeplake with ``pip install deeplake[enterprise]``. +as well as in :meth:`ds.query ` in our Python API. Syntax ~~~~~~~~ From caf16645d12b1fce595f61f0c792f90487a0413b Mon Sep 17 00:00:00 2001 From: Nathan Voxland Date: Mon, 6 Nov 2023 15:09:45 -0600 Subject: [PATCH 2/3] Removed pip install deeplake[enterprise] references in docs --- deeplake/core/vectorstore/deep_memory.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deeplake/core/vectorstore/deep_memory.py b/deeplake/core/vectorstore/deep_memory.py index a56b666c4f..2fb23bfa66 100644 --- a/deeplake/core/vectorstore/deep_memory.py +++ b/deeplake/core/vectorstore/deep_memory.py @@ -398,7 +398,7 @@ def evaluate( if not INDRA_INSTALLED: raise ImportError( - "indra is not installed. Please install indra to use this functionality with: pip install `deeplake[enterprise]`" + "The C++ library is not installed." ) from indra import api # type: ignore From 1a9d74c4a6ea2bbe5ed8f16a96d9df5eacdcaa55 Mon Sep 17 00:00:00 2001 From: Nathan Voxland Date: Tue, 7 Nov 2023 09:51:17 -0600 Subject: [PATCH 3/3] Removed pip install deeplake[enterprise] references in docs --- deeplake/core/vectorstore/deep_memory.py | 4 ++-- deeplake/integrations/pytorch/pytorch.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/deeplake/core/vectorstore/deep_memory.py b/deeplake/core/vectorstore/deep_memory.py index 2fb23bfa66..1fbb4f3455 100644 --- a/deeplake/core/vectorstore/deep_memory.py +++ b/deeplake/core/vectorstore/deep_memory.py @@ -398,7 +398,7 @@ def evaluate( if not INDRA_INSTALLED: raise ImportError( - "The C++ library is not installed." + "The C++ library is not installed. The library should be installed using `pip install deeplake`, but if you want to install it separately, you may run `pip install libdeeplake`" ) from indra import api # type: ignore @@ -421,7 +421,7 @@ def evaluate( if embedding_function is None: raise ValueError( - "Embedding function should be specifed either during initialization or during evaluation." + "Embedding function should be specified either during initialization or during evaluation." ) query_embs = embedding_function(queries) diff --git a/deeplake/integrations/pytorch/pytorch.py b/deeplake/integrations/pytorch/pytorch.py index 5e1121a3d3..2ee2195204 100644 --- a/deeplake/integrations/pytorch/pytorch.py +++ b/deeplake/integrations/pytorch/pytorch.py @@ -99,7 +99,7 @@ def dataset_to_pytorch( for t in tensors: if dataset[t].is_sequence: raise NotImplementedError( - f"Deep Lake’s OSS pure-python dataloader is not compatible with tensor `{t}` with htype = sequence[…]. Please use the C++ dataloader via ds.dataloader(…)" + f"Deep Lake’s OSS pure-python dataloader is not compatible with tensor `{t}` with htype = sequence[…]. Please use the high-performance dataloader via ds.dataloader(…)" ) tensors = map_tensor_keys(dataset, tensors)