Drop: LoadHubDataset due to deprecation in 1.3

README.md

@@ -105,14 +105,14 @@ Then run:
 ```python
 from distilabel.llms import OpenAILLM
 from distilabel.pipeline import Pipeline
-from distilabel.steps import LoadHubDataset
+from distilabel.steps import LoadDataFromHub
 from distilabel.steps.tasks import TextGeneration
 
 with Pipeline(
     name="simple-text-generation-pipeline",
     description="A simple text generation pipeline",
 ) as pipeline:
-    load_dataset = LoadHubDataset(output_mappings={"prompt": "instruction"})
+    load_dataset = LoadDataFromHub(output_mappings={"prompt": "instruction"})
 
     generate_with_openai = TextGeneration(llm=OpenAILLM(model="gpt-3.5-turbo"))
 

examples/arena_hard.py

@@ -335,7 +335,7 @@ def process(self, inputs: StepInput) -> StepOutput:  # type: ignore
     from distilabel.steps import (
         CombineColumns,
         KeepColumns,
-        LoadHubDataset,
+        LoadDataFromHub,
         StepInput,
         step,
     )
@@ -369,7 +369,7 @@ def LoadReference(*inputs: StepInput) -> StepOutput:
             yield input
 
     with Pipeline(name="arena-hard-v0.1") as pipeline:
-        load_dataset = LoadHubDataset(
+        load_dataset = LoadDataFromHub(
             name="load_dataset",
             repo_id="alvarobartt/lmsys-arena-hard-v0.1",
             split="test",

src/distilabel/pipeline/routing_batch_function.py

@@ -251,7 +251,7 @@ def routing_batch_function(
     ```python
     from distilabel.llms import MistralLLM, OpenAILLM, VertexAILLM
     from distilabel.pipeline import Pipeline, routing_batch_function
-    from distilabel.steps import LoadHubDataset, CombineColumns
+    from distilabel.steps import LoadDataFromHub, CombineColumns
 
 
     @routing_batch_function
@@ -260,7 +260,7 @@ def random_routing_batch(steps: List[str]) -> List[str]:
 
 
     with Pipeline(name="routing-batch-function") as pipeline:
-        load_data = LoadHubDataset()
+        load_data = LoadDataFromHub()
 
         generations = []
         for llm in (
@@ -336,14 +336,14 @@ def sample_n_steps(n: int) -> RoutingBatchFunction:
     ```python
     from distilabel.llms import MistralLLM, OpenAILLM, VertexAILLM
     from distilabel.pipeline import Pipeline, sample_n_steps
-    from distilabel.steps import LoadHubDataset, CombineColumns
+    from distilabel.steps import LoadDataFromHub, CombineColumns
 
 
     random_routing_batch = sample_n_steps(2)
 
 
     with Pipeline(name="routing-batch-function") as pipeline:
-        load_data = LoadHubDataset()
+        load_data = LoadDataFromHub()
 
         generations = []
         for llm in (

src/distilabel/steps/__init__.py

@@ -33,7 +33,6 @@
     LoadDataFromDisk,
     LoadDataFromFileSystem,
     LoadDataFromHub,
-    LoadHubDataset,
 )
 from distilabel.steps.globals.huggingface import PushToHub
 from distilabel.steps.keep import KeepColumns
@@ -58,7 +57,6 @@
     "LoadDataFromDisk",
     "LoadDataFromFileSystem",
     "LoadDataFromHub",
-    "LoadHubDataset",
     "PushToHub",
     "Step",
     "StepInput",

src/distilabel/steps/generators/huggingface.py

@@ -12,7 +12,6 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import warnings
 from collections import defaultdict
 from functools import cached_property
 from pathlib import Path
@@ -242,16 +241,6 @@ def _dataset_info(self) -> Dict[str, DatasetInfo]:
             return ds.info
 
 
-class LoadHubDataset(LoadDataFromHub):
-    def __init__(self, **data: Any) -> None:
-        warnings.warn(
-            "`LoadHubDataset` is deprecated and will be removed in version 1.3.0, use `LoadDataFromHub` instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        return super().__init__(**data)
-
-
 class LoadDataFromFileSystem(LoadDataFromHub):
     """Loads a dataset from a file in your filesystem.
 

tests/integration/test_pipe_llms.py

@@ -20,7 +20,7 @@
 from distilabel.mixins.runtime_parameters import RuntimeParameter
 from distilabel.pipeline.local import Pipeline
 from distilabel.steps.base import Step, StepInput
-from distilabel.steps.generators.huggingface import LoadHubDataset
+from distilabel.steps.generators.huggingface import LoadDataFromHub
 from distilabel.steps.tasks.text_generation import TextGeneration
 
 if TYPE_CHECKING:
@@ -51,7 +51,7 @@ def process(self, *inputs: StepInput) -> "StepOutput":
 
 def test_pipeline_with_llms_serde() -> None:
     with Pipeline(name="unit-test-pipeline") as pipeline:
-        load_hub_dataset = LoadHubDataset(name="load_dataset")
+        load_hub_dataset = LoadDataFromHub(name="load_dataset")
         rename_columns = RenameColumns(name="rename_columns")
         load_hub_dataset.connect(rename_columns)
 

tests/unit/cli/test_pipeline.yaml

@@ -27,7 +27,7 @@ pipeline:
               only needed if the dataset has multiple configurations.
         type_info:
           module: distilabel.steps.generators.huggingface
-          name: LoadHubDataset
+          name: LoadDataFromHub
       name: load_hub_dataset
     - step:
         name: text_generation_gpt

tests/unit/steps/generators/test_huggingface.py

@@ -25,7 +25,6 @@
     LoadDataFromDisk,
     LoadDataFromFileSystem,
     LoadDataFromHub,
-    LoadHubDataset,
 )
 
 DISTILABEL_RUN_SLOW_TESTS = os.getenv("DISTILABEL_RUN_SLOW_TESTS", False)
@@ -183,16 +182,3 @@ def test_load_distiset_from_disk(self) -> None:
             assert isinstance(generator_step_output, tuple)
             assert isinstance(generator_step_output[1], bool)
             assert len(generator_step_output[0]) == 3
-
-
-def test_LoadHubDataset_deprecation_warning():
-    with pytest.deprecated_call():
-        LoadHubDataset(
-            repo_id="distilabel-internal-testing/instruction-dataset-mini",
-            split="test",
-            batch_size=2,
-        )
-    import distilabel
-    from packaging.version import Version
-
-    assert Version(distilabel.__version__) <= Version("1.3.0")

tests/unit/test_imports.py

@@ -54,7 +54,6 @@ def test_imports() -> None:
         LoadDataFromDicts,
         LoadDataFromHub,
         LoadDataFromDisk,
-        LoadHubDataset,
         PushToHub,
         Step,
         StepOutput,