snowflake-ml-python 1.7.4__py3-none-any.whl → 1.7.5__py3-none-any.whl

snowflake/ml/model/_packager/model_task/model_task_utils.py

@@ -24,7 +24,11 @@ def get_task_skl(model: Union["sklearn.base.BaseEstimator", "sklearn.pipeline.Pi
     from sklearn.base import is_classifier, is_regressor
 
     if type_utils.LazyType("sklearn.pipeline.Pipeline").isinstance(model):
-        return type_hints.Task.UNKNOWN
+        if hasattr(model, "predict_proba") or hasattr(model, "predict"):
+            model = model.steps[-1][1]  # type: ignore[attr-defined]
+            return _get_model_task(model)
+        else:
+            return type_hints.Task.UNKNOWN
     if is_regressor(model):
         return type_hints.Task.TABULAR_REGRESSION
     if is_classifier(model):

snowflake/ml/model/_signatures/core.py

@@ -282,7 +282,7 @@ class FeatureSpec(BaseFeatureSpec):
             result_type = spt.ArrayType(result_type)
         return result_type
 
-    def as_dtype(self) -> Union[npt.DTypeLike, str, PandasExtensionTypes]:
+    def as_dtype(self, force_numpy_dtype: bool = False) -> Union[npt.DTypeLike, str, PandasExtensionTypes]:
         """Convert to corresponding local Type."""
 
         if not self._shape:
@@ -291,7 +291,7 @@ class FeatureSpec(BaseFeatureSpec):
                 return self._dtype._value
 
             np_type = self._dtype._numpy_type
-            if self._nullable:
+            if self._nullable and not force_numpy_dtype:
                 np_to_pd_dtype_mapping = {
                     np.int8: pd.Int8Dtype(),
                     np.int16: pd.Int16Dtype(),

snowflake/ml/model/_signatures/numpy_handler.py

@@ -50,7 +50,7 @@ class NumpyArrayHandler(base_handler.BaseDataHandler[model_types._SupportedNumpy
         dtype = core.DataType.from_numpy_type(data.dtype)
         role_prefix = (NumpyArrayHandler.INPUT_PREFIX if role == "input" else NumpyArrayHandler.OUTPUT_PREFIX) + "_"
         if len(data.shape) == 1:
-            return [core.FeatureSpec(dtype=dtype, name=f"{role_prefix}{feature_prefix}0")]
+            return [core.FeatureSpec(dtype=dtype, name=f"{role_prefix}{feature_prefix}0", nullable=False)]
         else:
             # For high-dimension array, 0-axis is for batch, 1-axis is for column, further more is details of columns.
             features = []
@@ -59,9 +59,9 @@ class NumpyArrayHandler(base_handler.BaseDataHandler[model_types._SupportedNumpy
             for col_data, ft_name in zip(data[0], ft_names):
                 if isinstance(col_data, np.ndarray):
                     ft_shape = np.shape(col_data)
-                    features.append(core.FeatureSpec(dtype=dtype, name=ft_name, shape=ft_shape))
+                    features.append(core.FeatureSpec(dtype=dtype, name=ft_name, shape=ft_shape, nullable=False))
                 else:
-                    features.append(core.FeatureSpec(dtype=dtype, name=ft_name))
+                    features.append(core.FeatureSpec(dtype=dtype, name=ft_name, nullable=False))
             return features
 
     @staticmethod
@@ -118,10 +118,10 @@ class SeqOfNumpyArrayHandler(base_handler.BaseDataHandler[Sequence[model_types._
             dtype = core.DataType.from_numpy_type(data_col.dtype)
             ft_name = f"{role_prefix}{feature_prefix}{i}"
             if len(data_col.shape) == 1:
-                features.append(core.FeatureSpec(dtype=dtype, name=ft_name))
+                features.append(core.FeatureSpec(dtype=dtype, name=ft_name, nullable=False))
             else:
                 ft_shape = tuple(data_col.shape[1:])
-                features.append(core.FeatureSpec(dtype=dtype, name=ft_name, shape=ft_shape))
+                features.append(core.FeatureSpec(dtype=dtype, name=ft_name, shape=ft_shape, nullable=False))
         return features
 
     @staticmethod

snowflake/ml/model/_signatures/pandas_handler.py

@@ -72,13 +72,6 @@ class PandasDataFrameHandler(base_handler.BaseDataHandler[pd.DataFrame]):
         df_col_dtypes = [data[col].dtype for col in data.columns]
         for df_col, df_col_dtype in zip(df_cols, df_col_dtypes):
             df_col_data = data[df_col]
-            if df_col_data.isnull().all():
-                raise snowml_exceptions.SnowflakeMLException(
-                    error_code=error_codes.INVALID_DATA,
-                    original_exception=ValueError(
-                        f"Data Validation Error: There is no non-null data in column {df_col}."
-                    ),
-                )
             if df_col_data.isnull().any():
                 warnings.warn(
                     (
@@ -163,6 +156,15 @@ class PandasDataFrameHandler(base_handler.BaseDataHandler[pd.DataFrame]):
         specs = []
         for df_col, df_col_dtype, ft_name in zip(df_cols, df_col_dtypes, ft_names):
             df_col_data = data[df_col]
+
+            if df_col_data.isnull().all():
+                raise snowml_exceptions.SnowflakeMLException(
+                    error_code=error_codes.INVALID_DATA,
+                    original_exception=ValueError(
+                        "Data Validation Error: "
+                        f"There is no non-null data in column {df_col} so the signature cannot be inferred."
+                    ),
+                )
             if df_col_data.isnull().any():
                 df_col_data = utils.series_dropna(df_col_data)
             df_col_dtype = df_col_data.dtype

snowflake/ml/model/_signatures/pytorch_handler.py

@@ -30,7 +30,7 @@ class SeqOfPyTorchTensorHandler(base_handler.BaseDataHandler[Sequence["torch.Ten
 
     @staticmethod
     def count(data: Sequence["torch.Tensor"]) -> int:
-        return min(data_col.shape[0] for data_col in data)  # type: ignore[no-any-return]
+        return min(data_col.shape[0] for data_col in data)
 
     @staticmethod
     def truncate(data: Sequence["torch.Tensor"], length: int) -> Sequence["torch.Tensor"]:

snowflake/ml/model/model_signature.py

@@ -21,6 +21,7 @@ from typing_extensions import Never
 import snowflake.snowpark
 import snowflake.snowpark.functions as F
 import snowflake.snowpark.types as spt
+from snowflake.ml._internal import telemetry
 from snowflake.ml._internal.exceptions import (
     error_codes,
     exceptions as snowml_exceptions,
@@ -56,6 +57,9 @@ _LOCAL_DATA_HANDLERS: List[Type[base_handler.BaseDataHandler[Any]]] = [
 ]
 _ALL_DATA_HANDLERS = _LOCAL_DATA_HANDLERS + [snowpark_handler.SnowparkDataFrameHandler]
 
+_TELEMETRY_PROJECT = "MLOps"
+_MODEL_TELEMETRY_SUBPROJECT = "ModelSignature"
+
 
 def _truncate_data(
     data: model_types.SupportedDataType,
@@ -687,6 +691,10 @@ def _convert_and_validate_local_data(
     return df
 
 
+@telemetry.send_api_usage_telemetry(
+    project=_TELEMETRY_PROJECT,
+    subproject=_MODEL_TELEMETRY_SUBPROJECT,
+)
 def infer_signature(
     input_data: model_types.SupportedLocalDataType,
     output_data: model_types.SupportedLocalDataType,

snowflake/ml/model/type_hints.py

@@ -7,6 +7,7 @@ from typing_extensions import NotRequired
 
 if TYPE_CHECKING:
     import catboost
+    import keras
     import lightgbm
     import mlflow
     import numpy as np
@@ -68,6 +69,7 @@ SupportedRequireSignatureModelType = Union[
     "torch.nn.Module",
     "torch.jit.ScriptModule",
     "tensorflow.Module",
+    "keras.Model",
 ]
 
 SupportedNoSignatureRequirementsModelType = Union[
@@ -103,6 +105,7 @@ Here is all acceptable types of Snowflake native model packaging and its handler
 | transformers.Pipeline | huggingface_pipeline.py | _HuggingFacePipelineHandler |
 | huggingface_pipeline.HuggingFacePipelineModel | huggingface_pipeline.py | _HuggingFacePipelineHandler |
 | sentence_transformers.SentenceTransformer | sentence_transformers.py | _SentenceTransformerHandler |
+| keras.Model | keras.py | _KerasHandler |
 """
 
 SupportedModelHandlerType = Literal[
@@ -118,6 +121,7 @@ SupportedModelHandlerType = Literal[
     "tensorflow",
     "torchscript",
     "xgboost",
+    "keras",
 ]
 
 _ModelType = TypeVar("_ModelType", bound=SupportedModelType)
@@ -202,6 +206,11 @@ class SentenceTransformersSaveOptions(BaseModelSaveOption):
     batch_size: NotRequired[int]
 
 
+class KerasSaveOptions(BaseModelSaveOption):
+    target_methods: NotRequired[Sequence[str]]
+    cuda_version: NotRequired[str]
+
+
 ModelSaveOption = Union[
     BaseModelSaveOption,
     CatBoostModelSaveOptions,
@@ -216,6 +225,7 @@ ModelSaveOption = Union[
     MLFlowSaveOptions,
     HuggingFaceSaveOptions,
     SentenceTransformersSaveOptions,
+    KerasSaveOptions,
 ]
 
 
@@ -276,6 +286,10 @@ class SentenceTransformersLoadOptions(BaseModelLoadOption):
     device: NotRequired[str]
 
 
+class KerasLoadOptions(BaseModelLoadOption):
+    use_gpu: NotRequired[bool]
+
+
 ModelLoadOption = Union[
     BaseModelLoadOption,
     CatBoostModelLoadOptions,
@@ -290,6 +304,7 @@ ModelLoadOption = Union[
     MLFlowLoadOptions,
     HuggingFaceLoadOptions,
     SentenceTransformersLoadOptions,
+    KerasLoadOptions,
 ]
 
 

snowflake/ml/modeling/_internal/snowpark_implementations/snowpark_handlers.py

@@ -199,8 +199,21 @@ class SnowparkTransformHandlers:
         if expected_output_cols_type == "":
             expected_output_cols_type = "string"
         assert expected_output_cols_type is not None
+
+        # If there is only one output column, the UDF might have generate complex objects (lists, dicts).
+        # In such cases, we attempt to not do explicit cast. (Example: PolynomialFeatures.transform)
+        try_parse_object = len(expected_output_cols) == 1 and expected_output_cols_type != "string"
         for output_feature in expected_output_cols:
-            output_cols.append(F.col(INTERMEDIATE_OBJ_NAME)[output_feature].astype(expected_output_cols_type))
+            column_expr = F.col(INTERMEDIATE_OBJ_NAME)[output_feature]
+
+            if try_parse_object and df_res.count() > 0:
+                # Only do type casting if it's not an array
+                if not df_res.select(F.is_array(column_expr)).first()[0]:
+                    column_expr = column_expr.astype(expected_output_cols_type)
+            else:
+                column_expr = column_expr.astype(expected_output_cols_type)
+
+            output_cols.append(column_expr)
             output_col_names.append(identifier.get_inferred_name(output_feature))
 
         # Extract output from INTERMEDIATE_OBJ_NAME and drop that column

snowflake/ml/modeling/pipeline/pipeline.py

@@ -854,6 +854,7 @@ class Pipeline(base.BaseTransformer):
         # Create a fitted sklearn pipeline object by translating each non-estimator step in pipeline with with
         # a fitted column transformer.
         sksteps = []
+        i = 0
         for i, (name, trans) in enumerate(self._get_transformers()):
             if isinstance(trans, base.BaseTransformer):
                 trans = self._construct_fitted_column_transformer_object(
@@ -899,7 +900,23 @@ class Pipeline(base.BaseTransformer):
         if estimator_step:
             estimator_signatures = estimator_step[1].model_signatures
             for method, signature in estimator_signatures.items():
-                self._model_signature_dict[method] = ModelSignature(inputs=inputs_signature, outputs=signature.outputs)
+                # Add the inferred input signature to the model signature dictionary for each method
+                self._model_signature_dict[method] = ModelSignature(
+                    inputs=inputs_signature,
+                    outputs=(
+                        # If _drop_input_cols is True, do not include any input columns in the output signature
+                        []
+                        if self._drop_input_cols
+                        else [
+                            # Include input columns in the output signature if they are not already present
+                            # Those already present means they are overwritten by the output of the estimator
+                            spec
+                            for spec in inputs_signature
+                            if spec.name not in [_spec.name for _spec in signature.outputs]
+                        ]
+                    )
+                    + signature.outputs,  # Append the existing output signature
+                )
 
     @property
     def model_signatures(self) -> Dict[str, ModelSignature]:

snowflake/ml/modeling/preprocessing/polynomial_features.py

@@ -337,7 +337,7 @@ class PolynomialFeatures(BaseTransformer):
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()   
                                 
         if isinstance(dataset, DataFrame):
-            expected_type_inferred = ""
+            expected_type_inferred = "float"
             # when it is classifier, infer the datatype from label columns
             if expected_type_inferred == "" and 'predict' in self.model_signatures:
                 # Batch inference takes a single expected output column type. Use the first columns type for now.
@@ -415,7 +415,7 @@ class PolynomialFeatures(BaseTransformer):
         # are specific to the type of dataset used. 
         transform_kwargs: BatchInferenceKwargsTypedDict = dict()
         if isinstance(dataset, DataFrame):
-            expected_dtype = ""
+            expected_dtype = "float"
             if False:  # is child of _BaseHeterogeneousEnsemble
                 # transform() method of HeterogeneousEnsemble estimators return responses of varying shapes
                 # from (n_samples, n_estimators) to (n_samples, n_estimators * n_classes) (and everything in between)

snowflake/ml/registry/registry.py

@@ -78,7 +78,7 @@ class Registry:
             session, database_name=self._database_name, schema_name=self._schema_name
         )
 
-        self.enable_monitoring = options.get("enable_monitoring", False) if options else False
+        self.enable_monitoring = options.get("enable_monitoring", True) if options else True
         if self.enable_monitoring:
             monitor_statement_params = telemetry.get_statement_params(
                 project=telemetry.TelemetryProject.MLOPS.value,
@@ -162,8 +162,12 @@ class Registry:
                 - relax_version: Whether to relax the version constraints of the dependencies when running in the
                     Warehouse. It detects any ==x.y.z in specifiers and replaced with >=x.y, <(x+1). Defaults to True.
                 - function_type: Set the method function type globally. To set method function types individually see
-                  function_type in model_options.
-                - method_options: Per-method saving options including:
+                    function_type in model_options.
+                - method_options: Per-method saving options. This dictionary has method names as keys and dictionary
+                    values with the desired options.
+
+                    The following are the available method options:
+
                     - case_sensitive: Indicates whether the method and its signature should be case sensitive.
                         This means when you refer the method in the SQL, you need to double quote it.
                         This will be helpful if you need case to tell apart your methods or features, or you have
@@ -283,7 +287,11 @@ class Registry:
                     Warehouse. It detects any ==x.y.z in specifiers and replaced with >=x.y, <(x+1). Defaults to True.
                 - function_type: Set the method function type globally. To set method function types individually see
                   function_type in model_options.
-                - method_options: Per-method saving options including:
+                - method_options: Per-method saving options. This dictionary has method names as keys and dictionary
+                    values with the desired options. See the example below.
+
+                    The following are the available method options:
+
                     - case_sensitive: Indicates whether the method and its signature should be case sensitive.
                         This means when you refer the method in the SQL, you need to double quote it.
                         This will be helpful if you need case to tell apart your methods or features, or you have
@@ -294,6 +302,28 @@ class Registry:
 
         Returns:
             ModelVersion: ModelVersion object corresponding to the model just logged.
+
+        Example::
+
+            from snowflake.ml.registry import Registry
+
+            # create a session
+            session = ...
+
+            registry = Registry(session=session)
+
+            # Define `method_options` for each inference method if needed.
+            method_options={
+              "predict": {
+                "case_sensitive": True
+              }
+            }
+
+            registry.log_model(
+              model=model,
+              model_name="my_model",
+              method_options=method_options,
+            )
         """
         statement_params = telemetry.get_statement_params(
             project=_TELEMETRY_PROJECT,

snowflake/ml/version.py

@@ -1 +1 @@
-VERSION="1.7.4"
+VERSION="1.7.5"

{snowflake_ml_python-1.7.4.dist-info → snowflake_ml_python-1.7.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: snowflake-ml-python
-Version: 1.7.4
+Version: 1.7.5
 Summary: The machine learning client library that is used for interacting with Snowflake to build machine learning solutions.
 Author-email: "Snowflake, Inc" <support@snowflake.com>
 License: 
@@ -223,13 +223,14 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Database
 Classifier: Topic :: Software Development
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: <3.12,>=3.9
+Requires-Python: <3.13,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: absl-py<2,>=0.15
@@ -257,39 +258,40 @@ Requires-Dist: typing-extensions<5,>=4.1.0
 Requires-Dist: xgboost<3,>=1.7.3
 Provides-Extra: all
 Requires-Dist: catboost<2,>=1.2.0; extra == "all"
-Requires-Dist: huggingface_hub<0.26; extra == "all"
+Requires-Dist: keras<4,>=2.0.0; extra == "all"
 Requires-Dist: lightgbm<5,>=4.1.0; extra == "all"
 Requires-Dist: mlflow<3,>=2.16.0; extra == "all"
-Requires-Dist: peft<1,>=0.5.0; extra == "all"
-Requires-Dist: sentence-transformers<3,>=2.2.2; extra == "all"
-Requires-Dist: sentencepiece<1,>=0.1.95; extra == "all"
+Requires-Dist: sentence-transformers<3,>=2.7.0; extra == "all"
+Requires-Dist: sentencepiece<0.2.0,>=0.1.95; extra == "all"
 Requires-Dist: shap<1,>=0.46.0; extra == "all"
-Requires-Dist: tensorflow<3,>=2.12.0; extra == "all"
-Requires-Dist: tokenizers<1,>=0.10; extra == "all"
-Requires-Dist: torch<2.3.0,>=2.0.1; extra == "all"
+Requires-Dist: tensorflow<3,>=2.17.0; extra == "all"
+Requires-Dist: tokenizers<1,>=0.15.1; extra == "all"
+Requires-Dist: torch<3,>=2.0.1; extra == "all"
 Requires-Dist: torchdata<1,>=0.4; extra == "all"
-Requires-Dist: transformers<5,>=4.32.1; extra == "all"
+Requires-Dist: transformers<5,>=4.37.2; extra == "all"
 Provides-Extra: catboost
 Requires-Dist: catboost<2,>=1.2.0; extra == "catboost"
+Provides-Extra: keras
+Requires-Dist: keras<4,>=2.0.0; extra == "keras"
+Requires-Dist: tensorflow<3,>=2.17.0; extra == "keras"
+Requires-Dist: torch<3,>=2.0.1; extra == "keras"
 Provides-Extra: lightgbm
 Requires-Dist: lightgbm<5,>=4.1.0; extra == "lightgbm"
-Provides-Extra: llm
-Requires-Dist: peft<1,>=0.5.0; extra == "llm"
 Provides-Extra: mlflow
 Requires-Dist: mlflow<3,>=2.16.0; extra == "mlflow"
 Provides-Extra: shap
 Requires-Dist: shap<1,>=0.46.0; extra == "shap"
 Provides-Extra: tensorflow
-Requires-Dist: tensorflow<3,>=2.12.0; extra == "tensorflow"
+Requires-Dist: tensorflow<3,>=2.17.0; extra == "tensorflow"
 Provides-Extra: torch
-Requires-Dist: torch<2.3.0,>=2.0.1; extra == "torch"
+Requires-Dist: torch<3,>=2.0.1; extra == "torch"
 Requires-Dist: torchdata<1,>=0.4; extra == "torch"
 Provides-Extra: transformers
-Requires-Dist: huggingface_hub<0.26; extra == "transformers"
-Requires-Dist: sentence-transformers<3,>=2.2.2; extra == "transformers"
-Requires-Dist: sentencepiece<1,>=0.1.95; extra == "transformers"
-Requires-Dist: tokenizers<1,>=0.10; extra == "transformers"
-Requires-Dist: transformers<5,>=4.32.1; extra == "transformers"
+Requires-Dist: sentence-transformers<3,>=2.7.0; extra == "transformers"
+Requires-Dist: sentencepiece<0.2.0,>=0.1.95; extra == "transformers"
+Requires-Dist: tokenizers<1,>=0.15.1; extra == "transformers"
+Requires-Dist: torch<3,>=2.0.1; extra == "transformers"
+Requires-Dist: transformers<5,>=4.37.2; extra == "transformers"
 
 # Snowpark ML
 
@@ -346,7 +348,7 @@ If you don't have a Snowflake account yet, you can [sign up for a 30-day free tr
 Follow the [installation instructions](https://docs.snowflake.com/en/developer-guide/snowpark-ml/index#installing-snowpark-ml)
 in the Snowflake documentation.
 
-Python versions 3.9 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
+Python versions 3.9 to 3.12 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
 [anaconda](https://www.anaconda.com/) to create a Conda environment (recommended),
 or [virtualenv](https://docs.python.org/3/tutorial/venv.html) to create a virtual environment.
 
@@ -399,28 +401,54 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
-## 1.7.4
+## 1.7.5
+
+- Support Python 3.12.
+- Explainability: Support native and snowml sklearn pipeline
+
+### Bug Fixes
+
+- Registry: Fixed a compatibility issue when using `snowflake-ml-python` 1.7.0 or greater to save a `tensorflow.keras`
+  model with `keras` 2.x, if `relax_version` is set or default to True, and newer version of `snowflake-ml-python`
+  is available in Snowflake Anaconda Channel, model could not be run in Snowflake. If you have such model, you could
+  use the latest version of `snowflake-ml-python` and call `ModelVersion.load` to load it back, and re-log it.
+  Alternatively, you can prevent this issue by setting `relax_version=False` when saving the model.
+- Registry: Removed the validation that disallows data that does not have non-null values being passed to
+  `ModelVersion.run`.
+- ML Job (PrPr): No longer require CREATE STAGE privilege if `stage_name` points to an existing stage
+- ML Job (PrPr): Fixed a bug causing some payload source and entrypoint path
+  combinations to be erroneously rejected with
+  `ValueError(f"{self.entrypoint} must be a subpath of {self.source}")`
+- ML Job (PrPr): Fixed a bug in Ray cluster startup config which caused certain Runtime APIs to fail
+
+### Behavior Change
+
+### New Features
+
+- Registry: Added support for handling Hugging Face model configurations with auto-mapping functionality.
+- Registry: Added support for `keras` 3.x model with `tensorflow` and `pytorch` backend
+- ML Job (PrPr): Support any serializable (pickleable) argument for `@remote` decorated functions
+
+## 1.7.4 (01-28-2025)
 
 - FileSet: The `snowflake.ml.fileset.FileSet` has been deprecated and will be removed in a future version.
   Use [snowflake.ml.dataset.Dataset](https://docs.snowflake.com/en/developer-guide/snowflake-ml/dataset) and
   [snowflake.ml.data.DataConnector](https://docs.snowflake.com/en/developer-guide/snowpark-ml/reference/latest/api/data/snowflake.ml.data.data_connector.DataConnector)
   instead.
+- Registry: `ModelVersion.run` on a service would require redeploying the service once account opts into nested function.
 
 ### Bug Fixes
 
 - Registry: Fixed an issue that the hugging face pipeline is loaded using incorrect dtype.
 - Registry: Fixed an issue that only 1 row is used when infer the model signature in the modeling model.
 
-### Behavior Changes
-
-- Registry: `ModelVersion.run` on a service would require redeploying the service once account opts into nested function.
-
 ### New Features
 
 - Add new `snowflake.ml.jobs` preview API for running headless workloads on SPCS using
   [Container Runtime for ML](https://docs.snowflake.com/en/developer-guide/snowflake-ml/container-runtime-ml)
 - Added `guardrails` option to Cortex `complete` function, enabling
   [Cortex Guard](https://docs.snowflake.com/en/user-guide/snowflake-cortex/llm-functions#cortex-guard) support
+- Model Monitoring: Expose Model Monitoring Python API by default.
 
 ## 1.7.3 (2025-01-08)
 
@@ -428,6 +456,7 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 - Bumped the requirements of `fsspec` and `s3fs` to `>=2024.6.1,<2026`
 - Bumped the requirement of `mlflow` to `>=2.16.0, <3`
 - Registry: Support 500+ features for model registry
+- Feature Store: Add support for `cluster_by` for feature views.
 
 ### Bug Fixes
 
@@ -545,6 +574,10 @@ class ExamplePipelineModel(custom_model.CustomModel):
 - Data Connector: Add the option of passing a `None` sized batch to `to_torch_dataset` for better
 interoperability with PyTorch DataLoader.
 - Model Registry: Support [pandas.CategoricalDtype](https://pandas.pydata.org/docs/reference/api/pandas.CategoricalDtype.html#pandas-categoricaldtype)
+  - Limitations:
+    - The native categorical data handling handling by XGBoost using `enable_categorical=True` is not supported.
+    Instead please use [`sklearn.pipeline`](https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html)
+    to preprocess the categorical datatype and log the pipeline with the XGBoost model.
 - Registry: It is now possible to pass `signatures` and `sample_input_data` at the same time to capture background
 data from explainablity and data lineage.