snowflake-ml-python 1.6.4__py3-none-any.whl → 1.7.0__py3-none-any.whl

snowflake/ml/_internal/telemetry.py

@@ -544,7 +544,7 @@ def send_api_usage_telemetry(
                 if not isinstance(e, snowml_exceptions.SnowflakeMLException):
                     # already handled via a nested decorated function
                     if getattr(e, "_snowflake_ml_handled", False):
-                        raise e
+                        raise
                     if isinstance(e, snowpark_exceptions.SnowparkClientException):
                         me = snowml_exceptions.SnowflakeMLException(
                             error_code=error_codes.INTERNAL_SNOWPARK_ERROR, original_exception=e
@@ -558,7 +558,9 @@ def send_api_usage_telemetry(
                 telemetry_args["error"] = repr(me)
                 telemetry_args["error_code"] = me.error_code
                 me.original_exception._snowflake_ml_handled = True  # type: ignore[attr-defined]
-                if me.suppress_source_trace:
+                if e is not me:
+                    raise  # Directly raise non-wrapped exceptions to preserve original stacktrace
+                elif me.suppress_source_trace:
                     raise me.original_exception from None
                 else:
                     raise me.original_exception from e

snowflake/ml/_internal/utils/import_utils.py

@@ -19,6 +19,33 @@ class MissingOptionalDependency:
         raise ImportError(f"Unable to import {self._dep_name}.")
 
 
+def import_with_fallbacks(*targets: str) -> Any:
+    """Import a module which may be located in different locations.
+
+    This method will iterate through the provided targets, returning the first available import target.
+    If none of the requested import targets are available, ImportError will be raised.
+
+    Args:
+        targets: Strings representing the target which needs to be imported. It should be a list of symbol name
+            joined by dot. Some valid examples:
+                - <some_package>
+                - <some_module>
+                - <some_package>.<some_module>
+                - <some_module>.<some_symbol>
+
+    Returns:
+        The imported target.
+
+    Raises:
+        ImportError: None of the requested targets are available
+    """
+    for target in targets:
+        result, success = import_or_get_dummy(target)
+        if success:
+            return result
+    raise ImportError(f"None of the requested targets could be imported. Requested: {', '.join(targets)}")
+
+
 def import_or_get_dummy(target: str) -> Tuple[Any, bool]:
     """Try to import the the given target or return a dummy object.
 
@@ -43,6 +70,10 @@ def import_or_get_dummy(target: str) -> Tuple[Any, bool]:
     except ImportError:
         pass
 
+    # Don't try symbol resolution if target doesn't contain '.'
+    if "." not in target:
+        return (MissingOptionalDependency(target), False)
+
     # Try to import the target as a symbol
     try:
         res = _try_import_symbol(target)

snowflake/ml/_internal/utils/snowpark_dataframe_utils.py

@@ -121,3 +121,16 @@ def cast_snowpark_dataframe_column_types(df: snowpark.DataFrame) -> snowpark.Dat
             selected_cols.append(functions.col(src))
     df = df.select(selected_cols)
     return df
+
+
+def is_single_query_snowpark_dataframe(df: snowpark.DataFrame) -> bool:
+    """Check if dataframe only has a single query.
+
+    Args:
+        df: A snowpark dataframe.
+
+    Returns:
+        true if there is only on query in the dataframe and no post_actions,
+        false otherwise.
+    """
+    return len(df.queries["queries"]) == 1 and len(df.queries["post_actions"]) == 0

snowflake/ml/data/_internal/arrow_ingestor.py

@@ -198,7 +198,15 @@ def _record_batch_to_arrays(rb: pa.RecordBatch) -> Dict[str, npt.NDArray[Any]]:
     for column, column_schema in zip(rb, rb.schema):
         # zero_copy_only=False because of nans. Ideally nans should have been imputed in feature engineering.
         array = column.to_numpy(zero_copy_only=False)
+        # If this column is a list, use the underlying type from the list values. Since this is just one column,
+        # there should only be one type within the list.
+        # TODO: Refactor to reduce data copies.
+        if isinstance(column_schema.type, pa.ListType):
+            # Update dtype of outer array:
+            array = np.array(array.tolist(), dtype=column_schema.type.value_type.to_pandas_dtype())
+
         batch_dict[column_schema.name] = array
+
     return batch_dict
 
 

snowflake/ml/data/data_connector.py

@@ -159,7 +159,7 @@ class DataConnector:
         func_params_to_log=["batch_size", "shuffle", "drop_last_batch"],
     )
     def to_torch_dataset(
-        self, *, batch_size: int = 1, shuffle: bool = False, drop_last_batch: bool = True
+        self, *, batch_size: Optional[int] = None, shuffle: bool = False, drop_last_batch: bool = True
     ) -> "torch_data.IterableDataset":  # type: ignore[type-arg]
         """Transform the Snowflake data into a PyTorch Iterable Dataset to be used with a DataLoader.
 

snowflake/ml/data/torch_utils.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, Iterator, List, Union
+from typing import Any, Dict, Iterator, List, Optional, Union
 
 import numpy as np
 import numpy.typing as npt
@@ -14,17 +14,21 @@ class TorchDatasetWrapper(torch.utils.data.IterableDataset[Dict[str, Any]]):
         self,
         ingestor: data_ingestor.DataIngestor,
         *,
-        batch_size: int,
+        batch_size: Optional[int],
         shuffle: bool = False,
         drop_last: bool = False,
-        squeeze_outputs: bool = True
     ) -> None:
         """Not intended for direct usage. Use DataConnector.to_torch_dataset() instead"""
+        squeeze = False
+        if batch_size is None:
+            batch_size = 1
+            squeeze = True
+
         self._ingestor = ingestor
         self._batch_size = batch_size
         self._shuffle = shuffle
         self._drop_last = drop_last
-        self._squeeze_outputs = squeeze_outputs
+        self._squeeze_outputs = squeeze
 
     def __iter__(self) -> Iterator[Dict[str, Union[npt.NDArray[Any], List[Any]]]]:
         max_idx = 0
@@ -43,15 +47,7 @@ class TorchDatasetWrapper(torch.utils.data.IterableDataset[Dict[str, Any]]):
         ):
             # Skip indices during multi-process data loading to prevent data duplication
             if counter == filter_idx:
-                # Basic preprocessing on batch values: squeeze away extra dimensions
-                # and convert object arrays (e.g. strings) to lists
-                if self._squeeze_outputs:
-                    yield {
-                        k: (v.squeeze().tolist() if v.dtype == np.object_ else v.squeeze()) for k, v in batch.items()
-                    }
-                else:
-                    yield batch  # type: ignore[misc]
-
+                yield {k: _preprocess_array(v, squeeze=self._squeeze_outputs) for k, v in batch.items()}
             if counter < max_idx:
                 counter += 1
             else:
@@ -65,4 +61,27 @@ class TorchDataPipeWrapper(TorchDatasetWrapper, torch.utils.data.IterDataPipe[Di
         self, ingestor: data_ingestor.DataIngestor, *, batch_size: int, shuffle: bool = False, drop_last: bool = False
     ) -> None:
         """Not intended for direct usage. Use DataConnector.to_torch_datapipe() instead"""
-        super().__init__(ingestor, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, squeeze_outputs=False)
+        super().__init__(ingestor, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last)
+
+
+def _preprocess_array(arr: npt.NDArray[Any], squeeze: bool = False) -> Union[npt.NDArray[Any], List[np.object_]]:
+    """Preprocesses batch column values."""
+    single_dimensional = arr.ndim < 2 and not arr.dtype == np.object_
+
+    # Squeeze away all extra dimensions. This is only used when batch_size = None.
+    if squeeze:
+        arr = arr.squeeze(axis=0)
+
+    # For single dimensional data,
+    if single_dimensional:
+        axis = 0 if arr.ndim == 0 else 1
+        arr = np.expand_dims(arr, axis=axis)
+
+    # Handle object arrays.
+    if arr.dtype == np.object_:
+        array_list = arr.tolist()
+        # If this is an array of arrays, convert the dtype to match the underlying array.
+        # Otherwise, if this is a numpy array of strings, convert the array to a list.
+        arr = np.array(array_list, dtype=arr.flat[0].dtype) if isinstance(arr.flat[0], np.ndarray) else array_list
+
+    return arr

snowflake/ml/feature_store/examples/airline_features/features/plane_features.py

@@ -6,15 +6,17 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about airplane model."""
     query = session.sql(
-        """
+        f"""
         select
            PLANE_MODEL,
            SEATING_CAPACITY
         from
-            PLANE_MODEL_ATTRIBUTES
+            {database}.{schema}.PLANE_MODEL_ATTRIBUTES
         """
     )
 

snowflake/ml/feature_store/examples/airline_features/features/weather_features.py

@@ -6,10 +6,12 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about airport weather."""
     query = session.sql(
-        """
+        f"""
         select
             DATETIME_UTC AS TS,
             AIRPORT_ZIP_CODE,
@@ -21,9 +23,9 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
             sum(RAIN_MM_H) over (
                 partition by AIRPORT_ZIP_CODE
                 order by DATETIME_UTC
-                range between interval '1 day' preceding and current row
+                range between interval '60 minutes' preceding and current row
             ) RAIN_SUM_60M
-        from AIRPORT_WEATHER_STATION
+        from {database}.{schema}.AIRPORT_WEATHER_STATION
         """
     )
 
@@ -37,6 +39,6 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
     ).attach_feature_desc(
         {
             "RAIN_SUM_30M": "The sum of rain fall over past 30 minutes for one zipcode.",
-            "RAIN_SUM_60M": "The sum of rain fall over past 1 day for one zipcode.",
+            "RAIN_SUM_60M": "The sum of rain fall over past 1 hour for one zipcode.",
         }
     )

snowflake/ml/feature_store/examples/citibike_trip_features/features/station_feature.py

@@ -8,7 +8,9 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about trip station."""
     query = session.sql(
         f"""
@@ -17,7 +19,7 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
             count(end_station_id) as f_count,
             avg(end_station_latitude) as f_avg_latitude,
             avg(end_station_longitude) as f_avg_longtitude
-        from {source_tables[0]}
+        from {database}.{schema}.{source_tables[0]}
         group by end_station_id
         """
     )

snowflake/ml/feature_store/examples/citibike_trip_features/features/trip_feature.py

@@ -6,7 +6,9 @@ from snowflake.snowpark import DataFrame, Session, functions as F
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about trip."""
     feature_df = source_dfs[0].select(
         "trip_id",

snowflake/ml/feature_store/examples/example_helper.py

@@ -66,7 +66,9 @@ class ExampleHelper:
                 continue
             mod_path = f"{__package__}.{self._selected_example}.features.{f_name.rstrip('.py')}"
             mod = importlib.import_module(mod_path)
-            fv = mod.create_draft_feature_view(self._session, self._source_dfs, self._source_tables)
+            fv = mod.create_draft_feature_view(
+                self._session, self._source_dfs, self._source_tables, self._database_name, self._dataset_schema
+            )
             fvs.append(fv)
 
         return fvs
@@ -140,7 +142,7 @@ class ExampleHelper:
             """
         ).collect()
 
-        return [destination_table]
+        return [schema_dict["destination_table_name"]]
 
     def _load_parquet(self, schema_dict: Dict[str, str], temp_stage_name: str) -> List[str]:
         regex_pattern = schema_dict["load_files_pattern"]
@@ -173,13 +175,14 @@ class ExampleHelper:
                 dest_table_name = (
                     f"{self._database_name}.{self._dataset_schema}.{schema_dict['destination_table_name']}"
                 )
+                result.append(schema_dict["destination_table_name"])
             else:
                 regex_pattern = schema_dict["destination_table_name"]
                 dest_table_name = re.match(regex_pattern, file_name).group("table_name")  # type: ignore[union-attr]
+                result.append(dest_table_name)
                 dest_table_name = f"{self._database_name}.{self._dataset_schema}.{dest_table_name}"
 
             df.write.mode("overwrite").save_as_table(dest_table_name)
-            result.append(dest_table_name)
 
         return result
 

snowflake/ml/feature_store/examples/new_york_taxi_features/features/location_features.py

@@ -8,7 +8,9 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a draft feature view."""
     feature_df = session.sql(
         f"""
@@ -25,7 +27,7 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
                 order by TPEP_DROPOFF_DATETIME
                 range between interval '10 hours' preceding and current row
             ) AVG_FARE_10h
-        from {source_tables[0]}
+        from {database}.{schema}.{source_tables[0]}
     """
     )
 

snowflake/ml/feature_store/examples/new_york_taxi_features/features/trip_features.py

@@ -6,7 +6,9 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a draft feature view."""
     feature_df = session.sql(
         f"""
@@ -16,7 +18,7 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
             TRIP_DISTANCE,
             FARE_AMOUNT
         from
-            {source_tables[0]}
+            {database}.{schema}.{source_tables[0]}
         """
     )
 

snowflake/ml/feature_store/examples/wine_quality_features/features/managed_wine_features.py

@@ -6,7 +6,9 @@ from snowflake.snowpark import DataFrame, Session, functions as F
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about trip station."""
     feature_df = source_dfs[0].select(
         "WINE_ID",

snowflake/ml/feature_store/examples/wine_quality_features/features/static_wine_features.py

@@ -6,7 +6,9 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about trip station."""
     feature_df = source_dfs[0].select("WINE_ID", "SULPHATES", "ALCOHOL")
 

snowflake/ml/feature_store/feature_store.py

@@ -1886,8 +1886,7 @@ class FeatureStore:
         if found_dts[0]["refresh_mode"] != "INCREMENTAL":
             warnings.warn(
                 "Your pipeline won't be incrementally refreshed due to: "
-                + f"\"{found_dts[0]['refresh_mode_reason']}\". "
-                + "It will likely incurr higher cost.",
+                + f"\"{found_dts[0]['refresh_mode_reason']}\".",
                 stacklevel=2,
                 category=UserWarning,
             )

snowflake/ml/feature_store/feature_view.py

@@ -169,6 +169,7 @@ class FeatureView(lineage_node.LineageNode):
         desc: str = "",
         warehouse: Optional[str] = None,
         initialize: str = "ON_CREATE",
+        refresh_mode: str = "AUTO",
         **_kwargs: Any,
     ) -> None:
         """
@@ -196,6 +197,9 @@ class FeatureView(lineage_node.LineageNode):
                 after you register the feature view. It supports ON_CREATE (default) or ON_SCHEDULE. ON_CREATE refreshes
                 the feature view synchronously at creation. ON_SCHEDULE refreshes the feature view at the next scheduled
                 refresh. It is only effective when refresh_freq is not None.
+            refresh_mode: The refresh mode of managed feature view. The value can be 'AUTO', 'FULL' or 'INCREMENETAL'.
+                For managed feature view, the default value is 'AUTO'. For static feature view it has no effect.
+                Check https://docs.snowflake.com/en/sql-reference/sql/create-dynamic-table for for details.
             _kwargs: reserved kwargs for system generated args. NOTE: DO NOT USE.
 
         Example::
@@ -242,7 +246,7 @@ class FeatureView(lineage_node.LineageNode):
         self._schema: Optional[SqlIdentifier] = None
         self._initialize: str = initialize
         self._warehouse: Optional[SqlIdentifier] = SqlIdentifier(warehouse) if warehouse is not None else None
-        self._refresh_mode: Optional[str] = _kwargs.get("refresh_mode", "AUTO")
+        self._refresh_mode: Optional[str] = refresh_mode
         self._refresh_mode_reason: Optional[str] = None
         self._owner: Optional[str] = None
         self._validate()

snowflake/ml/model/_client/model/model_version_impl.py

@@ -614,6 +614,102 @@ class ModelVersion(lineage_node.LineageNode):
             version_name=sql_identifier.SqlIdentifier(version),
         )
 
+    @overload
+    def create_service(
+        self,
+        *,
+        service_name: str,
+        image_build_compute_pool: Optional[str] = None,
+        service_compute_pool: str,
+        image_repo: str,
+        ingress_enabled: bool = False,
+        max_instances: int = 1,
+        cpu_requests: Optional[str] = None,
+        memory_requests: Optional[str] = None,
+        gpu_requests: Optional[str] = None,
+        num_workers: Optional[int] = None,
+        max_batch_rows: Optional[int] = None,
+        force_rebuild: bool = False,
+        build_external_access_integration: Optional[str] = None,
+    ) -> str:
+        """Create an inference service with the given spec.
+
+        Args:
+            service_name: The name of the service, can be fully qualified. If not fully qualified, the database or
+                schema of the model will be used.
+            image_build_compute_pool: The name of the compute pool used to build the model inference image. It uses
+                the service compute pool if None.
+            service_compute_pool: The name of the compute pool used to run the inference service.
+            image_repo: The name of the image repository, can be fully qualified. If not fully qualified, the database
+                or schema of the model will be used.
+            ingress_enabled: If true, creates an service endpoint associated with the service. User must have
+                BIND SERVICE ENDPOINT privilege on the account.
+            max_instances: The maximum number of inference service instances to run. The same value it set to
+                MIN_INSTANCES property of the service.
+            cpu_requests: The cpu limit for CPU based inference. Can be an integer, fractional or string values. If
+                None, we attempt to utilize all the vCPU of the node.
+            memory_requests: The memory limit with for CPU based inference. Can be an integer or a fractional value, but
+                requires a unit (GiB, MiB). If None, we attempt to utilize all the memory of the node.
+            gpu_requests: The gpu limit for GPU based inference. Can be integer, fractional or string values. Use CPU
+                if None.
+            num_workers: The number of workers to run the inference service for handling requests in parallel within an
+                instance of the service. By default, it is set to 2*vCPU+1 of the node for CPU based inference and 1 for
+                GPU based inference. For GPU based inference, please see best practices before playing with this value.
+            max_batch_rows: The maximum number of rows to batch for inference. Auto determined if None. Minimum 32.
+            force_rebuild: Whether to force a model inference image rebuild.
+            build_external_access_integration: (Deprecated) The external access integration for image build. This is
+                usually permitting access to conda & PyPI repositories.
+        """
+        ...
+
+    @overload
+    def create_service(
+        self,
+        *,
+        service_name: str,
+        image_build_compute_pool: Optional[str] = None,
+        service_compute_pool: str,
+        image_repo: str,
+        ingress_enabled: bool = False,
+        max_instances: int = 1,
+        cpu_requests: Optional[str] = None,
+        memory_requests: Optional[str] = None,
+        gpu_requests: Optional[str] = None,
+        num_workers: Optional[int] = None,
+        max_batch_rows: Optional[int] = None,
+        force_rebuild: bool = False,
+        build_external_access_integrations: Optional[List[str]] = None,
+    ) -> str:
+        """Create an inference service with the given spec.
+
+        Args:
+            service_name: The name of the service, can be fully qualified. If not fully qualified, the database or
+                schema of the model will be used.
+            image_build_compute_pool: The name of the compute pool used to build the model inference image. It uses
+                the service compute pool if None.
+            service_compute_pool: The name of the compute pool used to run the inference service.
+            image_repo: The name of the image repository, can be fully qualified. If not fully qualified, the database
+                or schema of the model will be used.
+            ingress_enabled: If true, creates an service endpoint associated with the service. User must have
+                BIND SERVICE ENDPOINT privilege on the account.
+            max_instances: The maximum number of inference service instances to run. The same value it set to
+                MIN_INSTANCES property of the service.
+            cpu_requests: The cpu limit for CPU based inference. Can be an integer, fractional or string values. If
+                None, we attempt to utilize all the vCPU of the node.
+            memory_requests: The memory limit with for CPU based inference. Can be an integer or a fractional value, but
+                requires a unit (GiB, MiB). If None, we attempt to utilize all the memory of the node.
+            gpu_requests: The gpu limit for GPU based inference. Can be integer, fractional or string values. Use CPU
+                if None.
+            num_workers: The number of workers to run the inference service for handling requests in parallel within an
+                instance of the service. By default, it is set to 2*vCPU+1 of the node for CPU based inference and 1 for
+                GPU based inference. For GPU based inference, please see best practices before playing with this value.
+            max_batch_rows: The maximum number of rows to batch for inference. Auto determined if None. Minimum 32.
+            force_rebuild: Whether to force a model inference image rebuild.
+            build_external_access_integrations: The external access integrations for image build. This is usually
+                permitting access to conda & PyPI repositories.
+        """
+        ...
+
     @telemetry.send_api_usage_telemetry(
         project=_TELEMETRY_PROJECT,
         subproject=_TELEMETRY_SUBPROJECT,
@@ -638,11 +734,14 @@ class ModelVersion(lineage_node.LineageNode):
         image_repo: str,
         ingress_enabled: bool = False,
         max_instances: int = 1,
+        cpu_requests: Optional[str] = None,
+        memory_requests: Optional[str] = None,
         gpu_requests: Optional[str] = None,
         num_workers: Optional[int] = None,
         max_batch_rows: Optional[int] = None,
         force_rebuild: bool = False,
-        build_external_access_integration: str,
+        build_external_access_integration: Optional[str] = None,
+        build_external_access_integrations: Optional[List[str]] = None,
     ) -> str:
         """Create an inference service with the given spec.
 
@@ -658,6 +757,10 @@ class ModelVersion(lineage_node.LineageNode):
                 BIND SERVICE ENDPOINT privilege on the account.
             max_instances: The maximum number of inference service instances to run. The same value it set to
                 MIN_INSTANCES property of the service.
+            cpu_requests: The cpu limit for CPU based inference. Can be an integer, fractional or string values. If
+                None, we attempt to utilize all the vCPU of the node.
+            memory_requests: The memory limit with for CPU based inference. Can be an integer or a fractional value, but
+                requires a unit (GiB, MiB). If None, we attempt to utilize all the memory of the node.
             gpu_requests: The gpu limit for GPU based inference. Can be integer, fractional or string values. Use CPU
                 if None.
             num_workers: The number of workers to run the inference service for handling requests in parallel within an
@@ -665,9 +768,14 @@ class ModelVersion(lineage_node.LineageNode):
                 GPU based inference. For GPU based inference, please see best practices before playing with this value.
             max_batch_rows: The maximum number of rows to batch for inference. Auto determined if None. Minimum 32.
             force_rebuild: Whether to force a model inference image rebuild.
-            build_external_access_integration: The external access integration for image build. This is usually
+            build_external_access_integration: (Deprecated) The external access integration for image build. This is
+                usually permitting access to conda & PyPI repositories.
+            build_external_access_integrations: The external access integrations for image build. This is usually
                 permitting access to conda & PyPI repositories.
 
+        Raises:
+            ValueError: Illegal external access integration arguments.
+
         Returns:
             Result information about service creation from server.
         """
@@ -675,6 +783,20 @@ class ModelVersion(lineage_node.LineageNode):
             project=_TELEMETRY_PROJECT,
             subproject=_TELEMETRY_SUBPROJECT,
         )
+        if build_external_access_integration is not None:
+            msg = (
+                "`build_external_access_integration` is deprecated. "
+                "Please use `build_external_access_integrations` instead."
+            )
+            warnings.warn(msg, DeprecationWarning, stacklevel=2)
+            if build_external_access_integrations is not None:
+                msg = (
+                    "`build_external_access_integration` and `build_external_access_integrations` cannot be set at the"
+                    "same time. Please use `build_external_access_integrations` only."
+                )
+                raise ValueError(msg)
+            build_external_access_integrations = [build_external_access_integration]
+
         service_db_id, service_schema_id, service_id = sql_identifier.parse_fully_qualified_name(service_name)
         image_repo_db_id, image_repo_schema_id, image_repo_id = sql_identifier.parse_fully_qualified_name(image_repo)
         return self._service_ops.create_service(
@@ -696,11 +818,17 @@ class ModelVersion(lineage_node.LineageNode):
             image_repo_name=image_repo_id,
             ingress_enabled=ingress_enabled,
             max_instances=max_instances,
+            cpu_requests=cpu_requests,
+            memory_requests=memory_requests,
             gpu_requests=gpu_requests,
             num_workers=num_workers,
             max_batch_rows=max_batch_rows,
             force_rebuild=force_rebuild,
-            build_external_access_integration=sql_identifier.SqlIdentifier(build_external_access_integration),
+            build_external_access_integrations=(
+                None
+                if build_external_access_integrations is None
+                else [sql_identifier.SqlIdentifier(eai) for eai in build_external_access_integrations]
+            ),
             statement_params=statement_params,
         )
 
@@ -710,7 +838,7 @@ class ModelVersion(lineage_node.LineageNode):
     )
     def list_services(
         self,
-    ) -> List[str]:
+    ) -> pd.DataFrame:
         """List all the service names using this model version.
 
         Returns:
@@ -722,12 +850,18 @@ class ModelVersion(lineage_node.LineageNode):
             subproject=_TELEMETRY_SUBPROJECT,
         )
 
-        return self._model_ops.list_inference_services(
-            database_name=None,
-            schema_name=None,
-            model_name=self._model_name,
-            version_name=self._version_name,
-            statement_params=statement_params,
+        return pd.DataFrame(
+            self._model_ops.list_inference_services(
+                database_name=None,
+                schema_name=None,
+                model_name=self._model_name,
+                version_name=self._version_name,
+                statement_params=statement_params,
+            ),
+            columns=[
+                self._model_ops.INFERENCE_SERVICE_NAME_COL_NAME,
+                self._model_ops.INFERENCE_SERVICE_ENDPOINT_COL_NAME,
+            ],
         )
 
     @telemetry.send_api_usage_telemetry(