snowflake-ml-python 1.8.3__tar.gz → 1.8.4__tar.gz

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/CHANGELOG.md

@@ -1,5 +1,30 @@
 # Release History
 
+## 1.8.4
+
+### Bug Fixes
+
+- Registry: Default `enable_explainability` to True when the model can be deployed to Warehouse.
+- Registry: Add `custom_model.partitioned_api` decorator and deprecate `partitioned_inference_api`.
+- Registry: Fixed a bug when logging pytroch and tensorflow models that caused
+  `UnboundLocalError: local variable 'multiple_inputs' referenced before assignment`.
+
+### Breaking change
+
+- ML Job: Updated property `id` to be fully qualified name; Introduced new property `name` to represent the ML Job name
+- ML Job: Modified `list_jobs()` to return ML Job `name` instead of `id`
+- Registry: Error in `log_model` if `enable_explainability` is True and model is only deployed to
+   Snowpark Container Services, instead of just user warning.
+
+### New Features
+
+- ML Job: Extend `@remote` function decorator, `submit_file()` and `submit_directory()` to accept `database` and
+  `schema` parameters
+- ML Job: Support querying by fully qualified name in `get_job()`
+- Explainability: Added visualization functions to `snowflake.ml.monitoring` to plot explanations in notebooks.
+- Explainability: Support explain for categorical transforms for sklearn pipeline
+- Support categorical type for `xgboost.DMatrix` inputs.
+
 ## 1.8.3
 
 ### Bug Fixes
@@ -13,6 +38,7 @@
   as a list of strings
 - Registry: Support `ModelVersion.run_job` to run inference with a single-node Snowpark Container Services job.
 - DataConnector: Removed PrPr decorators
+- Registry: Default the target platform to warehouse when logging a partitioned model.
 
 ## 1.8.2
 

{snowflake_ml_python-1.8.3/snowflake_ml_python.egg-info → snowflake_ml_python-1.8.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-ml-python
-Version: 1.8.3
+Version: 1.8.4
 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: 
@@ -236,7 +236,7 @@ License-File: LICENSE.txt
 Requires-Dist: absl-py<2,>=0.15
 Requires-Dist: anyio<5,>=3.5.0
 Requires-Dist: cachetools<6,>=3.1.1
-Requires-Dist: cloudpickle<3,>=2.0.0
+Requires-Dist: cloudpickle>=2.0.0
 Requires-Dist: cryptography
 Requires-Dist: fsspec[http]<2026,>=2024.6.1
 Requires-Dist: importlib_resources<7,>=6.1.1
@@ -250,27 +250,31 @@ Requires-Dist: pytimeparse<2,>=1.1.8
 Requires-Dist: pyyaml<7,>=6.0
 Requires-Dist: retrying<2,>=1.3.3
 Requires-Dist: s3fs<2026,>=2024.6.1
-Requires-Dist: scikit-learn<1.6,>=1.4
+Requires-Dist: scikit-learn<1.6
 Requires-Dist: scipy<2,>=1.9
-Requires-Dist: snowflake-connector-python[pandas]<4,>=3.12.0
+Requires-Dist: shap<1,>=0.46.0
+Requires-Dist: snowflake-connector-python[pandas]<4,>=3.14.0
 Requires-Dist: snowflake-snowpark-python!=1.26.0,<2,>=1.17.0
 Requires-Dist: snowflake.core<2,>=1.0.2
 Requires-Dist: sqlparse<1,>=0.4
 Requires-Dist: typing-extensions<5,>=4.1.0
-Requires-Dist: xgboost<3,>=1.7.3
 Provides-Extra: all
+Requires-Dist: altair<6,>=5; extra == "all"
 Requires-Dist: catboost<2,>=1.2.0; 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: sentence-transformers<4,>=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: streamlit<2,>=1.44.0; 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,>=4.39.3; extra == "all"
+Requires-Dist: xgboost<3,>=1.7.3; extra == "all"
+Provides-Extra: altair
+Requires-Dist: altair<6,>=5; extra == "altair"
 Provides-Extra: catboost
 Requires-Dist: catboost<2,>=1.2.0; extra == "catboost"
 Provides-Extra: keras
@@ -281,8 +285,8 @@ Provides-Extra: lightgbm
 Requires-Dist: lightgbm<5,>=4.1.0; extra == "lightgbm"
 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: streamlit
+Requires-Dist: streamlit<2,>=1.44.0; extra == "streamlit"
 Provides-Extra: tensorflow
 Requires-Dist: tensorflow<3,>=2.17.0; extra == "tensorflow"
 Provides-Extra: torch
@@ -294,6 +298,8 @@ 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,>=4.39.3; extra == "transformers"
+Provides-Extra: xgboost
+Requires-Dist: xgboost<3,>=1.7.3; extra == "xgboost"
 Dynamic: license-file
 
 # Snowpark ML
@@ -404,6 +410,31 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
+## 1.8.4
+
+### Bug Fixes
+
+- Registry: Default `enable_explainability` to True when the model can be deployed to Warehouse.
+- Registry: Add `custom_model.partitioned_api` decorator and deprecate `partitioned_inference_api`.
+- Registry: Fixed a bug when logging pytroch and tensorflow models that caused
+  `UnboundLocalError: local variable 'multiple_inputs' referenced before assignment`.
+
+### Breaking change
+
+- ML Job: Updated property `id` to be fully qualified name; Introduced new property `name` to represent the ML Job name
+- ML Job: Modified `list_jobs()` to return ML Job `name` instead of `id`
+- Registry: Error in `log_model` if `enable_explainability` is True and model is only deployed to
+   Snowpark Container Services, instead of just user warning.
+
+### New Features
+
+- ML Job: Extend `@remote` function decorator, `submit_file()` and `submit_directory()` to accept `database` and
+  `schema` parameters
+- ML Job: Support querying by fully qualified name in `get_job()`
+- Explainability: Added visualization functions to `snowflake.ml.monitoring` to plot explanations in notebooks.
+- Explainability: Support explain for categorical transforms for sklearn pipeline
+- Support categorical type for `xgboost.DMatrix` inputs.
+
 ## 1.8.3
 
 ### Bug Fixes
@@ -417,6 +448,7 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
   as a list of strings
 - Registry: Support `ModelVersion.run_job` to run inference with a single-node Snowpark Container Services job.
 - DataConnector: Removed PrPr decorators
+- Registry: Default the target platform to warehouse when logging a partitioned model.
 
 ## 1.8.2
 

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/pyproject.toml

@@ -8,7 +8,7 @@ description = "The machine learning client library that is used for interacting
 classifiers = [ "Development Status :: 5 - Production/Stable", "Environment :: Console", "Environment :: Other Environment", "Intended Audience :: Developers", "Intended Audience :: Education", "Intended Audience :: Information Technology", "Intended Audience :: System Administrators", "License :: OSI Approved :: Apache Software License", "Operating System :: OS Independent", "Programming Language :: Python :: 3.9", "Programming Language :: Python :: 3.10", "Programming Language :: Python :: 3.11", "Programming Language :: Python :: 3.12", "Topic :: Database", "Topic :: Software Development", "Topic :: Software Development :: Libraries", "Topic :: Software Development :: Libraries :: Application Frameworks", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Scientific/Engineering :: Information Analysis",]
 requires-python = ">=3.9, <3.13"
 dynamic = [ "version", "readme",]
-dependencies = [ "absl-py>=0.15,<2", "anyio>=3.5.0,<5", "cachetools>=3.1.1,<6", "cloudpickle>=2.0.0,<3", "cryptography", "fsspec[http]>=2024.6.1,<2026", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<2", "packaging>=20.9,<25", "pandas>=1.0.0,<3", "pyarrow", "pydantic>=2.8.2, <3", "pyjwt>=2.0.0, <3", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2024.6.1,<2026", "scikit-learn>=1.4,<1.6", "scipy>=1.9,<2", "snowflake-connector-python[pandas]>=3.12.0,<4", "snowflake-snowpark-python>=1.17.0,<2,!=1.26.0", "snowflake.core>=1.0.2,<2", "sqlparse>=0.4,<1", "typing-extensions>=4.1.0,<5", "xgboost>=1.7.3,<3",]
+dependencies = [ "absl-py>=0.15,<2", "anyio>=3.5.0,<5", "cachetools>=3.1.1,<6", "cloudpickle>=2.0.0", "cryptography", "fsspec[http]>=2024.6.1,<2026", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<2", "packaging>=20.9,<25", "pandas>=1.0.0,<3", "pyarrow", "pydantic>=2.8.2, <3", "pyjwt>=2.0.0, <3", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2024.6.1,<2026", "scikit-learn<1.6", "scipy>=1.9,<2", "shap>=0.46.0,<1", "snowflake-connector-python[pandas]>=3.14.0,<4", "snowflake-snowpark-python>=1.17.0,<2,!=1.26.0", "snowflake.core>=1.0.2,<2", "sqlparse>=0.4,<1", "typing-extensions>=4.1.0,<5",]
 [[project.authors]]
 name = "Snowflake, Inc"
 email = "support@snowflake.com"
@@ -24,15 +24,17 @@ Issues = "https://github.com/snowflakedb/snowflake-ml-python/issues"
 Changelog = "https://github.com/snowflakedb/snowflake-ml-python/blob/master/CHANGELOG.md"
 
 [project.optional-dependencies]
-all = [ "catboost>=1.2.0, <2", "keras>=2.0.0,<4", "lightgbm>=4.1.0, <5", "mlflow>=2.16.0, <3", "sentence-transformers>=2.7.0,<4", "sentencepiece>=0.1.95,<0.2.0", "shap>=0.46.0,<1", "tensorflow>=2.17.0,<3", "tokenizers>=0.15.1,<1", "torch>=2.0.1,<3", "torchdata>=0.4,<1", "transformers>=4.39.3,<5",]
+all = [ "altair>=5,<6", "catboost>=1.2.0, <2", "keras>=2.0.0,<4", "lightgbm>=4.1.0, <5", "mlflow>=2.16.0, <3", "sentence-transformers>=2.7.0,<4", "sentencepiece>=0.1.95,<0.2.0", "streamlit>=1.44.0,<2", "tensorflow>=2.17.0,<3", "tokenizers>=0.15.1,<1", "torch>=2.0.1,<3", "torchdata>=0.4,<1", "transformers>=4.39.3,<5", "xgboost>=1.7.3,<3",]
+altair = [ "altair>=5,<6",]
 catboost = [ "catboost>=1.2.0, <2",]
 keras = [ "keras>=2.0.0,<4", "tensorflow>=2.17.0,<3", "torch>=2.0.1,<3",]
 lightgbm = [ "lightgbm>=4.1.0, <5",]
 mlflow = [ "mlflow>=2.16.0, <3",]
-shap = [ "shap>=0.46.0,<1",]
+streamlit = [ "streamlit>=1.44.0,<2",]
 tensorflow = [ "tensorflow>=2.17.0,<3",]
 torch = [ "torch>=2.0.1,<3", "torchdata>=0.4,<1",]
 transformers = [ "sentence-transformers>=2.7.0,<4", "sentencepiece>=0.1.95,<0.2.0", "tokenizers>=0.15.1,<1", "torch>=2.0.1,<3", "transformers>=4.39.3,<5",]
+xgboost = [ "xgboost>=1.7.3,<3",]
 
 [tool.setuptools.package-data]
 "*" = [ "*",]

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/cortex/__init__.py

@@ -1,5 +1,10 @@
 from snowflake.cortex._classify_text import ClassifyText, classify_text
-from snowflake.cortex._complete import Complete, CompleteOptions, complete
+from snowflake.cortex._complete import (
+    Complete,
+    CompleteOptions,
+    ConversationMessage,
+    complete,
+)
 from snowflake.cortex._embed_text_768 import EmbedText768, embed_text_768
 from snowflake.cortex._embed_text_1024 import EmbedText1024, embed_text_1024
 from snowflake.cortex._extract_answer import ExtractAnswer, extract_answer
@@ -14,6 +19,7 @@ __all__ = [
     "Complete",
     "complete",
     "CompleteOptions",
+    "ConversationMessage",
     "EmbedText768",
     "embed_text_768",
     "EmbedText1024",

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/_internal/platform_capabilities.py

@@ -11,6 +11,9 @@ from snowflake.snowpark import (
     session as snowpark_session,
 )
 
+LIVE_COMMIT_PARAMETER = "ENABLE_LIVE_VERSION_IN_SDK"
+INLINE_DEPLOYMENT_SPEC_PARAMETER = "ENABLE_INLINE_DEPLOYMENT_SPEC"
+
 
 class PlatformCapabilities:
     """Class that retrieves platform feature values for the currently running server.
@@ -18,12 +21,12 @@ class PlatformCapabilities:
     Example usage:
     ```
     pc = PlatformCapabilities.get_instance(session)
-    if pc.is_nested_function_enabled():
-        # Nested functions are enabled.
-        print("Nested functions are enabled.")
+    if pc.is_inlined_deployment_spec_enabled():
+        # Inline deployment spec is enabled.
+        print("Inline deployment spec is enabled.")
     else:
-        # Nested functions are disabled.
-        print("Nested functions are disabled or not supported.")
+        # Inline deployment spec is disabled.
+        print("Inline deployment spec is disabled or not supported.")
     ```
     """
 
@@ -50,9 +53,11 @@ class PlatformCapabilities:
 
     # For contextmanager, we need to have return type Iterator[Never]. However, Never type is introduced only in
     # Python 3.11. So, we are ignoring the type for this method.
+    _dummy_features: dict[str, Any] = {"dummy": "dummy"}
+
     @classmethod  # type: ignore[arg-type]
     @contextmanager
-    def mock_features(cls, features: dict[str, Any]) -> None:  # type: ignore[misc]
+    def mock_features(cls, features: dict[str, Any] = _dummy_features) -> None:  # type: ignore[misc]
         logging.debug(f"Setting mock features: {features}")
         cls.set_mock_features(features)
         try:
@@ -61,14 +66,11 @@ class PlatformCapabilities:
             logging.debug(f"Clearing mock features: {features}")
             cls.clear_mock_features()
 
-    def is_nested_function_enabled(self) -> bool:
-        return self._get_bool_feature("SPCS_MODEL_ENABLE_EMBEDDED_SERVICE_FUNCTIONS", False)
-
     def is_inlined_deployment_spec_enabled(self) -> bool:
-        return self._get_bool_feature("ENABLE_INLINE_DEPLOYMENT_SPEC", False)
+        return self._get_bool_feature(INLINE_DEPLOYMENT_SPEC_PARAMETER, False)
 
     def is_live_commit_enabled(self) -> bool:
-        return self._get_bool_feature("ENABLE_BUNDLE_MODULE_CHECKOUT", False)
+        return self._get_bool_feature(LIVE_COMMIT_PARAMETER, False)
 
     @staticmethod
     def _get_features(session: snowpark_session.Session) -> dict[str, Any]:

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/_internal/utils/identifier.py

@@ -12,7 +12,7 @@ SF_IDENTIFIER_RE = re.compile(_SF_IDENTIFIER)
 _SF_SCHEMA_LEVEL_OBJECT = (
     rf"(?:(?:(?P<db>{_SF_IDENTIFIER})\.)?(?P<schema>{_SF_IDENTIFIER})\.)?(?P<object>{_SF_IDENTIFIER})"
 )
-_SF_STAGE_PATH = rf"{_SF_SCHEMA_LEVEL_OBJECT}(?P<path>.*)"
+_SF_STAGE_PATH = rf"@?{_SF_SCHEMA_LEVEL_OBJECT}(?P<path>/.*)?"
 _SF_SCHEMA_LEVEL_OBJECT_RE = re.compile(_SF_SCHEMA_LEVEL_OBJECT)
 _SF_STAGE_PATH_RE = re.compile(_SF_STAGE_PATH)
 
@@ -197,7 +197,7 @@ def parse_snowflake_stage_path(
         res.group("db"),
         res.group("schema"),
         res.group("object"),
-        res.group("path"),
+        res.group("path") or "",
     )
 
 

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/jobs/_utils/constants.py

@@ -13,7 +13,7 @@ STAGE_VOLUME_MOUNT_PATH = "/mnt/app"
 DEFAULT_IMAGE_REPO = "/snowflake/images/snowflake_images"
 DEFAULT_IMAGE_CPU = "st_plat/runtime/x86/runtime_image/snowbooks"
 DEFAULT_IMAGE_GPU = "st_plat/runtime/x86/generic_gpu/runtime_image/snowbooks"
-DEFAULT_IMAGE_TAG = "1.0.1"
+DEFAULT_IMAGE_TAG = "1.2.3"
 DEFAULT_ENTRYPOINT_PATH = "func.py"
 
 # Percent of container memory to allocate for /dev/shm volume

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/jobs/_utils/payload_utils.py

@@ -9,6 +9,7 @@ from pathlib import Path, PurePath
 from typing import Any, Callable, Optional, Union, cast, get_args, get_origin
 
 import cloudpickle as cp
+from packaging import version
 
 from snowflake import snowpark
 from snowflake.ml.jobs._utils import constants, types
@@ -97,11 +98,18 @@ _STARTUP_SCRIPT_CODE = textwrap.dedent(
         head_info=$(python3 get_instance_ip.py "$SNOWFLAKE_SERVICE_NAME" --head)
         if [ $? -eq 0 ]; then
             # Parse the output using read
-            read head_index head_ip <<< "$head_info"
+            read head_index head_ip head_status<<< "$head_info"
 
             # Use the parsed variables
             echo "Head Instance Index: $head_index"
             echo "Head Instance IP: $head_ip"
+            echo "Head Instance Status: $head_status"
+
+            # If the head status is not "READY" or "PENDING", exit early
+            if [ "$head_status" != "READY" ] && [ "$head_status" != "PENDING" ]; then
+                echo "Head instance status is not READY or PENDING. Exiting."
+                exit 0
+            fi
 
         else
             echo "Error: Failed to get head instance information."
@@ -278,17 +286,19 @@ class JobPayload:
         stage_path = PurePath(stage_path) if isinstance(stage_path, str) else stage_path
         source = resolve_source(self.source)
         entrypoint = resolve_entrypoint(source, self.entrypoint)
+        pip_requirements = self.pip_requirements or []
 
         # Create stage if necessary
         stage_name = stage_path.parts[0].lstrip("@")
         # Explicitly check if stage exists first since we may not have CREATE STAGE privilege
         try:
-            session.sql(f"describe stage {stage_name}").collect()
+            session.sql("describe stage identifier(?)", params=[stage_name]).collect()
         except sp_exceptions.SnowparkSQLException:
             session.sql(
-                f"create stage if not exists {stage_name}"
+                "create stage if not exists identifier(?)"
                 " encryption = ( type = 'SNOWFLAKE_SSE' )"
-                " comment = 'Created by snowflake.ml.jobs Python API'"
+                " comment = 'Created by snowflake.ml.jobs Python API'",
+                params=[stage_name],
             ).collect()
 
         # Upload payload to stage
@@ -301,6 +311,8 @@ class JobPayload:
                 overwrite=True,
             )
             source = Path(entrypoint.file_path.parent)
+            if not any(r.startswith("cloudpickle") for r in pip_requirements):
+                pip_requirements.append(f"cloudpickle~={version.parse(cp.__version__).major}.0")
         elif source.is_dir():
             # Manually traverse the directory and upload each file, since Snowflake PUT
             # can't handle directories. Reduce the number of PUT operations by using
@@ -325,10 +337,10 @@ class JobPayload:
 
         # Upload requirements
         # TODO: Check if payload includes both a requirements.txt file and pip_requirements
-        if self.pip_requirements:
+        if pip_requirements:
             # Upload requirements.txt to stage
             session.file.put_stream(
-                io.BytesIO("\n".join(self.pip_requirements).encode()),
+                io.BytesIO("\n".join(pip_requirements).encode()),
                 stage_location=stage_path.joinpath("requirements.txt").as_posix(),
                 auto_compress=False,
                 overwrite=True,
@@ -495,13 +507,6 @@ def generate_python_code(func: Callable[..., Any], source_code_display: bool = F
     # https://github.com/snowflakedb/snowpark-python/blob/main/src/snowflake/snowpark/_internal/udf_utils.py
     source_code_comment = _generate_source_code_comment(func) if source_code_display else ""
 
-    func_code = f"""
-{source_code_comment}
-
-import pickle
-{_ENTRYPOINT_FUNC_NAME} = pickle.loads(bytes.fromhex('{_serialize_callable(func).hex()}'))
-"""
-
     arg_dict_name = "kwargs"
     if getattr(func, constants.IS_MLJOB_REMOTE_ATTR, None):
         param_code = f"{arg_dict_name} = {{}}"
@@ -509,25 +514,29 @@ import pickle
         param_code = _generate_param_handler_code(signature, arg_dict_name)
 
     return f"""
-### Version guard to check compatibility across Python versions ###
-import os
 import sys
-import warnings
-
-if sys.version_info.major != {sys.version_info.major} or sys.version_info.minor != {sys.version_info.minor}:
-    warnings.warn(
-        "Python version mismatch: job was created using"
-        " python{sys.version_info.major}.{sys.version_info.minor}"
-        f" but runtime environment uses python{{sys.version_info.major}}.{{sys.version_info.minor}}."
-        " Compatibility across Python versions is not guaranteed and may result in unexpected behavior."
-        " This will be fixed in a future release; for now, please use Python version"
-        f" {{sys.version_info.major}}.{{sys.version_info.minor}}.",
-        RuntimeWarning,
-        stacklevel=0,
-    )
-### End version guard ###
+import pickle
 
-{func_code.strip()}
+try:
+    {textwrap.indent(source_code_comment, '    ')}
+    {_ENTRYPOINT_FUNC_NAME} = pickle.loads(bytes.fromhex('{_serialize_callable(func).hex()}'))
+except (TypeError, pickle.PickleError):
+    if sys.version_info.major != {sys.version_info.major} or sys.version_info.minor != {sys.version_info.minor}:
+        raise RuntimeError(
+            "Failed to deserialize function due to Python version mismatch."
+            f" Runtime environment is Python {{sys.version_info.major}}.{{sys.version_info.minor}}"
+            " but function was serialized using Python {sys.version_info.major}.{sys.version_info.minor}."
+        ) from None
+    raise
+except AttributeError as e:
+    if 'cloudpickle' in str(e):
+        import cloudpickle as cp
+        raise RuntimeError(
+            "Failed to deserialize function due to cloudpickle version mismatch."
+            f" Runtime environment uses cloudpickle=={{cp.__version__}}"
+            " but job was serialized using cloudpickle=={cp.__version__}."
+        ) from e
+    raise
 
 if __name__ == '__main__':
 {textwrap.indent(param_code, '    ')}

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/jobs/_utils/scripts/get_instance_ip.py

@@ -29,7 +29,7 @@ def get_self_ip() -> Optional[str]:
         return None
 
 
-def get_first_instance(service_name: str) -> Optional[tuple[str, str]]:
+def get_first_instance(service_name: str) -> Optional[tuple[str, str, str]]:
     """Get the first instance of a batch job based on start time and instance ID.
 
     Args:
@@ -42,7 +42,7 @@ def get_first_instance(service_name: str) -> Optional[tuple[str, str]]:
 
     session = session_utils.get_session()
     df = session.sql(f"show service instances in service {service_name}")
-    result = df.select('"instance_id"', '"ip_address"', '"start_time"').collect()
+    result = df.select('"instance_id"', '"ip_address"', '"start_time"', '"status"').collect()
 
     if not result:
         return None
@@ -57,7 +57,7 @@ def get_first_instance(service_name: str) -> Optional[tuple[str, str]]:
     ip_address = head_instance["ip_address"]
     try:
         socket.inet_aton(ip_address)  # Validate IPv4 address
-        return (head_instance["instance_id"], ip_address)
+        return (head_instance["instance_id"], ip_address, head_instance["status"])
     except OSError:
         logger.error(f"Error: Invalid IP address format: {ip_address}")
         return None
@@ -110,7 +110,7 @@ def main():
             head_info = get_first_instance(args.service_name)
             if head_info:
                 # Print to stdout to allow capture but don't use logger
-                sys.stdout.write(f"{head_info[0]} {head_info[1]}\n")
+                sys.stdout.write(" ".join(head_info) + "\n")
                 sys.exit(0)
             time.sleep(args.retry_interval)
         # If we get here, we've timed out

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/jobs/_utils/scripts/mljob_launcher.py

@@ -59,7 +59,7 @@ class SimpleJSONEncoder(json.JSONEncoder):
         try:
             return super().default(obj)
         except TypeError:
-            return str(obj)
+            return f"Unserializable object: {repr(obj)}"
 
 
 def run_script(script_path: str, *script_args: Any, main_func: Optional[str] = None) -> Any:

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/jobs/_utils/spec_utils.py

@@ -11,7 +11,7 @@ from snowflake.ml.jobs._utils import constants, types
 def _get_node_resources(session: snowpark.Session, compute_pool: str) -> types.ComputeResources:
     """Extract resource information for the specified compute pool"""
     # Get the instance family
-    rows = session.sql(f"show compute pools like '{compute_pool}'").collect()
+    rows = session.sql("show compute pools like ?", params=[compute_pool]).collect()
     if not rows:
         raise ValueError(f"Compute pool '{compute_pool}' not found")
     instance_family: str = rows[0]["instance_family"]

{snowflake_ml_python-1.8.3 → snowflake_ml_python-1.8.4}/snowflake/ml/jobs/decorators.py

@@ -26,6 +26,8 @@ def remote(
     env_vars: Optional[dict[str, str]] = None,
     num_instances: Optional[int] = None,
     enable_metrics: bool = False,
+    database: Optional[str] = None,
+    schema: Optional[str] = None,
     session: Optional[snowpark.Session] = None,
 ) -> Callable[[Callable[_Args, _ReturnValue]], Callable[_Args, jb.MLJob[_ReturnValue]]]:
     """
@@ -40,6 +42,8 @@ def remote(
         env_vars: Environment variables to set in container
         num_instances: The number of nodes in the job. If none specified, create a single node job.
         enable_metrics: Whether to enable metrics publishing for the job.
+        database: The database to use for the job.
+        schema: The schema to use for the job.
         session: The Snowpark session to use. If none specified, uses active session.
 
     Returns:
@@ -67,6 +71,8 @@ def remote(
                 env_vars=env_vars,
                 num_instances=num_instances,
                 enable_metrics=enable_metrics,
+                database=database,
+                schema=schema,
                 session=session,
             )
             assert isinstance(job, jb.MLJob), f"Unexpected job type: {type(job)}"