snowflake-ml-python 1.7.3__tar.gz → 1.7.4__tar.gz

{snowflake_ml_python-1.7.3 → snowflake_ml_python-1.7.4}/CHANGELOG.md

@@ -1,6 +1,29 @@
 # Release History
 
-## 1.7.3
+## 1.7.4
+
+- 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.
+
+### 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
+
+## 1.7.3 (2025-01-08)
 
 - Added lowercase versions of Cortex functions, added deprecation warning to Capitalized versions.
 - Bumped the requirements of `fsspec` and `s3fs` to `>=2024.6.1,<2026`
@@ -18,13 +41,13 @@
 - Registry: Fix error in log_model for any sklearn models with only data pre-processing including pre-processing only
   pipeline models due to default explainability enablement.
 
-### Behavior Changes
-
 ### New Features
 
 - Added `user_files` argument to `Registry.log_model` for including images or any extra file with the model.
 - Registry: Added support for handling Hugging Face model configurations with auto-mapping functionality
 - DataConnector: Add new `DataConnector.from_sql()` constructor
+- Registry: Provided new arguments to `snowflake.ml.model.model_signature.infer_signature` method to specify rows limit
+  to be used when inferring the signature.
 
 ## 1.7.2 (2024-11-21)
 
@@ -33,8 +56,6 @@
 - Model Explainability: Fix issue that explain is enabled for scikit-learn pipeline
 whose task is UNKNOWN and fails later when invoked.
 
-### Behavior Changes
-
 ### New Features
 
 - Registry: Support asynchronous model inference service creation with the `block` option
@@ -54,8 +75,6 @@ signature inference.
 - Dataset: Fix missing `snowflake.ml.dataset.*` module exports in wheel.
 - Registry: Fix the issue that `tf_keras.Model` is not recognized as keras model when logging.
 
-### Behavior Changes
-
 ### New Features
 
 - Registry: Option to `enable_monitoring` set to False by default.  This will gate access to preview features of Model Monitoring.
@@ -304,10 +323,6 @@ data from explainablity and data lineage.
 - Modeling: Quick fix `import snowflake.ml.modeling.parameters.enable_anonymous_sproc` cannot be imported due to package
   dependency error.
 
-### Behavior Changes
-
-### New Features
-
 ## 1.5.1 (05-22-2024)
 
 ### Bug Fixes

{snowflake_ml_python-1.7.3 → snowflake_ml_python-1.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: snowflake-ml-python
-Version: 1.7.3
+Version: 1.7.4
 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: 
@@ -233,7 +233,7 @@ Requires-Python: <3.12,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: absl-py<2,>=0.15
-Requires-Dist: anyio<4,>=3.5.0
+Requires-Dist: anyio<5,>=3.5.0
 Requires-Dist: cachetools<6,>=3.1.1
 Requires-Dist: cloudpickle>=2.0.0
 Requires-Dist: cryptography
@@ -251,7 +251,7 @@ Requires-Dist: s3fs<2026,>=2024.6.1
 Requires-Dist: scikit-learn<1.6,>=1.4
 Requires-Dist: scipy<2,>=1.9
 Requires-Dist: snowflake-connector-python[pandas]<4,>=3.5.0
-Requires-Dist: snowflake-snowpark-python<2,>=1.17.0
+Requires-Dist: snowflake-snowpark-python!=1.26.0,<2,>=1.17.0
 Requires-Dist: sqlparse<1,>=0.4
 Requires-Dist: typing-extensions<5,>=4.1.0
 Requires-Dist: xgboost<3,>=1.7.3
@@ -399,7 +399,30 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
-## 1.7.3
+## 1.7.4
+
+- 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.
+
+### 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
+
+## 1.7.3 (2025-01-08)
 
 - Added lowercase versions of Cortex functions, added deprecation warning to Capitalized versions.
 - Bumped the requirements of `fsspec` and `s3fs` to `>=2024.6.1,<2026`
@@ -417,13 +440,13 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 - Registry: Fix error in log_model for any sklearn models with only data pre-processing including pre-processing only
   pipeline models due to default explainability enablement.
 
-### Behavior Changes
-
 ### New Features
 
 - Added `user_files` argument to `Registry.log_model` for including images or any extra file with the model.
 - Registry: Added support for handling Hugging Face model configurations with auto-mapping functionality
 - DataConnector: Add new `DataConnector.from_sql()` constructor
+- Registry: Provided new arguments to `snowflake.ml.model.model_signature.infer_signature` method to specify rows limit
+  to be used when inferring the signature.
 
 ## 1.7.2 (2024-11-21)
 
@@ -432,8 +455,6 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 - Model Explainability: Fix issue that explain is enabled for scikit-learn pipeline
 whose task is UNKNOWN and fails later when invoked.
 
-### Behavior Changes
-
 ### New Features
 
 - Registry: Support asynchronous model inference service creation with the `block` option
@@ -453,8 +474,6 @@ signature inference.
 - Dataset: Fix missing `snowflake.ml.dataset.*` module exports in wheel.
 - Registry: Fix the issue that `tf_keras.Model` is not recognized as keras model when logging.
 
-### Behavior Changes
-
 ### New Features
 
 - Registry: Option to `enable_monitoring` set to False by default.  This will gate access to preview features of Model Monitoring.
@@ -703,10 +722,6 @@ data from explainablity and data lineage.
 - Modeling: Quick fix `import snowflake.ml.modeling.parameters.enable_anonymous_sproc` cannot be imported due to package
   dependency error.
 
-### Behavior Changes
-
-### New Features
-
 ## 1.5.1 (05-22-2024)
 
 ### Bug Fixes

{snowflake_ml_python-1.7.3 → snowflake_ml_python-1.7.4}/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", "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, <3.12"
 dynamic = [ "version", "readme",]
-dependencies = [ "absl-py>=0.15,<2", "anyio>=3.5.0,<4", "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", "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]>=3.5.0,<4", "snowflake-snowpark-python>=1.17.0,<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", "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]>=3.5.0,<4", "snowflake-snowpark-python>=1.17.0,<2,!=1.26.0", "sqlparse>=0.4,<1", "typing-extensions>=4.1.0,<5", "xgboost>=1.7.3,<3",]
 [[project.authors]]
 name = "Snowflake, Inc"
 email = "support@snowflake.com"

{snowflake_ml_python-1.7.3 → snowflake_ml_python-1.7.4}/snowflake/cortex/_complete.py

@@ -49,6 +49,10 @@ class CompleteOptions(TypedDict):
     generally used as an alternative to temperature. The difference is that top_p restricts the set of possible tokens
     that the model outputs, while temperature influences which tokens are chosen at each step. """
 
+    guardrails: NotRequired[bool]
+    """ A boolean value that controls whether Cortex Guard filters unsafe or harmful responses
+    from the language model. """
+
 
 class ResponseParseException(Exception):
     """This exception is raised when the server response cannot be parsed."""
@@ -56,6 +60,15 @@ class ResponseParseException(Exception):
     pass
 
 
+class GuardrailsOptions(TypedDict):
+    enabled: bool
+    """A boolean value that controls whether Cortex Guard filters unsafe or harmful responses
+    from the language model."""
+
+    response_when_unsafe: str
+    """The response to return when the language model generates unsafe or harmful content."""
+
+
 _MAX_RETRY_SECONDS = 30
 
 
@@ -117,6 +130,12 @@ def _make_request_body(
             data["temperature"] = options["temperature"]
         if "top_p" in options:
             data["top_p"] = options["top_p"]
+        if "guardrails" in options and options["guardrails"]:
+            guardrails_options: GuardrailsOptions = {
+                "enabled": True,
+                "response_when_unsafe": "Response filtered by Cortex Guard",
+            }
+            data["guardrails"] = guardrails_options
     return data
 
 

snowflake_ml_python-1.7.4/snowflake/ml/_internal/platform_capabilities.py

@@ -0,0 +1,87 @@
+import json
+from typing import Any, Dict, Optional
+
+from absl import logging
+
+from snowflake.ml._internal.exceptions import error_codes, exceptions
+from snowflake.ml._internal.utils import query_result_checker
+from snowflake.snowpark import (
+    exceptions as snowpark_exceptions,
+    session as snowpark_session,
+)
+
+
+class PlatformCapabilities:
+    """Class that retrieves platform feature values for the currently running server.
+
+    Example usage:
+    ```
+    pc = PlatformCapabilities.get_instance(session)
+    if pc.is_nested_function_enabled():
+        # Nested functions are enabled.
+        print("Nested functions are enabled.")
+    else:
+        # Nested functions are disabled.
+        print("Nested functions are disabled or not supported.")
+    ```
+    """
+
+    _instance: Optional["PlatformCapabilities"] = None
+
+    @classmethod
+    def get_instance(cls, session: Optional[snowpark_session.Session] = None) -> "PlatformCapabilities":
+        if not cls._instance:
+            cls._instance = cls(session)
+        return cls._instance
+
+    def is_nested_function_enabled(self) -> bool:
+        return self._get_bool_feature("SPCS_MODEL_ENABLE_EMBEDDED_SERVICE_FUNCTIONS", False)
+
+    @staticmethod
+    def _get_features(session: snowpark_session.Session) -> Dict[str, Any]:
+        try:
+            result = (
+                query_result_checker.SqlResultValidator(
+                    session=session,
+                    query="SELECT SYSTEM$ML_PLATFORM_CAPABILITIES() AS FEATURES;",
+                )
+                .has_dimensions(expected_rows=1, expected_cols=1)
+                .has_column("FEATURES")
+                .validate()[0]
+            )
+            if "FEATURES" in result:
+                capabilities_json: str = result["FEATURES"]
+                try:
+                    parsed_json = json.loads(capabilities_json)
+                    assert isinstance(parsed_json, dict), f"Expected JSON object, got {type(parsed_json)}"
+                    return parsed_json
+                except json.JSONDecodeError as e:
+                    message = f"""Unable to parse JSON from: "{capabilities_json}"; Error="{e}"."""
+                    raise exceptions.SnowflakeMLException(
+                        error_code=error_codes.INTERNAL_SNOWML_ERROR, original_exception=RuntimeError(message)
+                    )
+        except snowpark_exceptions.SnowparkSQLException as e:
+            logging.debug(f"Failed to retrieve platform capabilities: {e}")
+            # This can happen is server side is older than 9.2. That is fine.
+        return {}
+
+    def __init__(self, session: Optional[snowpark_session.Session] = None) -> None:
+        if not session:
+            session = next(iter(snowpark_session._get_active_sessions()))
+            assert session, "Missing active session object"
+        self.features: Dict[str, Any] = PlatformCapabilities._get_features(session)
+
+    def _get_bool_feature(self, feature_name: str, default_value: bool) -> bool:
+        value = self.features.get(feature_name, default_value)
+        if isinstance(value, bool):
+            return value
+        if isinstance(value, int) and value in [0, 1]:
+            return value == 1
+        if isinstance(value, str):
+            if value.lower() in ["true", "1"]:
+                return True
+            elif value.lower() in ["false", "0"]:
+                return False
+            else:
+                raise ValueError(f"Invalid boolean string: {value} for feature {feature_name}")
+        raise ValueError(f"Invalid boolean feature value: {value} for feature {feature_name}")

{snowflake_ml_python-1.7.3 → snowflake_ml_python-1.7.4}/snowflake/ml/dataset/dataset.py

@@ -419,7 +419,6 @@ class Dataset(lineage_node.LineageNode):
     @telemetry.send_api_usage_telemetry(project=_PROJECT)
     def delete(self) -> None:
         """Delete Dataset and all contained versions"""
-        # TODO: Check and warn if any versions exist
         self._session.sql(f"DROP DATASET {self.fully_qualified_name}").collect(
             statement_params=_TELEMETRY_STATEMENT_PARAMS
         )

{snowflake_ml_python-1.7.3 → snowflake_ml_python-1.7.4}/snowflake/ml/fileset/fileset.py

@@ -2,6 +2,8 @@ import functools
 import inspect
 from typing import Any, Callable, List, Optional
 
+from typing_extensions import deprecated
+
 from snowflake import snowpark
 from snowflake.connector import connection
 from snowflake.ml._internal import telemetry
@@ -42,6 +44,10 @@ def _raise_if_deleted(func: Callable[..., Any]) -> Callable[..., Any]:
     return raise_if_deleted_helper
 
 
+@deprecated(
+    "FileSet is deprecated and will be removed in a future release."
+    " Use snowflake.ml.dataset.Dataset and snowflake.ml.data.DataConnector instead"
+)
 class FileSet:
     """A FileSet represents an immutable snapshot of the result of a query in the form of files."""
 

snowflake_ml_python-1.7.4/snowflake/ml/jobs/__init__.py

@@ -0,0 +1,21 @@
+from snowflake.ml.jobs._utils.types import JOB_STATUS
+from snowflake.ml.jobs.decorators import remote
+from snowflake.ml.jobs.job import MLJob
+from snowflake.ml.jobs.manager import (
+    delete_job,
+    get_job,
+    list_jobs,
+    submit_directory,
+    submit_file,
+)
+
+__all__ = [
+    "remote",
+    "submit_file",
+    "submit_directory",
+    "list_jobs",
+    "get_job",
+    "delete_job",
+    "MLJob",
+    "JOB_STATUS",
+]

snowflake_ml_python-1.7.4/snowflake/ml/jobs/_utils/constants.py

@@ -0,0 +1,51 @@
+from snowflake.ml._internal.utils.snowflake_env import SnowflakeCloudType
+from snowflake.ml.jobs._utils.types import ComputeResources
+
+# SPCS specification constants
+DEFAULT_CONTAINER_NAME = "main"
+PAYLOAD_DIR_ENV_VAR = "MLRS_PAYLOAD_DIR"
+
+# Default container image information
+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 = "0.8.0"
+DEFAULT_ENTRYPOINT_PATH = "func.py"
+
+# Percent of container memory to allocate for /dev/shm volume
+MEMORY_VOLUME_SIZE = 0.3
+
+# Job status polling constants
+JOB_POLL_INITIAL_DELAY_SECONDS = 0.1
+JOB_POLL_MAX_DELAY_SECONDS = 1
+
+# Compute pool resource information
+# TODO: Query Snowflake for resource information instead of relying on this hardcoded
+#       table from https://docs.snowflake.com/en/sql-reference/sql/create-compute-pool
+COMMON_INSTANCE_FAMILIES = {
+    "CPU_X64_XS": ComputeResources(cpu=1, memory=6),
+    "CPU_X64_S": ComputeResources(cpu=3, memory=13),
+    "CPU_X64_M": ComputeResources(cpu=6, memory=28),
+    "CPU_X64_L": ComputeResources(cpu=28, memory=116),
+    "HIGHMEM_X64_S": ComputeResources(cpu=6, memory=58),
+}
+AWS_INSTANCE_FAMILIES = {
+    "HIGHMEM_X64_M": ComputeResources(cpu=28, memory=240),
+    "HIGHMEM_X64_L": ComputeResources(cpu=124, memory=984),
+    "GPU_NV_S": ComputeResources(cpu=6, memory=27, gpu=1, gpu_type="A10G"),
+    "GPU_NV_M": ComputeResources(cpu=44, memory=178, gpu=4, gpu_type="A10G"),
+    "GPU_NV_L": ComputeResources(cpu=92, memory=1112, gpu=8, gpu_type="A100"),
+}
+AZURE_INSTANCE_FAMILIES = {
+    "HIGHMEM_X64_M": ComputeResources(cpu=28, memory=244),
+    "HIGHMEM_X64_L": ComputeResources(cpu=92, memory=654),
+    "GPU_NV_XS": ComputeResources(cpu=3, memory=26, gpu=1, gpu_type="T4"),
+    "GPU_NV_SM": ComputeResources(cpu=32, memory=424, gpu=1, gpu_type="A10"),
+    "GPU_NV_2M": ComputeResources(cpu=68, memory=858, gpu=2, gpu_type="A10"),
+    "GPU_NV_3M": ComputeResources(cpu=44, memory=424, gpu=2, gpu_type="A100"),
+    "GPU_NV_SL": ComputeResources(cpu=92, memory=858, gpu=4, gpu_type="A100"),
+}
+CLOUD_INSTANCE_FAMILIES = {
+    SnowflakeCloudType.AWS: AWS_INSTANCE_FAMILIES,
+    SnowflakeCloudType.AZURE: AZURE_INSTANCE_FAMILIES,
+}