snowflake-ml-python 1.8.2__tar.gz → 1.8.4__tar.gz

{snowflake_ml_python-1.8.2 → snowflake_ml_python-1.8.4}/CHANGELOG.md

@@ -1,6 +1,31 @@
 # Release History
 
-## 1.8.2
+## 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
 
@@ -8,6 +33,17 @@
 
 ### New Features
 
+- Registry: Default to the runtime cuda version if available when logging a GPU model in Container Runtime.
+- ML Job: Added `as_list` argument to `MLJob.get_logs()` to enable retrieving logs
+  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
+
+### New Features
+
 - ML Job now available as a PuPr feature
 - ML Job: Add ability to retrieve results for `@remote` decorated functions using
   new `MLJobWithResult.result()` API, which will return the unpickled result
@@ -16,7 +52,6 @@
   `snowflake.snowpark.context.get_active_session()`
 - Registry: Introducing `save_location` to `log_model` using the `options` argument.
   User's can provide the path to write the model version's files that get stored in Snowflake's stage.
-- Registry: Include model dependencies in pip requirements by default when logging in Container Runtime.
 
 ```python
 reg.log_model(
@@ -28,8 +63,9 @@ reg.log_model(
 )
 ```
 
-- ML Job (PrPr): Add `instance_id` argument to `get_logs` and `show_logs` method to support multi node log retrieval
-- ML Job (PrPr): Add `job.get_instance_status(instance_id=...)` API to support multi node status retrieval
+- Registry: Include model dependencies in pip requirements by default when logging in Container Runtime.
+- Multi-node ML Job (PrPr): Add `instance_id` argument to `get_logs` and `show_logs` method to support multi node log retrieval
+- Multi-node ML Job (PrPr): Add `job.get_instance_status(instance_id=...)` API to support multi node status retrieval
 
 ## 1.8.1 (03-26-2025)
 
@@ -39,8 +75,6 @@ reg.log_model(
   inference method.
 - Registry: Fix a bug that model inference service creation fails on an existing and suspended service.
 
-### Behavior Change
-
 ### New Features
 
 - ML Job (PrPr): Update Container Runtime image version to `1.0.1`

{snowflake_ml_python-1.8.2/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: 1.8.2
+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
@@ -244,32 +244,37 @@ Requires-Dist: numpy<2,>=1.23
 Requires-Dist: packaging<25,>=20.9
 Requires-Dist: pandas<3,>=1.0.0
 Requires-Dist: pyarrow
+Requires-Dist: pydantic<3,>=2.8.2
 Requires-Dist: pyjwt<3,>=2.0.0
 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
@@ -280,8 +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
@@ -293,6 +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
@@ -403,7 +410,32 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
-## 1.8.2
+## 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
 
@@ -411,6 +443,17 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 ### New Features
 
+- Registry: Default to the runtime cuda version if available when logging a GPU model in Container Runtime.
+- ML Job: Added `as_list` argument to `MLJob.get_logs()` to enable retrieving logs
+  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
+
+### New Features
+
 - ML Job now available as a PuPr feature
 - ML Job: Add ability to retrieve results for `@remote` decorated functions using
   new `MLJobWithResult.result()` API, which will return the unpickled result
@@ -419,7 +462,6 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
   `snowflake.snowpark.context.get_active_session()`
 - Registry: Introducing `save_location` to `log_model` using the `options` argument.
   User's can provide the path to write the model version's files that get stored in Snowflake's stage.
-- Registry: Include model dependencies in pip requirements by default when logging in Container Runtime.
 
 ```python
 reg.log_model(
@@ -431,8 +473,9 @@ reg.log_model(
 )
 ```
 
-- ML Job (PrPr): Add `instance_id` argument to `get_logs` and `show_logs` method to support multi node log retrieval
-- ML Job (PrPr): Add `job.get_instance_status(instance_id=...)` API to support multi node status retrieval
+- Registry: Include model dependencies in pip requirements by default when logging in Container Runtime.
+- Multi-node ML Job (PrPr): Add `instance_id` argument to `get_logs` and `show_logs` method to support multi node log retrieval
+- Multi-node ML Job (PrPr): Add `job.get_instance_status(instance_id=...)` API to support multi node status retrieval
 
 ## 1.8.1 (03-26-2025)
 
@@ -442,8 +485,6 @@ reg.log_model(
   inference method.
 - Registry: Fix a bug that model inference service creation fails on an existing and suspended service.
 
-### Behavior Change
-
 ### New Features
 
 - ML Job (PrPr): Update Container Runtime image version to `1.0.1`

{snowflake_ml_python-1.8.2 → 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", "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-1.8.2 → 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-1.8.2 → snowflake_ml_python-1.8.4}/snowflake/cortex/_classify_text.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Union, cast
+from typing import Optional, Union, cast
 
 from typing_extensions import deprecated
 
@@ -12,7 +12,7 @@ from snowflake.ml._internal import telemetry
 )
 def classify_text(
     str_input: Union[str, snowpark.Column],
-    categories: Union[List[str], snowpark.Column],
+    categories: Union[list[str], snowpark.Column],
     session: Optional[snowpark.Session] = None,
 ) -> Union[str, snowpark.Column]:
     """Use the LLM inference service to classify the INPUT text into one of the target CATEGORIES.
@@ -32,7 +32,7 @@ def classify_text(
 def _classify_text_impl(
     function: str,
     str_input: Union[str, snowpark.Column],
-    categories: Union[List[str], snowpark.Column],
+    categories: Union[list[str], snowpark.Column],
     session: Optional[snowpark.Session] = None,
 ) -> Union[str, snowpark.Column]:
     return cast(Union[str, snowpark.Column], call_sql_function(function, session, str_input, categories))

{snowflake_ml_python-1.8.2 → snowflake_ml_python-1.8.4}/snowflake/cortex/_complete.py

@@ -3,7 +3,7 @@ import logging
 import time
 import typing
 from io import BytesIO
-from typing import Any, Callable, Dict, Iterator, List, Optional, TypedDict, Union, cast
+from typing import Any, Callable, Iterator, Optional, TypedDict, Union, cast
 from urllib.parse import urlunparse
 
 import requests
@@ -30,7 +30,7 @@ class ResponseFormat(TypedDict):
 
     type: str
     """The response format type (e.g. "json")"""
-    schema: Dict[str, Any]
+    schema: dict[str, Any]
     """The schema defining the structure of the response. For json it should be a valid json schema object"""
 
 
@@ -71,12 +71,11 @@ class CompleteOptions(TypedDict):
 class ResponseParseException(Exception):
     """This exception is raised when the server response cannot be parsed."""
 
-    pass
-
 
 class MidStreamException(Exception):
     """The SSE (Server-sent Event) stream can contain error messages in the middle of the stream,
-    using the “error” event type. This exception is raised when there is such a mid-stream error."""
+    using the “error” event type. This exception is raised when there is such a mid-stream error.
+    """
 
     def __init__(
         self,
@@ -135,7 +134,7 @@ def retry(func: Callable[..., requests.Response]) -> Callable[..., requests.Resp
     return inner
 
 
-def _make_common_request_headers() -> Dict[str, str]:
+def _make_common_request_headers() -> dict[str, str]:
     headers = {
         "Content-Type": "application/json",
         "Accept": "application/json, text/event-stream",
@@ -143,7 +142,7 @@ def _make_common_request_headers() -> Dict[str, str]:
     return headers
 
 
-def _get_request_id(resp: Dict[str, Any]) -> Optional[Any]:
+def _get_request_id(resp: dict[str, Any]) -> Optional[Any]:
     request_id = None
     if "headers" in resp:
         for key, value in resp["headers"].items():
@@ -183,14 +182,14 @@ def _validate_response_format_object(options: CompleteOptions) -> None:
 
 def _make_request_body(
     model: str,
-    prompt: Union[str, List[ConversationMessage]],
+    prompt: Union[str, list[ConversationMessage]],
     options: Optional[CompleteOptions] = None,
-) -> Dict[str, Any]:
+) -> dict[str, Any]:
     data = {
         "model": model,
         "stream": True,
     }
-    if isinstance(prompt, List):
+    if isinstance(prompt, list):
         data["messages"] = prompt
     else:
         data["messages"] = [{"content": prompt}]
@@ -217,7 +216,7 @@ def _make_request_body(
 
 # XP endpoint returns a dict response which needs to be converted to a format which can
 # be consumed by the SSEClient. This method does that.
-def _xp_dict_to_response(raw_resp: Dict[str, Any]) -> requests.Response:
+def _xp_dict_to_response(raw_resp: dict[str, Any]) -> requests.Response:
 
     response = requests.Response()
     response.status_code = int(raw_resp["status"])
@@ -251,9 +250,9 @@ def _xp_dict_to_response(raw_resp: Dict[str, Any]) -> requests.Response:
 
 @retry
 def _call_complete_xp(
-    snow_api_xp_request_handler: Optional[Callable[..., Dict[str, Any]]],
+    snow_api_xp_request_handler: Optional[Callable[..., dict[str, Any]]],
     model: str,
-    prompt: Union[str, List[ConversationMessage]],
+    prompt: Union[str, list[ConversationMessage]],
     options: Optional[CompleteOptions] = None,
     deadline: Optional[float] = None,
 ) -> requests.Response:
@@ -267,7 +266,7 @@ def _call_complete_xp(
 @retry
 def _call_complete_rest(
     model: str,
-    prompt: Union[str, List[ConversationMessage]],
+    prompt: Union[str, list[ConversationMessage]],
     options: Optional[CompleteOptions] = None,
     session: Optional[snowpark.Session] = None,
 ) -> requests.Response:
@@ -340,9 +339,9 @@ def _complete_call_sql_function_snowpark(
 
 
 def _complete_non_streaming_immediate(
-    snow_api_xp_request_handler: Optional[Callable[..., Dict[str, Any]]],
+    snow_api_xp_request_handler: Optional[Callable[..., dict[str, Any]]],
     model: str,
-    prompt: Union[str, List[ConversationMessage]],
+    prompt: Union[str, list[ConversationMessage]],
     options: Optional[CompleteOptions],
     session: Optional[snowpark.Session] = None,
     deadline: Optional[float] = None,
@@ -359,10 +358,10 @@ def _complete_non_streaming_immediate(
 
 
 def _complete_non_streaming_impl(
-    snow_api_xp_request_handler: Optional[Callable[..., Dict[str, Any]]],
+    snow_api_xp_request_handler: Optional[Callable[..., dict[str, Any]]],
     function: str,
     model: Union[str, snowpark.Column],
-    prompt: Union[str, List[ConversationMessage], snowpark.Column],
+    prompt: Union[str, list[ConversationMessage], snowpark.Column],
     options: Optional[Union[CompleteOptions, snowpark.Column]],
     session: Optional[snowpark.Session] = None,
     deadline: Optional[float] = None,
@@ -389,9 +388,9 @@ def _complete_non_streaming_impl(
 
 
 def _complete_rest(
-    snow_api_xp_request_handler: Optional[Callable[..., Dict[str, Any]]],
+    snow_api_xp_request_handler: Optional[Callable[..., dict[str, Any]]],
     model: str,
-    prompt: Union[str, List[ConversationMessage]],
+    prompt: Union[str, list[ConversationMessage]],
     options: Optional[CompleteOptions] = None,
     session: Optional[snowpark.Session] = None,
     deadline: Optional[float] = None,
@@ -414,8 +413,8 @@ def _complete_rest(
 
 def _complete_impl(
     model: Union[str, snowpark.Column],
-    prompt: Union[str, List[ConversationMessage], snowpark.Column],
-    snow_api_xp_request_handler: Optional[Callable[..., Dict[str, Any]]] = None,
+    prompt: Union[str, list[ConversationMessage], snowpark.Column],
+    snow_api_xp_request_handler: Optional[Callable[..., dict[str, Any]]] = None,
     function: str = "snowflake.cortex.complete",
     options: Optional[CompleteOptions] = None,
     session: Optional[snowpark.Session] = None,
@@ -430,7 +429,7 @@ def _complete_impl(
     if stream:
         if not isinstance(model, str):
             raise ValueError("in REST mode, 'model' must be a string")
-        if not isinstance(prompt, str) and not isinstance(prompt, List):
+        if not isinstance(prompt, str) and not isinstance(prompt, list):
             raise ValueError("in REST mode, 'prompt' must be a string or a list of ConversationMessage")
         return _complete_rest(
             snow_api_xp_request_handler=snow_api_xp_request_handler,
@@ -456,7 +455,7 @@ def _complete_impl(
 )
 def complete(
     model: Union[str, snowpark.Column],
-    prompt: Union[str, List[ConversationMessage], snowpark.Column],
+    prompt: Union[str, list[ConversationMessage], snowpark.Column],
     *,
     options: Optional[CompleteOptions] = None,
     session: Optional[snowpark.Session] = None,

{snowflake_ml_python-1.8.2 → snowflake_ml_python-1.8.4}/snowflake/cortex/_embed_text_1024.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Union, cast
+from typing import Optional, Union, cast
 
 from typing_extensions import deprecated
 
@@ -14,7 +14,7 @@ def embed_text_1024(
     model: Union[str, snowpark.Column],
     text: Union[str, snowpark.Column],
     session: Optional[snowpark.Session] = None,
-) -> Union[List[float], snowpark.Column]:
+) -> Union[list[float], snowpark.Column]:
     """Calls into the LLM inference service to embed the text.
 
     Args:
@@ -35,8 +35,8 @@ def _embed_text_1024_impl(
     model: Union[str, snowpark.Column],
     text: Union[str, snowpark.Column],
     session: Optional[snowpark.Session] = None,
-) -> Union[List[float], snowpark.Column]:
-    return cast(Union[List[float], snowpark.Column], call_sql_function(function, session, model, text))
+) -> Union[list[float], snowpark.Column]:
+    return cast(Union[list[float], snowpark.Column], call_sql_function(function, session, model, text))
 
 
 EmbedText1024 = deprecated(

{snowflake_ml_python-1.8.2 → snowflake_ml_python-1.8.4}/snowflake/cortex/_embed_text_768.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Union, cast
+from typing import Optional, Union, cast
 
 from typing_extensions import deprecated
 
@@ -14,7 +14,7 @@ def embed_text_768(
     model: Union[str, snowpark.Column],
     text: Union[str, snowpark.Column],
     session: Optional[snowpark.Session] = None,
-) -> Union[List[float], snowpark.Column]:
+) -> Union[list[float], snowpark.Column]:
     """Calls into the LLM inference service to embed the text.
 
     Args:
@@ -35,8 +35,8 @@ def _embed_text_768_impl(
     model: Union[str, snowpark.Column],
     text: Union[str, snowpark.Column],
     session: Optional[snowpark.Session] = None,
-) -> Union[List[float], snowpark.Column]:
-    return cast(Union[List[float], snowpark.Column], call_sql_function(function, session, model, text))
+) -> Union[list[float], snowpark.Column]:
+    return cast(Union[list[float], snowpark.Column], call_sql_function(function, session, model, text))
 
 
 EmbedText768 = deprecated(

{snowflake_ml_python-1.8.2 → snowflake_ml_python-1.8.4}/snowflake/cortex/_finetune.py

@@ -1,6 +1,6 @@
 import json
 from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Optional, Union, cast
 
 from snowflake import snowpark
 from snowflake.cortex._util import (
@@ -53,7 +53,7 @@ class FinetuneStatus:
     created_on: Optional[int] = None
     """Creation timestamp of the Fine-tuning job in milliseconds."""
 
-    error: Optional[Dict[str, Any]] = None
+    error: Optional[dict[str, Any]] = None
     """Error message propagated from the job."""
 
     finished_on: Optional[int] = None
@@ -62,7 +62,7 @@ class FinetuneStatus:
     progress: Optional[float] = None
     """Progress made as a fraction of total [0.0,1.0]."""
 
-    training_result: Optional[List[Dict[str, Any]]] = None
+    training_result: Optional[list[dict[str, Any]]] = None
     """Detailed metrics report for a completed training."""
 
     trained_tokens: Optional[int] = None
@@ -135,7 +135,7 @@ class FinetuneJob:
         """
         result_string = _finetune_impl(operation="DESCRIBE", session=self._session, function_args=[self.status.id])
 
-        result = FinetuneStatus(**cast(Dict[str, Any], _try_load_json(result_string)))
+        result = FinetuneStatus(**cast(dict[str, Any], _try_load_json(result_string)))
         return result
 
 
@@ -167,7 +167,7 @@ class Finetune:
         base_model: str,
         training_data: Union[str, snowpark.DataFrame],
         validation_data: Optional[Union[str, snowpark.DataFrame]] = None,
-        options: Optional[Dict[str, Any]] = None,
+        options: Optional[dict[str, Any]] = None,
     ) -> FinetuneJob:
         """Create a new fine-tuning runs.
 
@@ -240,7 +240,7 @@ class Finetune:
         project=CORTEX_FUNCTIONS_TELEMETRY_PROJECT,
         subproject=CORTEX_FINETUNE_TELEMETRY_SUBPROJECT,
     )
-    def list_jobs(self) -> List["FinetuneJob"]:
+    def list_jobs(self) -> list["FinetuneJob"]:
         """Show current and past fine-tuning runs.
 
         Returns:
@@ -253,7 +253,7 @@ class Finetune:
         return [FinetuneJob(session=self._session, status=FinetuneStatus(**run_status)) for run_status in result]
 
 
-def _try_load_json(json_string: str) -> Union[Dict[Any, Any], List[Any]]:
+def _try_load_json(json_string: str) -> Union[dict[Any, Any], list[Any]]:
     try:
         result = json.loads(str(json_string))
     except json.JSONDecodeError as e:
@@ -269,5 +269,5 @@ def _try_load_json(json_string: str) -> Union[Dict[Any, Any], List[Any]]:
     return result
 
 
-def _finetune_impl(operation: str, session: Optional[snowpark.Session], function_args: List[Any]) -> str:
+def _finetune_impl(operation: str, session: Optional[snowpark.Session], function_args: list[Any]) -> str:
     return call_sql_function_literals(_CORTEX_FINETUNE_SYSTEM_FUNCTION_NAME, session, operation, *function_args)

{snowflake_ml_python-1.8.2 → snowflake_ml_python-1.8.4}/snowflake/cortex/_util.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional, Union, cast
+from typing import Any, Optional, Union, cast
 
 from snowflake import snowpark
 from snowflake.ml._internal.exceptions import error_codes, exceptions
@@ -11,22 +11,18 @@ CORTEX_FUNCTIONS_TELEMETRY_PROJECT = "CortexFunctions"
 class SnowflakeAuthenticationException(Exception):
     """This exception is raised when there is an issue with Snowflake's configuration."""
 
-    pass
-
 
 class SnowflakeConfigurationException(Exception):
     """This exception is raised when there is an issue with Snowflake's configuration."""
 
-    pass
-
 
 # Calls a sql function, handling both immediate (e.g. python types) and batch
 # (e.g. snowpark column and literal type modes).
 def call_sql_function(
     function: str,
     session: Optional[snowpark.Session],
-    *args: Union[str, List[str], snowpark.Column, Dict[str, Union[int, float]]],
-) -> Union[str, List[float], snowpark.Column]:
+    *args: Union[str, list[str], snowpark.Column, dict[str, Union[int, float]]],
+) -> Union[str, list[float], snowpark.Column]:
     handle_as_column = False
 
     for arg in args:
@@ -34,15 +30,15 @@ def call_sql_function(
             handle_as_column = True
 
     if handle_as_column:
-        return cast(Union[str, List[float], snowpark.Column], _call_sql_function_column(function, *args))
+        return cast(Union[str, list[float], snowpark.Column], _call_sql_function_column(function, *args))
     return cast(
-        Union[str, List[float], snowpark.Column],
+        Union[str, list[float], snowpark.Column],
         _call_sql_function_immediate(function, session, *args),
     )
 
 
 def _call_sql_function_column(
-    function: str, *args: Union[str, List[str], snowpark.Column, Dict[str, Union[int, float]]]
+    function: str, *args: Union[str, list[str], snowpark.Column, dict[str, Union[int, float]]]
 ) -> snowpark.Column:
     return cast(snowpark.Column, functions.builtin(function)(*args))
 
@@ -50,8 +46,8 @@ def _call_sql_function_column(
 def _call_sql_function_immediate(
     function: str,
     session: Optional[snowpark.Session],
-    *args: Union[str, List[str], snowpark.Column, Dict[str, Union[int, float]]],
-) -> Union[str, List[float]]:
+    *args: Union[str, list[str], snowpark.Column, dict[str, Union[int, float]]],
+) -> Union[str, list[float]]:
     session = session or context.get_active_session()
     if session is None:
         raise SnowflakeAuthenticationException(

snowflake_ml_python-1.8.4/snowflake/ml/_internal/env.py

@@ -0,0 +1,9 @@
+import os
+import platform
+
+SOURCE = "SnowML"
+PYTHON_VERSION = platform.python_version()
+OS = platform.system()
+IN_ML_RUNTIME_ENV_VAR = "IN_SPCS_ML_RUNTIME"
+IN_ML_RUNTIME = os.getenv(IN_ML_RUNTIME_ENV_VAR)
+USE_OPTIMIZED_DATA_INGESTOR = "USE_OPTIMIZED_DATA_INGESTOR"