snowflake-ml-python 1.7.4__py3-none-any.whl → 1.8.0__py3-none-any.whl

{snowflake_ml_python-1.7.4.dist-info → snowflake_ml_python-1.8.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: snowflake-ml-python
-Version: 1.7.4
+Version: 1.8.0
 Summary: The machine learning client library that is used for interacting with Snowflake to build machine learning solutions.
 Author-email: "Snowflake, Inc" <support@snowflake.com>
 License: 
@@ -223,13 +223,14 @@ Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Database
 Classifier: Topic :: Software Development
 Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: <3.12,>=3.9
+Requires-Python: <3.13,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: absl-py<2,>=0.15
@@ -250,46 +251,48 @@ Requires-Dist: retrying<2,>=1.3.3
 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-connector-python[pandas]<4,>=3.12.0
 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
 Provides-Extra: all
 Requires-Dist: catboost<2,>=1.2.0; extra == "all"
-Requires-Dist: huggingface_hub<0.26; extra == "all"
+Requires-Dist: keras<4,>=2.0.0; extra == "all"
 Requires-Dist: lightgbm<5,>=4.1.0; extra == "all"
 Requires-Dist: mlflow<3,>=2.16.0; extra == "all"
-Requires-Dist: peft<1,>=0.5.0; extra == "all"
-Requires-Dist: sentence-transformers<3,>=2.2.2; extra == "all"
-Requires-Dist: sentencepiece<1,>=0.1.95; extra == "all"
+Requires-Dist: sentence-transformers<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: tensorflow<3,>=2.12.0; extra == "all"
-Requires-Dist: tokenizers<1,>=0.10; extra == "all"
-Requires-Dist: torch<2.3.0,>=2.0.1; extra == "all"
+Requires-Dist: tensorflow<3,>=2.17.0; extra == "all"
+Requires-Dist: tokenizers<1,>=0.15.1; extra == "all"
+Requires-Dist: torch<3,>=2.0.1; extra == "all"
 Requires-Dist: torchdata<1,>=0.4; extra == "all"
-Requires-Dist: transformers<5,>=4.32.1; extra == "all"
+Requires-Dist: transformers<5,>=4.39.3; extra == "all"
 Provides-Extra: catboost
 Requires-Dist: catboost<2,>=1.2.0; extra == "catboost"
+Provides-Extra: keras
+Requires-Dist: keras<4,>=2.0.0; extra == "keras"
+Requires-Dist: tensorflow<3,>=2.17.0; extra == "keras"
+Requires-Dist: torch<3,>=2.0.1; extra == "keras"
 Provides-Extra: lightgbm
 Requires-Dist: lightgbm<5,>=4.1.0; extra == "lightgbm"
-Provides-Extra: llm
-Requires-Dist: peft<1,>=0.5.0; extra == "llm"
 Provides-Extra: mlflow
 Requires-Dist: mlflow<3,>=2.16.0; extra == "mlflow"
 Provides-Extra: shap
 Requires-Dist: shap<1,>=0.46.0; extra == "shap"
 Provides-Extra: tensorflow
-Requires-Dist: tensorflow<3,>=2.12.0; extra == "tensorflow"
+Requires-Dist: tensorflow<3,>=2.17.0; extra == "tensorflow"
 Provides-Extra: torch
-Requires-Dist: torch<2.3.0,>=2.0.1; extra == "torch"
+Requires-Dist: torch<3,>=2.0.1; extra == "torch"
 Requires-Dist: torchdata<1,>=0.4; extra == "torch"
 Provides-Extra: transformers
-Requires-Dist: huggingface_hub<0.26; extra == "transformers"
-Requires-Dist: sentence-transformers<3,>=2.2.2; extra == "transformers"
-Requires-Dist: sentencepiece<1,>=0.1.95; extra == "transformers"
-Requires-Dist: tokenizers<1,>=0.10; extra == "transformers"
-Requires-Dist: transformers<5,>=4.32.1; extra == "transformers"
+Requires-Dist: sentence-transformers<4,>=2.7.0; extra == "transformers"
+Requires-Dist: sentencepiece<0.2.0,>=0.1.95; extra == "transformers"
+Requires-Dist: tokenizers<1,>=0.15.1; extra == "transformers"
+Requires-Dist: torch<3,>=2.0.1; extra == "transformers"
+Requires-Dist: transformers<5,>=4.39.3; extra == "transformers"
+Dynamic: license-file
 
 # Snowpark ML
 
@@ -346,7 +349,7 @@ If you don't have a Snowflake account yet, you can [sign up for a 30-day free tr
 Follow the [installation instructions](https://docs.snowflake.com/en/developer-guide/snowpark-ml/index#installing-snowpark-ml)
 in the Snowflake documentation.
 
-Python versions 3.9 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
+Python versions 3.9 to 3.12 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
 [anaconda](https://www.anaconda.com/) to create a Conda environment (recommended),
 or [virtualenv](https://docs.python.org/3/tutorial/venv.html) to create a virtual environment.
 
@@ -399,28 +402,329 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
-## 1.7.4
+## 1.8.0
+
+### Bug Fixes
+
+- Modeling: Fix a bug in some metrics that allowed an unsupported version of numpy to be installed
+  automatically in the stored procedure, resulting in a numpy error on execution
+- Registry: Fix a bug that leads to incorrect `Model is does not have _is_inference_api` error message when assigning
+  a supported model as a property of a CustomModel.
+- Registry: Fix a bug that inference is not working when models with more than 500 input features
+  are deployed to SPCS.
+
+### Behavior Change
+
+- Registry: With FeatureGroupSpec support, auto inferred model signature for `transformers.Pipeline` models have been
+  updated, including:
+  - Signature for fill-mask task has been changed from
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="inputs", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureSpec(name="outputs", dtype=DataType.STRING),
+        ],
+    )
+    ```
+
+    to
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="inputs", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureGroupSpec(
+                name="outputs",
+                specs=[
+                    FeatureSpec(name="sequence", dtype=DataType.STRING),
+                    FeatureSpec(name="score", dtype=DataType.DOUBLE),
+                    FeatureSpec(name="token", dtype=DataType.INT64),
+                    FeatureSpec(name="token_str", dtype=DataType.STRING),
+                ],
+                shape=(-1,),
+            ),
+        ],
+    )
+    ```
+
+  - Signature for token-classification task has been changed from
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="inputs", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureSpec(name="outputs", dtype=DataType.STRING),
+        ],
+    )
+    ```
+
+    to
+
+    ```python
+    ModelSignature(
+        inputs=[FeatureSpec(name="inputs", dtype=DataType.STRING)],
+        outputs=[
+            FeatureGroupSpec(
+                name="outputs",
+                specs=[
+                    FeatureSpec(name="word", dtype=DataType.STRING),
+                    FeatureSpec(name="score", dtype=DataType.DOUBLE),
+                    FeatureSpec(name="entity", dtype=DataType.STRING),
+                    FeatureSpec(name="index", dtype=DataType.INT64),
+                    FeatureSpec(name="start", dtype=DataType.INT64),
+                    FeatureSpec(name="end", dtype=DataType.INT64),
+                ],
+                shape=(-1,),
+            ),
+        ],
+    )
+    ```
+
+  - Signature for question-answering task when top_k is larger than 1 has been changed from
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="question", dtype=DataType.STRING),
+            FeatureSpec(name="context", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureSpec(name="outputs", dtype=DataType.STRING),
+        ],
+    )
+    ```
+
+    to
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="question", dtype=DataType.STRING),
+            FeatureSpec(name="context", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureGroupSpec(
+                name="answers",
+                specs=[
+                    FeatureSpec(name="score", dtype=DataType.DOUBLE),
+                    FeatureSpec(name="start", dtype=DataType.INT64),
+                    FeatureSpec(name="end", dtype=DataType.INT64),
+                    FeatureSpec(name="answer", dtype=DataType.STRING),
+                ],
+                shape=(-1,),
+            ),
+        ],
+    )
+    ```
+
+  - Signature for text-classification task when top_k is `None` has been changed from
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="text", dtype=DataType.STRING),
+            FeatureSpec(name="text_pair", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureSpec(name="label", dtype=DataType.STRING),
+            FeatureSpec(name="score", dtype=DataType.DOUBLE),
+        ],
+    )
+    ```
+
+    to
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="text", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureSpec(name="label", dtype=DataType.STRING),
+            FeatureSpec(name="score", dtype=DataType.DOUBLE),
+        ],
+    )
+    ```
+
+  - Signature for text-classification task when top_k is not `None` has been changed from
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="text", dtype=DataType.STRING),
+            FeatureSpec(name="text_pair", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureSpec(name="outputs", dtype=DataType.STRING),
+        ],
+    )
+    ```
+
+    to
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureSpec(name="text", dtype=DataType.STRING),
+        ],
+        outputs=[
+            FeatureGroupSpec(
+                name="labels",
+                specs=[
+                    FeatureSpec(name="label", dtype=DataType.STRING),
+                    FeatureSpec(name="score", dtype=DataType.DOUBLE),
+                ],
+                shape=(-1,),
+            ),
+        ],
+    )
+    ```
+
+  - Signature for text-generation task has been changed from
+
+    ```python
+    ModelSignature(
+        inputs=[FeatureSpec(name="inputs", dtype=DataType.STRING)],
+        outputs=[
+            FeatureSpec(name="outputs", dtype=DataType.STRING),
+        ],
+    )
+    ```
+
+    to
+
+    ```python
+    ModelSignature(
+        inputs=[
+            FeatureGroupSpec(
+                name="inputs",
+                specs=[
+                    FeatureSpec(name="role", dtype=DataType.STRING),
+                    FeatureSpec(name="content", dtype=DataType.STRING),
+                ],
+                shape=(-1,),
+            ),
+        ],
+        outputs=[
+            FeatureGroupSpec(
+                name="outputs",
+                specs=[
+                    FeatureSpec(name="generated_text", dtype=DataType.STRING),
+                ],
+                shape=(-1,),
+            )
+        ],
+    )
+    ```
+
+- Registry: PyTorch and TensorFlow models now expect a single tensor input/output by default when logging to Model
+  Registry. To use multiple tensors (previous behavior), set `options={"multiple_inputs": True}`.
+
+  Example with single tensor input:
+
+  ```python
+  import torch
+
+  class TorchModel(torch.nn.Module):
+      def __init__(self, n_input: int, n_hidden: int, n_out: int, dtype: torch.dtype = torch.float32) -> None:
+          super().__init__()
+          self.model = torch.nn.Sequential(
+              torch.nn.Linear(n_input, n_hidden, dtype=dtype),
+              torch.nn.ReLU(),
+              torch.nn.Linear(n_hidden, n_out, dtype=dtype),
+              torch.nn.Sigmoid(),
+          )
+
+      def forward(self, tensor: torch.Tensor) -> torch.Tensor:
+          return cast(torch.Tensor, self.model(tensor))
+
+  # Sample usage:
+  data_x = torch.rand(size=(batch_size, n_input))
+
+  # Log model with single tensor
+  reg.log_model(
+      model=model,
+      ...,
+      sample_input_data=data_x
+  )
+
+  # Run inference with single tensor
+  mv.run(data_x)
+  ```
+
+  For multiple tensor inputs/outputs, use:
+
+  ```python
+  reg.log_model(
+      model=model,
+      ...,
+      sample_input_data=[data_x_1, data_x_2],
+      options={"multiple_inputs": True}
+  )
+  ```
+
+- Registry: Default `enable_explainability` to False when the model can be deployed to Snowpark Container Services.
+
+### New Features
+
+- Registry: Added support to single `torch.Tensor`, `tensorflow.Tensor` and `tensorflow.Variable` as input or output
+  data.
+- Registry: Support [`xgboost.DMatrix`](https://xgboost.readthedocs.io/en/stable/python/python_api.html#xgboost.DMatrix)
+ datatype for XGBoost models.
+
+## 1.7.5 (03-06-2025)
+
+- Support Python 3.12.
+- Explainability: Support native and snowflake.ml.modeling sklearn pipeline
+
+### Bug Fixes
+
+- Registry: Fixed a compatibility issue when using `snowflake-ml-python` 1.7.0 or greater to save a `tensorflow.keras`
+  model with `keras` 2.x, if `relax_version` is set or default to True, and newer version of `snowflake-ml-python`
+  is available in Snowflake Anaconda Channel, model could not be run in Snowflake. If you have such model, you could
+  use the latest version of `snowflake-ml-python` and call `ModelVersion.load` to load it back, and re-log it.
+  Alternatively, you can prevent this issue by setting `relax_version=False` when saving the model.
+- Registry: Removed the validation that disallows data that does not have non-null values being passed to
+  `ModelVersion.run`.
+- ML Job (PrPr): No longer require CREATE STAGE privilege if `stage_name` points to an existing stage
+- ML Job (PrPr): Fixed a bug causing some payload source and entrypoint path
+  combinations to be erroneously rejected with
+  `ValueError(f"{self.entrypoint} must be a subpath of {self.source}")`
+- ML Job (PrPr): Fixed a bug in Ray cluster startup config which caused certain Runtime APIs to fail
+
+### New Features
+
+- Registry: Added support for handling Hugging Face model configurations with auto-mapping functionality.
+- Registry: Added support for `keras` 3.x model with `tensorflow` and `pytorch` backend
+- ML Job (PrPr): Support any serializable (pickleable) argument for `@remote` decorated functions
+
+## 1.7.4 (01-28-2025)
 
 - FileSet: The `snowflake.ml.fileset.FileSet` has been deprecated and will be removed in a future version.
   Use [snowflake.ml.dataset.Dataset](https://docs.snowflake.com/en/developer-guide/snowflake-ml/dataset) and
   [snowflake.ml.data.DataConnector](https://docs.snowflake.com/en/developer-guide/snowpark-ml/reference/latest/api/data/snowflake.ml.data.data_connector.DataConnector)
   instead.
+- Registry: `ModelVersion.run` on a service would require redeploying the service once account opts into nested function.
 
 ### Bug Fixes
 
 - Registry: Fixed an issue that the hugging face pipeline is loaded using incorrect dtype.
 - Registry: Fixed an issue that only 1 row is used when infer the model signature in the modeling model.
 
-### Behavior Changes
-
-- Registry: `ModelVersion.run` on a service would require redeploying the service once account opts into nested function.
-
 ### New Features
 
 - Add new `snowflake.ml.jobs` preview API for running headless workloads on SPCS using
   [Container Runtime for ML](https://docs.snowflake.com/en/developer-guide/snowflake-ml/container-runtime-ml)
 - Added `guardrails` option to Cortex `complete` function, enabling
   [Cortex Guard](https://docs.snowflake.com/en/user-guide/snowflake-cortex/llm-functions#cortex-guard) support
+- Model Monitoring: Expose Model Monitoring Python API by default.
 
 ## 1.7.3 (2025-01-08)
 
@@ -428,6 +732,7 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 - Bumped the requirements of `fsspec` and `s3fs` to `>=2024.6.1,<2026`
 - Bumped the requirement of `mlflow` to `>=2.16.0, <3`
 - Registry: Support 500+ features for model registry
+- Feature Store: Add support for `cluster_by` for feature views.
 
 ### Bug Fixes
 
@@ -545,6 +850,10 @@ class ExamplePipelineModel(custom_model.CustomModel):
 - Data Connector: Add the option of passing a `None` sized batch to `to_torch_dataset` for better
 interoperability with PyTorch DataLoader.
 - Model Registry: Support [pandas.CategoricalDtype](https://pandas.pydata.org/docs/reference/api/pandas.CategoricalDtype.html#pandas-categoricaldtype)
+  - Limitations:
+    - The native categorical data handling handling by XGBoost using `enable_categorical=True` is not supported.
+    Instead please use [`sklearn.pipeline`](https://scikit-learn.org/stable/modules/generated/sklearn.pipeline.Pipeline.html)
+    to preprocess the categorical datatype and log the pipeline with the XGBoost model.
 - Registry: It is now possible to pass `signatures` and `sample_input_data` at the same time to capture background
 data from explainablity and data lineage.