snowflake-ml-python 1.23.0__tar.gz → 1.25.0__tar.gz

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/CHANGELOG.md

@@ -1,5 +1,74 @@
 # Release History
 
+## 1.25.0
+
+### New Features
+
+* ML Job: Added support for creating ML job definitions and launching jobs with different
+  arguments without re-uploading payloads.
+
+* Inference Autocapture (PuPr): The `create_service` API will now accept `autocapture` as a new argument to indicate
+  whether inference data will be captured.
+
+* Model serving: Introduced the `min_instances` field in the `mv.create_service()` and
+  `HuggingFacePipelineModel.log_model_and_create_service()` APIs (defaulting to 0). The service now launches
+  with the `min_instances` and automatically scales between `min_instances` and `max_instances` based on
+  traffic and hardware utilization. When `min_instances` is set to 0, the service will automatically suspend
+  if no traffic is detected for a period of time.
+
+### Bug Fixes
+
+### Behavior Changes
+
+* Inference Autocapture (PuPr): `list_services()` now shows `autocapture_enabled` column to indicate if model
+  service has autocapture enabled.
+
+* Model serving: The `mv.create_service()` and `HuggingFacePipelineModel.log_model_and_create_service()` APIs now
+  include a `min_instances` field (defaulting to 0). When these APIs are called without specifying `min_instances`,
+  the system will now launch the service with 1 instance and enable auto scaling. This replaces the previous behavior,
+  where `min_instances` was automatically set to match `max_instances`, resulting in the immediate launch of the
+  maximum number of instances.
+
+### Deprecations
+
+## 1.24.0
+
+### New Features
+
+* Feature Store: Added tile-based aggregation support with a new `Feature` API for efficient and
+  point-in-time correct time-series feature computation using pre-computed tiles stored in Dynamic Tables.
+
+* Registry: Added auto-signature inference for SentenceTransformer models. When logging a SentenceTransformer
+  model, `sample_input_data` is now optional. If not provided, the signature is automatically inferred from
+  the model's embedding dimension. Supported methods: `encode`, `encode_query`, `encode_document`,
+  `encode_queries`, `encode_documents`.
+
+```python
+import sentence_transformers
+from snowflake.ml.registry import Registry
+
+# Create model
+model = sentence_transformers.SentenceTransformer("all-MiniLM-L6-v2")
+
+# Log model without sample_input_data - signature is auto-inferred
+registry = Registry(session)
+mv = registry.log_model(
+    model=model,
+    model_name="my_sentence_transformer",
+    version_name="v1",
+)
+
+# Run inference with auto-inferred signature (input: "text", output: "output")
+import pandas as pd
+result = mv.run(pd.DataFrame({"text": ["Hello world"]}))
+```
+
+### Bug Fixes
+
+### Behavior Changes
+
+### Deprecations
+
 ## 1.23.0
 
 ### New Features
@@ -65,7 +134,15 @@ x_df = pd.DataFrame.from_records(
     [
         {
             "messages": [
-                {"role": "system", "content": "Complete the sentence."},
+                {
+                  "role": "system",
+                  "content": [
+                        {
+                            "type": "text",
+                            "text": "Complete the sentence."
+                        },
+                  ]
+                },
                 {
                     "role": "user",
                     "content": [

{snowflake_ml_python-1.23.0/snowflake_ml_python.egg-info → snowflake_ml_python-1.25.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-ml-python
-Version: 1.23.0
+Version: 1.25.0
 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: 
@@ -417,6 +417,75 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
+## 1.25.0
+
+### New Features
+
+* ML Job: Added support for creating ML job definitions and launching jobs with different
+  arguments without re-uploading payloads.
+
+* Inference Autocapture (PuPr): The `create_service` API will now accept `autocapture` as a new argument to indicate
+  whether inference data will be captured.
+
+* Model serving: Introduced the `min_instances` field in the `mv.create_service()` and
+  `HuggingFacePipelineModel.log_model_and_create_service()` APIs (defaulting to 0). The service now launches
+  with the `min_instances` and automatically scales between `min_instances` and `max_instances` based on
+  traffic and hardware utilization. When `min_instances` is set to 0, the service will automatically suspend
+  if no traffic is detected for a period of time.
+
+### Bug Fixes
+
+### Behavior Changes
+
+* Inference Autocapture (PuPr): `list_services()` now shows `autocapture_enabled` column to indicate if model
+  service has autocapture enabled.
+
+* Model serving: The `mv.create_service()` and `HuggingFacePipelineModel.log_model_and_create_service()` APIs now
+  include a `min_instances` field (defaulting to 0). When these APIs are called without specifying `min_instances`,
+  the system will now launch the service with 1 instance and enable auto scaling. This replaces the previous behavior,
+  where `min_instances` was automatically set to match `max_instances`, resulting in the immediate launch of the
+  maximum number of instances.
+
+### Deprecations
+
+## 1.24.0
+
+### New Features
+
+* Feature Store: Added tile-based aggregation support with a new `Feature` API for efficient and
+  point-in-time correct time-series feature computation using pre-computed tiles stored in Dynamic Tables.
+
+* Registry: Added auto-signature inference for SentenceTransformer models. When logging a SentenceTransformer
+  model, `sample_input_data` is now optional. If not provided, the signature is automatically inferred from
+  the model's embedding dimension. Supported methods: `encode`, `encode_query`, `encode_document`,
+  `encode_queries`, `encode_documents`.
+
+```python
+import sentence_transformers
+from snowflake.ml.registry import Registry
+
+# Create model
+model = sentence_transformers.SentenceTransformer("all-MiniLM-L6-v2")
+
+# Log model without sample_input_data - signature is auto-inferred
+registry = Registry(session)
+mv = registry.log_model(
+    model=model,
+    model_name="my_sentence_transformer",
+    version_name="v1",
+)
+
+# Run inference with auto-inferred signature (input: "text", output: "output")
+import pandas as pd
+result = mv.run(pd.DataFrame({"text": ["Hello world"]}))
+```
+
+### Bug Fixes
+
+### Behavior Changes
+
+### Deprecations
+
 ## 1.23.0
 
 ### New Features
@@ -482,7 +551,15 @@ x_df = pd.DataFrame.from_records(
     [
         {
             "messages": [
-                {"role": "system", "content": "Complete the sentence."},
+                {
+                  "role": "system",
+                  "content": [
+                        {
+                            "type": "text",
+                            "text": "Complete the sentence."
+                        },
+                  ]
+                },
                 {
                     "role": "user",
                     "content": [

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/snowflake/ml/_internal/platform_capabilities.py

@@ -19,7 +19,6 @@ LIVE_COMMIT_PARAMETER = "ENABLE_LIVE_VERSION_IN_SDK"
 INLINE_DEPLOYMENT_SPEC_PARAMETER = "ENABLE_INLINE_DEPLOYMENT_SPEC_FROM_CLIENT_VERSION"
 SET_MODULE_FUNCTIONS_VOLATILITY_FROM_MANIFEST = "SET_MODULE_FUNCTIONS_VOLATILITY_FROM_MANIFEST"
 ENABLE_MODEL_METHOD_SIGNATURE_PARAMETERS = "ENABLE_MODEL_METHOD_SIGNATURE_PARAMETERS"
-FEATURE_MODEL_INFERENCE_AUTOCAPTURE = "FEATURE_MODEL_INFERENCE_AUTOCAPTURE"
 
 
 class PlatformCapabilities:
@@ -85,9 +84,6 @@ class PlatformCapabilities:
     def is_model_method_signature_parameters_enabled(self) -> bool:
         return self._get_bool_feature(ENABLE_MODEL_METHOD_SIGNATURE_PARAMETERS, False)
 
-    def is_inference_autocapture_enabled(self) -> bool:
-        return self._is_feature_enabled(FEATURE_MODEL_INFERENCE_AUTOCAPTURE)
-
     @staticmethod
     def _get_features(session: snowpark_session.Session) -> dict[str, Any]:
         try:

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/snowflake/ml/_internal/utils/mixins.py

@@ -9,6 +9,7 @@ _SESSION_ACCOUNT_KEY = "session$account"
 _SESSION_ROLE_KEY = "session$role"
 _SESSION_DATABASE_KEY = "session$database"
 _SESSION_SCHEMA_KEY = "session$schema"
+_SESSION_STATE_ATTR = "_session_state"
 
 
 def _identifiers_match(saved: Optional[str], current: Optional[str]) -> bool:
@@ -61,7 +62,7 @@ class SerializableSessionMixin:
         else:
             self.__dict__.update(state)
 
-        self._set_session(session_state)
+        setattr(self, _SESSION_STATE_ATTR, session_state)
 
     def _set_session(self, session_state: _SessionState) -> None:
 
@@ -86,3 +87,27 @@ class SerializableSessionMixin:
                     ),
                 ),
             )
+
+    @property
+    def session(self) -> Optional[snowpark_session.Session]:
+        if _SESSION_KEY not in self.__dict__:
+            session_state = getattr(self, _SESSION_STATE_ATTR, None)
+            if session_state is not None:
+                self._set_session(session_state)
+        return self.__dict__.get(_SESSION_KEY)
+
+    @session.setter
+    def session(self, value: Optional[snowpark_session.Session]) -> None:
+        self.__dict__[_SESSION_KEY] = value
+
+    # _getattr__ is only called when an attribute is NOT found through normal lookup.
+    # 1. Data descriptors (like @property with setter) from the class hierarchy
+    # 2. Instance __dict__ (e.g., self.x = 10)
+    # 3. Non-data descriptors (methods, `@property without setter) from the class hierarchy
+    # __getattr__ — only called if steps 1-3 all fail
+    def __getattr__(self, name: str) -> Any:
+        if name == _SESSION_KEY:
+            return self.session
+        if hasattr(super(), "__getattr__"):
+            return super().__getattr__(name)  # type: ignore[misc]
+        raise AttributeError(f"{type(self).__name__!s} object has no attribute {name!r}")

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/snowflake/ml/data/_internal/arrow_ingestor.py

@@ -73,15 +73,19 @@ class ArrowIngestor(data_ingestor.DataIngestor, mixins.SerializableSessionMixin)
         self._schema: Optional[pa.Schema] = None
 
     @classmethod
-    def from_sources(cls, session: snowpark.Session, sources: Sequence[data_source.DataSource]) -> "ArrowIngestor":
+    def from_sources(
+        cls, session: snowpark.Session, sources: Sequence[data_source.DataSource], **kwargs: Any
+    ) -> "ArrowIngestor":
         if session is None:
             raise ValueError("Session is required")
+        # Skipping kwargs until needed to avoid impact other workflows.
         return cls(session, sources)
 
     @classmethod
     def from_ray_dataset(
         cls,
         ray_ds: "ray.data.Dataset",
+        **kwargs: Any,
     ) -> "ArrowIngestor":
         raise NotImplementedError
 

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/snowflake/ml/data/data_connector.py

@@ -94,7 +94,7 @@ class DataConnector:
         **kwargs: Any,
     ) -> DataConnectorType:
         ingestor_class = ingestor_class or cls.DEFAULT_INGESTOR_CLASS
-        ray_ingestor = ingestor_class.from_ray_dataset(ray_ds=ray_ds)
+        ray_ingestor = ingestor_class.from_ray_dataset(ray_ds=ray_ds, **kwargs)
         return cls(ray_ingestor, **kwargs)
 
     @classmethod
@@ -111,7 +111,7 @@ class DataConnector:
         **kwargs: Any,
     ) -> DataConnectorType:
         ingestor_class = ingestor_class or cls.DEFAULT_INGESTOR_CLASS
-        ingestor = ingestor_class.from_sources(session, sources)
+        ingestor = ingestor_class.from_sources(session, sources, **kwargs)
         return cls(ingestor, **kwargs)
 
     @property

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/snowflake/ml/data/data_ingestor.py

@@ -16,7 +16,7 @@ DataIngestorType = TypeVar("DataIngestorType", bound="DataIngestor")
 class DataIngestor(Protocol):
     @classmethod
     def from_sources(
-        cls: type[DataIngestorType], session: snowpark.Session, sources: Sequence[data_source.DataSource]
+        cls: type[DataIngestorType], session: snowpark.Session, sources: Sequence[data_source.DataSource], **kwargs: Any
     ) -> DataIngestorType:
         raise NotImplementedError
 
@@ -24,6 +24,7 @@ class DataIngestor(Protocol):
     def from_ray_dataset(
         cls: type[DataIngestorType],
         ray_ds: "ray.data.Dataset",
+        **kwargs: Any,
     ) -> DataIngestorType:
         raise NotImplementedError
 

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/snowflake/ml/experiment/_experiment_info.py

@@ -3,7 +3,7 @@ import functools
 import types
 from typing import Callable, Optional
 
-from snowflake.ml import model
+from snowflake.ml.model._client.model import model_version_impl
 from snowflake.ml.registry._manager import model_manager
 
 
@@ -23,7 +23,7 @@ class ExperimentInfoPatcher:
     """
 
     # Store original method at class definition time to avoid recursive patching
-    _original_log_model: Callable[..., model.ModelVersion] = model_manager.ModelManager.log_model
+    _original_log_model: Callable[..., model_version_impl.ModelVersion] = model_manager.ModelManager.log_model
 
     # Stack of active experiment_info contexts for nested experiment support
     _experiment_info_stack: list[ExperimentInfo] = []
@@ -36,7 +36,7 @@ class ExperimentInfoPatcher:
         if not ExperimentInfoPatcher._experiment_info_stack:
 
             @functools.wraps(ExperimentInfoPatcher._original_log_model)
-            def patched(*args, **kwargs) -> model.ModelVersion:  # type: ignore[no-untyped-def]
+            def patched(*args, **kwargs) -> model_version_impl.ModelVersion:  # type: ignore[no-untyped-def]
                 # Use the most recent (top of stack) experiment_info for nested contexts
                 current_experiment_info = ExperimentInfoPatcher._experiment_info_stack[-1]
                 return ExperimentInfoPatcher._original_log_model(

{snowflake_ml_python-1.23.0 → snowflake_ml_python-1.25.0}/snowflake/ml/feature_store/__init__.py

@@ -3,6 +3,7 @@ import os
 from snowflake.ml._internal import init_utils
 
 from .access_manager import setup_feature_store
+from .feature import Feature
 
 pkg_dir = os.path.dirname(__file__)
 pkg_name = __name__
@@ -12,4 +13,5 @@ for k, v in exportable_classes.items():
 
 __all__ = list(exportable_classes.keys()) + [
     "setup_feature_store",
+    "Feature",
 ]