snowflake-ml-python 1.44.0__tar.gz → 1.46.0__tar.gz

{snowflake_ml_python-1.44.0 → snowflake_ml_python-1.46.0}/CHANGELOG.md

@@ -1,6 +1,94 @@
 # Release History
 
-## 1.44.0
+## 1.46.0
+
+### New Features
+
+### Bug Fixes
+
+### Behavior Changes
+
+* Registry: For Snowpark ML Pipeline models with explainability enabled, explanations now cover only the columns the
+  final estimator was actually trained on (its `input_cols`). Untransformed passthrough columns (e.g. raw string
+  columns left in place by an encoder using new `output_cols`, or the label column) are no longer included in the
+  explain output. This also fixes a failure where such passthrough columns could reach the SHAP explainer and raise an
+  error during `log_model(..., enable_explainability=True)`.
+
+### Deprecations
+
+## 1.45.0 (2026-07-01)
+
+### New Features
+
+* Feature Store: `FeatureView` now supports an `initialization_warehouse` that is used for the initial build and any
+  subsequent reinitializations of the backing dynamic table (a full scan of the source data), while `warehouse`
+  continues to drive the lighter incremental refreshes. This mirrors the dynamic table `INITIALIZATION_WAREHOUSE`
+  knob, lets you pair a larger warehouse for initialization with a smaller one for steady-state refresh, and is also
+  used for the one-time backfill of streaming feature views. It can be set at registration, changed via
+  `update_feature_view(initialization_warehouse=...)`, and is surfaced by `list_feature_views(verbose=True)`.
+
+```python
+draft_fv = FeatureView(
+    name="F_TRIP",
+    entities=[entity],
+    feature_df=feature_df,
+    refresh_freq="1d",
+    warehouse="SMALL_WH",            # incremental refreshes
+    initialization_warehouse="LARGE_WH",  # initial build / reinitialization
+)
+fv = fs.register_feature_view(draft_fv, version="1.0")
+```
+
+* Registry: LLM models deployed with the OpenAI chat signatures now support structured outputs
+  through an optional `response_format` param matching the OpenAI Chat Completions API
+  (`{"type": "json_schema", "json_schema": {"name": "...", "schema": {...}}}`), letting callers
+  constrain model output to a JSON Schema.
+
+```python
+from pydantic import BaseModel
+import pandas as pd
+
+class CityCountry(BaseModel):
+    city: str
+    country: str
+
+response_format = {
+    "type": "json_schema",
+    "json_schema": {
+        "name": "city_country",
+        "schema": CityCountry.model_json_schema(),
+    },
+}
+
+x_df = pd.DataFrame.from_records(
+    [
+        {
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": "What is the capital of France?"},
+                    ],
+                },
+            ],
+        }
+    ]
+)
+
+mv.run(
+    X=x_df,
+    params={"response_format": response_format},
+    service_name=...,
+)
+```
+
+### Bug Fixes
+
+### Behavior Changes
+
+### Deprecations
+
+## 1.44.0 (2026-06-23)
 
 ### New Features
 

{snowflake_ml_python-1.44.0 → snowflake_ml_python-1.46.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-ml-python
-Version: 1.44.0
+Version: 1.46.0
 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: 
@@ -264,7 +264,7 @@ Requires-Dist: altair<7,>=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<4,>=2.16.0; extra == "all"
+Requires-Dist: mlflow<3,>=2.16.0; extra == "all"
 Requires-Dist: prophet<2,>=1.1.0; extra == "all"
 Requires-Dist: sentence-transformers<6,>=2.7.0; extra == "all"
 Requires-Dist: sentencepiece<0.3,>=0.1.95; extra == "all"
@@ -285,7 +285,7 @@ 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: mlflow<4,>=2.16.0; extra == "llm"
+Requires-Dist: mlflow<3,>=2.16.0; extra == "llm"
 Requires-Dist: sentence-transformers<6,>=2.7.0; extra == "llm"
 Requires-Dist: sentencepiece<0.3,>=0.1.95; extra == "llm"
 Requires-Dist: tokenizers<1,>=0.15.1; extra == "llm"
@@ -293,7 +293,7 @@ Requires-Dist: torch<3,>=2.0.1; extra == "llm"
 Requires-Dist: torchdata<1,>=0.4; extra == "llm"
 Requires-Dist: transformers!=4.51.3,<6,>=4.39.3; extra == "llm"
 Provides-Extra: mlflow
-Requires-Dist: mlflow<4,>=2.16.0; extra == "mlflow"
+Requires-Dist: mlflow<3,>=2.16.0; extra == "mlflow"
 Provides-Extra: prophet
 Requires-Dist: prophet<2,>=1.1.0; extra == "prophet"
 Provides-Extra: streamlit
@@ -416,7 +416,95 @@ NOTE: Version 1.7.0 is used as example here. Please choose the the latest versio
 
 # Release History
 
-## 1.44.0
+## 1.46.0
+
+### New Features
+
+### Bug Fixes
+
+### Behavior Changes
+
+* Registry: For Snowpark ML Pipeline models with explainability enabled, explanations now cover only the columns the
+  final estimator was actually trained on (its `input_cols`). Untransformed passthrough columns (e.g. raw string
+  columns left in place by an encoder using new `output_cols`, or the label column) are no longer included in the
+  explain output. This also fixes a failure where such passthrough columns could reach the SHAP explainer and raise an
+  error during `log_model(..., enable_explainability=True)`.
+
+### Deprecations
+
+## 1.45.0 (2026-07-01)
+
+### New Features
+
+* Feature Store: `FeatureView` now supports an `initialization_warehouse` that is used for the initial build and any
+  subsequent reinitializations of the backing dynamic table (a full scan of the source data), while `warehouse`
+  continues to drive the lighter incremental refreshes. This mirrors the dynamic table `INITIALIZATION_WAREHOUSE`
+  knob, lets you pair a larger warehouse for initialization with a smaller one for steady-state refresh, and is also
+  used for the one-time backfill of streaming feature views. It can be set at registration, changed via
+  `update_feature_view(initialization_warehouse=...)`, and is surfaced by `list_feature_views(verbose=True)`.
+
+```python
+draft_fv = FeatureView(
+    name="F_TRIP",
+    entities=[entity],
+    feature_df=feature_df,
+    refresh_freq="1d",
+    warehouse="SMALL_WH",            # incremental refreshes
+    initialization_warehouse="LARGE_WH",  # initial build / reinitialization
+)
+fv = fs.register_feature_view(draft_fv, version="1.0")
+```
+
+* Registry: LLM models deployed with the OpenAI chat signatures now support structured outputs
+  through an optional `response_format` param matching the OpenAI Chat Completions API
+  (`{"type": "json_schema", "json_schema": {"name": "...", "schema": {...}}}`), letting callers
+  constrain model output to a JSON Schema.
+
+```python
+from pydantic import BaseModel
+import pandas as pd
+
+class CityCountry(BaseModel):
+    city: str
+    country: str
+
+response_format = {
+    "type": "json_schema",
+    "json_schema": {
+        "name": "city_country",
+        "schema": CityCountry.model_json_schema(),
+    },
+}
+
+x_df = pd.DataFrame.from_records(
+    [
+        {
+            "messages": [
+                {
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": "What is the capital of France?"},
+                    ],
+                },
+            ],
+        }
+    ]
+)
+
+mv.run(
+    X=x_df,
+    params={"response_format": response_format},
+    service_name=...,
+)
+```
+
+### Bug Fixes
+
+### Behavior Changes
+
+### Deprecations
+
+## 1.44.0 (2026-06-23)
 
 ### New Features
 

{snowflake_ml_python-1.44.0 → snowflake_ml_python-1.46.0}/pyproject.toml

@@ -24,13 +24,13 @@ 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 = [ "altair>=5,<7", "catboost>=1.2.0, <2", "keras>=2.0.0,<4", "lightgbm>=4.1.0, <5", "mlflow>=2.16.0, <4", "prophet>=1.1.0, <2", "sentence-transformers>=2.7.0,<6", "sentencepiece>=0.1.95,<0.3", "streamlit>=1.30.0,<2", "tensorflow>=2.17.0,<3", "tokenizers>=0.15.1,<1", "torch>=2.0.1,<3", "torchdata>=0.4,<1", "transformers>=4.39.3,!=4.51.3,<6",]
+all = [ "altair>=5,<7", "catboost>=1.2.0, <2", "keras>=2.0.0,<4", "lightgbm>=4.1.0, <5", "mlflow>=2.16.0, <3", "prophet>=1.1.0, <2", "sentence-transformers>=2.7.0,<6", "sentencepiece>=0.1.95,<0.3", "streamlit>=1.30.0,<2", "tensorflow>=2.17.0,<3", "tokenizers>=0.15.1,<1", "torch>=2.0.1,<3", "torchdata>=0.4,<1", "transformers>=4.39.3,!=4.51.3,<6",]
 altair = [ "altair>=5,<7",]
 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",]
-llm = [ "mlflow>=2.16.0, <4", "sentence-transformers>=2.7.0,<6", "sentencepiece>=0.1.95,<0.3", "tokenizers>=0.15.1,<1", "torch>=2.0.1,<3", "torchdata>=0.4,<1", "transformers>=4.39.3,!=4.51.3,<6",]
-mlflow = [ "mlflow>=2.16.0, <4",]
+llm = [ "mlflow>=2.16.0, <3", "sentence-transformers>=2.7.0,<6", "sentencepiece>=0.1.95,<0.3", "tokenizers>=0.15.1,<1", "torch>=2.0.1,<3", "torchdata>=0.4,<1", "transformers>=4.39.3,!=4.51.3,<6",]
+mlflow = [ "mlflow>=2.16.0, <3",]
 prophet = [ "prophet>=1.1.0, <2",]
 streamlit = [ "streamlit>=1.30.0,<2",]
 tensorflow = [ "tensorflow>=2.17.0,<3",]

{snowflake_ml_python-1.44.0 → snowflake_ml_python-1.46.0}/snowflake/ml/_internal/file_utils.py

@@ -313,6 +313,38 @@ def _resolve_stage_dir_path(
         return str((stage_path / relative_path).parent)
 
 
+def upload_file_to_stage(
+    session: snowpark.Session,
+    local_file_path: Union[str, pathlib.Path],
+    stage_dir_path: str,
+    *,
+    statement_params: Optional[dict[str, Any]] = None,
+) -> None:
+    """Upload a single local file to a stage directory.
+
+    Args:
+        session: Snowpark Session.
+        local_file_path: Local path of the file to upload.
+        stage_dir_path: Destination directory path in the stage.
+        statement_params: Statement Params.
+    """
+    import retrying
+
+    file_operation = snowpark.FileOperation(session=session)
+    retrying.retry(
+        retry_on_exception=_retry_on_sql_error,
+        stop_max_attempt_number=5,
+        wait_exponential_multiplier=100,
+        wait_exponential_max=10000,
+    )(file_operation.put)(
+        str(local_file_path),
+        str(stage_dir_path),
+        auto_compress=False,
+        overwrite=False,
+        statement_params=statement_params,
+    )
+
+
 def upload_directory_to_stage(
     session: snowpark.Session,
     local_path: pathlib.Path,
@@ -328,27 +360,16 @@ def upload_directory_to_stage(
         stage_path: Base path in the stage.
         statement_params: Statement Params.
     """
-    import retrying
-
-    file_operation = snowpark.FileOperation(session=session)
-
     for root, _, filenames in os.walk(local_path):
         root_path = pathlib.Path(root)
         for filename in filenames:
             local_file_path = root_path / filename
             relative_path = pathlib.PurePosixPath(local_file_path.relative_to(local_path).as_posix())
             stage_dir_path = _resolve_stage_dir_path(stage_path, relative_path)
-
-            retrying.retry(
-                retry_on_exception=_retry_on_sql_error,
-                stop_max_attempt_number=5,
-                wait_exponential_multiplier=100,
-                wait_exponential_max=10000,
-            )(file_operation.put)(
-                str(local_file_path),
-                str(stage_dir_path),
-                auto_compress=False,
-                overwrite=False,
+            upload_file_to_stage(
+                session,
+                local_file_path,
+                stage_dir_path,
                 statement_params=statement_params,
             )
 

{snowflake_ml_python-1.44.0 → snowflake_ml_python-1.46.0}/snowflake/ml/_internal/utils/jwt_generator.py

@@ -1,3 +1,7 @@
+# Annotations are lazy so ``types.PrivateKeyTypes`` (added in cryptography 40.0, replacing the
+# now-removed ``PRIVATE_KEY_TYPES``) is never evaluated at runtime and stays version-tolerant.
+from __future__ import annotations
+
 import base64
 import hashlib
 import logging
@@ -30,7 +34,7 @@ class JWTGenerator:
         self,
         account: str,
         user: str,
-        private_key: types.PRIVATE_KEY_TYPES,
+        private_key: types.PrivateKeyTypes,
         lifetime: Optional[timedelta] = None,
         renewal_delay: Optional[timedelta] = None,
     ) -> None:
@@ -125,7 +129,7 @@ class JWTGenerator:
         return token
 
     @staticmethod
-    def _calculate_public_key_fingerprint(private_key: types.PRIVATE_KEY_TYPES) -> str:
+    def _calculate_public_key_fingerprint(private_key: types.PrivateKeyTypes) -> str:
         # Get the raw bytes of public key.
         public_key_raw = private_key.public_key().public_bytes(
             serialization.Encoding.DER, serialization.PublicFormat.SubjectPublicKeyInfo

{snowflake_ml_python-1.44.0 → snowflake_ml_python-1.46.0}/snowflake/ml/experiment/_client/experiment_tracking_sql_client.py

@@ -118,11 +118,20 @@ class ExperimentTrackingSQLClient(_base._BaseSQLClient):
         ).validate()
 
     @telemetry.send_api_usage_telemetry(project=telemetry.TelemetryProject.EXPERIMENT_TRACKING.value)
-    def add_run(self, *, experiment_name: sql_identifier.SqlIdentifier, run_name: sql_identifier.SqlIdentifier) -> None:
+    def add_run(
+        self,
+        *,
+        experiment_name: sql_identifier.SqlIdentifier,
+        run_name: sql_identifier.SqlIdentifier,
+        source_info: Optional[str] = None,
+    ) -> None:
         experiment_fqn = self.fully_qualified_object_name(self._database_name, self._schema_name, experiment_name)
-        query_result_checker.SqlResultValidator(
-            self._session, f"ALTER EXPERIMENT {experiment_fqn} ADD RUN {run_name}"
-        ).has_dimensions(expected_rows=1, expected_cols=1).validate()
+        query = f"ALTER EXPERIMENT {experiment_fqn} ADD RUN {run_name}"
+        if source_info:
+            query += f" WITH (SOURCE_INFO = $${source_info}$$)"
+        query_result_checker.SqlResultValidator(self._session, query).has_dimensions(
+            expected_rows=1, expected_cols=1
+        ).validate()
 
     @telemetry.send_api_usage_telemetry(project=telemetry.TelemetryProject.EXPERIMENT_TRACKING.value)
     def commit_run(