snowflake-ml-python 1.6.4__tar.gz → 1.7.1__tar.gz

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.1}/CHANGELOG.md

@@ -1,6 +1,95 @@
 # Release History
 
-## 1.6.4
+## 1.7.1
+
+### Bug Fixes
+
+- Registry: Null value is now allowed in the dataframe used in model signature inference. Null values will be ignored
+ and others will be used to infer the signature.
+- Registry: Pandas Extension DTypes (`pandas.StringDType()`, `pandas.BooleanDType()`, etc.) are now supported in model
+signature inference.
+- Registry: Null value is now allowed in the dataframe used to predict.
+- Data: Fix missing `snowflake.ml.data.*` module exports in wheel
+- 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.
+- Model Monitoring: `show_model_monitors` Registry method.  This feature is still in Private Preview.
+- Registry: Support `pd.Series` in input and output data.
+- Model Monitoring: `add_monitor` Registry method.  This feature is still in Private Preview.
+- Model Monitoring: `resume` and `suspend` ModelMonitor.  This feature is still in Private Preview.
+- Model Monitoring: `get_monitor` Registry method.  This feature is still in Private Preview.
+- Model Monitoring: `delete_monitor` Registry method.  This feature is still in Private Preview.
+
+## 1.7.0 (10-22-2024)
+
+### Behavior Change
+
+- Generic: Require python >= 3.9.
+- Data Connector: Update `to_torch_dataset` and `to_torch_datapipe` to add a dimension for scalar data.
+This allows for more seamless integration with PyTorch `DataLoader`, which creates batches by stacking inputs of each batch.
+
+Examples:
+
+```python
+ds = connector.to_torch_dataset(shuffle=False, batch_size=3)
+```
+
+- Input: "col1": [10, 11, 12]
+  - Previous batch: array([10., 11., 12.]) with shape (3,)
+  - New batch: array([[10.], [11.], [12.]]) with shape (3, 1)
+
+- Input: "col2": [[0, 100], [1, 110], [2, 200]]
+  - Previous batch: array([[  0, 100], [  1, 110], [  2, 200]]) with shape (3,2)
+  - New batch: No change
+
+- Model Registry: External access integrations are optional when creating a model inference service in
+  Snowflake >= 8.40.0.
+- Model Registry: Deprecate `build_external_access_integration` with `build_external_access_integrations` in
+  `ModelVersion.create_service()`.
+
+### Bug Fixes
+
+- Registry: Updated `log_model` API to accept both signature and sample_input_data parameters.
+- Feature Store: ExampleHelper uses fully qualified path for table name. change weather features aggregation from 1d to 1h.
+- Data Connector: Return numpy array with appropriate object type instead of list for multi-dimensional
+data from `to_torch_dataset` and `to_torch_datapipe`
+- Model explainability: Incompatibility between SHAP 0.42.1 and XGB 2.1.1 resolved by using latest SHAP 0.46.0.
+
+### New Features
+
+- Registry: Provide pass keyworded variable length of arguments to class ModelContext. Example usage:
+
+```python
+mc = custom_model.ModelContext(
+    config = 'local_model_dir/config.json',
+    m1 = model1
+)
+
+class ExamplePipelineModel(custom_model.CustomModel):
+    def __init__(self, context: custom_model.ModelContext) -> None:
+      super().__init__(context)
+      v = open(self.context['config']).read()
+      self.bias = json.loads(v)['bias']
+
+    @custom_model.inference_api
+    def predict(self, input: pd.DataFrame) -> pd.DataFrame:
+      model_output = self.context['m1'].predict(input)
+      return pd.DataFrame({'output': model_output + self.bias})
+```
+
+- Model Development: Upgrade scikit-learn in UDTF backend for log_loss metric. As a result, `eps` argument is now ignored.
+- 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)
+- 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.
+
+## 1.6.4 (2024-10-17)
 
 ### Bug Fixes
 
@@ -18,6 +107,9 @@
 - Registry: Fix a bug that `ModelVersion.run` is called in a nested way.
 - Registry: Fix an issue that leads to `log_model` failure when local package version contains parts other than
   base version.
+- Fix issue where `sample_weights` were not being applied to search estimators.
+- Model explainability: Fix bug which creates explain as a function instead of table function when enabling by default.
+- Model explainability: Update lightgbm binary classification to return non-json values, from customer feedback.
 
 ### New Features
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: snowflake-ml-python
-Version: 1.6.4
+Version: 1.7.1
 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: 
@@ -220,7 +220,6 @@ Classifier: Intended Audience :: Information Technology
 Classifier: Intended Audience :: System Administrators
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
@@ -230,38 +229,39 @@ 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,>=3.8
+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: cachetools<6,>=3.1.1
 Requires-Dist: cloudpickle>=2.0.0
+Requires-Dist: cryptography
 Requires-Dist: fsspec[http]<2024,>=2022.11
 Requires-Dist: importlib_resources<7,>=6.1.1
 Requires-Dist: numpy<2,>=1.23
-Requires-Dist: packaging<24,>=20.9
+Requires-Dist: packaging<25,>=20.9
 Requires-Dist: pandas<3,>=1.0.0
 Requires-Dist: pyarrow
 Requires-Dist: pytimeparse<2,>=1.1.8
 Requires-Dist: pyyaml<7,>=6.0
 Requires-Dist: retrying<2,>=1.3.3
 Requires-Dist: s3fs<2024,>=2022.11
-Requires-Dist: scikit-learn<1.6,>=1.2.1
+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: sqlparse<1,>=0.4
 Requires-Dist: typing-extensions<5,>=4.1.0
-Requires-Dist: xgboost<2.1,>=1.7.3
+Requires-Dist: xgboost<3,>=1.7.3
 Provides-Extra: all
 Requires-Dist: catboost<2,>=1.2.0; extra == "all"
-Requires-Dist: lightgbm<5,>=3.3.5; extra == "all"
+Requires-Dist: lightgbm<5,>=4.1.0; extra == "all"
 Requires-Dist: mlflow<2.4,>=2.1.0; 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: shap<1,>=0.42.0; extra == "all"
+Requires-Dist: shap<1,>=0.46.0; extra == "all"
 Requires-Dist: tensorflow<3,>=2.10; extra == "all"
 Requires-Dist: tokenizers<1,>=0.10; extra == "all"
 Requires-Dist: torch<2.3.0,>=2.0.1; extra == "all"
@@ -270,13 +270,13 @@ Requires-Dist: transformers<5,>=4.32.1; extra == "all"
 Provides-Extra: catboost
 Requires-Dist: catboost<2,>=1.2.0; extra == "catboost"
 Provides-Extra: lightgbm
-Requires-Dist: lightgbm<5,>=3.3.5; 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<2.4,>=2.1.0; extra == "mlflow"
 Provides-Extra: shap
-Requires-Dist: shap<1,>=0.42.0; extra == "shap"
+Requires-Dist: shap<1,>=0.46.0; extra == "shap"
 Provides-Extra: tensorflow
 Requires-Dist: tensorflow<3,>=2.10; extra == "tensorflow"
 Provides-Extra: torch
@@ -336,7 +336,7 @@ 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 3.8 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
+Python versions 3.9 to 3.11 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.
 
@@ -373,7 +373,96 @@ be compatibility issues. Server-side functionality that `snowflake-ml-python` de
 
 # Release History
 
-## 1.6.4
+## 1.7.1
+
+### Bug Fixes
+
+- Registry: Null value is now allowed in the dataframe used in model signature inference. Null values will be ignored
+ and others will be used to infer the signature.
+- Registry: Pandas Extension DTypes (`pandas.StringDType()`, `pandas.BooleanDType()`, etc.) are now supported in model
+signature inference.
+- Registry: Null value is now allowed in the dataframe used to predict.
+- Data: Fix missing `snowflake.ml.data.*` module exports in wheel
+- 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.
+- Model Monitoring: `show_model_monitors` Registry method.  This feature is still in Private Preview.
+- Registry: Support `pd.Series` in input and output data.
+- Model Monitoring: `add_monitor` Registry method.  This feature is still in Private Preview.
+- Model Monitoring: `resume` and `suspend` ModelMonitor.  This feature is still in Private Preview.
+- Model Monitoring: `get_monitor` Registry method.  This feature is still in Private Preview.
+- Model Monitoring: `delete_monitor` Registry method.  This feature is still in Private Preview.
+
+## 1.7.0 (10-22-2024)
+
+### Behavior Change
+
+- Generic: Require python >= 3.9.
+- Data Connector: Update `to_torch_dataset` and `to_torch_datapipe` to add a dimension for scalar data.
+This allows for more seamless integration with PyTorch `DataLoader`, which creates batches by stacking inputs of each batch.
+
+Examples:
+
+```python
+ds = connector.to_torch_dataset(shuffle=False, batch_size=3)
+```
+
+- Input: "col1": [10, 11, 12]
+  - Previous batch: array([10., 11., 12.]) with shape (3,)
+  - New batch: array([[10.], [11.], [12.]]) with shape (3, 1)
+
+- Input: "col2": [[0, 100], [1, 110], [2, 200]]
+  - Previous batch: array([[  0, 100], [  1, 110], [  2, 200]]) with shape (3,2)
+  - New batch: No change
+
+- Model Registry: External access integrations are optional when creating a model inference service in
+  Snowflake >= 8.40.0.
+- Model Registry: Deprecate `build_external_access_integration` with `build_external_access_integrations` in
+  `ModelVersion.create_service()`.
+
+### Bug Fixes
+
+- Registry: Updated `log_model` API to accept both signature and sample_input_data parameters.
+- Feature Store: ExampleHelper uses fully qualified path for table name. change weather features aggregation from 1d to 1h.
+- Data Connector: Return numpy array with appropriate object type instead of list for multi-dimensional
+data from `to_torch_dataset` and `to_torch_datapipe`
+- Model explainability: Incompatibility between SHAP 0.42.1 and XGB 2.1.1 resolved by using latest SHAP 0.46.0.
+
+### New Features
+
+- Registry: Provide pass keyworded variable length of arguments to class ModelContext. Example usage:
+
+```python
+mc = custom_model.ModelContext(
+    config = 'local_model_dir/config.json',
+    m1 = model1
+)
+
+class ExamplePipelineModel(custom_model.CustomModel):
+    def __init__(self, context: custom_model.ModelContext) -> None:
+      super().__init__(context)
+      v = open(self.context['config']).read()
+      self.bias = json.loads(v)['bias']
+
+    @custom_model.inference_api
+    def predict(self, input: pd.DataFrame) -> pd.DataFrame:
+      model_output = self.context['m1'].predict(input)
+      return pd.DataFrame({'output': model_output + self.bias})
+```
+
+- Model Development: Upgrade scikit-learn in UDTF backend for log_loss metric. As a result, `eps` argument is now ignored.
+- 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)
+- 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.
+
+## 1.6.4 (2024-10-17)
 
 ### Bug Fixes
 
@@ -391,6 +480,9 @@ be compatibility issues. Server-side functionality that `snowflake-ml-python` de
 - Registry: Fix a bug that `ModelVersion.run` is called in a nested way.
 - Registry: Fix an issue that leads to `log_model` failure when local package version contains parts other than
   base version.
+- Fix issue where `sample_weights` were not being applied to search estimators.
+- Model explainability: Fix bug which creates explain as a function instead of table function when enabling by default.
+- Model explainability: Update lightgbm binary classification to return non-json values, from customer feedback.
 
 ### New Features
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.1}/README.md

@@ -46,7 +46,7 @@ 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 3.8 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
+Python versions 3.9 to 3.11 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.
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.1}/pyproject.toml

@@ -5,10 +5,10 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "snowflake-ml-python"
 description = "The machine learning client library that is used for interacting with Snowflake to build machine learning solutions."
-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 :: 3.8", "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 = ">=3.8, <3.12"
+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", "fsspec[http]>=2022.11,<2024", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<2", "packaging>=20.9,<24", "pandas>=1.0.0,<3", "pyarrow", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2022.11,<2024", "scikit-learn>=1.2.1,<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,<2.1",]
+dependencies = [ "absl-py>=0.15,<2", "anyio>=3.5.0,<4", "cachetools>=3.1.1,<6", "cloudpickle>=2.0.0", "cryptography", "fsspec[http]>=2022.11,<2024", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<2", "packaging>=20.9,<25", "pandas>=1.0.0,<3", "pyarrow", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2022.11,<2024", "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",]
 [[project.authors]]
 name = "Snowflake, Inc"
 email = "support@snowflake.com"
@@ -24,12 +24,12 @@ 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", "lightgbm>=3.3.5,<5", "mlflow>=2.1.0,<2.4", "peft>=0.5.0,<1", "sentence-transformers>=2.2.2,<3", "sentencepiece>=0.1.95,<1", "shap>=0.42.0,<1", "tensorflow>=2.10,<3", "tokenizers>=0.10,<1", "torch>=2.0.1,<2.3.0", "torchdata>=0.4,<1", "transformers>=4.32.1,<5",]
+all = [ "catboost>=1.2.0, <2", "lightgbm>=4.1.0, <5", "mlflow>=2.1.0,<2.4", "peft>=0.5.0,<1", "sentence-transformers>=2.2.2,<3", "sentencepiece>=0.1.95,<1", "shap>=0.46.0,<1", "tensorflow>=2.10,<3", "tokenizers>=0.10,<1", "torch>=2.0.1,<2.3.0", "torchdata>=0.4,<1", "transformers>=4.32.1,<5",]
 catboost = [ "catboost>=1.2.0, <2",]
-lightgbm = [ "lightgbm>=3.3.5,<5",]
+lightgbm = [ "lightgbm>=4.1.0, <5",]
 llm = [ "peft>=0.5.0,<1",]
 mlflow = [ "mlflow>=2.1.0,<2.4",]
-shap = [ "shap>=0.42.0,<1",]
+shap = [ "shap>=0.46.0,<1",]
 tensorflow = [ "tensorflow>=2.10,<3",]
 torch = [ "torch>=2.0.1,<2.3.0", "torchdata>=0.4,<1",]
 transformers = [ "sentence-transformers>=2.2.2,<3", "sentencepiece>=0.1.95,<1", "tokenizers>=0.10,<1", "transformers>=4.32.1,<5",]

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.1}/snowflake/cortex/__init__.py

@@ -3,6 +3,7 @@ from snowflake.cortex._complete import Complete, CompleteOptions
 from snowflake.cortex._embed_text_768 import EmbedText768
 from snowflake.cortex._embed_text_1024 import EmbedText1024
 from snowflake.cortex._extract_answer import ExtractAnswer
+from snowflake.cortex._finetune import Finetune, FinetuneJob, FinetuneStatus
 from snowflake.cortex._sentiment import Sentiment
 from snowflake.cortex._summarize import Summarize
 from snowflake.cortex._translate import Translate
@@ -14,6 +15,9 @@ __all__ = [
     "EmbedText768",
     "EmbedText1024",
     "ExtractAnswer",
+    "Finetune",
+    "FinetuneJob",
+    "FinetuneStatus",
     "Sentiment",
     "Summarize",
     "Translate",

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.1}/snowflake/cortex/_complete.py

@@ -1,7 +1,8 @@
 import json
 import logging
 import time
-from typing import Any, Callable, Iterator, List, Optional, TypedDict, Union, cast
+from io import BytesIO
+from typing import Any, Callable, Dict, Iterator, List, Optional, TypedDict, Union, cast
 from urllib.parse import urlunparse
 
 import requests
@@ -16,8 +17,10 @@ from snowflake.cortex._util import (
 )
 from snowflake.ml._internal import telemetry
 from snowflake.snowpark import context, functions
+from snowflake.snowpark._internal.utils import is_in_stored_procedure
 
 logger = logging.getLogger(__name__)
+_REST_COMPLETE_URL = "/api/v2/cortex/inference:complete"
 
 
 class ConversationMessage(TypedDict):
@@ -84,6 +87,76 @@ def retry(func: Callable[..., requests.Response]) -> Callable[..., requests.Resp
     return inner
 
 
+def _make_common_request_headers() -> Dict[str, str]:
+    headers = {
+        "Content-Type": "application/json",
+        "Accept": "application/json, text/event-stream",
+    }
+    return headers
+
+
+def _make_request_body(
+    model: str,
+    prompt: Union[str, List[ConversationMessage]],
+    options: Optional[CompleteOptions] = None,
+) -> Dict[str, Any]:
+    data = {
+        "model": model,
+        "stream": True,
+    }
+    if isinstance(prompt, List):
+        data["messages"] = prompt
+    else:
+        data["messages"] = [{"content": prompt}]
+
+    if options:
+        if "max_tokens" in options:
+            data["max_tokens"] = options["max_tokens"]
+            data["max_output_tokens"] = options["max_tokens"]
+        if "temperature" in options:
+            data["temperature"] = options["temperature"]
+        if "top_p" in options:
+            data["top_p"] = options["top_p"]
+    return data
+
+
+# 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:
+    response = requests.Response()
+    response.status_code = int(raw_resp["status"])
+    response.headers = raw_resp["headers"]
+
+    data = raw_resp["content"]
+    data = json.loads(data)
+    # Convert the dictionary to a string format that resembles the SSE event format
+    # For example, if the dict is {'event': 'message', 'data': 'your data'}, it should be formatted like this:
+    sse_format_data = ""
+    for event in data:
+        event_type = event.get("event", "message")
+        event_data = event.get("data", "")
+        event_data = json.dumps(event_data)
+        sse_format_data += f"event: {event_type}\ndata: {event_data}\n\n"  # Add each event with new lines
+
+    response.raw = BytesIO(sse_format_data.encode("utf-8"))
+    return response
+
+
+@retry
+def _call_complete_xp(
+    model: str,
+    prompt: Union[str, List[ConversationMessage]],
+    options: Optional[CompleteOptions] = None,
+    deadline: Optional[float] = None,
+) -> requests.Response:
+    headers = _make_common_request_headers()
+    body = _make_request_body(model, prompt, options)
+    import _snowflake
+
+    raw_resp = _snowflake.send_snow_api_request("POST", _REST_COMPLETE_URL, {}, headers, body, {}, deadline)
+    return _xp_dict_to_response(raw_resp)
+
+
 @retry
 def _call_complete_rest(
     model: str,
@@ -110,36 +183,16 @@ def _call_complete_rest(
     scheme = "https"
     if hasattr(session.connection, "scheme"):
         scheme = session.connection.scheme
-    url = urlunparse((scheme, session.connection.host, "api/v2/cortex/inference:complete", "", "", ""))
+    url = urlunparse((scheme, session.connection.host, _REST_COMPLETE_URL, "", "", ""))
 
-    headers = {
-        "Content-Type": "application/json",
-        "Authorization": f'Snowflake Token="{session.connection.rest.token}"',
-        "Accept": "application/json, text/event-stream",
-    }
-
-    data = {
-        "model": model,
-        "stream": True,
-    }
-    if isinstance(prompt, List):
-        data["messages"] = prompt
-    else:
-        data["messages"] = [{"content": prompt}]
-
-    if options:
-        if "max_tokens" in options:
-            data["max_tokens"] = options["max_tokens"]
-            data["max_output_tokens"] = options["max_tokens"]
-        if "temperature" in options:
-            data["temperature"] = options["temperature"]
-        if "top_p" in options:
-            data["top_p"] = options["top_p"]
+    headers = _make_common_request_headers()
+    headers["Authorization"] = f'Snowflake Token="{session.connection.rest.token}"'
 
+    body = _make_request_body(model, prompt, options)
     logger.debug(f"making POST request to {url} (model={model})")
     return requests.post(
         url,
-        json=data,
+        json=body,
         headers=headers,
         stream=True,
     )
@@ -164,49 +217,24 @@ def _complete_call_sql_function_snowpark(
     return cast(snowpark.Column, functions.builtin(function)(*args))
 
 
-def _complete_call_sql_function_immediate(
-    function: str,
+def _complete_non_streaming_immediate(
     model: str,
     prompt: Union[str, List[ConversationMessage]],
     options: Optional[CompleteOptions],
-    session: Optional[snowpark.Session],
+    session: Optional[snowpark.Session] = None,
+    deadline: Optional[float] = None,
 ) -> str:
-    session = session or context.get_active_session()
-    if session is None:
-        raise SnowflakeAuthenticationException(
-            """Session required. Provide the session through a session=... argument or ensure an active session is
-            available in your environment."""
-        )
+    response = _complete_rest(model=model, prompt=prompt, options=options, session=session, deadline=deadline)
+    return "".join(response)
 
-    # https://docs.snowflake.com/en/sql-reference/functions/complete-snowflake-cortex
-    if options is not None or not isinstance(prompt, str):
-        if isinstance(prompt, List):
-            prompt_arg = prompt
-        else:
-            prompt_arg = [{"role": "user", "content": prompt}]
-        options = options or {}
-        lit_args = [
-            functions.lit(model),
-            functions.lit(prompt_arg),
-            functions.lit(options),
-        ]
-    else:
-        lit_args = [
-            functions.lit(model),
-            functions.lit(prompt),
-        ]
-
-    empty_df = session.create_dataframe([snowpark.Row()])
-    df = empty_df.select(functions.builtin(function)(*lit_args))
-    return cast(str, df.collect()[0][0])
 
-
-def _complete_sql_impl(
+def _complete_non_streaming_impl(
     function: str,
     model: Union[str, snowpark.Column],
     prompt: Union[str, List[ConversationMessage], snowpark.Column],
     options: Optional[Union[CompleteOptions, snowpark.Column]],
-    session: Optional[snowpark.Session],
+    session: Optional[snowpark.Session] = None,
+    deadline: Optional[float] = None,
 ) -> Union[str, snowpark.Column]:
     if isinstance(prompt, snowpark.Column):
         if options is not None:
@@ -217,7 +245,24 @@ def _complete_sql_impl(
         raise ValueError("'model' cannot be a snowpark.Column when 'prompt' is a string.")
     if isinstance(options, snowpark.Column):
         raise ValueError("'options' cannot be a snowpark.Column when 'prompt' is a string.")
-    return _complete_call_sql_function_immediate(function, model, prompt, options, session)
+    return _complete_non_streaming_immediate(
+        model=model, prompt=prompt, options=options, session=session, deadline=deadline
+    )
+
+
+def _complete_rest(
+    model: str,
+    prompt: Union[str, List[ConversationMessage]],
+    options: Optional[CompleteOptions] = None,
+    session: Optional[snowpark.Session] = None,
+    deadline: Optional[float] = None,
+) -> Iterator[str]:
+    if is_in_stored_procedure():  # type: ignore[no-untyped-call]
+        response = _call_complete_xp(model=model, prompt=prompt, options=options, deadline=deadline)
+    else:
+        response = _call_complete_rest(model=model, prompt=prompt, options=options, session=session, deadline=deadline)
+    assert response.status_code >= 200 and response.status_code < 300
+    return _return_stream_response(response, deadline)
 
 
 def _complete_impl(
@@ -239,10 +284,8 @@ def _complete_impl(
             raise ValueError("in REST mode, 'model' must be a string")
         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")
-        response = _call_complete_rest(model, prompt, options, session=session, deadline=deadline)
-        assert response.status_code >= 200 and response.status_code < 300
-        return _return_stream_response(response, deadline)
-    return _complete_sql_impl(function, model, prompt, options, session)
+        return _complete_rest(model=model, prompt=prompt, options=options, session=session, deadline=deadline)
+    return _complete_non_streaming_impl(function, model, prompt, options, session, deadline)
 
 
 @telemetry.send_api_usage_telemetry(