snowflake-ml-python 1.6.0__py3-none-any.whl → 1.6.2__py3-none-any.whl

snowflake/cortex/_complete.py

@@ -90,7 +90,6 @@ def _call_complete_rest(
     prompt: Union[str, List[ConversationMessage]],
     options: Optional[CompleteOptions] = None,
     session: Optional[snowpark.Session] = None,
-    stream: bool = False,
 ) -> requests.Response:
     session = session or context.get_active_session()
     if session is None:
@@ -121,7 +120,7 @@ def _call_complete_rest(
 
     data = {
         "model": model,
-        "stream": stream,
+        "stream": True,
     }
     if isinstance(prompt, List):
         data["messages"] = prompt
@@ -137,32 +136,15 @@ def _call_complete_rest(
         if "top_p" in options:
             data["top_p"] = options["top_p"]
 
-    logger.debug(f"making POST request to {url} (model={model}, stream={stream})")
+    logger.debug(f"making POST request to {url} (model={model})")
     return requests.post(
         url,
         json=data,
         headers=headers,
-        stream=stream,
+        stream=True,
     )
 
 
-def _process_rest_response(
-    response: requests.Response,
-    stream: bool = False,
-    deadline: Optional[float] = None,
-) -> Union[str, Iterator[str]]:
-    if stream:
-        return _return_stream_response(response, deadline)
-
-    try:
-        content = response.json()["choices"][0]["message"]["content"]
-        assert isinstance(content, str)
-        return content
-    except (KeyError, IndexError, AssertionError) as e:
-        # Unlike the streaming case, errors are not ignored because a message must be returned.
-        raise ResponseParseException("Failed to parse message from response.") from e
-
-
 def _return_stream_response(response: requests.Response, deadline: Optional[float]) -> Iterator[str]:
     client = SSEClient(response)
     for event in client.events():
@@ -243,7 +225,6 @@ def _complete_impl(
     prompt: Union[str, List[ConversationMessage], snowpark.Column],
     options: Optional[CompleteOptions] = None,
     session: Optional[snowpark.Session] = None,
-    use_rest_api_experimental: bool = False,
     stream: bool = False,
     function: str = "snowflake.cortex.complete",
     timeout: Optional[float] = None,
@@ -253,16 +234,14 @@ def _complete_impl(
         raise ValueError('only one of "timeout" and "deadline" must be set')
     if timeout is not None:
         deadline = time.time() + timeout
-    if use_rest_api_experimental:
+    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):
             raise ValueError("in REST mode, 'prompt' must be a string or a list of ConversationMessage")
-        response = _call_complete_rest(model, prompt, options, session=session, stream=stream, deadline=deadline)
+        response = _call_complete_rest(model, prompt, options, session=session, deadline=deadline)
         assert response.status_code >= 200 and response.status_code < 300
-        return _process_rest_response(response, stream=stream)
-    if stream is True:
-        raise ValueError("streaming can only be enabled in REST mode, set use_rest_api_experimental=True")
+        return _return_stream_response(response, deadline)
     return _complete_sql_impl(function, model, prompt, options, session)
 
 
@@ -275,7 +254,6 @@ def Complete(
     *,
     options: Optional[CompleteOptions] = None,
     session: Optional[snowpark.Session] = None,
-    use_rest_api_experimental: bool = False,
     stream: bool = False,
     timeout: Optional[float] = None,
     deadline: Optional[float] = None,
@@ -287,16 +265,13 @@ def Complete(
         prompt: A Column of prompts to send to the LLM.
         options: A instance of snowflake.cortex.CompleteOptions
         session: The snowpark session to use. Will be inferred by context if not specified.
-        use_rest_api_experimental (bool): Toggles between the use of SQL and REST implementation. This feature is
-            experimental and can be removed at any time.
         stream (bool): Enables streaming. When enabled, a generator function is returned that provides the streaming
             output as it is received. Each update is a string containing the new text content since the previous update.
-            The use of streaming requires the experimental use_rest_api_experimental flag to be enabled.
         timeout (float): Timeout in seconds to retry failed REST requests.
         deadline (float): Time in seconds since the epoch (as returned by time.time()) to retry failed REST requests.
 
     Raises:
-        ValueError: If `stream` is set to True and `use_rest_api_experimental` is set to False.
+        ValueError: incorrect argument.
 
     Returns:
         A column of string responses.
@@ -307,7 +282,6 @@ def Complete(
             prompt,
             options=options,
             session=session,
-            use_rest_api_experimental=use_rest_api_experimental,
             stream=stream,
             timeout=timeout,
             deadline=deadline,

snowflake/ml/_internal/env_utils.py

@@ -27,7 +27,6 @@ class CONDA_OS(Enum):
     NO_ARCH = "noarch"
 
 
-_SNOWFLAKE_CONDA_CHANNEL_URL = "https://repo.anaconda.com/pkgs/snowflake"
 _NODEFAULTS = "nodefaults"
 _SNOWFLAKE_INFO_SCHEMA_PACKAGE_CACHE: Dict[str, List[version.Version]] = {}
 _SNOWFLAKE_CONDA_PACKAGE_CACHE: Dict[str, List[version.Version]] = {}
@@ -36,6 +35,7 @@ _SUPPORTED_PACKAGE_SPEC_OPS = ["==", ">=", "<=", ">", "<"]
 DEFAULT_CHANNEL_NAME = ""
 SNOWML_SPROC_ENV = "IN_SNOWML_SPROC"
 SNOWPARK_ML_PKG_NAME = "snowflake-ml-python"
+SNOWFLAKE_CONDA_CHANNEL_URL = "https://repo.anaconda.com/pkgs/snowflake"
 
 
 def _validate_pip_requirement_string(req_str: str) -> requirements.Requirement:
@@ -370,7 +370,7 @@ def get_matched_package_versions_in_snowflake_conda_channel(
 
     assert not snowpark_utils.is_in_stored_procedure()  # type: ignore[no-untyped-call]
 
-    url = f"{_SNOWFLAKE_CONDA_CHANNEL_URL}/{conda_os.value}/repodata.json"
+    url = f"{SNOWFLAKE_CONDA_CHANNEL_URL}/{conda_os.value}/repodata.json"
 
     if req.name not in _SNOWFLAKE_CONDA_PACKAGE_CACHE:
         try:
@@ -477,6 +477,7 @@ def save_conda_env_file(
     path: pathlib.Path,
     conda_chan_deps: DefaultDict[str, List[requirements.Requirement]],
     python_version: str,
+    default_channel_override: str = SNOWFLAKE_CONDA_CHANNEL_URL,
 ) -> None:
     """Generate conda.yml file given a dict of dependencies after validation.
     The channels part of conda.yml file will contains Snowflake Anaconda Channel, nodefaults and all channel names
@@ -489,6 +490,7 @@ def save_conda_env_file(
         path: Path to the conda.yml file.
         conda_chan_deps: Dict of conda dependencies after validated.
         python_version: A string 'major.minor' showing python version relate to model.
+        default_channel_override: The default channel to be put in the first place of the channels section.
     """
     assert path.suffix in [".yml", ".yaml"], "Conda environment file should have extension of yml or yaml."
     path.parent.mkdir(parents=True, exist_ok=True)
@@ -499,7 +501,11 @@ def save_conda_env_file(
     channels = list(dict(sorted(conda_chan_deps.items(), key=lambda item: len(item[1]), reverse=True)).keys())
     if DEFAULT_CHANNEL_NAME in channels:
         channels.remove(DEFAULT_CHANNEL_NAME)
-    env["channels"] = [_SNOWFLAKE_CONDA_CHANNEL_URL] + channels + [_NODEFAULTS]
+
+    if default_channel_override in channels:
+        channels.remove(default_channel_override)
+
+    env["channels"] = [default_channel_override] + channels + [_NODEFAULTS]
     env["dependencies"] = [f"python=={python_version}.*"]
     for chan, reqs in conda_chan_deps.items():
         env["dependencies"].extend(
@@ -567,8 +573,8 @@ def load_conda_env_file(
     python_version = None
 
     channels = env.get("channels", [])
-    if _SNOWFLAKE_CONDA_CHANNEL_URL in channels:
-        channels.remove(_SNOWFLAKE_CONDA_CHANNEL_URL)
+    if len(channels) >= 1:
+        channels = channels[1:]  # Skip the first channel which is the default channel
     if _NODEFAULTS in channels:
         channels.remove(_NODEFAULTS)
 

snowflake/ml/_internal/exceptions/modeling_error_messages.py

@@ -4,7 +4,10 @@ ATTRIBUTE_NOT_SET = (
     "-differences."
 )
 SIZE_MISMATCH = "Size mismatch: {}={}, {}={}."
-INVALID_MODEL_PARAM = "Invalid parameter {} for model {}. Valid parameters: {}."
+INVALID_MODEL_PARAM = (
+    "Invalid parameter {} for model {}. Valid parameters: {}."
+    "Note: Scikit learn params cannot be set until the model has been fit."
+)
 UNSUPPORTED_MODEL_CONVERSION = "Object doesn't support {}. Please use {}."
 INCOMPATIBLE_NEW_SKLEARN_PARAM = "Incompatible scikit-learn version: {} requires scikit-learn>={}. Installed: {}."
 REMOVED_SKLEARN_PARAM = "Incompatible scikit-learn version: {} is removed in scikit-learn>={}. Installed: {}."

snowflake/ml/_internal/telemetry.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+import contextvars
 import enum
 import functools
 import inspect
@@ -12,6 +13,7 @@ from typing import (
     List,
     Mapping,
     Optional,
+    Set,
     Tuple,
     TypeVar,
     Union,
@@ -28,7 +30,7 @@ from snowflake.ml._internal.exceptions import (
     exceptions as snowml_exceptions,
 )
 from snowflake.snowpark import dataframe, exceptions as snowpark_exceptions, session
-from snowflake.snowpark._internal import utils
+from snowflake.snowpark._internal import server_connection, utils
 
 _log_counter = 0
 _FLUSH_SIZE = 10
@@ -44,6 +46,20 @@ _Args = ParamSpec("_Args")
 _ReturnValue = TypeVar("_ReturnValue")
 
 
+@enum.unique
+class TelemetryProject(enum.Enum):
+    MLOPS = "MLOps"
+    MODELING = "ModelDevelopment"
+    # TODO: Update with remaining projects.
+
+
+@enum.unique
+class TelemetrySubProject(enum.Enum):
+    MONITORING = "Monitoring"
+    REGISTRY = "ModelManagement"
+    # TODO: Update with remaining subprojects.
+
+
 @enum.unique
 class TelemetryField(enum.Enum):
     # constants
@@ -71,6 +87,122 @@ class TelemetryField(enum.Enum):
     FUNC_CAT_USAGE = "usage"
 
 
+class _TelemetrySourceType(enum.Enum):
+    # Automatically inferred telemetry/statement parameters
+    AUTO_TELEMETRY = "SNOWML_AUTO_TELEMETRY"
+    # Mixture of manual and automatic telemetry/statement parameters
+    AUGMENT_TELEMETRY = "SNOWML_AUGMENT_TELEMETRY"
+
+
+_statement_params_context_var: contextvars.ContextVar[Dict[str, str]] = contextvars.ContextVar("statement_params")
+
+
+class _StatementParamsPatchManager:
+    def __init__(self) -> None:
+        self._patch_cache: Set[server_connection.ServerConnection] = set()
+        self._context_var: contextvars.ContextVar[Dict[str, str]] = _statement_params_context_var
+
+    def apply_patches(self) -> None:
+        try:
+            # Apply patching to all active sessions in case of multiple
+            for sess in session._get_active_sessions():
+                # Check patch cache here to avoid unnecessary context switches
+                if self._get_target(sess) not in self._patch_cache:
+                    self._patch_session(sess)
+        except snowpark_exceptions.SnowparkSessionException:
+            pass
+
+    def set_statement_params(self, statement_params: Dict[str, str]) -> None:
+        # Only set value if not already set in context
+        if not self._context_var.get({}):
+            self._context_var.set(statement_params)
+
+    def _get_target(self, session: session.Session) -> server_connection.ServerConnection:
+        return cast(server_connection.ServerConnection, session._conn)
+
+    def _patch_session(self, session: session.Session, throw_on_patch_fail: bool = False) -> None:
+        # Extract target
+        try:
+            target = self._get_target(session)
+        except AttributeError:
+            if throw_on_patch_fail:
+                raise
+            # TODO: Log a warning, this probably means there was a breaking change in Snowpark/SnowflakeConnection
+            return
+
+        # Check if session has already been patched
+        if target in self._patch_cache:
+            return
+        self._patch_cache.add(target)
+
+        functions = [
+            ("execute_and_notify_query_listener", "_statement_params"),
+            ("execute_async_and_notify_query_listener", "_statement_params"),
+        ]
+
+        for func, param_name in functions:
+            try:
+                self._patch_with_statement_params(target, func, param_name=param_name)
+            except AttributeError:
+                if throw_on_patch_fail:  # primarily used for testing
+                    raise
+                # TODO: Log a warning, this probably means there was a breaking change in Snowpark/SnowflakeConnection
+                pass
+
+    def _patch_with_statement_params(
+        self, target: object, function_name: str, param_name: str = "statement_params"
+    ) -> None:
+        func = getattr(target, function_name)
+        assert callable(func)
+
+        @functools.wraps(func)
+        def wrapper(*args: Any, **kwargs: Any) -> Any:
+            # Retrieve context level statement parameters
+            context_params = self._context_var.get(dict())
+            if not context_params:
+                # Exit early if not in SnowML (decorator) context
+                return func(*args, **kwargs)
+
+            # Extract any explicitly provided statement parameters
+            orig_kwargs = dict(kwargs)
+            in_params = kwargs.pop(param_name, None) or {}
+
+            # Inject a special flag to statement parameters so we can filter out these patched logs if necessary
+            # Calls that include SnowML telemetry are tagged with "SNOWML_AUGMENT_TELEMETRY"
+            # and calls without SnowML telemetry are tagged with "SNOWML_AUTO_TELEMETRY"
+            if TelemetryField.KEY_PROJECT.value in in_params:
+                context_params["snowml_telemetry_type"] = _TelemetrySourceType.AUGMENT_TELEMETRY.value
+            else:
+                context_params["snowml_telemetry_type"] = _TelemetrySourceType.AUTO_TELEMETRY.value
+
+            # Apply any explicitly provided statement parameters and result into function call
+            context_params.update(in_params)
+            kwargs[param_name] = context_params
+
+            try:
+                return func(*args, **kwargs)
+            except TypeError as e:
+                if str(e).endswith(f"unexpected keyword argument '{param_name}'"):
+                    # TODO: Log warning that this patch is invalid
+                    # Unwrap function for future invocations
+                    setattr(target, function_name, func)
+                    return func(*args, **orig_kwargs)
+                else:
+                    raise
+
+        setattr(target, function_name, wrapper)
+
+    def __getstate__(self) -> Dict[str, Any]:
+        return {}
+
+    def __setstate__(self, state: Dict[str, Any]) -> None:
+        # unpickling does not call __init__ by default, do it manually here
+        self.__init__()  # type: ignore[misc]
+
+
+_patch_manager = _StatementParamsPatchManager()
+
+
 def get_statement_params(
     project: str, subproject: Optional[str] = None, class_name: Optional[str] = None
 ) -> Dict[str, Any]:
@@ -361,7 +493,18 @@ def send_api_usage_telemetry(
                         obj._statement_params = statement_params  # type: ignore[assignment]
                 return obj
 
+            # Set up framework-level credit usage instrumentation
+            ctx = contextvars.copy_context()
+            _patch_manager.apply_patches()
+
+            # This function should be executed with ctx.run()
+            def execute_func_with_statement_params() -> _ReturnValue:
+                _patch_manager.set_statement_params(statement_params)
+                result = func(*args, **kwargs)
+                return update_stmt_params_if_snowpark_df(result, statement_params)
+
             # prioritize `conn_attr_name` over the active session
+            telemetry_enabled = True
             if conn_attr_name:
                 # raise AttributeError if conn attribute does not exist in `self`
                 conn = operator.attrgetter(conn_attr_name)(args[0])
@@ -373,22 +516,17 @@ def send_api_usage_telemetry(
             else:
                 try:
                     active_session = next(iter(session._get_active_sessions()))
-                # server no default session
+                    conn = active_session._conn._conn
+                    telemetry_enabled = active_session.telemetry_enabled
                 except snowpark_exceptions.SnowparkSessionException:
-                    try:
-                        return update_stmt_params_if_snowpark_df(func(*args, **kwargs), statement_params)
-                    except Exception as e:
-                        if isinstance(e, snowml_exceptions.SnowflakeMLException):
-                            raise e.original_exception.with_traceback(e.__traceback__) from None
-                        # suppress SnowparkSessionException from telemetry in the stack trace
-                        raise e from None
-
-                conn = active_session._conn._conn
-                if (not active_session.telemetry_enabled) or (conn is None):
-                    try:
-                        return update_stmt_params_if_snowpark_df(func(*args, **kwargs), statement_params)
-                    except snowml_exceptions.SnowflakeMLException as e:
-                        raise e.original_exception from e
+                    conn = None
+
+            if conn is None or not telemetry_enabled:
+                # Telemetry not enabled, just execute without our additional telemetry logic
+                try:
+                    return ctx.run(execute_func_with_statement_params)
+                except snowml_exceptions.SnowflakeMLException as e:
+                    raise e.original_exception from e
 
             # TODO(hayu): [SNOW-750287] Optimize telemetry client to a singleton.
             telemetry = _SourceTelemetryClient(conn=conn, project=project, subproject=subproject_name)
@@ -401,11 +539,11 @@ def send_api_usage_telemetry(
                 custom_tags=custom_tags,
             )
             try:
-                res = func(*args, **kwargs)
+                return ctx.run(execute_func_with_statement_params)
             except Exception as e:
                 if not isinstance(e, snowml_exceptions.SnowflakeMLException):
                     # already handled via a nested decorated function
-                    if hasattr(e, "_snowflake_ml_handled") and e._snowflake_ml_handled:
+                    if getattr(e, "_snowflake_ml_handled", False):
                         raise e
                     if isinstance(e, snowpark_exceptions.SnowparkClientException):
                         me = snowml_exceptions.SnowflakeMLException(
@@ -424,8 +562,6 @@ def send_api_usage_telemetry(
                     raise me.original_exception from None
                 else:
                     raise me.original_exception from e
-            else:
-                return update_stmt_params_if_snowpark_df(res, statement_params)
             finally:
                 telemetry.send_function_usage_telemetry(**telemetry_args)
                 global _log_counter

snowflake/ml/_internal/utils/identifier.py

@@ -10,9 +10,11 @@ SF_QUOTED_IDENTIFIER = '"(?:[^"]|"")*"'
 _SF_IDENTIFIER = f"({_SF_UNQUOTED_CASE_INSENSITIVE_IDENTIFIER}|{SF_QUOTED_IDENTIFIER})"
 SF_IDENTIFIER_RE = re.compile(_SF_IDENTIFIER)
 _SF_SCHEMA_LEVEL_OBJECT = (
-    rf"(?:(?:(?P<db>{_SF_IDENTIFIER})\.)?(?P<schema>{_SF_IDENTIFIER})\.)?(?P<object>{_SF_IDENTIFIER})(?P<others>.*)"
+    rf"(?:(?:(?P<db>{_SF_IDENTIFIER})\.)?(?P<schema>{_SF_IDENTIFIER})\.)?(?P<object>{_SF_IDENTIFIER})"
 )
+_SF_STAGE_PATH = rf"{_SF_SCHEMA_LEVEL_OBJECT}(?P<path>.*)"
 _SF_SCHEMA_LEVEL_OBJECT_RE = re.compile(_SF_SCHEMA_LEVEL_OBJECT)
+_SF_STAGE_PATH_RE = re.compile(_SF_STAGE_PATH)
 
 UNQUOTED_CASE_INSENSITIVE_RE = re.compile(f"^({_SF_UNQUOTED_CASE_INSENSITIVE_IDENTIFIER})$")
 UNQUOTED_CASE_SENSITIVE_RE = re.compile(f"^({_SF_UNQUOTED_CASE_SENSITIVE_IDENTIFIER})$")
@@ -139,29 +141,61 @@ def rename_to_valid_snowflake_identifier(name: str) -> str:
 
 
 def parse_schema_level_object_identifier(
+    object_name: str,
+) -> Tuple[Union[str, Any], Union[str, Any], Union[str, Any]]:
+    """Parse a string which starts with schema level object.
+
+    Args:
+        object_name: A string starts with a schema level object path, which is in the format
+            '<db>.<schema>.<object_name>'. Here, '<db>', '<schema>' and '<object_name>' are all snowflake identifiers.
+
+    Returns:
+        A tuple of 3 strings in the form of (db, schema, object_name).
+
+    Raises:
+        ValueError: If the id is invalid.
+    """
+    res = _SF_SCHEMA_LEVEL_OBJECT_RE.fullmatch(object_name)
+    if not res:
+        raise ValueError(
+            "Invalid identifier because it does not follow the pattern. "
+            f"It should start with [[database.]schema.]object. Getting {object_name}"
+        )
+    return (
+        res.group("db"),
+        res.group("schema"),
+        res.group("object"),
+    )
+
+
+def parse_snowflake_stage_path(
     path: str,
 ) -> Tuple[Union[str, Any], Union[str, Any], Union[str, Any], Union[str, Any]]:
-    """Parse a string which starts with schema level object.
+    """Parse a string which represents a snowflake stage path.
 
     Args:
-        path: A string starts with a schema level object path, which is in the format '<db>.<schema>.<object_name>'.
-            Here, '<db>', '<schema>' and '<object_name>' are all snowflake identifiers.
+        path: A string starts with a schema level object path, which is in the format
+            '<db>.<schema>.<object_name><path>'. Here, '<db>', '<schema>' and '<object_name>' are all snowflake
+            identifiers.
 
     Returns:
-        A tuple of 4 strings in the form of (db, schema, object_name, others). 'db', 'schema', 'object_name' are parsed
-            from the schema level object and 'others' are all the content post to the object.
+        A tuple of 4 strings in the form of (db, schema, object_name, path). 'db', 'schema', 'object_name' are parsed
+            from the schema level object and 'path' are all the content post to the object.
 
     Raises:
         ValueError: If the id is invalid.
     """
-    res = _SF_SCHEMA_LEVEL_OBJECT_RE.fullmatch(path)
+    res = _SF_STAGE_PATH_RE.fullmatch(path)
     if not res:
-        raise ValueError(f"Invalid identifier. It should start with database.schema.object. Getting {path}")
+        raise ValueError(
+            "Invalid identifier because it does not follow the pattern. "
+            f"It should start with [[database.]schema.]object. Getting {path}"
+        )
     return (
         res.group("db"),
         res.group("schema"),
         res.group("object"),
-        res.group("others"),
+        res.group("path"),
     )
 
 
@@ -175,8 +209,11 @@ def is_fully_qualified_name(name: str) -> bool:
     Returns:
         bool: True if the name is fully qualified, False otherwise.
     """
-    res = parse_schema_level_object_identifier(name)
-    return res[0] is not None and res[1] is not None and res[2] is not None and not res[3]
+    try:
+        res = parse_schema_level_object_identifier(name)
+        return all(res)
+    except ValueError:
+        return False
 
 
 def get_schema_level_object_identifier(

snowflake/ml/_internal/utils/pkg_version_utils.py

@@ -26,30 +26,11 @@ def get_valid_pkg_versions_supported_in_snowflake_conda_channel(
     pkg_versions: List[str], session: Session, subproject: Optional[str] = None
 ) -> List[str]:
     if snowpark_utils.is_in_stored_procedure():  # type: ignore[no-untyped-call]
-        return _get_valid_pkg_versions_supported_in_snowflake_conda_channel_sync(pkg_versions, session, subproject)
+        return pkg_versions
     else:
         return _get_valid_pkg_versions_supported_in_snowflake_conda_channel_async(pkg_versions, session, subproject)
 
 
-def _get_valid_pkg_versions_supported_in_snowflake_conda_channel_sync(
-    pkg_versions: List[str], session: Session, subproject: Optional[str] = None
-) -> List[str]:
-    for pkg_version in pkg_versions:
-        if pkg_version not in cache:
-            pkg_version_list = _query_pkg_version_supported_in_snowflake_conda_channel(
-                pkg_version=pkg_version, session=session, block=True, subproject=subproject
-            )
-            assert isinstance(pkg_version_list, list)  # keep mypy happy
-            try:
-                cache[pkg_version] = pkg_version_list[0]["VERSION"]
-            except IndexError:
-                cache[pkg_version] = None
-
-    pkg_version_conda_list = _get_conda_packages_and_emit_warnings(pkg_versions)
-
-    return pkg_version_conda_list
-
-
 def _get_valid_pkg_versions_supported_in_snowflake_conda_channel_async(
     pkg_versions: List[str], session: Session, subproject: Optional[str] = None
 ) -> List[str]:
@@ -60,7 +41,11 @@ def _get_valid_pkg_versions_supported_in_snowflake_conda_channel_async(
             async_job = _query_pkg_version_supported_in_snowflake_conda_channel(
                 pkg_version=pkg_version, session=session, block=False, subproject=subproject
             )
-            assert isinstance(async_job, AsyncJob)
+            if isinstance(async_job, list):
+                raise RuntimeError(
+                    "Async job was expected, executed query was returned. Please contact Snowflake support."
+                )
+
             pkg_version_async_job_list.append((pkg_version, async_job))
 
     # Populate the cache.
@@ -143,7 +128,8 @@ def _get_conda_packages_and_emit_warnings(pkg_versions: List[str]) -> List[str]:
         warnings.warn(
             f"Package {', '.join([pkg[0] for pkg in pkg_version_warning_list])} is not supported "
             f"in snowflake conda channel for python runtime "
-            f"{', '.join([pkg[1] for pkg in pkg_version_warning_list])}."
+            f"{', '.join([pkg[1] for pkg in pkg_version_warning_list])}.",
+            stacklevel=1,
         )
 
     return pkg_version_conda_list

snowflake/ml/_internal/utils/snowflake_env.py

@@ -2,7 +2,7 @@ import enum
 from typing import Any, Dict, Optional, TypedDict, cast
 
 from packaging import version
-from typing_extensions import Required
+from typing_extensions import NotRequired, Required
 
 from snowflake.ml._internal.utils import query_result_checker
 from snowflake.snowpark import session
@@ -52,7 +52,7 @@ class SnowflakeCloudType(enum.Enum):
 
 
 class SnowflakeRegion(TypedDict):
-    region_group: Required[str]
+    region_group: NotRequired[str]
     snowflake_region: Required[str]
     cloud: Required[SnowflakeCloudType]
     region: Required[str]
@@ -64,23 +64,33 @@ def get_regions(
 ) -> Dict[str, SnowflakeRegion]:
     res = (
         query_result_checker.SqlResultValidator(sess, "SHOW REGIONS", statement_params=statement_params)
-        .has_column("region_group")
         .has_column("snowflake_region")
         .has_column("cloud")
         .has_column("region")
         .has_column("display_name")
         .validate()
     )
-    return {
-        f"{r.region_group}.{r.snowflake_region}": SnowflakeRegion(
-            region_group=r.region_group,
-            snowflake_region=r.snowflake_region,
-            cloud=SnowflakeCloudType.from_value(r.cloud),
-            region=r.region,
-            display_name=r.display_name,
-        )
-        for r in res
-    }
+    res_dict = {}
+    for r in res:
+        if hasattr(r, "region_group") and r.region_group:
+            key = f"{r.region_group}.{r.snowflake_region}"
+            res_dict[key] = SnowflakeRegion(
+                region_group=r.region_group,
+                snowflake_region=r.snowflake_region,
+                cloud=SnowflakeCloudType.from_value(r.cloud),
+                region=r.region,
+                display_name=r.display_name,
+            )
+        else:
+            key = r.snowflake_region
+            res_dict[key] = SnowflakeRegion(
+                snowflake_region=r.snowflake_region,
+                cloud=SnowflakeCloudType.from_value(r.cloud),
+                region=r.region,
+                display_name=r.display_name,
+            )
+
+    return res_dict
 
 
 def get_current_region_id(sess: session.Session, *, statement_params: Optional[Dict[str, Any]] = None) -> str:

snowflake/ml/_internal/utils/sql_identifier.py

@@ -84,7 +84,7 @@ def to_sql_identifiers(list_of_str: List[str], *, case_sensitive: bool = False)
 def parse_fully_qualified_name(
     name: str,
 ) -> Tuple[Optional[SqlIdentifier], Optional[SqlIdentifier], SqlIdentifier]:
-    db, schema, object, _ = identifier.parse_schema_level_object_identifier(name)
+    db, schema, object = identifier.parse_schema_level_object_identifier(name)
 
     assert name is not None, f"Unable parse the input name `{name}` as fully qualified."
     return (