kumoai 2.13.0.dev202511131731__cp310-cp310-macosx_11_0_arm64.whl → 2.14.0.dev202512271732__cp310-cp310-macosx_11_0_arm64.whl

kumoai/__init__.py

@@ -184,15 +184,12 @@ def init(
         snowflake_credentials
     ) if not api_key and snowflake_credentials else None
     client = KumoClient(url=url, api_key=api_key, spcs_token=spcs_token)
-    if client.authenticate():
-        global_state._url = client._url
-        global_state._api_key = client._api_key
-        global_state._snowflake_credentials = snowflake_credentials
-        global_state._spcs_token = client._spcs_token
-        global_state._snowpark_session = snowpark_session
-    else:
-        raise ValueError("Client authentication failed. Please check if you "
-                         "have a valid API key.")
+    client.authenticate()
+    global_state._url = client._url
+    global_state._api_key = client._api_key
+    global_state._snowflake_credentials = snowflake_credentials
+    global_state._spcs_token = client._spcs_token
+    global_state._snowpark_session = snowpark_session
 
     if not api_key and snowflake_credentials:
         # Refresh token every 10 minutes (expires in 1 hour):
@@ -283,7 +280,19 @@ __all__ = [
 ]
 
 
+def in_snowflake_notebook() -> bool:
+    try:
+        from snowflake.snowpark.context import get_active_session
+        import streamlit  # noqa: F401
+        get_active_session()
+        return True
+    except Exception:
+        return False
+
+
 def in_notebook() -> bool:
+    if in_snowflake_notebook():
+        return True
     try:
         from IPython import get_ipython
         shell = get_ipython()

kumoai/_version.py

@@ -1 +1 @@
-__version__ = '2.13.0.dev202511131731'
+__version__ = '2.14.0.dev202512271732'

kumoai/client/client.py

@@ -13,6 +13,7 @@ if TYPE_CHECKING:
         ArtifactExportJobAPI,
         BaselineJobAPI,
         BatchPredictionJobAPI,
+        DistillationJobAPI,
         GeneratePredictionTableJobAPI,
         GenerateTrainTableJobAPI,
         LLMJobAPI,
@@ -20,7 +21,6 @@ if TYPE_CHECKING:
     )
     from kumoai.client.online import OnlineServingEndpointAPI
     from kumoai.client.pquery import PQueryAPI
-    from kumoai.client.rfm import RFMAPI
     from kumoai.client.source_table import SourceTableAPI
     from kumoai.client.table import TableAPI
 
@@ -73,12 +73,15 @@ class KumoClient:
             self._session.headers.update(
                 {'Authorization': f'Snowflake Token={self._spcs_token}'})
 
-    def authenticate(self) -> bool:
-        r"""Raises an exception if authentication fails. Succeeds if the
-        client is properly formed.
-        """
-        return self._session.get(f"{self._url}/v1/connectors",
-                                 verify=self._verify_ssl).ok
+    def authenticate(self) -> None:
+        """Raises an exception if authentication fails."""
+        try:
+            self._session.get(self._url + '/v1/connectors',
+                              verify=self._verify_ssl).raise_for_status()
+        except Exception:
+            raise ValueError(
+                "Client authentication failed. Please check if you "
+                "have a valid API key/credentials.")
 
     def set_spcs_token(self, spcs_token: str) -> None:
         r"""Sets the SPCS token for the client and updates the session
@@ -130,6 +133,11 @@ class KumoClient:
         from kumoai.client.jobs import TrainingJobAPI
         return TrainingJobAPI(self)
 
+    @property
+    def distillation_job_api(self) -> 'DistillationJobAPI':
+        from kumoai.client.jobs import DistillationJobAPI
+        return DistillationJobAPI(self)
+
     @property
     def batch_prediction_job_api(self) -> 'BatchPredictionJobAPI':
         from kumoai.client.jobs import BatchPredictionJobAPI
@@ -163,12 +171,6 @@ class KumoClient:
         from kumoai.client.online import OnlineServingEndpointAPI
         return OnlineServingEndpointAPI(self)
 
-    @property
-    def rfm_api(self) -> 'RFMAPI':
-        r"""Returns the typed RFM API."""
-        from kumoai.client.rfm import RFMAPI
-        return RFMAPI(self)
-
     def _request(self, endpoint: Endpoint, **kwargs: Any) -> requests.Response:
         r"""Send a HTTP request to the specified endpoint."""
         endpoint_str = endpoint.get_path()

kumoai/client/jobs.py

@@ -22,6 +22,8 @@ from kumoapi.jobs import (
     BatchPredictionRequest,
     CancelBatchPredictionJobResponse,
     CancelTrainingJobResponse,
+    DistillationJobRequest,
+    DistillationJobResource,
     ErrorDetails,
     GeneratePredictionTableJobResource,
     GeneratePredictionTableRequest,
@@ -171,6 +173,28 @@ class TrainingJobAPI(CommonJobAPI[TrainingJobRequest, TrainingJobResource]):
         return resource.config
 
 
+class DistillationJobAPI(CommonJobAPI[DistillationJobRequest,
+                                      DistillationJobResource]):
+    r"""Typed API definition for the distillation job resource."""
+    def __init__(self, client: KumoClient) -> None:
+        super().__init__(client, '/training_jobs/distilled_training_job',
+                         DistillationJobResource)
+
+    def get_config(self, job_id: str) -> DistillationJobRequest:
+        raise NotImplementedError(
+            "Getting the configuration for a distillation job is "
+            "not implemented yet.")
+
+    def get_progress(self, id: str) -> AutoTrainerProgress:
+        raise NotImplementedError(
+            "Getting the progress for a distillation job is not "
+            "implemented yet.")
+
+    def cancel(self, id: str) -> CancelTrainingJobResponse:
+        raise NotImplementedError(
+            "Cancelling a distillation job is not implemented yet.")
+
+
 class BatchPredictionJobAPI(CommonJobAPI[BatchPredictionRequest,
                                          BatchPredictionJobResource]):
     r"""Typed API definition for the prediction job resource."""

kumoai/client/pquery.py

@@ -176,8 +176,12 @@ def filter_model_plan(
                     # Undefined
                     pass
 
-            new_opt_fields.append((field.name, _type, default))
-            new_opts.append(getattr(section, field.name))
+            # Forward compatibility - Remove any newly introduced arguments not
+            # returned yet by the backend:
+            value = getattr(section, field.name)
+            if value != MissingType.VALUE:
+                new_opt_fields.append((field.name, _type, default))
+                new_opts.append(value)
 
         Section = dataclass(
             config=dict(validate_assignment=True),

kumoai/connector/utils.py

@@ -381,8 +381,29 @@ def _handle_duplicate_names(names: List[str]) -> List[str]:
 
 
 def _sanitize_columns(names: List[str]) -> Tuple[List[str], bool]:
-    _SAN_RE = re.compile(r"[^0-9A-Za-z]+")
+    """Normalize column names in a CSV or Parquet file.
+
+    Rules:
+      - Replace any non-alphanumeric character with "_"
+      - Strip leading/trailing underscores
+      - Ensure uniqueness by appending suffixes: _1, _2, ...
+      - Auto-name empty columns as auto_named_<n>
+
+    Returns:
+        (new_column_names, changed)
+    """
+    _SAN_RE = re.compile(r"[^0-9A-Za-z,\t]")
+    # 1) Replace non-alphanumeric sequences with underscore
     new = [_SAN_RE.sub("_", n).strip("_") for n in names]
+
+    # 2) Auto-name any empty column names to match UI behavior
+    unnamed_counter = 0
+    for i, n in enumerate(new):
+        if not n:
+            new[i] = f"auto_named_{unnamed_counter}"
+            unnamed_counter += 1
+
+    # 3) Ensure uniqueness (append suffixes where needed)
     new = _handle_duplicate_names(new)
     return new, new != names
 
@@ -1168,7 +1189,7 @@ def _detect_and_validate_csv(head_bytes: bytes) -> str:
     - Re-serializes those rows and validates with pandas (small nrows) to catch
       malformed inputs.
     - Raises ValueError on empty input or if parsing fails with the chosen
-    delimiter.
+      delimiter.
     """
     if not head_bytes:
         raise ValueError("Could not auto-detect a delimiter: file is empty.")

kumoai/experimental/rfm/__init__.py

@@ -1,67 +1,208 @@
-try:
-    import kumoai.kumolib  # noqa: F401
-except Exception as e:
-    import platform
-
-    _msg = f"""RFM is not supported in your environment.
-
-💻 Your Environment:
-Python version: {platform.python_version()}
-Operating system: {platform.system()}
-CPU architecture: {platform.machine()}
-glibc version: {platform.libc_ver()[1]}
-
-✅ Supported Environments:
-* Python versions: 3.10, 3.11, 3.12, 3.13
-* Operating systems and CPU architectures:
-  * Linux (x86_64)
-  * macOS (arm64)
-  * Windows (x86_64)
-* glibc versions: >=2.28
-
-❌ Unsupported Environments:
-* Python versions: 3.8, 3.9, 3.14
-* Operating systems and CPU architectures:
-  * Linux (arm64)
-  * macOS (x86_64)
-  * Windows (arm64)
-* glibc versions: <2.28
-
-Please create a feature request at 'https://github.com/kumo-ai/kumo-rfm'."""
-
-    raise RuntimeError(_msg) from e
-
-from typing import Optional, Dict
+import ipaddress
+import logging
 import os
+import re
+import socket
+import threading
+from dataclasses import dataclass
+from enum import Enum
+from urllib.parse import urlparse
+
 import kumoai
-from .local_table import LocalTable
-from .local_graph import LocalGraph
-from .rfm import ExplainConfig, Explanation, KumoRFM
+from kumoai.client.client import KumoClient
+from kumoai.spcs import _get_active_session
+
 from .authenticate import authenticate
+from .sagemaker import (
+    KumoClient_SageMakerAdapter,
+    KumoClient_SageMakerProxy_Local,
+)
+from .base import Table
+from .backend.local import LocalTable
+from .graph import Graph
+from .rfm import ExplainConfig, Explanation, KumoRFM
+
+logger = logging.getLogger('kumoai_rfm')
+
+
+def _is_local_address(host: str | None) -> bool:
+    """Return True if the hostname/IP refers to the local machine."""
+    if not host:
+        return False
+    try:
+        infos = socket.getaddrinfo(host, None)
+        for _, _, _, _, sockaddr in infos:
+            ip = sockaddr[0]
+            ip_obj = ipaddress.ip_address(ip)
+            if ip_obj.is_loopback or ip_obj.is_unspecified:
+                return True
+        return False
+    except Exception:
+        return False
+
+
+class InferenceBackend(str, Enum):
+    REST = "REST"
+    LOCAL_SAGEMAKER = "LOCAL_SAGEMAKER"
+    AWS_SAGEMAKER = "AWS_SAGEMAKER"
+    UNKNOWN = "UNKNOWN"
+
+
+def _detect_backend(
+        url: str,  #
+) -> tuple[InferenceBackend, str | None, str | None]:
+    parsed = urlparse(url)
+
+    # Remote SageMaker
+    if ("runtime.sagemaker" in parsed.netloc
+            and parsed.path.endswith("/invocations")):
+        # Example: https://runtime.sagemaker.us-west-2.amazonaws.com/
+        # endpoints/Name/invocations
+        match = re.search(r"runtime\.sagemaker\.([a-z0-9-]+)\.amazonaws\.com",
+                          parsed.netloc)
+        region = match.group(1) if match else None
+        m = re.search(r"/endpoints/([^/]+)/invocations", parsed.path)
+        endpoint_name = m.group(1) if m else None
+        return InferenceBackend.AWS_SAGEMAKER, region, endpoint_name
+
+    # Local SageMaker
+    if parsed.port == 8080 and parsed.path.endswith(
+            "/invocations") and _is_local_address(parsed.hostname):
+        return InferenceBackend.LOCAL_SAGEMAKER, None, None
+
+    # Default: regular REST
+    return InferenceBackend.REST, None, None
+
+
+def _get_snowflake_url(snowflake_application: str) -> str:
+    snowpark_session = _get_active_session()
+    if not snowpark_session:
+        raise ValueError(
+            "Client creation failed: snowflake_application is specified "
+            "without an active snowpark session. If running outside "
+            "a snowflake notebook, specify a URL and credentials.")
+    with snowpark_session.connection.cursor() as cur:
+        cur.execute(
+            f"DESCRIBE SERVICE {snowflake_application}.user_schema.rfm_service"
+            f" ->> SELECT \"dns_name\" from $1")
+        dns_name: str = cur.fetchone()[0]
+    return f"http://{dns_name}:8000/api"
+
+
+@dataclass
+class RfmGlobalState:
+    _url: str = '__url_not_provided__'
+    _backend: InferenceBackend = InferenceBackend.UNKNOWN
+    _region: str | None = None
+    _endpoint_name: str | None = None
+    _thread_local = threading.local()
+
+    # Thread-safe init-once.
+    _initialized: bool = False
+    _lock: threading.Lock = threading.Lock()
+
+    @property
+    def client(self) -> KumoClient:
+        if self._backend == InferenceBackend.REST:
+            return kumoai.global_state.client
+
+        if hasattr(self._thread_local, '_sagemaker'):
+            # Set the spcs token in the client to ensure it has the latest.
+            return self._thread_local._sagemaker
+
+        sagemaker_client: KumoClient
+        if self._backend == InferenceBackend.LOCAL_SAGEMAKER:
+            sagemaker_client = KumoClient_SageMakerProxy_Local(self._url)
+        else:
+            assert self._backend == InferenceBackend.AWS_SAGEMAKER
+            assert self._region
+            assert self._endpoint_name
+            sagemaker_client = KumoClient_SageMakerAdapter(
+                self._region, self._endpoint_name)
+
+        self._thread_local._sagemaker = sagemaker_client
+        return sagemaker_client
+
+    def reset(self) -> None:  # For testing only.
+        with self._lock:
+            self._initialized = False
+            self._url = '__url_not_provided__'
+            self._backend = InferenceBackend.UNKNOWN
+            self._region = None
+            self._endpoint_name = None
+            self._thread_local = threading.local()
+
+
+global_state = RfmGlobalState()
 
 
 def init(
-    url: Optional[str] = None,
-    api_key: Optional[str] = None,
-    snowflake_credentials: Optional[Dict[str, str]] = None,
-    snowflake_application: Optional[str] = None,
+    url: str | None = None,
+    api_key: str | None = None,
+    snowflake_credentials: dict[str, str] | None = None,
+    snowflake_application: str | None = None,
     log_level: str = "INFO",
 ) -> None:
-    if url is None:
-        url = os.getenv("KUMO_API_URL", "https://kumorfm.ai/api")
+    with global_state._lock:
+        if global_state._initialized:
+            if url != global_state._url:
+                raise ValueError(
+                    "Kumo RFM has already been initialized with a different "
+                    "URL. Re-initialization with a different URL is not "
+                    "supported.")
+            return
 
-    kumoai.init(url=url, api_key=api_key,
-                snowflake_credentials=snowflake_credentials,
-                snowflake_application=snowflake_application,
-                log_level=log_level)
+        if snowflake_application:
+            if url is not None:
+                raise ValueError(
+                    "Client creation failed: both snowflake_application and "
+                    "url are specified. If running from a snowflake notebook, "
+                    "specify only snowflake_application.")
+            url = _get_snowflake_url(snowflake_application)
+            api_key = "test:DISABLED"
 
+        if url is None:
+            url = os.getenv("RFM_API_URL", "https://kumorfm.ai/api")
+
+        backend, region, endpoint_name = _detect_backend(url)
+        if backend == InferenceBackend.REST:
+            # Initialize kumoai.global_state
+            if (kumoai.global_state.initialized
+                    and kumoai.global_state._url != url):
+                raise ValueError(
+                    "Kumo AI SDK has already been initialized with different "
+                    "API URL. Please restart Python interpreter and "
+                    "initialize via kumoai.rfm.init()")
+            kumoai.init(url=url, api_key=api_key,
+                        snowflake_credentials=snowflake_credentials,
+                        snowflake_application=snowflake_application,
+                        log_level=log_level)
+        elif backend == InferenceBackend.AWS_SAGEMAKER:
+            assert region
+            assert endpoint_name
+            KumoClient_SageMakerAdapter(region, endpoint_name).authenticate()
+        else:
+            assert backend == InferenceBackend.LOCAL_SAGEMAKER
+            KumoClient_SageMakerProxy_Local(url).authenticate()
+
+        global_state._url = url
+        global_state._backend = backend
+        global_state._region = region
+        global_state._endpoint_name = endpoint_name
+        global_state._initialized = True
+        logger.info("Kumo RFM initialized with backend: %s, url: %s", backend,
+                    url)
+
+
+LocalGraph = Graph  # NOTE Backward compatibility - do not use anymore.
 
 __all__ = [
+    'authenticate',
+    'init',
+    'Table',
     'LocalTable',
-    'LocalGraph',
+    'Graph',
     'KumoRFM',
     'ExplainConfig',
     'Explanation',
-    'authenticate',
-    'init',
 ]

kumoai/experimental/rfm/authenticate.py

@@ -2,12 +2,11 @@ import logging
 import os
 import platform
 from datetime import datetime
-from typing import Optional
 
 from kumoai import in_notebook
 
 
-def authenticate(api_url: Optional[str] = None) -> None:
+def authenticate(api_url: str | None = None) -> None:
     """Authenticates the user and sets the Kumo API key for the SDK.
 
     This function detects the current environment and launches the appropriate
@@ -65,11 +64,11 @@ def _authenticate_local(api_url: str, redirect_port: int = 8765) -> None:
     import webbrowser
     from getpass import getpass
     from socketserver import TCPServer
-    from typing import Any, Dict
+    from typing import Any
 
     logger = logging.getLogger('kumoai')
 
-    token_status: Dict[str, Any] = {
+    token_status: dict[str, Any] = {
         'token': None,
         'token_name': None,
         'failed': False

kumoai/experimental/rfm/backend/local/__init__.py

@@ -0,0 +1,42 @@
+try:
+    import kumoai.kumolib  # noqa: F401
+except Exception as e:
+    import platform
+
+    _msg = f"""RFM is not supported in your environment.
+
+💻 Your Environment:
+Python version: {platform.python_version()}
+Operating system: {platform.system()}
+CPU architecture: {platform.machine()}
+glibc version: {platform.libc_ver()[1]}
+
+✅ Supported Environments:
+* Python versions: 3.10, 3.11, 3.12, 3.13
+* Operating systems and CPU architectures:
+  * Linux (x86_64)
+  * macOS (arm64)
+  * Windows (x86_64)
+* glibc versions: >=2.28
+
+❌ Unsupported Environments:
+* Python versions: 3.8, 3.9, 3.14
+* Operating systems and CPU architectures:
+  * Linux (arm64)
+  * macOS (x86_64)
+  * Windows (arm64)
+* glibc versions: <2.28
+
+Please create a feature request at 'https://github.com/kumo-ai/kumo-rfm'."""
+
+    raise RuntimeError(_msg) from e
+
+from .table import LocalTable
+from .graph_store import LocalGraphStore
+from .sampler import LocalSampler
+
+__all__ = [
+    'LocalTable',
+    'LocalGraphStore',
+    'LocalSampler',
+]