kumoai 2.10.0.dev202509281831__cp313-cp313-win_amd64.whl → 2.13.0.dev202511211730__cp313-cp313-win_amd64.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):
@@ -200,9 +197,11 @@ def init(
 
     logger = logging.getLogger('kumoai')
     log_level = logging.getLevelName(logger.getEffectiveLevel())
+
     logger.info(
-        "Successfully initialized the Kumo SDK against deployment %s, with "
-        "log level %s.", url, log_level)
+        f"Successfully initialized the Kumo SDK (version {__version__}) "
+        f"against deployment {url}, with "
+        f"log level {log_level}.")
 
 
 def set_log_level(level: str) -> None:

kumoai/_version.py

@@ -1 +1 @@
-__version__ = '2.10.0.dev202509281831'
+__version__ = '2.13.0.dev202511211730'

kumoai/client/client.py

@@ -20,7 +20,6 @@ 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
 
@@ -33,6 +32,7 @@ class KumoClient:
         url: str,
         api_key: Optional[str],
         spcs_token: Optional[str] = None,
+        verify_ssl: bool = True,
     ) -> None:
         r"""Creates a client against the Kumo public API, provided a URL of
         the endpoint and an authentication token.
@@ -42,11 +42,14 @@ class KumoClient:
             api_key: the public API authentication token.
             spcs_token: the SPCS token used for authentication to access the
                 Kumo API endpoint.
+            verify_ssl: whether to verify SSL certificates. Set to False to
+                skip SSL certificate verification (equivalent to curl -k).
         """
         self._url = url
         self._api_url = f"{url}/{API_VERSION}"
         self._api_key = api_key
         self._spcs_token = spcs_token
+        self._verify_ssl = verify_ssl
 
         retry_strategy = Retry(
             total=10,  # Maximum number of retries
@@ -69,11 +72,15 @@ 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").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
@@ -158,12 +165,6 @@ 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()
@@ -184,7 +185,7 @@ class KumoClient:
         :meth:`requests.Session.get`.
         """
         url = self._format_endpoint_url(endpoint)
-        return self._session.get(url=url, **kwargs)
+        return self._session.get(url=url, verify=self._verify_ssl, **kwargs)
 
     def _post(self, endpoint: str, **kwargs: Any) -> requests.Response:
         r"""Send a POST request to the specified endpoint, with keyword
@@ -192,7 +193,7 @@ class KumoClient:
         :meth:`requests.Session.post`.
         """
         url = self._format_endpoint_url(endpoint)
-        return self._session.post(url=url, **kwargs)
+        return self._session.post(url=url, verify=self._verify_ssl, **kwargs)
 
     def _patch(self, endpoint: str, **kwargs: Any) -> requests.Response:
         r"""Send a PATCH request to the specified endpoint, with keyword
@@ -200,7 +201,7 @@ class KumoClient:
         :meth:`requests.Session.patch`.
         """
         url = self._format_endpoint_url(endpoint)
-        return self._session.patch(url=url, **kwargs)
+        return self._session.patch(url=url, verify=self._verify_ssl, **kwargs)
 
     def _delete(self, endpoint: str, **kwargs: Any) -> requests.Response:
         r"""Send a DELETE request to the specified endpoint, with keyword
@@ -208,7 +209,7 @@ class KumoClient:
         :meth:`requests.Session.delete`.
         """
         url = self._format_endpoint_url(endpoint)
-        return self._session.delete(url=url, **kwargs)
+        return self._session.delete(url=url, verify=self._verify_ssl, **kwargs)
 
     def _format_endpoint_url(self, endpoint: str) -> str:
         if endpoint[0] == "/":

kumoai/client/endpoints.py

@@ -147,3 +147,4 @@ class RFMEndpoints:
     explain = Endpoint(f"{BASE}/explain", HTTPMethod.POST)
     evaluate = Endpoint(f"{BASE}/evaluate", HTTPMethod.POST)
     validate_query = Endpoint(f"{BASE}/validate_query", HTTPMethod.POST)
+    parse_query = Endpoint(f"{BASE}/parse_query", HTTPMethod.POST)

kumoai/client/rfm.py

@@ -1,6 +1,11 @@
+from typing import Any
+
 from kumoapi.json_serde import to_json_dict
 from kumoapi.rfm import (
     RFMEvaluateResponse,
+    RFMExplanationResponse,
+    RFMParseQueryRequest,
+    RFMParseQueryResponse,
     RFMPredictResponse,
     RFMValidateQueryRequest,
     RFMValidateQueryResponse,
@@ -25,28 +30,35 @@ class RFMAPI:
         Returns:
             RFMPredictResponse containing the predictions
         """
-        # Send binary data to the predict endpoint
         response = self._client._request(
-            RFMEndpoints.predict, data=request,
-            headers={'Content-Type': 'application/x-protobuf'})
+            RFMEndpoints.predict,
+            data=request,
+            headers={'Content-Type': 'application/x-protobuf'},
+        )
         raise_on_error(response)
         return parse_response(RFMPredictResponse, response)
 
-    def explain(self, request: bytes) -> RFMPredictResponse:
+    def explain(
+        self,
+        request: bytes,
+        skip_summary: bool = False,
+    ) -> RFMExplanationResponse:
         """Explain the RFM model on the given context.
 
         Args:
             request: The predict request as serialized protobuf.
+            skip_summary: Whether to skip generating a human-readable summary
+                of the explanation.
 
         Returns:
             RFMPredictResponse containing the explanations
         """
-        # Send binary data to the explain endpoint
+        params: dict[str, Any] = {'generate_summary': not skip_summary}
         response = self._client._request(
-            RFMEndpoints.explain, data=request,
+            RFMEndpoints.explain, data=request, params=params,
             headers={'Content-Type': 'application/x-protobuf'})
         raise_on_error(response)
-        return parse_response(RFMPredictResponse, response)
+        return parse_response(RFMExplanationResponse, response)
 
     def evaluate(self, request: bytes) -> RFMEvaluateResponse:
         """Evaluate the RFM model on the given context.
@@ -57,7 +69,6 @@ class RFMAPI:
         Returns:
             RFMEvaluateResponse containing the computed metrics
         """
-        # Send binary data to the evaluate endpoint
         response = self._client._request(
             RFMEndpoints.evaluate, data=request,
             headers={'Content-Type': 'application/x-protobuf'})
@@ -81,3 +92,21 @@ class RFMAPI:
                                          json=to_json_dict(request))
         raise_on_error(response)
         return parse_response(RFMValidateQueryResponse, response)
+
+    def parse_query(
+        self,
+        request: RFMParseQueryRequest,
+    ) -> RFMParseQueryResponse:
+        """Validate a predictive query against a graph.
+
+        Args:
+            request: The request object containing
+                the query and graph definition
+
+        Returns:
+            RFMParseQueryResponse containing the QueryDefinition
+        """
+        response = self._client._request(RFMEndpoints.parse_query,
+                                         json=to_json_dict(request))
+        raise_on_error(response)
+        return parse_response(RFMParseQueryResponse, response)

kumoai/experimental/rfm/__init__.py

@@ -12,7 +12,7 @@ CPU architecture: {platform.machine()}
 glibc version: {platform.libc_ver()[1]}
 
 ✅ Supported Environments:
-* Python versions: 3.9, 3.10, 3.11, 3.12, 3.13
+* Python versions: 3.10, 3.11, 3.12, 3.13
 * Operating systems and CPU architectures:
   * Linux (x86_64)
   * macOS (arm64)
@@ -20,7 +20,7 @@ glibc version: {platform.libc_ver()[1]}
 * glibc versions: >=2.28
 
 ❌ Unsupported Environments:
-* Python versions: 3.8, 3.14
+* Python versions: 3.8, 3.9, 3.14
 * Operating systems and CPU architectures:
   * Linux (arm64)
   * macOS (x86_64)
@@ -31,14 +31,122 @@ Please create a feature request at 'https://github.com/kumo-ai/kumo-rfm'."""
 
     raise RuntimeError(_msg) from e
 
-from typing import Optional, Dict
+from dataclasses import dataclass
+from enum import Enum
+import ipaddress
+import logging
+import re
+import socket
+import threading
+from typing import Optional, Dict, Tuple
 import os
+from urllib.parse import urlparse
 import kumoai
+from kumoai.client.client import KumoClient
+from .sagemaker import (KumoClient_SageMakerAdapter,
+                        KumoClient_SageMakerProxy_Local)
 from .local_table import LocalTable
 from .local_graph import LocalGraph
-from .rfm import KumoRFM
+from .rfm import ExplainConfig, Explanation, KumoRFM
 from .authenticate import authenticate
 
+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, Optional[str], Optional[str]]:
+    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
+
+
+@dataclass
+class RfmGlobalState:
+    _url: str = '__url_not_provided__'
+    _backend: InferenceBackend = InferenceBackend.UNKNOWN
+    _region: Optional[str] = None
+    _endpoint_name: Optional[str] = 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,
@@ -47,19 +155,54 @@ def init(
     snowflake_application: Optional[str] = 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
+
+        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()
 
-    kumoai.init(url=url, api_key=api_key,
-                snowflake_credentials=snowflake_credentials,
-                snowflake_application=snowflake_application,
-                log_level=log_level)
+        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)
 
 
 __all__ = [
     'LocalTable',
     'LocalGraph',
     'KumoRFM',
+    'ExplainConfig',
+    'Explanation',
     'authenticate',
     'init',
 ]

kumoai/experimental/rfm/infer/timestamp.py

@@ -2,6 +2,7 @@ import re
 import warnings
 
 import pandas as pd
+from dateutil.parser import UnknownTimezoneWarning
 from kumoapi.typing import Dtype, Stype
 
 
@@ -20,9 +21,7 @@ def contains_timestamp(ser: pd.Series, column_name: str, dtype: Dtype) -> bool:
         column_name,
         re.IGNORECASE,
     )
-
-    if match is not None:
-        return True
+    score = 0.3 if match is not None else 0.0
 
     ser = ser.iloc[:100]
     ser = ser.dropna()
@@ -34,5 +33,9 @@ def contains_timestamp(ser: pd.Series, column_name: str, dtype: Dtype) -> bool:
     ser = ser.astype(str)  # Avoid parsing numbers as unix timestamps.
 
     with warnings.catch_warnings():
+        warnings.simplefilter('ignore', UnknownTimezoneWarning)
         warnings.filterwarnings('ignore', message='Could not infer format')
-        return pd.to_datetime(ser, errors='coerce').notna().all()
+        mask = pd.to_datetime(ser, errors='coerce').notna()
+        score += int(mask.sum()) / len(mask)
+
+    return score >= 1.0