kumoai 2.12.1__py3-none-any.whl → 2.14.0.dev202512141732__py3-none-any.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__ = '2.12.1'
+__version__ = '2.14.0.dev202512141732'

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
 
@@ -73,12 +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",
-                                 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
@@ -163,12 +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()

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

@@ -1,43 +1,123 @@
-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 typing import Dict, Optional, Tuple
+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 .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, 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(
@@ -47,21 +127,57 @@ 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
 
-    kumoai.init(url=url, api_key=api_key,
-                snowflake_credentials=snowflake_credentials,
-                snowflake_application=snowflake_application,
-                log_level=log_level)
+        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/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',
+]

kumoai/experimental/rfm/{local_graph_store.py → backend/local/graph_store.py}

@@ -1,13 +1,12 @@
 import warnings
-from typing import Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Dict, List, Optional, Tuple, Union
 
 import numpy as np
 import pandas as pd
 from kumoapi.rfm.context import Subgraph
 from kumoapi.typing import Stype
 
-from kumoai.experimental.rfm import LocalGraph
-from kumoai.experimental.rfm.utils import normalize_text
+from kumoai.experimental.rfm.backend.local import LocalTable
 from kumoai.utils import InteractiveProgressLogger, ProgressLogger
 
 try:
@@ -16,12 +15,14 @@ try:
 except ImportError:
     WITH_TORCH = False
 
+if TYPE_CHECKING:
+    from kumoai.experimental.rfm import Graph
+
 
 class LocalGraphStore:
     def __init__(
         self,
-        graph: LocalGraph,
-        preprocess: bool = False,
+        graph: 'Graph',
         verbose: Union[bool, ProgressLogger] = True,
     ) -> None:
 
@@ -32,27 +33,22 @@ class LocalGraphStore:
             )
 
         with verbose as logger:
-            self.df_dict, self.mask_dict = self.sanitize(graph, preprocess)
-            self.stype_dict = self.get_stype_dict(graph)
+            self.df_dict, self.mask_dict = self.sanitize(graph)
             logger.log("Sanitized input data")
 
-            self.pkey_name_dict, self.pkey_map_dict = self.get_pkey_data(graph)
+            self.pkey_map_dict = self.get_pkey_map_dict(graph)
             num_pkeys = sum(t.has_primary_key() for t in graph.tables.values())
             if num_pkeys > 1:
                 logger.log(f"Collected primary keys from {num_pkeys} tables")
             else:
                 logger.log(f"Collected primary key from {num_pkeys} table")
 
-            (
-                self.time_column_dict,
-                self.end_time_column_dict,
-                self.time_dict,
-                self.min_time,
-                self.max_time,
-            ) = self.get_time_data(graph)
-            if self.max_time != pd.Timestamp.min:
+            self.time_dict, self.min_max_time_dict = self.get_time_data(graph)
+            if len(self.min_max_time_dict) > 0:
+                min_time = min(t for t, _ in self.min_max_time_dict.values())
+                max_time = max(t for _, t in self.min_max_time_dict.values())
                 logger.log(f"Identified temporal graph from "
-                           f"{self.min_time.date()} to {self.max_time.date()}")
+                           f"{min_time.date()} to {max_time.date()}")
             else:
                 logger.log("Identified static graph without timestamps")
 
@@ -62,14 +58,6 @@ class LocalGraphStore:
             logger.log(f"Created graph with {num_nodes:,} nodes and "
                        f"{num_edges:,} edges")
 
-    @property
-    def node_types(self) -> List[str]:
-        return list(self.df_dict.keys())
-
-    @property
-    def edge_types(self) -> List[Tuple[str, str, str]]:
-        return list(self.row_dict.keys())
-
     def get_node_id(self, table_name: str, pkey: pd.Series) -> np.ndarray:
         r"""Returns the node ID given primary keys.
 
@@ -105,8 +93,7 @@ class LocalGraphStore:
 
     def sanitize(
         self,
-        graph: LocalGraph,
-        preprocess: bool = False,
+        graph: 'Graph',
     ) -> Tuple[Dict[str, pd.DataFrame], Dict[str, np.ndarray]]:
         r"""Sanitizes raw data according to table schema definition:
 
@@ -115,17 +102,12 @@ class LocalGraphStore:
         * drops timezone information from timestamps
         * drops duplicate primary keys
         * removes rows with missing primary keys or time values
-
-        If ``preprocess`` is set to ``True``, it will additionally pre-process
-        data for faster model processing. In particular, it:
-        * tokenizes any text column that is not a foreign key
         """
-        df_dict: Dict[str, pd.DataFrame] = {
-            table_name: table._data.copy(deep=False).reset_index(drop=True)
-            for table_name, table in graph.tables.items()
-        }
-
-        foreign_keys = {(edge.src_table, edge.fkey) for edge in graph.edges}
+        df_dict: Dict[str, pd.DataFrame] = {}
+        for table_name, table in graph.tables.items():
+            assert isinstance(table, LocalTable)
+            df = table._data
+            df_dict[table_name] = df.copy(deep=False).reset_index(drop=True)
 
         mask_dict: Dict[str, np.ndarray] = {}
         for table in graph.tables.values():
@@ -144,12 +126,6 @@ class LocalGraphStore:
                         ser = ser.dt.tz_localize(None)
                         df_dict[table.name][col.name] = ser
 
-                # Normalize text in advance (but exclude foreign keys):
-                if (preprocess and col.stype == Stype.text
-                        and (table.name, col.name) not in foreign_keys):
-                    ser = df_dict[table.name][col.name]
-                    df_dict[table.name][col.name] = normalize_text(ser)
-
             mask: Optional[np.ndarray] = None
             if table._time_column is not None:
                 ser = df_dict[table.name][table._time_column]
@@ -165,34 +141,16 @@ class LocalGraphStore:
 
         return df_dict, mask_dict
 
-    def get_stype_dict(self, graph: LocalGraph) -> Dict[str, Dict[str, Stype]]:
-        stype_dict: Dict[str, Dict[str, Stype]] = {}
-        foreign_keys = {(edge.src_table, edge.fkey) for edge in graph.edges}
-        for table in graph.tables.values():
-            stype_dict[table.name] = {}
-            for column in table.columns:
-                if column == table.primary_key:
-                    continue
-                if (table.name, column.name) in foreign_keys:
-                    continue
-                stype_dict[table.name][column.name] = column.stype
-        return stype_dict
-
-    def get_pkey_data(
+    def get_pkey_map_dict(
         self,
-        graph: LocalGraph,
-    ) -> Tuple[
-            Dict[str, str],
-            Dict[str, pd.DataFrame],
-    ]:
-        pkey_name_dict: Dict[str, str] = {}
+        graph: 'Graph',
+    ) -> Dict[str, pd.DataFrame]:
         pkey_map_dict: Dict[str, pd.DataFrame] = {}
 
         for table in graph.tables.values():
             if table._primary_key is None:
                 continue
 
-            pkey_name_dict[table.name] = table._primary_key
             pkey = self.df_dict[table.name][table._primary_key]
             pkey_map = pd.DataFrame(
                 dict(arange=range(len(pkey))),
@@ -214,52 +172,41 @@ class LocalGraphStore:
 
             pkey_map_dict[table.name] = pkey_map
 
-        return pkey_name_dict, pkey_map_dict
+        return pkey_map_dict
 
     def get_time_data(
         self,
-        graph: LocalGraph,
+        graph: 'Graph',
     ) -> Tuple[
-            Dict[str, str],
-            Dict[str, str],
             Dict[str, np.ndarray],
-            pd.Timestamp,
-            pd.Timestamp,
+            Dict[str, Tuple[pd.Timestamp, pd.Timestamp]],
     ]:
-        time_column_dict: Dict[str, str] = {}
-        end_time_column_dict: Dict[str, str] = {}
         time_dict: Dict[str, np.ndarray] = {}
-        min_time = pd.Timestamp.max
-        max_time = pd.Timestamp.min
+        min_max_time_dict: Dict[str, tuple[pd.Timestamp, pd.Timestamp]] = {}
         for table in graph.tables.values():
-            if table._end_time_column is not None:
-                end_time_column_dict[table.name] = table._end_time_column
-
             if table._time_column is None:
                 continue
 
             time = self.df_dict[table.name][table._time_column]
-            time_dict[table.name] = time.astype('datetime64[ns]').astype(
-                int).to_numpy() // 1000**3
-            time_column_dict[table.name] = table._time_column
+            if time.dtype != 'datetime64[ns]':
+                time = time.astype('datetime64[ns]')
+            time_dict[table.name] = time.astype(int).to_numpy() // 1000**3
 
             if table.name in self.mask_dict.keys():
                 time = time[self.mask_dict[table.name]]
             if len(time) > 0:
-                min_time = min(min_time, time.min())
-                max_time = max(max_time, time.max())
+                min_max_time_dict[table.name] = (time.min(), time.max())
+            else:
+                min_max_time_dict[table.name] = (
+                    pd.Timestamp.max,
+                    pd.Timestamp.min,
+                )
 
-        return (
-            time_column_dict,
-            end_time_column_dict,
-            time_dict,
-            min_time,
-            max_time,
-        )
+        return time_dict, min_max_time_dict
 
     def get_csc(
         self,
-        graph: LocalGraph,
+        graph: 'Graph',
     ) -> Tuple[
             Dict[Tuple[str, str, str], np.ndarray],
             Dict[Tuple[str, str, str], np.ndarray],