kumoai 2.10.0.dev202509231831__cp313-cp313-macosx_11_0_arm64.whl → 2.14.0.dev202512161731__cp313-cp313-macosx_11_0_arm64.whl

kumoai/experimental/rfm/sagemaker.py

@@ -0,0 +1,138 @@
+import base64
+import json
+from typing import Any, Dict, List, Tuple
+
+import requests
+
+from kumoai.client import KumoClient
+from kumoai.client.endpoints import Endpoint, HTTPMethod
+from kumoai.exceptions import HTTPException
+
+try:
+    # isort: off
+    from mypy_boto3_sagemaker_runtime.client import SageMakerRuntimeClient
+    from mypy_boto3_sagemaker_runtime.type_defs import (
+        InvokeEndpointOutputTypeDef, )
+    # isort: on
+except ImportError:
+    SageMakerRuntimeClient = Any
+    InvokeEndpointOutputTypeDef = Any
+
+
+class SageMakerResponseAdapter(requests.Response):
+    def __init__(self, sm_response: InvokeEndpointOutputTypeDef):
+        super().__init__()
+        # Read the body bytes
+        self._content = sm_response['Body'].read()
+        self.status_code = 200
+        self.headers['Content-Type'] = sm_response.get('ContentType',
+                                                       'application/json')
+        # Optionally, you can store original sm_response for debugging
+        self.sm_response = sm_response
+
+    @property
+    def text(self) -> str:
+        assert isinstance(self._content, bytes)
+        return self._content.decode('utf-8')
+
+    def json(self, **kwargs) -> dict[str, Any]:  # type: ignore
+        return json.loads(self.text, **kwargs)
+
+
+class KumoClient_SageMakerAdapter(KumoClient):
+    def __init__(self, region: str, endpoint_name: str):
+        import boto3
+        self._client: SageMakerRuntimeClient = boto3.client(
+            service_name="sagemaker-runtime", region_name=region)
+        self._endpoint_name = endpoint_name
+
+        # Recording buffers.
+        self._recording_active = False
+        self._recorded_reqs: List[Dict[str, Any]] = []
+        self._recorded_resps: List[Dict[str, Any]] = []
+
+    def authenticate(self) -> None:
+        # TODO(siyang): call /ping to verify?
+        pass
+
+    def _request(self, endpoint: Endpoint, **kwargs: Any) -> requests.Response:
+        assert endpoint.method == HTTPMethod.POST
+        if 'json' in kwargs:
+            payload = json.dumps(kwargs.pop('json'))
+        elif 'data' in kwargs:
+            raw_payload = kwargs.pop('data')
+            assert isinstance(raw_payload, bytes)
+            payload = base64.b64encode(raw_payload).decode()
+        else:
+            raise HTTPException(400, 'Unable to send data to KumoRFM.')
+
+        request = {
+            'method': endpoint.get_path().rsplit('/')[-1],
+            'payload': payload,
+        }
+        response: InvokeEndpointOutputTypeDef = self._client.invoke_endpoint(
+            EndpointName=self._endpoint_name,
+            ContentType="application/json",
+            Body=json.dumps(request),
+        )
+
+        adapted_response = SageMakerResponseAdapter(response)
+
+        # If validation is active, store input/output
+        if self._recording_active:
+            self._recorded_reqs.append(request)
+            self._recorded_resps.append(adapted_response.json())
+
+        return adapted_response
+
+    def start_recording(self) -> None:
+        """Start recording requests/responses to/from sagemaker endpoint."""
+        assert not self._recording_active
+        self._recording_active = True
+        self._recorded_reqs.clear()
+        self._recorded_resps.clear()
+
+    def end_recording(self) -> List[Tuple[Dict[str, Any], Dict[str, Any]]]:
+        """Stop recording and return recorded requests/responses."""
+        assert self._recording_active
+        self._recording_active = False
+        recorded = list(zip(self._recorded_reqs, self._recorded_resps))
+        self._recorded_reqs.clear()
+        self._recorded_resps.clear()
+        return recorded
+
+
+class KumoClient_SageMakerProxy_Local(KumoClient):
+    def __init__(self, url: str):
+        self._client = KumoClient(url, api_key=None)
+        self._client._api_url = self._client._url
+        self._endpoint = Endpoint('/invocations', HTTPMethod.POST)
+
+    def authenticate(self) -> None:
+        try:
+            self._client._session.get(
+                self._url + '/ping',
+                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 _request(self, endpoint: Endpoint, **kwargs: Any) -> requests.Response:
+        assert endpoint.method == HTTPMethod.POST
+        if 'json' in kwargs:
+            payload = json.dumps(kwargs.pop('json'))
+        elif 'data' in kwargs:
+            raw_payload = kwargs.pop('data')
+            assert isinstance(raw_payload, bytes)
+            payload = base64.b64encode(raw_payload).decode()
+        else:
+            raise HTTPException(400, 'Unable to send data to KumoRFM.')
+        return self._client._request(
+            self._endpoint,
+            json={
+                'method': endpoint.get_path().rsplit('/')[-1],
+                'payload': payload,
+            },
+            **kwargs,
+        )

kumoai/jobs.py

@@ -26,6 +26,7 @@ class JobInterface(ABC, Generic[IDType, JobRequestType, JobResourceType]):
             limit (int): Max number of jobs to list, default 10.
 
         Example:
+            >>> # doctest: +SKIP
             >>> tags = {'pquery_name': 'my_pquery_name'}
             >>> jobs = BatchPredictionJob.search_by_tags(tags)
             Search limited to 10 results based on the `limit` parameter.

kumoai/pquery/predictive_query.py

@@ -370,9 +370,11 @@ class PredictiveQuery:
         train_table_job_api = global_state.client.generate_train_table_job_api
         job_id: GenerateTrainTableJobID = train_table_job_api.create(
             GenerateTrainTableRequest(
-                dict(custom_tags), pq_id, plan,
-                graph_snapshot_id=self.graph.snapshot(
-                    non_blocking=non_blocking)))
+                dict(custom_tags),
+                pq_id,
+                plan,
+                None,
+            ))
 
         self._train_table = TrainingTableJob(job_id=job_id)
         if non_blocking:
@@ -451,9 +453,11 @@ class PredictiveQuery:
         bp_table_api = global_state.client.generate_prediction_table_job_api
         job_id: GeneratePredictionTableJobID = bp_table_api.create(
             GeneratePredictionTableRequest(
-                dict(custom_tags), pq_id, plan,
-                graph_snapshot_id=self.graph.snapshot(
-                    non_blocking=non_blocking)))
+                dict(custom_tags),
+                pq_id,
+                plan,
+                None,
+            ))
 
         self._prediction_table = PredictionTableJob(job_id=job_id)
         if non_blocking:

kumoai/spcs.py

@@ -54,9 +54,7 @@ def _refresh_spcs_token() -> None:
         api_key=global_state._api_key,
         spcs_token=spcs_token,
     )
-    if not client.authenticate():
-        raise ValueError("Client authentication failed. Please check if you "
-                         "have a valid API key.")
+    client.authenticate()
 
     # Update state:
     global_state.set_spcs_token(spcs_token)

kumoai/testing/decorators.py

@@ -25,7 +25,7 @@ def onlyFullTest(func: Callable) -> Callable:
 def has_package(package: str) -> bool:
     r"""Returns ``True`` in case ``package`` is installed."""
     req = Requirement(package)
-    if importlib.util.find_spec(req.name) is None:
+    if importlib.util.find_spec(req.name) is None:  # type: ignore
         return False
 
     try:

kumoai/testing/snow.py

@@ -0,0 +1,50 @@
+import json
+import os
+
+from kumoai.experimental.rfm.backend.snow import Connection
+from kumoai.experimental.rfm.backend.snow import connect as _connect
+
+
+def connect(
+    region: str,
+    id: str,
+    account: str,
+    user: str,
+    warehouse: str,
+    database: str | None = None,
+    schema: str | None = None,
+) -> Connection:
+
+    kwargs = dict(password=os.getenv('SNOWFLAKE_PASSWORD'))
+    if kwargs['password'] is None:
+        import boto3
+        from cryptography.hazmat.primitives import serialization
+
+        client = boto3.client(
+            service_name='secretsmanager',
+            region_name=region,
+        )
+        secret_id = (f'arn:aws:secretsmanager:{region}:{id}:secret:'
+                     f'{account}.snowflakecomputing.com')
+        response = client.get_secret_value(SecretId=secret_id)['SecretString']
+        secret = json.loads(response)
+
+        private_key = serialization.load_pem_private_key(
+            secret['kumo_user_secretkey'].encode(),
+            password=None,
+        )
+        kwargs['private_key'] = private_key.private_bytes(
+            encoding=serialization.Encoding.DER,
+            format=serialization.PrivateFormat.PKCS8,
+            encryption_algorithm=serialization.NoEncryption(),
+        )
+
+    return _connect(
+        account=account,
+        user=user,
+        warehouse='WH_XS',
+        database='KUMO',
+        schema=schema,
+        session_parameters=dict(CLIENT_TELEMETRY_ENABLED=False),
+        **kwargs,
+    )

kumoai/trainer/trainer.py

@@ -20,7 +20,6 @@ from kumoapi.jobs import (
     TrainingJobResource,
 )
 from kumoapi.model_plan import ModelPlan
-from kumoapi.task import TaskType
 
 from kumoai import global_state
 from kumoai.artifact_export.config import OutputConfig
@@ -360,6 +359,9 @@ class Trainer:
                 'deprecated. Please use output_config to specify these '
                 'parameters.')
         assert output_config is not None
+        # Be able to pass output_config as a dictionary
+        if isinstance(output_config, dict):
+            output_config = OutputConfig(**output_config)
         output_table_name = to_db_table_name(output_config.output_table_name)
         validate_output_arguments(
             output_config.output_types,
@@ -402,15 +404,15 @@ class Trainer:
                 pred_table_data_path = prediction_table.table_data_uri
 
         api = global_state.client.batch_prediction_job_api
-
-        from kumoai.pquery.predictive_query import PredictiveQuery
-        pquery = PredictiveQuery.load_from_training_job(training_job_id)
-        if pquery.get_task_type() == TaskType.BINARY_CLASSIFICATION:
-            if binary_classification_threshold is None:
-                logger.warning("No binary classification threshold provided. "
-                               "Using default threshold of 0.5.")
-                binary_classification_threshold = 0.5
-
+        # Remove to resolve https://github.com/kumo-ai/kumo/issues/24250
+        # from kumoai.pquery.predictive_query import PredictiveQuery
+        # pquery = PredictiveQuery.load_from_training_job(training_job_id)
+        # if pquery.get_task_type() == TaskType.BINARY_CLASSIFICATION:
+        #     if binary_classification_threshold is None:
+        #         logger.warning(
+        # "No binary classification threshold provided. "
+        # "Using default threshold of 0.5.")
+        #         binary_classification_threshold = 0.5
         job_id, response = api.maybe_create(
             BatchPredictionRequest(
                 dict(custom_tags),

kumoai/utils/__init__.py

@@ -1,10 +1,11 @@
-from .progress_logger import ProgressLogger, InteractiveProgressLogger
+from .sql import quote_ident
+from .progress_logger import ProgressLogger
 from .forecasting import ForecastVisualizer
 from .datasets import from_relbench
 
 __all__ = [
+    'quote_ident',
     'ProgressLogger',
-    'InteractiveProgressLogger',
     'ForecastVisualizer',
     'from_relbench',
 ]

kumoai/utils/progress_logger.py

@@ -1,9 +1,19 @@
+import re
+import sys
 import time
 from typing import Any, List, Optional, Union
 
 from rich.console import Console, ConsoleOptions, RenderResult
 from rich.live import Live
 from rich.padding import Padding
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    Task,
+    TextColumn,
+    TimeRemainingColumn,
+)
 from rich.spinner import Spinner
 from rich.table import Table
 from rich.text import Text
@@ -11,13 +21,23 @@ from typing_extensions import Self
 
 
 class ProgressLogger:
-    def __init__(self, msg: str) -> None:
+    def __init__(self, msg: str, verbose: bool = True) -> None:
         self.msg = msg
+        self.verbose = verbose
+
         self.logs: List[str] = []
 
         self.start_time: Optional[float] = None
         self.end_time: Optional[float] = None
 
+    @classmethod
+    def default(cls, msg: str, verbose: bool = True) -> 'ProgressLogger':
+        from kumoai import in_snowflake_notebook
+
+        if in_snowflake_notebook():
+            return StreamlitProgressLogger(msg, verbose)
+        return RichProgressLogger(msg, verbose)
+
     @property
     def duration(self) -> float:
         assert self.start_time is not None
@@ -28,6 +48,12 @@ class ProgressLogger:
     def log(self, msg: str) -> None:
         self.logs.append(msg)
 
+    def init_progress(self, total: int, description: str) -> None:
+        pass
+
+    def step(self) -> None:
+        pass
+
     def __enter__(self) -> Self:
         self.start_time = time.perf_counter()
         return self
@@ -39,24 +65,68 @@ class ProgressLogger:
         return f'{self.__class__.__name__}({self.msg})'
 
 
-class InteractiveProgressLogger(ProgressLogger):
+class ColoredMofNCompleteColumn(MofNCompleteColumn):
+    def __init__(self, style: str = 'green') -> None:
+        super().__init__()
+        self.style = style
+
+    def render(self, task: Task) -> Text:
+        return Text(str(super().render(task)), style=self.style)
+
+
+class ColoredTimeRemainingColumn(TimeRemainingColumn):
+    def __init__(self, style: str = 'cyan') -> None:
+        super().__init__()
+        self.style = style
+
+    def render(self, task: Task) -> Text:
+        return Text(str(super().render(task)), style=self.style)
+
+
+class RichProgressLogger(ProgressLogger):
     def __init__(
         self,
         msg: str,
         verbose: bool = True,
         refresh_per_second: int = 10,
     ) -> None:
-        super().__init__(msg=msg)
+        super().__init__(msg=msg, verbose=verbose)
 
-        self.verbose = verbose
         self.refresh_per_second = refresh_per_second
 
+        self._progress: Optional[Progress] = None
+        self._task: Optional[int] = None
+
         self._live: Optional[Live] = None
         self._exception: bool = False
 
+    def init_progress(self, total: int, description: str) -> None:
+        assert self._progress is None
+        if self.verbose:
+            self._progress = Progress(
+                TextColumn(f'   ↳ {description}', style='dim'),
+                BarColumn(bar_width=None),
+                ColoredMofNCompleteColumn(style='dim'),
+                TextColumn('•', style='dim'),
+                ColoredTimeRemainingColumn(style='dim'),
+            )
+            self._task = self._progress.add_task("Progress", total=total)
+
+    def step(self) -> None:
+        if self.verbose:
+            assert self._progress is not None
+            assert self._task is not None
+            self._progress.update(self._task, advance=1)  # type: ignore
+
     def __enter__(self) -> Self:
+        from kumoai import in_notebook
+
         super().__enter__()
 
+        if not in_notebook():  # Render progress bar in TUI.
+            sys.stdout.write("\x1b]9;4;3\x07")
+            sys.stdout.flush()
+
         if self.verbose:
             self._live = Live(
                 self,
@@ -68,16 +138,27 @@ class InteractiveProgressLogger(ProgressLogger):
         return self
 
     def __exit__(self, exc_type: Any, exc_val: Any, exc_tb: Any) -> None:
+        from kumoai import in_notebook
+
         super().__exit__(exc_type, exc_val, exc_tb)
 
         if exc_type is not None:
             self._exception = True
 
+        if self._progress is not None:
+            self._progress.stop()
+            self._progress = None
+            self._task = None
+
         if self._live is not None:
             self._live.update(self, refresh=True)
             self._live.stop()
             self._live = None
 
+        if not in_notebook():
+            sys.stdout.write("\x1b]9;4;0\x07")
+            sys.stdout.flush()
+
     def __rich_console__(
         self,
         console: Console,
@@ -107,3 +188,157 @@ class InteractiveProgressLogger(ProgressLogger):
             table.add_row('', Text(f'↳ {log}', style='dim'))
 
         yield table
+
+        if self.verbose and self._progress is not None:
+            yield self._progress.get_renderable()
+
+
+class StreamlitProgressLogger(ProgressLogger):
+    def __init__(
+        self,
+        msg: str,
+        verbose: bool = True,
+    ) -> None:
+        super().__init__(msg=msg, verbose=verbose)
+
+        self._status: Any = None
+
+        self._total = 0
+        self._current = 0
+        self._description: str = ''
+        self._progress: Any = None
+
+    def __enter__(self) -> Self:
+        super().__enter__()
+
+        import streamlit as st
+
+        # Adjust layout for prettier output:
+        st.markdown(STREAMLIT_CSS, unsafe_allow_html=True)
+
+        if self.verbose:
+            self._status = st.status(
+                f':blue[{self._sanitize_text(self.msg)}]',
+                expanded=True,
+            )
+
+        return self
+
+    def log(self, msg: str) -> None:
+        super().log(msg)
+        if self.verbose and self._status is not None:
+            self._status.write(self._sanitize_text(msg))
+
+    def init_progress(self, total: int, description: str) -> None:
+        if self.verbose and self._status is not None:
+            self._total = total
+            self._current = 0
+            self._description = self._sanitize_text(description)
+            percent = min(self._current / self._total, 1.0)
+            self._progress = self._status.progress(
+                value=percent,
+                text=f'{self._description} [{self._current}/{self._total}]',
+            )
+        pass
+
+    def step(self) -> None:
+        self._current += 1
+
+        if self.verbose and self._progress is not None:
+            percent = min(self._current / self._total, 1.0)
+            self._progress.progress(
+                value=percent,
+                text=f'{self._description} [{self._current}/{self._total}]',
+            )
+
+    def __exit__(self, exc_type: Any, exc_val: Any, exc_tb: Any) -> None:
+        super().__exit__(exc_type, exc_val, exc_tb)
+
+        if not self.verbose or self._status is None:
+            return
+
+        label = f'{self._sanitize_text(self.msg)} ({self.duration:.2f}s)'
+
+        if exc_type is not None:
+            self._status.update(
+                label=f':red[{label}]',
+                state='error',
+                expanded=True,
+            )
+        else:
+            self._status.update(
+                label=f':green[{label}]',
+                state='complete',
+                expanded=True,
+            )
+
+    @staticmethod
+    def _sanitize_text(msg: str) -> str:
+        return re.sub(r'\[/?bold\]', '**', msg)
+
+
+STREAMLIT_CSS = """
+<style>
+/* Fix horizontal scrollbar */
+.stExpander summary {
+    width: auto;
+}
+
+/* Fix paddings/margins */
+.stExpander summary {
+    padding: 0.75rem 1rem 0.5rem;
+}
+.stExpander p {
+    margin: 0px 0px 0.2rem;
+}
+.stExpander [data-testid="stExpanderDetails"] {
+    padding-bottom: 1.45rem;
+}
+.stExpander .stProgress div:first-child {
+    padding-bottom: 4px;
+}
+
+/* Fix expand icon position */
+.stExpander summary svg {
+    height: 1.5rem;
+}
+
+/* Fix summary icons */
+.stExpander summary [data-testid="stExpanderIconCheck"] {
+    font-size: 1.8rem;
+    margin-top: -3px;
+    color: rgb(21, 130, 55);
+}
+.stExpander summary [data-testid="stExpanderIconError"] {
+    font-size: 1.8rem;
+    margin-top: -3px;
+    color: rgb(255, 43, 43);
+}
+.stExpander summary span:first-child span:first-child {
+    width: 1.6rem;
+}
+
+/* Add border between title and content */
+.stExpander [data-testid="stExpanderDetails"] {
+    border-top: 1px solid rgba(30, 37, 47, 0.2);
+    padding-top: 0.5rem;
+}
+
+/* Fix title font size */
+.stExpander summary p {
+    font-size: 1rem;
+}
+
+/* Gray out content */
+.stExpander [data-testid="stExpanderDetails"] {
+    color: rgba(30, 37, 47, 0.5);
+}
+
+/* Fix progress bar font size */
+.stExpander .stProgress p {
+    line-height: 1.6;
+    font-size: 1rem;
+    color: rgba(30, 37, 47, 0.5);
+}
+</style>
+"""

kumoai/utils/sql.py

@@ -0,0 +1,3 @@
+def quote_ident(name: str) -> str:
+    r"""Quotes a SQL identifier."""
+    return '"' + name.replace('"', '""') + '"'

{kumoai-2.10.0.dev202509231831.dist-info → kumoai-2.14.0.dev202512161731.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kumoai
-Version: 2.10.0.dev202509231831
+Version: 2.14.0.dev202512161731
 Summary: AI on the Modern Data Stack
 Author-email: "Kumo.AI" <hello@kumo.ai>
 License-Expression: MIT
@@ -9,13 +9,12 @@ Project-URL: documentation, https://kumo.ai/docs
 Keywords: deep-learning,graph-neural-networks,cloud-data-warehouse
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3 :: Only
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pandas
@@ -24,7 +23,7 @@ Requires-Dist: requests>=2.28.2
 Requires-Dist: urllib3
 Requires-Dist: plotly
 Requires-Dist: typing_extensions>=4.5.0
-Requires-Dist: kumo-api==0.34.0
+Requires-Dist: kumo-api==0.49.0
 Requires-Dist: tqdm>=4.66.0
 Requires-Dist: aiohttp>=3.10.0
 Requires-Dist: pydantic>=1.10.21
@@ -39,6 +38,17 @@ Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-mock; extra == "test"
 Requires-Dist: requests-mock; extra == "test"
+Provides-Extra: sqlite
+Requires-Dist: adbc_driver_sqlite; extra == "sqlite"
+Provides-Extra: snowflake
+Requires-Dist: numpy<2.0; extra == "snowflake"
+Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: pyyaml; extra == "snowflake"
+Provides-Extra: sagemaker
+Requires-Dist: boto3<2.0,>=1.30.0; extra == "sagemaker"
+Requires-Dist: mypy-boto3-sagemaker-runtime<2.0,>=1.34.0; extra == "sagemaker"
+Provides-Extra: test-sagemaker
+Requires-Dist: sagemaker<3.0; extra == "test-sagemaker"
 Dynamic: license-file
 Dynamic: requires-dist
 
@@ -54,7 +64,7 @@ interact with the Kumo machine learning platform
 
 ## Installation
 
-The Kumo SDK is available for Python 3.9 to Python 3.13. To install, simply run
+The Kumo SDK is available for Python 3.10 to Python 3.13. To install, simply run
 
 ```
 pip install kumoai