arize 8.0.0a23__py3-none-any.whl → 8.0.0b1__py3-none-any.whl

arize/config.py

@@ -167,112 +167,71 @@ def _parse_bool(val: bool | str | None) -> bool:
 class SDKConfiguration:
     """Configuration for the Arize SDK with endpoint and authentication settings.
 
-    This class is used internally by ArizeClient to manage SDK configuration. Users
-    typically interact with ArizeClient rather than instantiating this class directly.
+    This class is used internally by ArizeClient to manage SDK configuration. It is not
+    recommended to use this class directly; users should interact with ArizeClient
+    instead.
 
-    Configuration Precedence
-    ------------------------
     Each configuration parameter follows this resolution order:
         1. Explicit value passed to ArizeClient constructor (highest priority)
         2. Environment variable value
         3. Built-in default value (lowest priority)
 
-    Parameters
-    ----------
-    api_key : str
-        Arize API key for authentication. Required.
-        Environment variable: ARIZE_API_KEY
-        Default: None (must be provided via argument or environment variable)
-
-    api_host : str
-        API endpoint host.
-        Environment variable: ARIZE_API_HOST
-        Default: "api.arize.com"
-
-    api_scheme : str
-        API endpoint scheme (http/https).
-        Environment variable: ARIZE_API_SCHEME
-        Default: "https"
-
-    otlp_host : str
-        OTLP (OpenTelemetry Protocol) endpoint host.
-        Environment variable: ARIZE_OTLP_HOST
-        Default: "otlp.arize.com"
-
-    otlp_scheme : str
-        OTLP endpoint scheme (http/https).
-        Environment variable: ARIZE_OTLP_SCHEME
-        Default: "https"
-
-    flight_host : str
-        Apache Arrow Flight endpoint host.
-        Environment variable: ARIZE_FLIGHT_HOST
-        Default: "flight.arize.com"
-
-    flight_port : int
-        Apache Arrow Flight endpoint port (1-65535).
-        Environment variable: ARIZE_FLIGHT_PORT
-        Default: 443
-
-    flight_scheme : str
-        Apache Arrow Flight endpoint scheme.
-        Environment variable: ARIZE_FLIGHT_SCHEME
-        Default: "grpc+tls"
-
-    pyarrow_max_chunksize : int
-        Maximum chunk size for PyArrow operations (1 to MAX_CHUNKSIZE).
-        Environment variable: ARIZE_MAX_CHUNKSIZE
-        Default: 10_000
-
-    request_verify : bool
-        Whether to verify SSL certificates for HTTP requests.
-        Environment variable: ARIZE_REQUEST_VERIFY
-        Default: True
-
-    stream_max_workers : int
-        Maximum number of worker threads for streaming operations (minimum: 1).
-        Environment variable: ARIZE_STREAM_MAX_WORKERS
-        Default: 8
-
-    stream_max_queue_bound : int
-        Maximum queue size for streaming operations (minimum: 1).
-        Environment variable: ARIZE_STREAM_MAX_QUEUE_BOUND
-        Default: 5000
-
-    max_http_payload_size_mb : float
-        Maximum HTTP payload size in megabytes (minimum: 1).
-        Environment variable: ARIZE_MAX_HTTP_PAYLOAD_SIZE_MB
-        Default: 100
-
-    arize_directory : str
-        Directory for Arize SDK files (cache, logs, etc.).
-        Environment variable: ARIZE_DIRECTORY
-        Default: "~/.arize"
-
-    enable_caching : bool
-        Whether to enable local caching.
-        Environment variable: ARIZE_ENABLE_CACHING
-        Default: True
-
-    region : Region
-        Arize region (e.g., US_CENTRAL, EU_WEST). When specified, overrides
-        individual host/port settings.
-        Environment variable: ARIZE_REGION
-        Default: Region.UNSPECIFIED
-
-    single_host : str
-        Single host to use for all endpoints. Overrides individual host settings.
-        Environment variable: ARIZE_SINGLE_HOST
-        Default: "" (not set)
-
-    single_port : int
-        Single port to use for all endpoints. Overrides individual port settings (0-65535).
-        Environment variable: ARIZE_SINGLE_PORT
-        Default: 0 (not set)
-
-    See Also:
-    --------
-    ArizeClient : Main client class that uses this configuration
+    Args:
+        api_key: Arize API key for authentication. Required.
+            Environment variable: ARIZE_API_KEY.
+            Default: None (must be provided via argument or environment variable).
+        api_host: API endpoint host.
+            Environment variable: ARIZE_API_HOST.
+            Default: "api.arize.com".
+        api_scheme: API endpoint scheme (http/https).
+            Environment variable: ARIZE_API_SCHEME.
+            Default: "https".
+        otlp_host: OTLP (OpenTelemetry Protocol) endpoint host.
+            Environment variable: ARIZE_OTLP_HOST.
+            Default: "otlp.arize.com".
+        otlp_scheme: OTLP endpoint scheme (http/https).
+            Environment variable: ARIZE_OTLP_SCHEME.
+            Default: "https".
+        flight_host: Apache Arrow Flight endpoint host.
+            Environment variable: ARIZE_FLIGHT_HOST.
+            Default: "flight.arize.com".
+        flight_port: Apache Arrow Flight endpoint port (1-65535).
+            Environment variable: ARIZE_FLIGHT_PORT.
+            Default: 443.
+        flight_scheme: Apache Arrow Flight endpoint scheme.
+            Environment variable: ARIZE_FLIGHT_SCHEME.
+            Default: "grpc+tls".
+        pyarrow_max_chunksize: Maximum chunk size for PyArrow operations (1 to MAX_CHUNKSIZE).
+            Environment variable: ARIZE_MAX_CHUNKSIZE.
+            Default: 10_000.
+        request_verify: Whether to verify SSL certificates for HTTP requests.
+            Environment variable: ARIZE_REQUEST_VERIFY.
+            Default: True.
+        stream_max_workers: Maximum number of worker threads for streaming operations (minimum: 1).
+            Environment variable: ARIZE_STREAM_MAX_WORKERS.
+            Default: 8.
+        stream_max_queue_bound: Maximum queue size for streaming operations (minimum: 1).
+            Environment variable: ARIZE_STREAM_MAX_QUEUE_BOUND.
+            Default: 5000.
+        max_http_payload_size_mb: Maximum HTTP payload size in megabytes (minimum: 1).
+            Environment variable: ARIZE_MAX_HTTP_PAYLOAD_SIZE_MB.
+            Default: 100.
+        arize_directory: Directory for Arize SDK files (cache, logs, etc.).
+            Environment variable: ARIZE_DIRECTORY.
+            Default: "~/.arize".
+        enable_caching: Whether to enable local caching.
+            Environment variable: ARIZE_ENABLE_CACHING.
+            Default: True.
+        region: Arize region (e.g., US_CENTRAL, EU_WEST). When specified, overrides
+            individual host/port settings.
+            Environment variable: ARIZE_REGION.
+            Default: Region.UNSPECIFIED.
+        single_host: Single host to use for all endpoints. Overrides individual host settings.
+            Environment variable: ARIZE_SINGLE_HOST.
+            Default: "" (not set).
+        single_port: Single port to use for all endpoints. Overrides individual port settings (0-65535).
+            Environment variable: ARIZE_SINGLE_PORT.
+            Default: 0 (not set).
     """
 
     api_key: str = field(

arize/datasets/client.py

@@ -30,17 +30,22 @@ logger = logging.getLogger(__name__)
 
 
 class DatasetsClient:
-    """Client for managing datasets including creation, retrieval, and example management."""
+    """Client for managing datasets including creation, retrieval, and example management.
 
-    def __init__(self, *, sdk_config: SDKConfiguration) -> None:
-        """Create a datasets sub-client.
+    This class is primarily intended for internal use within the SDK. Users are
+    highly encouraged to access resource-specific functionality via
+    :class:`arize.ArizeClient`.
 
-        The datasets client is a thin wrapper around the generated REST API client,
-        using the shared generated API client owned by `SDKConfiguration`.
+    The datasets client is a thin wrapper around the generated REST API client,
+    using the shared generated API client owned by
+    :class:`arize.config.SDKConfiguration`.
+    """
 
+    def __init__(self, *, sdk_config: SDKConfiguration) -> None:
+        """
         Args:
             sdk_config: Resolved SDK configuration.
-        """
+        """  # noqa: D205, D212
         self._sdk_config = sdk_config
 
         # Import at runtime so it's still lazy and extras-gated by the parent

arize/embeddings/nlp_generators.py

@@ -49,10 +49,13 @@ class EmbeddingGeneratorForNLPSequenceClassification(NLPEmbeddingGenerator):
     ) -> pd.Series:
         """Obtain embedding vectors from your text data using pre-trained large language models.
 
-        :param text_col: a pandas Series containing the different pieces of text.
-        :param class_label_col: if this column is passed, the sentence "The classification label
-        is <class_label>" will be appended to the text in the `text_col`.
-        :return: a pandas Series containing the embedding vectors.
+        Args:
+            text_col: A pandas Series containing the different pieces of text.
+            class_label_col: If this column is passed, the sentence "The classification label
+                is <class_label>" will be appended to the text in the `text_col`.
+
+        Returns:
+            A pandas Series containing the embedding vectors.
         """
         if not isinstance(text_col, pd.Series):
             raise TypeError("text_col must be a pandas Series")
@@ -110,8 +113,11 @@ class EmbeddingGeneratorForNLPSummarization(NLPEmbeddingGenerator):
     ) -> pd.Series:
         """Obtain embedding vectors from your text data using pre-trained large language models.
 
-        :param text_col: a pandas Series containing the different pieces of text.
-        :return: a pandas Series containing the embedding vectors.
+        Args:
+            text_col: A pandas Series containing the different pieces of text.
+
+        Returns:
+            A pandas Series containing the embedding vectors.
         """
         if not isinstance(text_col, pd.Series):
             raise TypeError("text_col must be a pandas Series")

arize/embeddings/tabular_generators.py

@@ -11,7 +11,7 @@ from arize.embeddings.constants import (
     IMPORT_ERROR_MESSAGE,
 )
 from arize.embeddings.usecases import UseCases
-from arize.types import is_list_of
+from arize.utils.types import is_list_of
 
 try:
     from datasets import Dataset
@@ -79,16 +79,19 @@ class EmbeddingGeneratorForTabularFeatures(NLPEmbeddingGenerator):
         Prompts are generated from your `selected_columns` and passed to a pre-trained
         large language model for embedding vector computation.
 
-        :param df: pandas DataFrame containing the tabular data, not all columns will be
-        considered, see `selected_columns`.
-        :param selected_columns: columns to be considered to construct the prompt to be passed to
-        the LLM.
-        :param col_name_map: mapping between selected column names and a more verbose description of
-        the name. This helps the LLM understand the features better.
-        :param return_prompt_col: if set to True, an extra pandas Series will be returned
-        containing the constructed prompts. Defaults to False.
-        :return: a pandas Series containing the embedding vectors and, if `return_prompt_col` is
-        set to True, a pandas Series containing the prompts created from tabular features.
+        Args:
+            df: Pandas DataFrame containing the tabular data. Not all columns will be
+                considered, see `selected_columns`.
+            selected_columns: Columns to be considered to construct the prompt to be passed to
+                the LLM.
+            col_name_map: Mapping between selected column names and a more verbose description of
+                the name. This helps the LLM understand the features better.
+            return_prompt_col: If set to True, an extra pandas Series will be returned
+                containing the constructed prompts. Defaults to False.
+
+        Returns:
+            A pandas Series containing the embedding vectors and, if `return_prompt_col` is
+            set to True, a pandas Series containing the prompts created from tabular features.
         """
         if col_name_map is None:
             col_name_map = {}

arize/experiments/__init__.py

@@ -1 +1,13 @@
 """Experiment tracking and evaluation functionality for the Arize SDK."""
+
+from arize.experiments.evaluators.types import (
+    EvaluationResult,
+    EvaluationResultFieldNames,
+)
+from arize.experiments.types import ExperimentTaskFieldNames
+
+__all__ = [
+    "EvaluationResult",
+    "EvaluationResultFieldNames",
+    "ExperimentTaskFieldNames",
+]

arize/experiments/client.py

@@ -43,24 +43,29 @@ if TYPE_CHECKING:
     from arize.experiments.evaluators.types import EvaluationResultFieldNames
     from arize.experiments.types import (
         ExperimentTask,
-        ExperimentTaskResultFieldNames,
+        ExperimentTaskFieldNames,
     )
 
 logger = logging.getLogger(__name__)
 
 
 class ExperimentsClient:
-    """Client for managing experiments including creation, execution, and result tracking."""
+    """Client for managing experiments including creation, execution, and result tracking.
 
-    def __init__(self, *, sdk_config: SDKConfiguration) -> None:
-        """Create an experiments sub-client.
+    This class is primarily intended for internal use within the SDK. Users are
+    highly encouraged to access resource-specific functionality via
+    :class:`arize.ArizeClient`.
 
-        The experiments client is a thin wrapper around the generated REST API client,
-        using the shared generated API client owned by `SDKConfiguration`.
+    The experiments client is a thin wrapper around the generated REST API client,
+    using the shared generated API client owned by
+    :class:`arize.config.SDKConfiguration`.
+    """
 
+    def __init__(self, *, sdk_config: SDKConfiguration) -> None:
+        """
         Args:
             sdk_config: Resolved SDK configuration.
-        """
+        """  # noqa: D205, D212
         self._sdk_config = sdk_config
         from arize._generated import api_client as gen
 
@@ -109,7 +114,7 @@ class ExperimentsClient:
         name: str,
         dataset_id: str,
         experiment_runs: list[dict[str, object]] | pd.DataFrame,
-        task_fields: ExperimentTaskResultFieldNames,
+        task_fields: ExperimentTaskFieldNames,
         evaluator_columns: dict[str, EvaluationResultFieldNames] | None = None,
         force_http: bool = False,
     ) -> models.Experiment:
@@ -170,7 +175,6 @@ class ExperimentsClient:
             from arize._generated import api_client as gen
 
             data = experiment_df.to_dict(orient="records")
-
             body = gen.ExperimentsCreateRequest(
                 name=name,
                 dataset_id=dataset_id,

arize/experiments/functions.py

@@ -56,7 +56,7 @@ from arize.experiments.types import (
     ExperimentEvaluationRun,
     ExperimentRun,
     ExperimentTask,
-    ExperimentTaskResultFieldNames,
+    ExperimentTaskFieldNames,
     _TaskSummary,
 )
 
@@ -768,7 +768,7 @@ def get_result_attr(r: object, attr: str, default: object = None) -> object:
 
 def transform_to_experiment_format(
     experiment_runs: list[dict[str, object]] | pd.DataFrame,
-    task_fields: ExperimentTaskResultFieldNames,
+    task_fields: ExperimentTaskFieldNames,
     evaluator_fields: dict[str, EvaluationResultFieldNames] | None = None,
 ) -> pd.DataFrame:
     """Transform a DataFrame to match the format returned by run_experiment().
@@ -788,7 +788,7 @@ def transform_to_experiment_format(
         else pd.DataFrame(experiment_runs)
     )
     # Validate required columns
-    required_cols = {task_fields.example_id, task_fields.result}
+    required_cols = {task_fields.example_id, task_fields.output}
     missing_cols = required_cols - set(data.columns)
     if missing_cols:
         raise ValueError(f"Missing required columns: {missing_cols}")
@@ -799,11 +799,11 @@ def transform_to_experiment_format(
     out_df["example_id"] = data[task_fields.example_id]
     if task_fields.example_id != "example_id":
         out_df.drop(task_fields.example_id, axis=1, inplace=True)
-    out_df["result"] = data[task_fields.result].apply(
+    out_df["output"] = data[task_fields.output].apply(
         lambda x: json.dumps(x) if isinstance(x, dict) else x
     )
-    if task_fields.result != "result":
-        out_df.drop(task_fields.result, axis=1, inplace=True)
+    if task_fields.output != "output":
+        out_df.drop(task_fields.output, axis=1, inplace=True)
 
     # Process evaluator results
     if evaluator_fields:

arize/experiments/types.py

@@ -397,17 +397,17 @@ def _top_string(s: pd.Series, length: int = 100) -> str | None:
 
 
 @dataclass
-class ExperimentTaskResultFieldNames:
+class ExperimentTaskFieldNames:
     """Column names for mapping experiment task results in a DataFrame.
 
     Args:
         example_id: Name of column containing example IDs.
             The ID values must match the id of the dataset rows.
-        result: Name of column containing task results
+        output: Name of column containing task results
     """
 
     example_id: str
-    result: str
+    output: str
 
 
 TaskOutput = JSONSerializable

arize/{models → ml}/batch_validation/errors.py

@@ -16,12 +16,12 @@ from arize.constants.ml import (
     MAX_TAG_LENGTH,
 )
 from arize.logging import log_a_list
-from arize.types import Environments, ModelTypes
+from arize.ml.types import Environments, ModelTypes
 
 if TYPE_CHECKING:
     from collections.abc import Iterable
 
-    from arize.types import Metrics
+    from arize.ml.types import Metrics
 
 
 class ValidationError(Exception, ABC):

arize/{models → ml}/batch_validation/validator.py

@@ -40,8 +40,8 @@ from arize.constants.ml import (
     MODEL_MAPPING_CONFIG,
 )
 from arize.logging import get_truncation_warning_message
-from arize.models.batch_validation import errors as err
-from arize.types import (
+from arize.ml.batch_validation import errors as err
+from arize.ml.types import (
     CATEGORICAL_MODEL_TYPES,
     NUMERIC_MODEL_TYPES,
     BaseSchema,
@@ -53,9 +53,11 @@ from arize.types import (
     ModelTypes,
     PromptTemplateColumnNames,
     Schema,
+    segments_intersect,
+)
+from arize.utils.types import (
     is_dict_of,
     is_iterable_of,
-    segments_intersect,
 )
 
 logger = logging.getLogger(__name__)

arize/{models → ml}/casting.py

@@ -9,7 +9,13 @@ from typing import TYPE_CHECKING
 import numpy as np
 
 from arize.logging import log_a_list
-from arize.types import ArizeTypes, Schema, TypedColumns, TypedValue, is_list_of
+from arize.ml.types import (
+    ArizeTypes,
+    Schema,
+    TypedColumns,
+    TypedValue,
+)
+from arize.utils.types import is_list_of
 
 if TYPE_CHECKING:
     import pandas as pd
@@ -125,29 +131,20 @@ def cast_typed_columns(
     This optional feature provides a simple way for users to prevent type drift within
     a column across many SDK uploads.
 
-    Arguments:
-    ---------
-        dataframe: pd.DataFrame
-            A deepcopy of the user's dataframe.
-        schema: Schema
-            The schema, which may include feature and tag column names
+    Args:
+        dataframe (pd.DataFrame): A deepcopy of the user's dataframe.
+        schema (Schema): The schema, which may include feature and tag column names
             in a TypedColumns object or a List[string].
 
     Returns:
-    -------
-        dataframe: pd.DataFrame
-            The dataframe, with columns cast to the specified types.
-        schema: Schema
-            A new Schema object, with feature and tag column names converted to the List[string] format
-            expected in downstream validation.
+        tuple[pd.DataFrame, Schema]: A tuple containing:
+            - dataframe: The dataframe, with columns cast to the specified types.
+            - schema: A new Schema object, with feature and tag column names converted
+                to the List[string] format expected in downstream validation.
 
     Raises:
-    ------
-        ColumnCastingError
-            If casting fails.
-        InvalidTypedColumnsError
-            If the TypedColumns object is invalid.
-
+        ColumnCastingError: If casting fails.
+        InvalidTypedColumnsError: If the TypedColumns object is invalid.
     """
     typed_column_fields = schema.typed_column_fields()
     feature_field = "feature_column_names"
@@ -204,21 +201,14 @@ def _cast_value(
 ) -> str | int | float | list[str] | None:
     """Casts a TypedValue to its provided type, preserving all null values as None or float('nan').
 
-    Arguments:
-    ---------
-    typed_value: TypedValue
-        The TypedValue to cast.
+    Args:
+        typed_value (TypedValue): The TypedValue to cast.
 
     Returns:
-    -------
-    Union[str, int, float, List[str], None]
-        The cast value.
+        str | int | float | list[str] | None: The cast value.
 
     Raises:
-    ------
-    CastingError
-        If the value cannot be cast to the provided type.
-
+        CastingError: If the value cannot be cast to the provided type.
     """
     if typed_value.value is None:
         return None
@@ -274,18 +264,13 @@ def _validate_typed_columns(
 ) -> None:
     """Validate a TypedColumns object.
 
-    Arguments:
-    ---------
-        field_name: str
-            The name of the Schema field that the TypedColumns object is associated with.
-        typed_columns: TypedColumns
-            The TypedColumns object to validate.
+    Args:
+        field_name (str): The name of the Schema field that the TypedColumns object
+            is associated with.
+        typed_columns (TypedColumns): The TypedColumns object to validate.
 
     Raises:
-    ------
-        InvalidTypedColumnsError
-            If the TypedColumns object is invalid.
-
+        InvalidTypedColumnsError: If the TypedColumns object is invalid.
     """
     if typed_columns.is_empty():
         raise InvalidTypedColumnsError(field_name=field_name, reason="is empty")
@@ -304,24 +289,16 @@ def _cast_columns(
 
     (feature_column_names or tag_column_names)
 
-    Arguments:
-    ---------
-        dataframe: pd.DataFrame
-            A deepcopy of the user's dataframe.
-        columns: TypedColumns
-            The TypedColumns object, which specifies the columns to cast
-            (and/or to not cast) and their target types.
+    Args:
+        dataframe (pd.DataFrame): A deepcopy of the user's dataframe.
+        columns (TypedColumns): The TypedColumns object, which specifies the columns
+            to cast (and/or to not cast) and their target types.
 
     Returns:
-    -------
-        dataframe: pd.DataFrame
-            The dataframe with columns cast to the specified types.
+        pd.DataFrame: The dataframe with columns cast to the specified types.
 
     Raises:
-    ------
-        ColumnCastingError
-            If casting fails.
-
+        ColumnCastingError: If casting fails.
     """
     if columns.to_str:
         try:
@@ -372,25 +349,17 @@ def _cast_df(
 ) -> pd.DataFrame:
     """Cast columns in a dataframe to the specified type.
 
-    Arguments:
-    ---------
-        df: pd.DataFrame
-            A deepcopy of the user's dataframe.
-        cols: List[str]
-            The list of column names to cast.
-        target_type_str: str
-            The target type to cast to.
+    Args:
+        df (pd.DataFrame): A deepcopy of the user's dataframe.
+        cols (list[str]): The list of column names to cast.
+        target_type_str (str): The target type to cast to.
 
     Returns:
-    -------
-        df: pd.DataFrame
-            The dataframe with columns cast to the specified types.
+        pd.DataFrame: The dataframe with columns cast to the specified types.
 
     Raises:
-    ------
-        Exception
-            If casting fails. Common exceptions raised by astype() are TypeError and ValueError.
-
+        Exception: If casting fails. Common exceptions raised by astype() are
+            TypeError and ValueError.
     """
     nan_mapping = {"nan": np.nan, "NaN": np.nan}
     df = df.replace(nan_mapping)
@@ -404,18 +373,13 @@ def _convert_schema_field_types(
 ) -> Schema:
     """Convert schema field types from TypedColumns to List[string] format.
 
-    Arguments:
-    ---------
-        schema: Schema
-            The schema, which may include feature and tag column names
+    Args:
+        schema (Schema): The schema, which may include feature and tag column names
             in a TypedColumns object or a List[string].
 
     Returns:
-    -------
-        schema: Schema
-            A Schema, with feature and tag column names
-            converted to the List[string] format expected in downstream validation.
-
+        Schema: A Schema, with feature and tag column names converted to the
+            List[string] format expected in downstream validation.
     """
     feature_column_names_list = (
         schema.feature_column_names