arize 8.0.0b2__py3-none-any.whl → 8.0.1__py3-none-any.whl

arize/embeddings/tabular_generators.py

@@ -64,10 +64,10 @@ class EmbeddingGeneratorForTabularFeatures(NLPEmbeddingGenerator):
         super().__init__(
             use_case=UseCases.STRUCTURED.TABULAR_EMBEDDINGS,
             model_name=model_name,
-            **kwargs,
+            **kwargs,  # type: ignore[arg-type]
         )
 
-    def generate_embeddings(
+    def generate_embeddings(  # type: ignore[override]
         self,
         df: pd.DataFrame,
         selected_columns: list[str],
@@ -145,11 +145,11 @@ class EmbeddingGeneratorForTabularFeatures(NLPEmbeddingGenerator):
             batch_size=self.batch_size,
         )
 
-        df: pd.DataFrame = ds.to_pandas()
+        result_df: pd.DataFrame = ds.to_pandas()
         if return_prompt_col:
-            return df["embedding_vector"], prompts
+            return result_df["embedding_vector"], prompts
 
-        return df["embedding_vector"]
+        return result_df["embedding_vector"]
 
     @staticmethod
     def __prompt_fn(row: pd.DataFrame, columns: list[str]) -> str:

arize/exceptions/config.py

@@ -0,0 +1,22 @@
+"""Configuration validation exceptions."""
+
+from __future__ import annotations
+
+
+class MultipleEndpointOverridesError(Exception):
+    """Raised when multiple endpoint override options are provided.
+
+    Only one of the following can be specified: region, single_host/single_port, or base_domain.
+    """
+
+    def __init__(self, message: str) -> None:
+        """Initialize the exception with an optional custom message.
+
+        Args:
+            message: Custom error message, or empty string.
+        """
+        self.message = message
+
+    def __str__(self) -> str:
+        """Return the error message."""
+        return self.message

arize/exceptions/parameters.py

@@ -61,7 +61,7 @@ class InvalidValueType(Exception):
     def __init__(
         self,
         value_name: str,
-        value: bool | int | float | str,
+        value: object,
         correct_type: str,
     ) -> None:
         """Initialize the exception with value type validation context.

arize/exceptions/values.py

@@ -533,14 +533,15 @@ class InvalidMultiClassClassNameLength(ValidationError):
         err_msg = ""
         for col, class_names in self.invalid_col_class_name.items():
             # limit to 10
-            class_names = (
+            class_names_list = (
                 list(class_names)[:10]
                 if len(class_names) > 10
                 else list(class_names)
             )
             err_msg += (
-                f"Found some invalid class names: {log_a_list(class_names, 'and')} in the {col} column. Class"
-                f" names must have at least one character and less than {MAX_MULTI_CLASS_NAME_LENGTH}.\n"
+                f"Found some invalid class names: {log_a_list(class_names_list, 'and')} "
+                f"in the {col} column. Class names must have at least one character and "
+                f"less than {MAX_MULTI_CLASS_NAME_LENGTH}.\n"
             )
         return err_msg
 
@@ -565,9 +566,11 @@ class InvalidMultiClassPredScoreValue(ValidationError):
         err_msg = ""
         for col, scores in self.invalid_col_class_scores.items():
             # limit to 10
-            scores = list(scores)[:10] if len(scores) > 10 else list(scores)
+            scores_list = (
+                list(scores)[:10] if len(scores) > 10 else list(scores)
+            )
             err_msg += (
-                f"Found some invalid scores: {log_a_list(scores, 'and')} in the {col} column that was "
+                f"Found some invalid scores: {log_a_list(scores_list, 'and')} in the {col} column that was "
                 "invalid. All scores (values in dictionary) must be between 0 and 1, inclusive. \n"
             )
         return err_msg

arize/experiments/__init__.py

@@ -1,5 +1,8 @@
 """Experiment tracking and evaluation functionality for the Arize SDK."""
 
+from arize.experiments.evaluators.base import (
+    Evaluator,
+)
 from arize.experiments.evaluators.types import (
     EvaluationResult,
     EvaluationResultFieldNames,
@@ -9,5 +12,6 @@ from arize.experiments.types import ExperimentTaskFieldNames
 __all__ = [
     "EvaluationResult",
     "EvaluationResultFieldNames",
+    "Evaluator",
     "ExperimentTaskFieldNames",
 ]

arize/experiments/client.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 import logging
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, cast
 
 import opentelemetry.sdk.trace as trace_sdk
 import pandas as pd
@@ -36,6 +36,10 @@ from arize.utils.openinference_conversion import (
 from arize.utils.size import get_payload_size_mb
 
 if TYPE_CHECKING:
+    # builtins is needed to use builtins.list in type annotations because
+    # the class has a list() method that shadows the built-in list type
+    import builtins
+
     from opentelemetry.trace import Tracer
 
     from arize._generated.api_client.api_client import ApiClient
@@ -116,7 +120,7 @@ class ExperimentsClient:
         *,
         name: str,
         dataset_id: str,
-        experiment_runs: list[dict[str, object]] | pd.DataFrame,
+        experiment_runs: builtins.list[dict[str, object]] | pd.DataFrame,
         task_fields: ExperimentTaskFieldNames,
         evaluator_columns: dict[str, EvaluationResultFieldNames] | None = None,
         force_http: bool = False,
@@ -181,7 +185,7 @@ class ExperimentsClient:
             body = gen.ExperimentsCreateRequest(
                 name=name,
                 dataset_id=dataset_id,
-                experiment_runs=data,  # type: ignore
+                experiment_runs=cast("list[gen.ExperimentRunCreate]", data),
             )
             return self._api.experiments_create(experiments_create_request=body)
 
@@ -303,7 +307,10 @@ class ExperimentsClient:
             )
         if experiment_df is not None:
             return models.ExperimentsRunsList200Response(
-                experimentRuns=experiment_df.to_dict(orient="records"),  # type: ignore
+                experiment_runs=cast(
+                    "list[models.ExperimentRun]",
+                    experiment_df.to_dict(orient="records"),
+                ),
                 pagination=models.PaginationMetadata(
                     has_more=False,  # Note that all=True
                 ),
@@ -343,7 +350,10 @@ class ExperimentsClient:
         )
 
         return models.ExperimentsRunsList200Response(
-            experimentRuns=experiment_df.to_dict(orient="records"),  # type: ignore
+            experiment_runs=cast(
+                "list[models.ExperimentRun]",
+                experiment_df.to_dict(orient="records"),
+            ),
             pagination=models.PaginationMetadata(
                 has_more=False,  # Note that all=True
             ),
@@ -553,9 +563,7 @@ class ExperimentsClient:
                 logger.error(msg)
                 raise RuntimeError(msg)
 
-            experiment = self.get(
-                experiment_id=str(post_resp.experiment_id)  # type: ignore
-            )
+            experiment = self.get(experiment_id=str(post_resp.experiment_id))
             return experiment, output_df
 
     def _create_experiment_via_flight(
@@ -636,9 +644,7 @@ class ExperimentsClient:
                 logger.error(msg)
                 raise RuntimeError(msg)
 
-        return self.get(
-            experiment_id=str(post_resp.experiment_id)  # type: ignore
-        )
+        return self.get(experiment_id=str(post_resp.experiment_id))
 
 
 def _get_tracer_resource(

arize/experiments/evaluators/base.py

@@ -7,7 +7,7 @@ import inspect
 from abc import ABC
 from collections.abc import Awaitable, Callable, Mapping, Sequence
 from types import MappingProxyType
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any, cast
 
 from arize.experiments.evaluators.types import (
     AnnotatorKind,
@@ -162,7 +162,9 @@ class Evaluator(ABC):
                         f"`evaluate()` method should be callable, got {type(evaluate)}"
                     )
                 # need to remove the first param, i.e. `self`
-                _validate_sig(functools.partial(evaluate, None), "evaluate")
+                _validate_sig(
+                    functools.partial(evaluate, cast("Any", None)), "evaluate"
+                )
                 return
             if async_evaluate := super_cls.__dict__.get(
                 Evaluator.async_evaluate.__name__
@@ -175,7 +177,8 @@ class Evaluator(ABC):
                     )
                 # need to remove the first param, i.e. `self`
                 _validate_sig(
-                    functools.partial(async_evaluate, None), "async_evaluate"
+                    functools.partial(async_evaluate, cast("Any", None)),
+                    "async_evaluate",
                 )
                 return
         raise ValueError(

arize/experiments/evaluators/executors.py

@@ -77,7 +77,7 @@ class Executor(Protocol):
 
     def run(
         self, inputs: Sequence[Any]
-    ) -> tuple[list[object], list[ExecutionDetails]]:
+    ) -> tuple[list[Unset | object], list[ExecutionDetails]]:
         """Execute the generation function on all inputs and return outputs with execution details."""
         ...
 
@@ -255,7 +255,7 @@ class AsyncExecutor(Executor):
 
     async def execute(
         self, inputs: Sequence[Any]
-    ) -> tuple[list[object], list[ExecutionDetails]]:
+    ) -> tuple[list[Unset | object], list[ExecutionDetails]]:
         """Execute all inputs asynchronously using producer-consumer pattern."""
         termination_event = asyncio.Event()
 
@@ -332,7 +332,7 @@ class AsyncExecutor(Executor):
 
     def run(
         self, inputs: Sequence[Any]
-    ) -> tuple[list[object], list[ExecutionDetails]]:
+    ) -> tuple[list[Unset | object], list[ExecutionDetails]]:
         """Execute all inputs asynchronously and return outputs with execution details."""
         return asyncio.run(self.execute(inputs))
 
@@ -406,7 +406,9 @@ class SyncExecutor(Executor):
         else:
             yield
 
-    def run(self, inputs: Sequence[Any]) -> tuple[list[object], list[object]]:
+    def run(
+        self, inputs: Sequence[Any]
+    ) -> tuple[list[Unset | object], list[ExecutionDetails]]:
         """Execute all inputs synchronously and return outputs with execution details."""
         with self._executor_signal_handling(self.termination_signal):
             outputs = [self.fallback_return_value] * len(inputs)

arize/experiments/evaluators/rate_limiters.py

@@ -276,7 +276,9 @@ class RateLimiter:
         """Apply rate limiting to an asynchronous function."""
 
         @wraps(fn)
-        async def wrapper(*args: object, **kwargs: object) -> GenericType:
+        async def wrapper(
+            *args: ParameterSpec.args, **kwargs: ParameterSpec.kwargs
+        ) -> GenericType:
             self._initialize_async_primitives()
             if self._rate_limit_handling_lock is None or not isinstance(
                 self._rate_limit_handling_lock, asyncio.Lock

arize/experiments/evaluators/types.py

@@ -4,7 +4,7 @@ from __future__ import annotations
 
 from dataclasses import dataclass, field
 from enum import Enum
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, cast
 
 if TYPE_CHECKING:
     from collections.abc import Mapping
@@ -60,10 +60,12 @@ class EvaluationResult:
         if not obj:
             return None
         return cls(
-            score=obj.get("score"),
-            label=obj.get("label"),
-            explanation=obj.get("explanation"),
-            metadata=obj.get("metadata") or {},
+            score=cast("float | None", obj.get("score")),
+            label=cast("str | None", obj.get("label")),
+            explanation=cast("str | None", obj.get("explanation")),
+            metadata=cast(
+                "Mapping[str, JSONSerializable]", obj.get("metadata") or {}
+            ),
         )
 
     def __post_init__(self) -> None:

arize/experiments/evaluators/utils.py

@@ -2,8 +2,8 @@
 
 import functools
 import inspect
-from collections.abc import Callable
-from typing import TYPE_CHECKING
+from collections.abc import Awaitable, Callable
+from typing import TYPE_CHECKING, Any
 
 from tqdm.auto import tqdm
 
@@ -154,10 +154,10 @@ def _wrap_coroutine_evaluation_function(
     name: str,
     sig: inspect.Signature,
     convert_to_score: Callable[[object], EvaluationResult],
-) -> Callable[[Callable[..., object]], "Evaluator"]:
+) -> Callable[[Callable[..., Awaitable[object]]], "Evaluator"]:
     from ..evaluators.base import Evaluator
 
-    def wrapper(func: Callable[..., object]) -> "Evaluator":
+    def wrapper(func: Callable[..., Awaitable[object]]) -> "Evaluator":
         class AsyncEvaluator(Evaluator):
             def __init__(self) -> None:
                 self._name = name
@@ -224,9 +224,11 @@ def _default_eval_scorer(result: object) -> EvaluationResult:
     raise ValueError(f"Unsupported evaluation result type: {type(result)}")
 
 
-def printif(condition: bool, *args: object, **kwargs: object) -> None:
+def printif(condition: bool, *args: Any, **kwargs: Any) -> None:  # noqa: ANN401
     """Print to tqdm output if the condition is true.
 
+    Note: *args/**kwargs use Any for proper pass-through to tqdm.write().
+
     Args:
         condition: Whether to print the message.
         *args: Positional arguments to pass to tqdm.write.