Benign python Download

pydantic-evals 2.2.0

Legitimate Python package

“Framework for evaluating stochastic code execution, especially code making use of LLMs”

setup() call followed by other codeBundled Python dependency library path

SHA-2568c9238ecd488fca99a1db3540016be569010f46cce28adf7b6760d5919e7b9e8

URLhttps://files.pythonhosted.org/packages/33/0c/d97fb3fb258aee3b713f11369ff62bf326b6e760bb1a26afa5ba639e5d7f/pydantic_evals-2.2.0-py3-none-any.whl

MaleculeO₂(AsC)

Evidence

Long base64 string literal __init__.py · lines 1–48

1from __future__ import annotations as _annotations
2
3from collections import defaultdict
4from collections.abc import Callable, Mapping, Sequence
5from dataclasses import dataclass, field
6from io import StringIO
7from typing import Any, Generic, Literal, Protocol
8
9from pydantic import BaseModel, TypeAdapter
10from rich.console import Console, Group, RenderableType
11from rich.panel import Panel
12from rich.table import Table
13from rich.text import Text
14from typing_extensions import TypedDict, TypeVar, assert_never
15
16from pydantic_evals._utils import UNSET, Unset
17
18from ..evaluators import EvaluationResult
19from .analyses import (
20    ConfusionMatrix,
21    LinePlot,
22    PrecisionRecall,
23    PrecisionRecallCurve,
24    PrecisionRecallPoint,
25    ReportAnalysis,
26    ScalarResult,
27    TableResult,
28)
29from .render_numbers import (
30    default_render_duration,
31    default_render_duration_diff,
32    default_render_number,
33    default_render_number_diff,
34    default_render_percentage,
35)
36
⋯4 lines
41    'ReportCaseAdapter',
42    'ReportCaseFailure',
43    'ReportCaseFailureAdapter',
44    'ReportCaseGroup',
45    'EvaluationRenderer',
46    'RenderValueConfig',
47    'RenderNumberConfig',
48    'ReportCaseAggregate' …

Module assigns a no-arg call __init__.py · lines 918–925

918:60…  None, new: T_contra | None) -> str: ...  # pragma: no branch
919
920
921_DEFAULT_NUMBER_CONFIG = RenderNumberConfig()
922_DEFAULT_VALUE_CONFIG = RenderValueConfig()
923_DEFAULT_DURATION_CONFIG = RenderNumberConfig(
924    value_formatter=default_render_duration,
925    diff_formatter=default_render_d …

JSON command or task field key __init__.py · lines 1212–1216

39…  duration value."""
      case_durations: dict[str, float] = {'task': case.task_duration}
      if self.include_total_duration:
          case_durations['total'] = case.total_duration
      r …

Hex decoding via int(x, 16) _otel_emit.py · lines 115–120

16… erence is None:
      return None
  try:
      trace_id = int(span_reference.trace_id, 16)
      span_id = int(span_reference.span_id, 16)
  except ValueError:  # pragma: no cover — d …

Explicit LLM or language-model reference __init__.py · lines 1–5

1"""A toolkit for evaluating the execution of arbitrary "stochastic functions", such as LLM calls.
2
3This package provides functionality for:
4- Creating and loading test datasets with structured inputs and outputs
5- Evaluating model performance using various metrics and evaluato …

No evidence locations were recorded for this file. Raw result