evalsuite-python 0.3.1__py3-none-any.whl → 0.4.1__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- evalsuite/__init__.py +5 -1
- evalsuite/_bench_metrics.py +1391 -0
- evalsuite/benchmarks.py +171 -10
- evalsuite/cli/main.py +33 -2
- evalsuite/clinical/metrics.py +7 -4
- evalsuite/plot.py +146 -0
- evalsuite/stats/_resolve.py +23 -3
- evalsuite/stats/compare.py +7 -3
- evalsuite/text/__init__.py +152 -0
- evalsuite/text/_common.py +94 -0
- evalsuite/text/factuality.py +469 -0
- evalsuite/text/generation.py +1127 -0
- evalsuite/text/judge.py +532 -0
- evalsuite/text/qa.py +108 -0
- evalsuite/text/rag.py +235 -0
- evalsuite/text/reasoning.py +215 -0
- evalsuite/text/report.py +158 -0
- evalsuite/text/retrieval.py +238 -0
- evalsuite/text/semantic.py +465 -0
- evalsuite/text/structured.py +789 -0
- evalsuite/version.py +1 -1
- {evalsuite_python-0.3.1.dist-info → evalsuite_python-0.4.1.dist-info}/METADATA +65 -22
- {evalsuite_python-0.3.1.dist-info → evalsuite_python-0.4.1.dist-info}/RECORD +26 -13
- {evalsuite_python-0.3.1.dist-info → evalsuite_python-0.4.1.dist-info}/WHEEL +0 -0
- {evalsuite_python-0.3.1.dist-info → evalsuite_python-0.4.1.dist-info}/entry_points.txt +0 -0
- {evalsuite_python-0.3.1.dist-info → evalsuite_python-0.4.1.dist-info}/licenses/LICENSE +0 -0
evalsuite/__init__.py
CHANGED
|
@@ -5,7 +5,7 @@
|
|
|
5
5
|
>>> print(result.summary()) # doctest: +SKIP
|
|
6
6
|
"""
|
|
7
7
|
|
|
8
|
-
from . import calibration, classification, clinical, plot, regression, stats, vision
|
|
8
|
+
from . import calibration, classification, clinical, plot, regression, stats, text, vision
|
|
9
9
|
from .api import evaluate
|
|
10
10
|
from .calibration import (
|
|
11
11
|
CalibrationReport,
|
|
@@ -110,6 +110,8 @@ from .stats import (
|
|
|
110
110
|
t_test,
|
|
111
111
|
wilcoxon_test,
|
|
112
112
|
)
|
|
113
|
+
from .text import * # noqa: F403 (every LLM-evaluation function, listed in text.__all__)
|
|
114
|
+
from .text import __all__ as _text_all
|
|
113
115
|
from .version import __version__
|
|
114
116
|
from .vision import (
|
|
115
117
|
DetectionReport,
|
|
@@ -134,6 +136,7 @@ from .vision import (
|
|
|
134
136
|
)
|
|
135
137
|
|
|
136
138
|
__all__ = [
|
|
139
|
+
"text",
|
|
137
140
|
"SegmentationReport",
|
|
138
141
|
"segmentation_report",
|
|
139
142
|
"detection_pr_curve",
|
|
@@ -258,3 +261,4 @@ __all__ = [
|
|
|
258
261
|
"specificity",
|
|
259
262
|
"top_k_accuracy",
|
|
260
263
|
]
|
|
264
|
+
__all__ += list(_text_all)
|