pydantic-evals 1.0.14__tar.gz → 1.0.15__tar.gz
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.
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/PKG-INFO +2 -2
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/dataset.py +3 -2
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/.gitignore +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/LICENSE +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/README.md +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/__init__.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/_utils.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/evaluators/__init__.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/evaluators/_run_evaluator.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/evaluators/common.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/evaluators/context.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/evaluators/evaluator.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/evaluators/llm_as_a_judge.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/evaluators/spec.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/generation.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/otel/__init__.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/otel/_context_in_memory_span_exporter.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/otel/_context_subtree.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/otel/_errors.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/otel/span_tree.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/py.typed +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/reporting/__init__.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pydantic_evals/reporting/render_numbers.py +0 -0
- {pydantic_evals-1.0.14 → pydantic_evals-1.0.15}/pyproject.toml +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: pydantic-evals
|
|
3
|
-
Version: 1.0.
|
|
3
|
+
Version: 1.0.15
|
|
4
4
|
Summary: Framework for evaluating stochastic code execution, especially code making use of LLMs
|
|
5
5
|
Project-URL: Homepage, https://ai.pydantic.dev/evals
|
|
6
6
|
Project-URL: Source, https://github.com/pydantic/pydantic-ai
|
|
@@ -30,7 +30,7 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
|
30
30
|
Requires-Python: >=3.10
|
|
31
31
|
Requires-Dist: anyio>=0
|
|
32
32
|
Requires-Dist: logfire-api>=3.14.1
|
|
33
|
-
Requires-Dist: pydantic-ai-slim==1.0.
|
|
33
|
+
Requires-Dist: pydantic-ai-slim==1.0.15
|
|
34
34
|
Requires-Dist: pydantic>=2.10
|
|
35
35
|
Requires-Dist: pyyaml>=6.0.2
|
|
36
36
|
Requires-Dist: rich>=13.9.4
|
|
@@ -646,7 +646,7 @@ class Dataset(BaseModel, Generic[InputsT, OutputT, MetadataT], extra='forbid', a
|
|
|
646
646
|
|
|
647
647
|
context: dict[str, Any] = {'use_short_form': True}
|
|
648
648
|
if fmt == 'yaml':
|
|
649
|
-
dumped_data = self.model_dump(mode='json', by_alias=True,
|
|
649
|
+
dumped_data = self.model_dump(mode='json', by_alias=True, context=context)
|
|
650
650
|
content = yaml.dump(dumped_data, sort_keys=False)
|
|
651
651
|
if schema_ref: # pragma: no branch
|
|
652
652
|
yaml_language_server_line = f'{_YAML_SCHEMA_LINE_PREFIX}{schema_ref}'
|
|
@@ -654,7 +654,7 @@ class Dataset(BaseModel, Generic[InputsT, OutputT, MetadataT], extra='forbid', a
|
|
|
654
654
|
path.write_text(content)
|
|
655
655
|
else:
|
|
656
656
|
context['$schema'] = schema_ref
|
|
657
|
-
json_data = self.model_dump_json(indent=2, by_alias=True,
|
|
657
|
+
json_data = self.model_dump_json(indent=2, by_alias=True, context=context)
|
|
658
658
|
path.write_text(json_data + '\n')
|
|
659
659
|
|
|
660
660
|
@classmethod
|
|
@@ -724,6 +724,7 @@ class Dataset(BaseModel, Generic[InputsT, OutputT, MetadataT], extra='forbid', a
|
|
|
724
724
|
evaluators: list[Union[tuple(evaluator_schema_types)]] = [] # pyright: ignore # noqa UP007
|
|
725
725
|
|
|
726
726
|
class Dataset(BaseModel, extra='forbid'):
|
|
727
|
+
name: str | None = None
|
|
727
728
|
cases: list[Case]
|
|
728
729
|
if evaluator_schema_types: # pragma: no branch
|
|
729
730
|
evaluators: list[Union[tuple(evaluator_schema_types)]] = [] # pyright: ignore # noqa UP007
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|