pydantic-evals 0.7.4__py3-none-any.whl → 0.7.5__py3-none-any.whl

pydantic_evals/dataset.py

@@ -297,6 +297,12 @@ class Dataset(BaseModel, Generic[InputsT, OutputT, MetadataT], extra='forbid', a
                         progress_bar.update(task_id, advance=1)
                     return result
 
+            if (context := eval_span.context) is None:  # pragma: no cover
+                trace_id = None
+                span_id = None
+            else:
+                trace_id = f'{context.trace_id:032x}'
+                span_id = f'{context.span_id:016x}'
             report = EvaluationReport(
                 name=name,
                 cases=await task_group_gather(
@@ -305,6 +311,8 @@ class Dataset(BaseModel, Generic[InputsT, OutputT, MetadataT], extra='forbid', a
                         for i, case in enumerate(self.cases, 1)
                     ]
                 ),
+                span_id=span_id,
+                trace_id=trace_id,
             )
             # TODO(DavidM): This attribute will be too big in general; remove it once we can use child spans in details panel:
             eval_span.set_attribute('cases', _REPORT_CASES_ADAPTER.dump_python(report.cases))
@@ -929,8 +937,8 @@ async def _run_task_and_evaluators(
 
         context = case_span.context
         if context is None:  # pragma: no cover
-            trace_id = ''
-            span_id = ''
+            trace_id = None
+            span_id = None
         else:
             trace_id = f'{context.trace_id:032x}'
             span_id = f'{context.span_id:016x}'

pydantic_evals/reporting/__init__.py

@@ -68,8 +68,8 @@ class ReportCase(Generic[InputsT, OutputT, MetadataT]):
     total_duration: float  # includes evaluator execution time
 
     # TODO(DavidM): Drop these once we can reference child spans in details panel:
-    trace_id: str
-    span_id: str
+    trace_id: str | None
+    span_id: str | None
 
 
 ReportCaseAdapter = TypeAdapter(ReportCase[Any, Any, Any])
@@ -158,9 +158,16 @@ class EvaluationReport(Generic[InputsT, OutputT, MetadataT]):
 
     name: str
     """The name of the report."""
+
     cases: list[ReportCase[InputsT, OutputT, MetadataT]]
     """The cases in the report."""
 
+    span_id: str | None = None
+    """The span ID of the evaluation."""
+
+    trace_id: str | None = None
+    """The trace ID of the evaluation."""
+
     def averages(self) -> ReportCaseAggregate:
         return ReportCaseAggregate.average(self.cases)
 

{pydantic_evals-0.7.4.dist-info → pydantic_evals-0.7.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pydantic-evals
-Version: 0.7.4
+Version: 0.7.5
 Summary: Framework for evaluating stochastic code execution, especially code making use of LLMs
 Project-URL: Homepage, https://ai.pydantic.dev/evals
 Project-URL: Source, https://github.com/pydantic/pydantic-ai
@@ -32,7 +32,7 @@ Requires-Python: >=3.9
 Requires-Dist: anyio>=0
 Requires-Dist: eval-type-backport>=0; python_version < '3.11'
 Requires-Dist: logfire-api>=3.14.1
-Requires-Dist: pydantic-ai-slim==0.7.4
+Requires-Dist: pydantic-ai-slim==0.7.5
 Requires-Dist: pydantic>=2.10
 Requires-Dist: pyyaml>=6.0.2
 Requires-Dist: rich>=13.9.4

{pydantic_evals-0.7.4.dist-info → pydantic_evals-0.7.5.dist-info}/RECORD

@@ -1,6 +1,6 @@
 pydantic_evals/__init__.py,sha256=OKRbfhdc8UZPzrPJMZUQwvzIxLhXmEZxz1ZuD921fy4,839
 pydantic_evals/_utils.py,sha256=PfhmPbdQp-q90s568LuG45zDDXxgO13BEz8MQJK8qw4,2922
-pydantic_evals/dataset.py,sha256=ZtDSqsLQYe2ExdLeVpwZo1akdSU8mkBrZ8Xgm7jh7n4,46702
+pydantic_evals/dataset.py,sha256=NSEKJLqKfVVu0YpmPJsb6rygwgglyc7h6_dIZAsKqqk,47036
 pydantic_evals/generation.py,sha256=Yd1rfbsDjjBBHDk-1KDu48hlITjM2-74rTnPBD_sqbA,3494
 pydantic_evals/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 pydantic_evals/evaluators/__init__.py,sha256=k_sTzRezIOUj7L2x3WC0_r8943jRo72uqb2vKplD5EU,660
@@ -15,9 +15,9 @@ pydantic_evals/otel/_context_in_memory_span_exporter.py,sha256=sQBaIH7NM_bCPnew9
 pydantic_evals/otel/_context_subtree.py,sha256=Iazp4w3IIBMCrkqWL-hTG-2QG_-2X81p794WG9MAsGk,1175
 pydantic_evals/otel/_errors.py,sha256=aW1414eTofpA7R_DUgOeT-gj7YA6OXmm8Y4oYeFukD4,268
 pydantic_evals/otel/span_tree.py,sha256=LV5Hsyo4riJzevHyBz8wxP82S-ry5zeKYi9bKWjGCS8,23057
-pydantic_evals/reporting/__init__.py,sha256=lRDlveMIOzYHaqqTIEiD2PQi6FSSejEMmY4aQbmIzTc,43233
+pydantic_evals/reporting/__init__.py,sha256=J6xdy6b1MG1kk47Za3oKu0c-RXD8jEi2TYGkRU1_qZU,43396
 pydantic_evals/reporting/render_numbers.py,sha256=8SKlK3etbD7HnSWWHCE993ceCNLZCepVQ-SsqUIhyxk,6916
-pydantic_evals-0.7.4.dist-info/METADATA,sha256=STrUGGJe5ydNMltngdja0610DpDwZ_7B96E4Ntvqaws,7942
-pydantic_evals-0.7.4.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-pydantic_evals-0.7.4.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
-pydantic_evals-0.7.4.dist-info/RECORD,,
+pydantic_evals-0.7.5.dist-info/METADATA,sha256=9fkNsIxmLfG5mXsu9u62AAZEK0AiuVeVwWTG9D5EX3U,7942
+pydantic_evals-0.7.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pydantic_evals-0.7.5.dist-info/licenses/LICENSE,sha256=vA6Jc482lEyBBuGUfD1pYx-cM7jxvLYOxPidZ30t_PQ,1100
+pydantic_evals-0.7.5.dist-info/RECORD,,