phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

result_data in evaluation response

Browse source
This commit is contained in:
Xi Yan 2025-03-18 22:09:35 -07:00
parent 08c0c5505e
commit a92756a4b7
3 changed files with 43 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

21
llama_stack/apis/evaluation/evaluation.py
View file

@ -76,30 +76,17 @@ class EvaluationJob(CommonJobFields):
candidate: EvaluationCandidate
@json_schema_type
class ScoringResult(BaseModel):
"""
A scoring result for a single row.
:param scores: The scoring result for each row. Each row is a map of grader column name to value.
:param metrics: Map of metric name to aggregated value.
"""
scores: List[Dict[str, Any]]
metrics: Dict[str, Any]
@json_schema_type
class EvaluationResponse(BaseModel):
"""
A response to an inline evaluation.
:param generations: The generations in rows for the evaluation.
:param scores: The scores for the evaluation. Map of grader id to ScoringResult.
:param result_data: The result data containing generations and grades in each row.
:param metrics: Map of metric name to aggregated value.
"""
generations: List[Dict[str, Any]]
scores: Dict[str, ScoringResult]
result_data: List[Dict[str, Any]]
metrics: Dict[str, Any]
class Evaluation(Protocol):