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

comments

Browse source
This commit is contained in:
Xi Yan 2025-03-18 15:01:41 -07:00
parent a8b0467ec3
commit a69759613a
7 changed files with 2486 additions and 389 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/apis/evaluation/evaluation.py
View file

@ -48,28 +48,28 @@ EvaluationCandidate = register_schema(
@json_schema_type
class BenchmarkTask(BaseModel):
type: Literal["benchmark_id"] = "benchmark_id"
class BenchmarkEvaluationTask(BaseModel):
type: Literal["benchmark"] = "benchmark"
benchmark_id: str
@json_schema_type
class DatasetGraderTask(BaseModel):
type: Literal["dataset_grader"] = "dataset_grader"
class DatasetEvaluationTask(BaseModel):
type: Literal["dataset"] = "dataset"
dataset_id: str
grader_ids: List[str]
@json_schema_type
class DataSourceGraderTask(BaseModel):
type: Literal["data_source_grader"] = "data_source_grader"
class DataEvaluationTask(BaseModel):
type: Literal["data"] = "data"
data_source: DataSource
grader_ids: List[str]
EvaluationTask = register_schema(
Annotated[
Union[BenchmarkTask, DatasetGraderTask, DataSourceGraderTask],
Union[BenchmarkEvaluationTask, DatasetEvaluationTask, DataEvaluationTask],
Field(discriminator="type"),
],
name="EvaluationTask",