phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 19:12:09 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

scoring fn id

Browse source
This commit is contained in:
Xi Yan 2025-03-12 21:09:17 -07:00
parent d7dbc8cf64
commit 6408bdbc9d
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/apis/benchmarks/benchmarks.py
View file

@ -20,7 +20,7 @@ class CommonBenchmarkFields(BaseModel):
""" """
dataset_id: str dataset_id: str
scoring_functions: List[ScoringFnParams] scoring_fn_ids: List[str]
metadata: Dict[str, Any] = Field( metadata: Dict[str, Any] = Field(
default_factory=dict, default_factory=dict,
description="Metadata for this benchmark", description="Metadata for this benchmark",
@ -65,7 +65,7 @@ class Benchmarks(Protocol):
async def register_benchmark( async def register_benchmark(
self, self,
dataset_id: str, dataset_id: str,
scoring_functions: List[ScoringFnParams], scoring_fn_ids: List[str],
benchmark_id: Optional[str] = None, benchmark_id: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None, metadata: Optional[Dict[str, Any]] = None,
) -> Benchmark: ) -> Benchmark:
@ -73,7 +73,7 @@ class Benchmarks(Protocol):
Register a new benchmark. Register a new benchmark.
:param dataset_id: The ID of the dataset to used to run the benchmark. :param dataset_id: The ID of the dataset to used to run the benchmark.
:param scoring_functions: The scoring functions with parameters to use for this benchmark. :param scoring_fn_ids: List of scoring function ids to use for this benchmark.
:param benchmark_id: (Optional) The ID of the benchmark to register. If not provided, a random ID will be generated. :param benchmark_id: (Optional) The ID of the benchmark to register. If not provided, a random ID will be generated.
:param metadata: (Optional) Metadata for this benchmark for additional descriptions. :param metadata: (Optional) Metadata for this benchmark for additional descriptions.
""" """