phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 13:00:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

tmp

Browse source
This commit is contained in:
Xi Yan 2025-03-12 00:39:49 -07:00
parent 3e0d4901da
commit 4acd1e404e
2 changed files with 12 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/common/job_types.py
View file

@ -28,9 +28,11 @@ class CommonJobFields(BaseModel):
:param status: The status of the job. :param status: The status of the job.
:param created_at: The time the job was created. :param created_at: The time the job was created.
:param finished_at: The time the job finished. :param finished_at: The time the job finished.
:param error: If status of the job is failed, this will contain the error message.
""" """
id: str id: str
status: JobStatus status: JobStatus
created_at: datetime created_at: datetime
finished_at: Optional[datetime] = None finished_at: Optional[datetime] = None
error: Optional[str] = None

17
llama_stack/apis/eval/eval.py
View file

@ -10,7 +10,7 @@ from pydantic import BaseModel, Field
from typing_extensions import Annotated from typing_extensions import Annotated
from llama_stack.apis.agents import AgentConfig from llama_stack.apis.agents import AgentConfig
from llama_stack.apis.common.job_types import Job, JobStatus from llama_stack.apis.common.job_types import CommonJobFields, JobStatus
from llama_stack.apis.inference import SamplingParams, SystemMessage from llama_stack.apis.inference import SamplingParams, SystemMessage
from llama_stack.apis.scoring import ScoringResult from llama_stack.apis.scoring import ScoringResult
from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.apis.scoring_functions import ScoringFnParams
@ -84,12 +84,15 @@ class EvaluateResponse(BaseModel):
@json_schema_type @json_schema_type
class EvalJob(Job): class EvalJob(CommonJobFields):
"""The EvalJob object representing a evaluation job that was created through API. """The EvalJob object representing a evaluation job that was created through API."""
:param job_id: The ID of the job. type: Literal["eval"] = "eval"
:param status: The status of the job. # TODO: result files or result datasets ids?
""" result_files: List[str] = Field(
default_factory=list,
description="Result files of an evaluation run. Which can be queried for results.",
)
class Eval(Protocol): class Eval(Protocol):
@ -99,7 +102,7 @@ class Eval(Protocol):
async def evaluate_benchmark( async def evaluate_benchmark(
self, self,
benchmark_id: str, benchmark_id: str,
benchmark_config: BenchmarkConfig, candidate: EvalCandidate,
) -> EvalJob: ) -> EvalJob:
"""Run an evaluation on a benchmark. """Run an evaluation on a benchmark.