chore!: deprecate eval/tasks (#1186)

# What does this PR do?
- Fully deprecate eval/tasks

[//]: # (If resolving an issue, uncomment and update the line below)
Closes #1088 

NOTE: this will be a breaking change. We have introduced the new API in
0.1.3 .

Notebook has been updated to use the new endpoints.

## Test Plan
```
pytest -v -s --nbval-lax ./docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb 
```
<img width="611" alt="image"
src="https://github.com/user-attachments/assets/79f6efe1-81ba-494e-bf36-1fc0c2b9bc6f"
/>



cc @SLR722  for awareness

[//]: # (## Documentation)
This commit is contained in:
Xi Yan 2025-02-20 14:06:21 -08:00 committed by GitHub
parent 07ccf908f7
commit ea1faae50e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 1358 additions and 2161 deletions

View file

@ -234,45 +234,3 @@ class MetaReferenceEvalImpl(
raise ValueError(f"Job is not completed, Status: {status.value}")
return self.jobs[job_id]
async def DEPRECATED_run_eval(
self,
task_id: str,
task_config: BenchmarkConfig,
) -> Job:
return await self.run_eval(benchmark_id=task_id, task_config=task_config)
async def DEPRECATED_evaluate_rows(
self,
task_id: str,
input_rows: List[Dict[str, Any]],
scoring_functions: List[str],
task_config: BenchmarkConfig,
) -> EvaluateResponse:
return await self.evaluate_rows(
benchmark_id=task_id,
input_rows=input_rows,
scoring_functions=scoring_functions,
task_config=task_config,
)
async def DEPRECATED_job_status(
self,
task_id: str,
job_id: str,
) -> Optional[JobStatus]:
return await self.job_status(benchmark_id=task_id, job_id=job_id)
async def DEPRECATED_job_cancel(
self,
task_id: str,
job_id: str,
) -> None:
return await self.job_cancel(benchmark_id=task_id, job_id=job_id)
async def DEPRECATED_job_result(
self,
task_id: str,
job_id: str,
) -> EvaluateResponse:
return await self.job_result(benchmark_id=task_id, job_id=job_id)