[Evals API][10/n] API updates for EvalTaskDef + new test migration (#379)

* wip

* scoring fn api

* eval api

* eval task

* evaluate api update

* pre commit

* unwrap context -> config

* config field doc

* typo

* naming fix

* separate benchmark / app eval

* api name

* rename

* wip tests

* wip

* datasetio test

* delete unused

* fixture

* scoring resolve

* fix scoring register

* scoring test pass

* score batch

* scoring fix

* fix eval

* test eval works

* remove type ignore

* api refactor

* add default task_eval_id for routing

* add eval_id for jobs

* remove type ignore

* only keep 1 run_eval

* fix optional

* register task required

* register task required

* delete old tests

* delete old tests

* fixture return impl
This commit is contained in:
Xi Yan 2024-11-07 21:24:12 -08:00 committed by GitHub
parent 8350f2df4c
commit 6192bf43a4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
32 changed files with 916 additions and 389 deletions

View file

@ -17,6 +17,7 @@ from llama_stack.apis.agents import Agents
from llama_stack.apis.datasetio import DatasetIO
from llama_stack.apis.datasets import Datasets
from llama_stack.apis.eval import Eval
from llama_stack.apis.eval_tasks import EvalTasks
from llama_stack.apis.inference import Inference
from llama_stack.apis.inspect import Inspect
from llama_stack.apis.memory import Memory
@ -48,6 +49,7 @@ def api_protocol_map() -> Dict[Api, Any]:
Api.scoring: Scoring,
Api.scoring_functions: ScoringFunctions,
Api.eval: Eval,
Api.eval_tasks: EvalTasks,
}
@ -58,6 +60,7 @@ def additional_protocols_map() -> Dict[Api, Any]:
Api.safety: (ShieldsProtocolPrivate, Shields),
Api.datasetio: (DatasetsProtocolPrivate, Datasets),
Api.scoring: (ScoringFunctionsProtocolPrivate, ScoringFunctions),
Api.eval_tasks: (EvalTasksProtocolPrivate, EvalTasks),
}