[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

@ -12,6 +12,7 @@ from llama_stack.distribution.store import DistributionRegistry
from .routing_tables import (
DatasetsRoutingTable,
EvalTasksRoutingTable,
MemoryBanksRoutingTable,
ModelsRoutingTable,
ScoringFunctionsRoutingTable,
@ -31,6 +32,7 @@ async def get_routing_table_impl(
"shields": ShieldsRoutingTable,
"datasets": DatasetsRoutingTable,
"scoring_functions": ScoringFunctionsRoutingTable,
"eval_tasks": EvalTasksRoutingTable,
}
if api.value not in api_to_tables:
@ -44,6 +46,7 @@ async def get_routing_table_impl(
async def get_auto_router_impl(api: Api, routing_table: RoutingTable, _deps) -> Any:
from .routers import (
DatasetIORouter,
EvalRouter,
InferenceRouter,
MemoryRouter,
SafetyRouter,
@ -56,6 +59,7 @@ async def get_auto_router_impl(api: Api, routing_table: RoutingTable, _deps) ->
"safety": SafetyRouter,
"datasetio": DatasetIORouter,
"scoring": ScoringRouter,
"eval": EvalRouter,
}
if api.value not in api_to_routers:
raise ValueError(f"API {api.value} not found in router map")