migrate dataset to resource

This commit is contained in:
Dinesh Yeduguru 2024-11-11 12:15:41 -08:00
parent 38cce97597
commit f8e39ae873
7 changed files with 70 additions and 51 deletions

View file

@ -34,7 +34,7 @@ RoutableObject = Union[
Model,
Shield,
MemoryBank,
DatasetDef,
Dataset,
ScoringFnDef,
]
@ -44,7 +44,7 @@ RoutableObjectWithProvider = Annotated[
Model,
Shield,
MemoryBank,
DatasetDefWithProvider,
Dataset,
ScoringFnDefWithProvider,
],
Field(discriminator="type"),

View file

@ -17,6 +17,9 @@ from llama_stack.apis.datasets import * # noqa: F403
from llama_stack.apis.eval_tasks import * # noqa: F403
from llama_models.llama3.api.datatypes import URL
from llama_stack.apis.common.type_system import ParamType
from llama_stack.distribution.store import DistributionRegistry
from llama_stack.distribution.datatypes import * # noqa: F403
@ -95,7 +98,7 @@ class CommonRoutingTableImpl(RoutingTable):
elif api == Api.datasetio:
p.dataset_store = self
datasets = await p.list_datasets()
await add_objects(datasets, pid, DatasetDefWithProvider)
await add_objects(datasets, pid, Dataset)
elif api == Api.scoring:
p.scoring_function_store = self
@ -302,16 +305,42 @@ class MemoryBanksRoutingTable(CommonRoutingTableImpl, MemoryBanks):
class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):
async def list_datasets(self) -> List[DatasetDefWithProvider]:
async def list_datasets(self) -> List[Dataset]:
return await self.get_all_with_type("dataset")
async def get_dataset(
self, dataset_identifier: str
) -> Optional[DatasetDefWithProvider]:
return await self.get_object_by_identifier(dataset_identifier)
async def get_dataset(self, dataset_id: str) -> Optional[Dataset]:
return await self.get_object_by_identifier(dataset_id)
async def register_dataset(self, dataset_def: DatasetDefWithProvider) -> None:
await self.register_object(dataset_def)
async def register_dataset(
self,
dataset_id: str,
schema: Dict[str, ParamType],
url: URL,
provider_dataset_id: Optional[str] = None,
provider_id: Optional[str] = None,
metadata: Optional[Dict[str, Any]] = None,
) -> None:
if provider_dataset_id is None:
provider_dataset_id = dataset_id
if provider_id is None:
# If provider_id not specified, use the only provider if it supports this dataset
if len(self.impls_by_provider_id) == 1:
provider_id = list(self.impls_by_provider_id.keys())[0]
else:
raise ValueError(
"No provider specified and multiple providers available. Please specify a provider_id."
)
if metadata is None:
metadata = {}
dataset = Dataset(
identifier=dataset_id,
provider_resource_id=provider_dataset_id,
provider_id=provider_id,
schema=schema,
url=url,
metadata=metadata,
)
await self.register_object(dataset)
class ScoringFunctionsRoutingTable(CommonRoutingTableImpl, ScoringFunctions):