phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

migrate dataset to resource (#420)

Browse source 
* migrate dataset to resource

* remove auto discovery

* remove listing of providers's datasets

* fix after rebase

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru 2024-11-11 17:14:41 -08:00 • committed by GitHub
parent 38cce97597
commit b95cb5308f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 71 additions and 62 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/datasetio/datasetio.py
View file

@ -21,7 +21,7 @@ class PaginatedRowsResult(BaseModel):
class DatasetStore(Protocol):
def get_dataset(self, identifier: str) -> DatasetDefWithProvider: ...
def get_dataset(self, dataset_id: str) -> Dataset: ...
@runtime_checkable

34
llama_stack/apis/datasets/datasets.py
View file

@ -10,19 +10,16 @@ from llama_models.llama3.api.datatypes import URL
from llama_models.schema_utils import json_schema_type, webmethod
from pydantic import BaseModel, Field
from pydantic import Field
from llama_stack.apis.common.type_system import ParamType
from llama_stack.apis.resource import Resource
@json_schema_type
class DatasetDef(BaseModel):
identifier: str = Field(
description="A unique name for the dataset",
)
dataset_schema: Dict[str, ParamType] = Field(
description="The schema definition for this dataset",
)
class Dataset(Resource):
type: Literal["dataset"] = "dataset"
schema: Dict[str, ParamType]
url: URL
metadata: Dict[str, Any] = Field(
default_factory=dict,
@ -30,26 +27,23 @@ class DatasetDef(BaseModel):
)
@json_schema_type
class DatasetDefWithProvider(DatasetDef):
type: Literal["dataset"] = "dataset"
provider_id: str = Field(
description="ID of the provider which serves this dataset",
)
class Datasets(Protocol):
@webmethod(route="/datasets/register", method="POST")
async def register_dataset(
self,
dataset_def: DatasetDefWithProvider,
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: ...
@webmethod(route="/datasets/get", method="GET")
async def get_dataset(
self,
dataset_identifier: str,
) -> Optional[DatasetDefWithProvider]: ...
dataset_id: str,
) -> Optional[Dataset]: ...
@webmethod(route="/datasets/list", method="GET")
async def list_datasets(self) -> List[DatasetDefWithProvider]: ...
async def list_datasets(self) -> List[Dataset]: ...