forked from phoenix-oss/llama-stack-mirror
09269e2a44
# What does this PR do? This is a follow-up to #425. That PR allows for specifying models in the registry, but each entry needs to look like: ```yaml - identifier: ... provider_id: ... provider_resource_identifier: ... ``` This is headache-inducing. The current PR makes this situation better by adopting the shape of our APIs. Namely, we need the user to only specify `model-id`. The rest should be optional and figured out by the Stack. You can always override it. Here's what example `ollama` "full stack" registry looks like (we still need to kill or simplify shield_type crap): ```yaml models: - model_id: Llama3.2-3B-Instruct - model_id: Llama-Guard-3-1B shields: - shield_id: llama_guard shield_type: llama_guard ``` ## Test Plan See test plan for #425. Re-ran it.
67 lines
1.9 KiB
Python
67 lines
1.9 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from typing import Any, Dict, List, Literal, Optional, Protocol
|
|
|
|
from llama_models.llama3.api.datatypes import URL
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.apis.common.type_system import ParamType
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
|
|
|
|
class CommonDatasetFields(BaseModel):
|
|
schema: Dict[str, ParamType]
|
|
url: URL
|
|
metadata: Dict[str, Any] = Field(
|
|
default_factory=dict,
|
|
description="Any additional metadata for this dataset",
|
|
)
|
|
|
|
|
|
@json_schema_type
|
|
class Dataset(CommonDatasetFields, Resource):
|
|
type: Literal[ResourceType.dataset.value] = ResourceType.dataset.value
|
|
|
|
@property
|
|
def dataset_id(self) -> str:
|
|
return self.identifier
|
|
|
|
@property
|
|
def provider_dataset_id(self) -> str:
|
|
return self.provider_resource_id
|
|
|
|
|
|
@json_schema_type
|
|
class DatasetInput(CommonDatasetFields, BaseModel):
|
|
dataset_id: str
|
|
provider_id: Optional[str] = None
|
|
provider_dataset_id: Optional[str] = None
|
|
|
|
|
|
class Datasets(Protocol):
|
|
@webmethod(route="/datasets/register", method="POST")
|
|
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: ...
|
|
|
|
@webmethod(route="/datasets/get", method="GET")
|
|
async def get_dataset(
|
|
self,
|
|
dataset_id: str,
|
|
) -> Optional[Dataset]: ...
|
|
|
|
@webmethod(route="/datasets/list", method="GET")
|
|
async def list_datasets(self) -> List[Dataset]: ...
|