mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
1a529705da
# What does this PR do? Mainly tried to cover the entire llama_stack/apis directory, we only have one left. Some excludes were just noop. Signed-off-by: Sébastien Han <seb@redhat.com>
66 lines
1.9 KiB
Python
66 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, Literal, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from llama_stack.apis.resource import Resource, ResourceType
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
|
|
class CommonBenchmarkFields(BaseModel):
|
|
dataset_id: str
|
|
scoring_functions: list[str]
|
|
metadata: dict[str, Any] = Field(
|
|
default_factory=dict,
|
|
description="Metadata for this evaluation task",
|
|
)
|
|
|
|
|
|
@json_schema_type
|
|
class Benchmark(CommonBenchmarkFields, Resource):
|
|
type: Literal[ResourceType.benchmark] = ResourceType.benchmark
|
|
|
|
@property
|
|
def benchmark_id(self) -> str:
|
|
return self.identifier
|
|
|
|
@property
|
|
def provider_benchmark_id(self) -> str | None:
|
|
return self.provider_resource_id
|
|
|
|
|
|
class BenchmarkInput(CommonBenchmarkFields, BaseModel):
|
|
benchmark_id: str
|
|
provider_id: str | None = None
|
|
provider_benchmark_id: str | None = None
|
|
|
|
|
|
class ListBenchmarksResponse(BaseModel):
|
|
data: list[Benchmark]
|
|
|
|
|
|
@runtime_checkable
|
|
class Benchmarks(Protocol):
|
|
@webmethod(route="/eval/benchmarks", method="GET")
|
|
async def list_benchmarks(self) -> ListBenchmarksResponse: ...
|
|
|
|
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET")
|
|
async def get_benchmark(
|
|
self,
|
|
benchmark_id: str,
|
|
) -> Benchmark: ...
|
|
|
|
@webmethod(route="/eval/benchmarks", method="POST")
|
|
async def register_benchmark(
|
|
self,
|
|
benchmark_id: str,
|
|
dataset_id: str,
|
|
scoring_functions: list[str],
|
|
provider_benchmark_id: str | None = None,
|
|
provider_id: str | None = None,
|
|
metadata: dict[str, Any] | None = None,
|
|
) -> None: ...
|