mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
c88c4ff2c6
# What does this PR do? Rather than have a single `LLAMA_STACK_VERSION`, we need to have a `_V1`, `_V1ALPHA`, and `_V1BETA` constant. This also necessitated addition of `level` to the `WebMethod` so that routing can be handeled properly. For backwards compat, the `v1` routes are being kept around and marked as `deprecated`. When used, the server will log a deprecation warning. Deprecation log: <img width="1224" height="134" alt="Screenshot 2025-09-25 at 2 43 36 PM" src="https://github.com/user-attachments/assets/0cc7c245-dafc-48f0-be99-269fb9a686f9" /> move: 1. post_training to `v1alpha` as it is under heavy development and not near its final state 2. eval: job scheduling is not implemented. Relies heavily on the datasetio API which is under development missing implementations of specific routes indicating the structure of those routes might change. Additionally eval depends on the `inference` API which is going to be deprecated, eval will likely need a major API surface change to conform to using completions properly implements leveling in #3317 note: integration tests will fail until the SDK is regenerated with v1alpha/inference as opposed to v1/inference ## Test Plan existing tests should pass with newly generated schema. Conformance will also pass as these routes are not the ones we currently test for stability Signed-off-by: Charlie Doern <cdoern@redhat.com>
108 lines
3.8 KiB
Python
108 lines
3.8 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.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA
|
|
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):
|
|
"""A benchmark resource for evaluating model performance.
|
|
|
|
:param dataset_id: Identifier of the dataset to use for the benchmark evaluation
|
|
:param scoring_functions: List of scoring function identifiers to apply during evaluation
|
|
:param metadata: Metadata for this evaluation task
|
|
:param type: The resource type, always benchmark
|
|
"""
|
|
|
|
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", level=LLAMA_STACK_API_V1, deprecated=True)
|
|
@webmethod(route="/eval/benchmarks", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
|
async def list_benchmarks(self) -> ListBenchmarksResponse:
|
|
"""List all benchmarks.
|
|
|
|
:returns: A ListBenchmarksResponse.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
|
|
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="GET", level=LLAMA_STACK_API_V1ALPHA)
|
|
async def get_benchmark(
|
|
self,
|
|
benchmark_id: str,
|
|
) -> Benchmark:
|
|
"""Get a benchmark by its ID.
|
|
|
|
:param benchmark_id: The ID of the benchmark to get.
|
|
:returns: A Benchmark.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
|
|
@webmethod(route="/eval/benchmarks", method="POST", level=LLAMA_STACK_API_V1ALPHA)
|
|
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:
|
|
"""Register a benchmark.
|
|
|
|
:param benchmark_id: The ID of the benchmark to register.
|
|
:param dataset_id: The ID of the dataset to use for the benchmark.
|
|
:param scoring_functions: The scoring functions to use for the benchmark.
|
|
:param provider_benchmark_id: The ID of the provider benchmark to use for the benchmark.
|
|
:param provider_id: The ID of the provider to use for the benchmark.
|
|
:param metadata: The metadata to use for the benchmark.
|
|
"""
|
|
...
|
|
|
|
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1, deprecated=True)
|
|
@webmethod(route="/eval/benchmarks/{benchmark_id}", method="DELETE", level=LLAMA_STACK_API_V1ALPHA)
|
|
async def unregister_benchmark(self, benchmark_id: str) -> None:
|
|
"""Unregister a benchmark.
|
|
|
|
:param benchmark_id: The ID of the benchmark to unregister.
|
|
"""
|
|
...
|