[Evals API][3/n] scoring_functions / scoring meta-reference implementations (#296)

* wip

* dataset validation

* test_scoring

* cleanup

* clean up test

* comments

* error checking

* dataset client

* test client:

* datasetio client

* clean up

* basic scoring function works

* scorer wip

* equality scorer

* score batch impl

* score batch

* update scoring test

* refactor

* validate scorer input

* address comments

* add all rows scores to ScoringResult

* bugfix

* scoring function def rename
This commit is contained in:
Xi Yan 2024-10-24 14:52:30 -07:00 committed by GitHub
parent e70420a06e
commit cb84034567
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
28 changed files with 904 additions and 51 deletions

View file

@ -0,0 +1,25 @@
# 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 List
from llama_stack.distribution.datatypes import * # noqa: F403
def available_providers() -> List[ProviderSpec]:
return [
InlineProviderSpec(
api=Api.scoring,
provider_type="meta-reference",
pip_packages=[],
module="llama_stack.providers.impls.meta_reference.scoring",
config_class="llama_stack.providers.impls.meta_reference.scoring.MetaReferenceScoringConfig",
api_dependencies=[
Api.datasetio,
Api.datasets,
],
),
]