[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

@ -20,6 +20,8 @@ from llama_stack.apis.memory import Memory
from llama_stack.apis.memory_banks import MemoryBanks
from llama_stack.apis.models import Models
from llama_stack.apis.safety import Safety
from llama_stack.apis.scoring import Scoring
from llama_stack.apis.scoring_functions import ScoringFunctions
from llama_stack.apis.shields import Shields
from llama_stack.apis.telemetry import Telemetry
from llama_stack.distribution.distribution import (
@ -42,6 +44,8 @@ def api_protocol_map() -> Dict[Api, Any]:
Api.telemetry: Telemetry,
Api.datasets: Datasets,
Api.datasetio: DatasetIO,
Api.scoring_functions: ScoringFunctions,
Api.scoring: Scoring,
}