forked from phoenix-oss/llama-stack-mirror
314ee09ae3
llama-models should have extremely minimal cruft. Its sole purpose should be didactic -- show the simplest implementation of the llama models and document the prompt formats, etc. This PR is the complement to https://github.com/meta-llama/llama-models/pull/279 ## Test Plan Ensure all `llama` CLI `model` sub-commands work: ```bash llama model list llama model download --model-id ... llama model prompt-format -m ... ``` Ran tests: ```bash cd tests/client-sdk LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/ LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/ LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/ ``` Create a fresh venv `uv venv && source .venv/bin/activate` and run `llama stack build --template fireworks --image-type venv` followed by `llama stack run together --image-type venv` <-- the server runs Also checked that the OpenAPI generator can run and there is no change in the generated files as a result. ```bash cd docs/openapi_generator sh run_openapi_generator.sh ```
58 lines
1.6 KiB
Python
58 lines
1.6 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, Optional, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
# mapping of metric to value
|
|
ScoringResultRow = Dict[str, Any]
|
|
|
|
|
|
@json_schema_type
|
|
class ScoringResult(BaseModel):
|
|
score_rows: List[ScoringResultRow]
|
|
# aggregated metrics to value
|
|
aggregated_results: Dict[str, Any]
|
|
|
|
|
|
@json_schema_type
|
|
class ScoreBatchResponse(BaseModel):
|
|
dataset_id: Optional[str] = None
|
|
results: Dict[str, ScoringResult]
|
|
|
|
|
|
@json_schema_type
|
|
class ScoreResponse(BaseModel):
|
|
# each key in the dict is a scoring function name
|
|
results: Dict[str, ScoringResult]
|
|
|
|
|
|
class ScoringFunctionStore(Protocol):
|
|
def get_scoring_function(self, scoring_fn_id: str) -> ScoringFn: ...
|
|
|
|
|
|
@runtime_checkable
|
|
class Scoring(Protocol):
|
|
scoring_function_store: ScoringFunctionStore
|
|
|
|
@webmethod(route="/scoring/score-batch", method="POST")
|
|
async def score_batch(
|
|
self,
|
|
dataset_id: str,
|
|
scoring_functions: Dict[str, Optional[ScoringFnParams]],
|
|
save_results_dataset: bool = False,
|
|
) -> ScoreBatchResponse: ...
|
|
|
|
@webmethod(route="/scoring/score", method="POST")
|
|
async def score(
|
|
self,
|
|
input_rows: List[Dict[str, Any]],
|
|
scoring_functions: Dict[str, Optional[ScoringFnParams]],
|
|
) -> ScoreResponse: ...
|