Spaces:
Running
Running
File size: 1,538 Bytes
9c84f9d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | from typing import Any
from solar_eval.models.base import CustomBaseModel
from solar_eval.models.enums import RunStatus
class RunCreate(CustomBaseModel):
task: str
prompt_id: str
config: dict[str, Any] | None = None # workers, delay, etc.
class RunResponse(CustomBaseModel):
id: str
project_id: str
task: str
prompt_id: str
status: RunStatus
total_samples: int
completed_samples: int
config: dict[str, Any] | None = None
started_at: str | None = None
completed_at: str | None = None
created_at: str
class RunResultResponse(CustomBaseModel):
id: str
run_id: str
sample_idx: int
input: dict[str, Any]
output: str
golden: Any
input_tokens: int
output_tokens: int
inference_time_ms: float
class EvaluationResponse(CustomBaseModel):
id: str
run_id: str
scores: dict[str, float]
overall_score: float
eval_model: str
evaluated_at: str
class EvalDetailResponse(CustomBaseModel):
id: str
evaluation_id: str
sample_idx: int
category_scores: dict[str, float] | None = None
error_counts: dict[str, int] | None = None
severity: str | None = None
feedback: str | None = None
class DashboardResponse(CustomBaseModel):
project_id: str
task: str
runs: list[dict[str, Any]] # [{run_id, prompt_version, model, overall_score, date}]
class TrendResponse(CustomBaseModel):
project_id: str
task: str
data_points: list[dict[str, Any]] # [{date, score, prompt_version, model}]
|