siemens_ragas/webapp/models.py

"""Pydantic response models for the evaluation console HTTP API."""

from __future__ import annotations

from typing import Any

from pydantic import BaseModel, Field


class RunSummary(BaseModel):
    """Compact description of a single evaluation run for list views."""

    run_id: str
    scenario_name: str
    mode: str = ""
    judge_model: str = ""
    embedding_model: str = ""
    started_at: str = ""
    finished_at: str = ""
    dataset: str = ""
    total_samples: int = 0
    valid_samples: int = 0
    invalid_samples: int = 0
    metrics: list[str] = Field(default_factory=list)
    metric_means: dict[str, float | None] = Field(default_factory=dict)
    output_path: str = ""


class GroupStat(BaseModel):
    """Mean metric values for one slice of samples grouped by a metadata field."""

    key: str
    count: int
    means: dict[str, float | None] = Field(default_factory=dict)


class DistributionBin(BaseModel):
    """One histogram bucket of sample counts for a single metric."""

    label: str
    lower: float
    upper: float
    count: int


class SampleScore(BaseModel):
    """Per-sample row used for the lowest-score review table."""

    sample_id: str
    question: str = ""
    contexts: list[str] = Field(default_factory=list)
    answer: str = ""
    ground_truth: str = ""
    language: str = ""
    difficulty: str = ""
    question_type: str = ""
    metrics: dict[str, float | None] = Field(default_factory=dict)
    mean_score: float | None = None
    error: str = ""


class ReportData(BaseModel):
    """Aggregated report payload rendered by the report detail page."""

    metrics: list[str] = Field(default_factory=list)
    metric_means: dict[str, float | None] = Field(default_factory=dict)
    distributions: dict[str, list[DistributionBin]] = Field(default_factory=dict)
    groupings: dict[str, list[GroupStat]] = Field(default_factory=dict)
    lowest_samples: list[SampleScore] = Field(default_factory=list)
    summary_markdown: str = ""


class RunDetail(BaseModel):
    """Full payload for a single run: summary metadata plus the report."""

    summary: RunSummary
    report: ReportData


class ScenarioInfo(BaseModel):
    """One discoverable scenario YAML file that can be evaluated from the UI."""

    path: str
    scenario_name: str = ""
    mode: str = ""
    dataset: str = ""
    judge_model: str = ""
    metrics: list[str] = Field(default_factory=list)
    error: str = ""


class TaskStatus(BaseModel):
    """State of a background evaluation task tracked by the task manager."""

    task_id: str
    scenario_path: str
    status: str
    logs: list[str] = Field(default_factory=list)
    run_id: str | None = None
    error: str | None = None
    created_at: str = ""
    finished_at: str = ""


class TriggerEvaluationRequest(BaseModel):
    """Request body for launching an evaluation run from the UI."""

    scenario_path: str


class TriggerEvaluationResponse(BaseModel):
    """Response returned immediately after queuing an evaluation task."""

    task_id: str


def jsonable(value: Any) -> Any:
    """Convert NaN/inf floats into None so the payload stays valid JSON."""
    import math

    if isinstance(value, float):
        if math.isnan(value) or math.isinf(value):
            return None
        return value
    if isinstance(value, dict):
        return {key: jsonable(item) for key, item in value.items()}
    if isinstance(value, list):
        return [jsonable(item) for item in value]
    return value