wangwei
e89695e490
- webapp/: FastAPI backend with runs/scenarios/evaluations API routers; services for run_reader, report_builder, scenario_scanner, task_manager (lazy ragas import — server boots even without ragas); Pydantic models - webapp/static/: single-page console (layout A: left-nav + main area); report detail with metric cards, Chart.js distribution histogram, grouping table, lowest-score sample review; trigger evaluation + log polling - webmain.py: uvicorn entry point (alongside existing main.py CLI) - start.bat: Windows one-click launcher with env checks and auto-browser open - rag_eval/datasets/: implement missing loader + normalizer modules (load_dataset_records, normalize_records) required by evaluator - scripts/seed_sample_run.py: generate realistic demo run artifacts - .gitignore: exclude datasets/ data files but keep rag_eval/datasets/ source Co-Authored-By: Claude Sonnet 4 <noreply@anthropic.com>
45 lines
1.5 KiB
Python
45 lines
1.5 KiB
Python
"""Routes for triggering evaluations and polling background task status."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
|
|
from webapp.models import (
|
|
TaskStatus,
|
|
TriggerEvaluationRequest,
|
|
TriggerEvaluationResponse,
|
|
)
|
|
from webapp.services import scenario_scanner
|
|
from webapp.services.task_manager import task_manager
|
|
|
|
router = APIRouter(prefix="/api/evaluations", tags=["evaluations"])
|
|
|
|
|
|
@router.post("", response_model=TriggerEvaluationResponse)
|
|
def trigger_evaluation(request: TriggerEvaluationRequest) -> TriggerEvaluationResponse:
|
|
"""Validate the scenario path and queue a background evaluation task."""
|
|
resolved = scenario_scanner.resolve_scenario_path(request.scenario_path)
|
|
if resolved is None:
|
|
raise HTTPException(
|
|
status_code=400,
|
|
detail=f"无效或不允许的场景路径: {request.scenario_path}",
|
|
)
|
|
|
|
task_id = task_manager.submit(request.scenario_path)
|
|
return TriggerEvaluationResponse(task_id=task_id)
|
|
|
|
|
|
@router.get("/{task_id}", response_model=TaskStatus)
|
|
def get_task_status(task_id: str) -> TaskStatus:
|
|
"""Return the current status and logs for one evaluation task."""
|
|
status = task_manager.get(task_id)
|
|
if status is None:
|
|
raise HTTPException(status_code=404, detail=f"未找到任务: {task_id}")
|
|
return status
|
|
|
|
|
|
@router.get("", response_model=dict)
|
|
def list_tasks() -> dict[str, list]:
|
|
"""Return all known evaluation tasks for this server session."""
|
|
return {"tasks": [task.model_dump() for task in task_manager.list_tasks()]}
|