54 lines
1.2 KiB
PHP
54 lines
1.2 KiB
PHP
<?php
|
|
|
|
declare(strict_types=1);
|
|
|
|
namespace App\Eval;
|
|
|
|
use App\Eval\Dto\EvalCase;
|
|
use App\Eval\Dto\EvalResult;
|
|
|
|
final readonly class AgentEvalRunner
|
|
{
|
|
public function __construct(
|
|
private RetrievalDebugRunner $retrievalDebugRunner,
|
|
private ShopQueryEvalRunner $shopQueryEvalRunner,
|
|
private AnswerGuardEvalRunner $answerGuardEvalRunner,
|
|
) {
|
|
}
|
|
|
|
public function run(EvalCase $case): EvalResult
|
|
{
|
|
if ($case->isRetrievalCase()) {
|
|
return $this->retrievalDebugRunner->run($case);
|
|
}
|
|
|
|
if ($case->isShopQueryCase() || $case->isFollowUpCase()) {
|
|
return $this->shopQueryEvalRunner->run($case);
|
|
}
|
|
|
|
if ($case->isAnswerGuardCase()) {
|
|
return $this->answerGuardEvalRunner->run($case);
|
|
}
|
|
|
|
throw new \InvalidArgumentException(sprintf(
|
|
'Unsupported eval case type: %s',
|
|
$case->type
|
|
));
|
|
}
|
|
|
|
/**
|
|
* @param array<int, EvalCase> $cases
|
|
* @return array<int, EvalResult>
|
|
*/
|
|
public function runAll(array $cases): array
|
|
{
|
|
$results = [];
|
|
|
|
foreach ($cases as $case) {
|
|
$results[] = $this->run($case);
|
|
}
|
|
|
|
return $results;
|
|
}
|
|
}
|