Slide 11
Slide 11 text
フィルタートリガーのレスポンス
ユーザー入力でトリガーされた場合 モデルの出力でトリガーされた場合
Status:400
{
"error": {
"message": "The response was filtered due to the prom…",
"type": null,
"param": "prompt",
"code": "content_filter",
"status": 400,
“innererror":
{
”code": "ResponsibleAIPolicyViolation",
“content_filter_result": {
”hate": { "filtered": true, "severity": "high" },
“self-harm": { "filtered": true, "severity": "high" },
"sexual": { "filtered": false, "severity": "safe" },
“violence": { "filtered":true, "severity": "medium" }
}
}
}
}
Status:200
{
"choices": [
{
"content_filter_results": {
"custom_blocklists": [],
"hate": { "filtered": false, "severity": "safe" },
"self_harm": { "filtered": false, "severity": "safe" },
"sexual": { "filtered": false, "severity": "safe" },
"violence": { "filtered": true, "severity": "medium" }
},
"finish_reason": "content_filter",
…
}
],
…
}
※APIバージョンによっても異なります。上記は2023-12-01-previewの例