I/O is live! Tune in for livestreamed keynotes and sessions May 20-21 starting at 10 AM PT. Watch now.

本頁面由 Cloud Translation API 翻譯而成。

瞭解並使用安全性設定
透過集合功能整理內容你可以依據偏好儲存及分類內容。

您可以使用安全性設定，調整收到可能有害回覆的可能性。根據預設，安全設定會封鎖所有維度中屬於中等和/或高機率有害的內容。

前往Gemini安全設定前往Imagen安全設定

Gemini 型號的安全性設定

按一下您的 Gemini API 供應商，即可在本頁查看供應商專屬內容和程式碼。

如要進一步瞭解 Gemini 型號的安全設定，請參閱 Gemini Developer API 說明文件。

Swift

建立 GenerativeModel 執行個體時，您會設定 SafetySettings。

以下是包含一個安全設定的範例：


import FirebaseAI

// Initialize the Gemini Developer API backend service
// Create an `GenerativeModel` instance and add safety settings to its config
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [
    SafetySetting(harmCategory: .harassment, threshold: .blockOnlyHigh)
  ]
)

// ...

含有多個安全性設定的範例：


import FirebaseAI

let harassmentSafety = SafetySetting(harmCategory: .harassment, threshold: .blockOnlyHigh)
let hateSpeechSafety = SafetySetting(harmCategory: .hateSpeech, threshold: .blockMediumAndAbove)

// Initialize the Gemini Developer API backend service
// Create an `GenerativeModel` instance and add safety settings to its config
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [harassmentSafety, hateSpeechSafety]
)

// ...

Kotlin

建立 GenerativeModel 執行個體時，您會設定 SafetySettings。

以下是包含一個安全設定的範例：


import com.google.firebase.vertexai.type.HarmBlockThreshold
import com.google.firebase.vertexai.type.HarmCategory
import com.google.firebase.vertexai.type.SafetySetting

// Create a `GenerativeModel` instance and add safety settings to its config
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    safetySettings = listOf(
        SafetySetting(HarmCategory.HARASSMENT, HarmBlockThreshold.ONLY_HIGH)
    )
)

// ...

含有多個安全性設定的範例：


import com.google.firebase.vertexai.type.HarmBlockThreshold
import com.google.firebase.vertexai.type.HarmCategory
import com.google.firebase.vertexai.type.SafetySetting

val harassmentSafety = SafetySetting(HarmCategory.HARASSMENT, HarmBlockThreshold.ONLY_HIGH)
val hateSpeechSafety = SafetySetting(HarmCategory.HATE_SPEECH, HarmBlockThreshold.MEDIUM_AND_ABOVE)

// Create a `GenerativeModel` instance and add safety settings to its config
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    safetySettings = listOf(harassmentSafety, hateSpeechSafety)
)

// ...

Java

建立 GenerativeModel 執行個體時，您會設定 SafetySettings。


SafetySetting harassmentSafety = new SafetySetting(HarmCategory.HARASSMENT,
HarmBlockThreshold.ONLY_HIGH);

// Create an `GenerativeModel` instance and add safety settings to its config
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* generationConfig is optional */ null,
                  Collections.singletonList(harassmentSafety)
                );
);

// ...

含有多個安全性設定的範例：


SafetySetting harassmentSafety = new SafetySetting(HarmCategory.HARASSMENT,
HarmBlockThreshold.ONLY_HIGH);

SafetySetting hateSpeechSafety = new SafetySetting(HarmCategory.HATE_SPEECH,
HarmBlockThreshold.MEDIUM_AND_ABOVE);

// Create an `GenerativeModel` instance and add safety settings to its config
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* generationConfig is optional */ null,
                  List.of(harassmentSafety, hateSpeechSafety)
                );
);

// ...

Web

建立 GenerativeModel 執行個體時，您會設定 SafetySettings。

以下是包含一個安全設定的範例：


import { HarmBlockThreshold, HarmCategory, getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// ...

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

const safetySettings = [
  {
    category: HarmCategory.HARM_CATEGORY_HARASSMENT,
    threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
  },
];

// Create a `GenerativeModel` instance and add safety settings to its config
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

含有多個安全性設定的範例：


import { HarmBlockThreshold, HarmCategory, getAI, getGenerativeModel, GoogleAIBackend } from "firebase/ai";

// ...

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

const safetySettings = [
  {
    category: HarmCategory.HARM_CATEGORY_HARASSMENT,
    threshold: HarmBlockThreshold.BLOCK_ONLY_HIGH,
  },
  {
    category: HarmCategory.HARM_CATEGORY_HATE_SPEECH,
    threshold: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE,
  },
];

// Create a `GenerativeModel` instance and add safety settings to its config
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

Dart

建立 GenerativeModel 執行個體時，請設定 SafetySettings。

以下是包含一個安全設定的範例：


// ...

final safetySettings = [
  SafetySetting(HarmCategory.harassment, HarmBlockThreshold.high)
];

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance and add safety settings to its config
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

含有多個安全性設定的範例：


// ...

final safetySettings = [
  SafetySetting(HarmCategory.harassment, HarmBlockThreshold.high),
  SafetySetting(HarmCategory.hateSpeech, HarmBlockThreshold.high),
];

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance and add safety settings to its config
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

Unity

建立 GenerativeModel 執行個體時，您會設定 SafetySettings。

以下是包含一個安全設定的範例：


// ...

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance and add safety settings to its config
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());
var model = ai.GetGenerativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: new SafetySetting[] {
    new SafetySetting(HarmCategory.Harassment, SafetySetting.HarmBlockThreshold.OnlyHigh)
  }
);

// ...

含有多個安全性設定的範例：


// ...

var harassmentSafety = new SafetySetting(HarmCategory.Harassment, SafetySetting.HarmBlockThreshold.OnlyHigh);
var hateSpeechSafety = new SafetySetting(HarmCategory.HateSpeech, SafetySetting.HarmBlockThreshold.MediumAndAbove);

// Initialize the Vertex AI Gemini API backend service
// Create a `GenerativeModel` instance and add safety settings to its config
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());
var model = ai.GetGenerativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: new SafetySetting[] { harassmentSafety, hateSpeechSafety }
);

// ...

Imagen 型號的安全性設定

按一下您的 Gemini API 供應商，即可在本頁查看供應商專屬內容和程式碼。

如要瞭解 Imagen 型別支援的所有安全設定和可用值，請參閱 Google Cloud 說明文件。

Swift

建立 ImagenModel 執行個體時，您會設定 ImagenSafetySettings。


import FirebaseAI

// Initialize the Gemini Developer API backend service
// Create an `ImagenModel` instance and add safety settings to its config
let model = FirebaseAI.firebaseAI(backend: .googleAI()).imagenModel(
  modelName: "IMAGEN_MODEL_NAME",
  safetySettings: ImagenSafetySettings(
    safetyFilterLevel: .blockLowAndAbove,
    personFilterLevel: .allowAdult
  )
)

// ...

Kotlin

建立 ImagenModel 執行個體時，您會設定 ImagenSafetySettings。


// Initialize the Vertex AI Gemini API backend service
// Create an `ImagenModel` instance and add safety settings to its config
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).imagenModel(
  modelName = "IMAGEN_MODEL_NAME",
  safetySettings = ImagenSafetySettings(
    safetyFilterLevel = ImagenSafetyFilterLevel.BLOCK_LOW_AND_ABOVE,
    personFilterLevel = ImagenPersonFilterLevel.BLOCK_ALL
  )
)

// ...

Java

建立 ImagenModel 執行個體時，您會設定 ImagenSafetySettings。


// Create an `ImagenModel` instance and add safety settings to its config
ImagenModelFutures model = ImagenModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .imagenModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* imageGenerationConfig */ null);
);

// ...

Web

建立 ImagenModel 執行個體時，您會設定 ImagenSafetySettings。


// ...

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create an `ImagenModel` instance and add safety settings to its config
const model = getImagenModel(
  ai,
  {
    model: "IMAGEN_MODEL_NAME",
    safetySettings: {
      safetyFilterLevel: ImagenSafetyFilterLevel.BLOCK_LOW_AND_ABOVE,
      personFilterLevel: ImagenPersonFilterLevel.ALLOW_ADULT,
    }
  }
);

// ...

Dart

建立 ImagenModel 執行個體時，請設定 ImagenSafetySettings。


// ...

// Initialize the Gemini Developer API backend service
// Create an `ImagenModel` instance and add safety settings to its config
final model = FirebaseAI.googleAI().imagenModel(
  model: 'IMAGEN_MODEL_NAME',
  safetySettings: ImagenSafetySettings(
    ImagenSafetyFilterLevel.blockLowAndAbove,
    ImagenPersonFilterLevel.allowAdult,
  ),
);

// ...

Unity

Unity 目前不支援使用 Imagen，但請稍後再回來看看！

其他控管內容產生作業的選項

進一步瞭解提示設計，以便影響模型產生符合您需求的輸出內容。
設定模型參數，控制模型產生回覆的方式。對於 Gemini 模型，這些參數包括輸出符記數量上限、溫度、topK 和 topP。對於 Imagen 模型，這些參數包括顯示比例、人物生成、浮水印等。
設定系統指令，即可引導模型的行為。這項功能就像是前言，可在模型公開給使用者進一步指示之前新增。
傳遞回覆結構定義和提示，即可指定特定輸出結構定義。這項功能最常用於產生 JSON 輸出內容，但也可以用於分類作業 (例如希望模型使用特定標籤或標記時)。

瞭解並使用安全性設定 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

Gemini 型號的安全性設定

Swift

Kotlin

Java

Web

Dart

Unity

Imagen 型號的安全性設定

Swift

Kotlin

Java

Web

Dart

Unity

其他控管內容產生作業的選項

瞭解並使用安全性設定
透過集合功能整理內容你可以依據偏好儲存及分類內容。