瞭解並使用安全性設定

您可以透過安全設定，調整收到可能有害回覆的機率。根據預設，只要內容屬於任何不安全維度/類別的機率為中等或較高，安全設定就會加以封鎖。

跳至Gemini安全設定 跳至Imagen安全設定

Gemini 模型安全性設定

按一下 Gemini API 供應商，即可在這個頁面查看供應商專屬內容和程式碼。 Gemini Developer API Vertex AI Gemini API

如要進一步瞭解 Gemini 模型適用的安全設定，請參閱Gemini Developer API說明文件。

注意： 如果您使用 Gemini Live API，安全設定就不適用。

Swift

建立 GenerativeModel 執行個體時，請設定 SafetySettings。

一個安全設定的範例：

import FirebaseAI

// Specify the safety settings as part of creating the `GenerativeModel` instance
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [
    SafetySetting(harmCategory: .harassment, threshold: .blockOnlyHigh)
  ]
)

// ...

多項安全性設定的範例：

import FirebaseAI

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
let model = FirebaseAI.firebaseAI(backend: .googleAI()).generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [harassmentSafety, hateSpeechSafety]
)

// ...

Kotlin

建立 GenerativeModel 執行個體時，請設定 SafetySettings。

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    safetySettings = listOf(
        SafetySetting(HarmCategory.HARASSMENT, HarmBlockThreshold.ONLY_HIGH)
    )
)

// ...

多項安全性設定的範例：

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)

// Specify the safety settings as part of creating the `GenerativeModel` instance
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，請設定 SafetySettings。

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
GenerativeModelFutures model = GenerativeModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .generativeModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* generationConfig is optional */ null,
                  Collections.singletonList(harassmentSafety)
                );
);

// ...

多項安全性設定的範例：

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

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
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，請設定 SafetySettings。

一個安全設定的範例：

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

// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

多項安全性設定的範例：

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

// ...

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,
  },
];

// Specify the safety settings as part of creating the `GenerativeModel` instance
const model = getGenerativeModel(ai, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

Dart

建立 GenerativeModel 執行個體時，請設定 SafetySettings。

一個安全設定的範例：

// ...

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

多項安全性設定的範例：

// ...

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
final model = FirebaseAI.googleAI().generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

Unity

建立 GenerativeModel 執行個體時，請設定 SafetySettings。

一個安全設定的範例：

// ...

// Specify the safety settings as part of creating the `GenerativeModel` instance
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)
  }
);

// ...

多項安全性設定的範例：

// ...

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

// Specify the safety settings as part of creating the `GenerativeModel` instance
var ai = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI());
var model = ai.GetGenerativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: new SafetySetting[] { harassmentSafety, hateSpeechSafety }
);

// ...

Imagen 模型安全性設定

按一下 Gemini API 供應商，即可在這個頁面查看供應商專屬內容和程式碼。 Gemini Developer API Vertex AI Gemini API

如要瞭解所有支援的安全設定及其可用值，請參閱 Imagen 模型適用的 Google Cloud 說明文件。

Swift

建立 ImagenModel 執行個體時，請設定 ImagenSafetySettings。

import FirebaseAI

// Specify the safety settings as part of creating the `ImagenModel` instance
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，請設定 ImagenSafetySettings。

// Specify the safety settings as part of creating the `ImagenModel` instance
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，請設定 ImagenSafetySettings。

// Specify the safety settings as part of creating the `ImagenModel` instance
ImagenModelFutures model = ImagenModelFutures.from(
        FirebaseAI.getInstance(GenerativeBackend.googleAI())
                .imagenModel(
                  /* modelName */ "IMAGEN_MODEL_NAME",
                  /* imageGenerationConfig */ null);
);

// ...

Web

建立 ImagenModel 執行個體時，請設定 ImagenSafetySettings。

// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Specify the safety settings as part of creating the `ImagenModel` instance
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。

// ...

// Specify the safety settings as part of creating the `ImagenModel` instance
final model = FirebaseAI.googleAI().imagenModel(
  model: 'IMAGEN_MODEL_NAME',
  safetySettings: ImagenSafetySettings(
    ImagenSafetyFilterLevel.blockLowAndAbove,
    ImagenPersonFilterLevel.allowAdult,
  ),
);

// ...

Unity

Unity 目前尚未支援使用 Imagen，但這項功能即將推出，敬請期待！

控制內容生成的其他選項

• 進一步瞭解提示設計，讓模型根據您的需求生成輸出內容。
• 設定模型參數，控制模型生成回覆的方式。如果是 Gemini 模型，這些參數包括輸出詞元數量上限、隨機性參數、TopK 和 TopP。如果是 Imagen 模型，則包括長寬比、人物生成、浮水印等。
• 設定系統指令，引導模型行為。這項功能就像前言，您可以在模型接收使用者提供的任何後續指令前新增前言。
• 連同提示傳遞回覆結構定義，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，但也可用於分類工作 (例如想讓模型使用特定標籤)。