了解和使用安全设置

您可以使用安全设置来调整收到可能被视为有害的回答的可能性。默认情况下，安全设置会屏蔽在所有维度中不安全概率为中等和/或较高的内容。

跳转到Gemini安全设置 跳转到Imagen安全设置

适用于 Gemini 模型的安全设置

如需详细了解 Gemini 模型的安全设置，请参阅 Google Cloud 文档。

Swift

您可以在创建 GenerativeModel 实例时配置 SafetySettings。

包含一个安全设置的示例：

// ...

let model = vertex.generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [
    SafetySetting(harmCategory: .harassment, threshold: .blockOnlyHigh)
  ]
)

// ...

包含多个安全设置的示例：

// ...

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

let model = vertex.generativeModel(
  modelName: "GEMINI_MODEL_NAME",
  safetySettings: [harassmentSafety, hateSpeechSafety]
)

// ...

Kotlin

您可以在创建 GenerativeModel 实例时配置 SafetySettings。

包含一个安全设置的示例：

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

val generativeModel = Firebase.vertexAI.generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    safetySettings = listOf(
        SafetySetting(HarmCategory.HARASSMENT, HarmBlockThreshold.ONLY_HIGH)
    )
)

// ...

包含多个安全设置的示例：

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)

val generativeModel = Firebase.vertexAI.generativeModel(
    modelName = "GEMINI_MODEL_NAME",
    safetySettings = listOf(harassmentSafety, hateSpeechSafety)
)

// ...

Java

您可以在创建 GenerativeModel 实例时配置 SafetySettings。

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

GenerativeModel gm = FirebaseVertexAI.getInstance().generativeModel(
    "GEMINI_MODEL_NAME",
    /* generationConfig is optional */ null,
    Collections.singletonList(harassmentSafety)
);

GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// ...

包含多个安全设置的示例：

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

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

GenerativeModel gm = FirebaseVertexAI.getInstance().generativeModel(
    "GEMINI_MODEL_NAME",
    /* generationConfig is optional */ null,
    List.of(harassmentSafety, hateSpeechSafety)
);

GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// ...

Web

您可以在创建 GenerativeModel 实例时配置 SafetySettings。

包含一个安全设置的示例：

import { HarmBlockThreshold, HarmCategory, getGenerativeModel } from "firebase/vertexai";

// ...

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

const model = getGenerativeModel(vertex, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

包含多个安全设置的示例：

import { HarmBlockThreshold, HarmCategory, getGenerativeModel } from "firebase/vertexai";

// ...

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

const model = getGenerativeModel(vertex, { model: "GEMINI_MODEL_NAME", safetySettings });

// ...

Dart

您可以在创建 GenerativeModel 实例时配置 SafetySettings。

包含一个安全设置的示例：

// ...

final safetySettings = [
  SafetySetting(HarmCategory.harassment, HarmBlockThreshold.high)
];
final model = FirebaseVertexAI.instance.generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

包含多个安全设置的示例：

// ...

final safetySettings = [
  SafetySetting(HarmCategory.harassment, HarmBlockThreshold.high),
  SafetySetting(HarmCategory.hateSpeech, HarmBlockThreshold.high),
];
final model = FirebaseVertexAI.instance.generativeModel(
  model: 'GEMINI_MODEL_NAME',
  safetySettings: safetySettings,
);

// ...

适用于 Imagen 模型的安全设置

如需了解 Imagen 模型的所有受支持的安全设置及其可用值，请参阅 Google Cloud 文档。

Swift

您可以在创建 ImagenModel 实例时配置 ImagenSafetySettings。

// Initialize the Vertex AI service
let vertex = VertexAI.vertexAI()

// Create an `ImagenModel` instance
let model = vertex.imagenModel(
  modelName: "IMAGEN_MODEL_NAME",
  // Configure image generation safety settings for the model
  safetySettings: ImagenSafetySettings(
    safetyFilterLevel: .blockLowAndAbove,
    personFilterLevel: .allowAdult
  )
)

// ...

Kotlin

您可以在创建 ImagenModel 实例时配置 ImagenSafetySettings。

// Create an `ImagenModel` instance
val imagenModel = Firebase.vertexAI.imagenModel(
  modelName = "IMAGEN_MODEL_NAME",
  // Configure image generation safety settings for the model
  safetySettings = ImagenSafetySettings(
    safetyFilterLevel = ImagenSafetyFilterLevel.BLOCK_LOW_AND_ABOVE,
    personFilterLevel = ImagenPersonFilterLevel.BLOCK_ALL
  )
)

// ...

Java

您可以在创建 ImagenModel 实例时配置 ImagenSafetySettings。

// Create an `ImagenModel` instance
ImagenModel imagenModel =
    FirebaseVertexAI.getInstance().imagenModel(
            /* modelName */ "IMAGEN_MODEL_NAME",
            /* imageGenerationConfig */ null);
ImagenModelFutures model = ImagenModelFutures.from(imagenModel);

// ...

Web

您可以在创建 ImagenModel 实例时配置 ImagenSafetySettings。

// Create an `ImagenModel` instance
const imagenModel = getImagenModel(
  vertexAI,
  {
    model: "IMAGEN_MODEL_NAME",
    // Configure image generation safety settings for the model
    safetySettings: {
      safetyFilterLevel: ImagenSafetyFilterLevel.BLOCK_LOW_AND_ABOVE,
      personFilterLevel: ImagenPersonFilterLevel.ALLOW_ADULT,
    }
  }
);

// ...

Dart

您可以在创建 ImagenModel 实例时配置 ImagenSafetySettings。

// Create an `ImagenModel` instance
var model = FirebaseVertexAI.instance.imagenModel(
  model: 'IMAGEN_MODEL_NAME',
  // Configure image generation safety settings for the model
  safetySettings: ImagenSafetySettings(
    ImagenSafetyFilterLevel.blockLowAndAbove,
    ImagenPersonFilterLevel.allowAdult,
  ),
);

// ...

用于控制内容生成的其他选项

  • 详细了解问题设计，以便影响模型生成符合您需求的输出。
  • 配置模型参数以控制模型如何生成回答。对于 Gemini 模型，这些参数包括输出 token 数上限、温度、topK 和 topP。 对于 Imagen 模型，这些包括宽高比、生成人物、添加水印等。
  • 设置系统指令，以引导模型的行为。此功能类似于您在模型接触到来自最终用户的任何进一步指令之前添加的“序言”。
  • 将回答架构与提示一起传递，以指定特定的输出架构。此功能最常用于生成 JSON 输出，但也可以用于分类任务（例如，当您希望模型使用特定标签或标记时）。