Memahami dan menggunakan setelan keamanan

Anda dapat menggunakan setelan keamanan untuk menyesuaikan kemungkinan mendapatkan respons yang dapat dianggap berbahaya. Secara default, setelan keamanan memblokir konten dengan probabilitas sedang dan/atau tinggi sebagai konten tidak aman di semua dimensi.

Langsung ke setelan keamanan Gemini Langsung ke setelan keamanan Imagen

Setelan keamanan untuk model Gemini

Klik penyedia Gemini API untuk melihat konten dan kode khusus penyedia di halaman ini.

Pelajari lebih lanjut setelan keamanan untuk model Gemini dalam dokumentasi Gemini Developer API.

Swift

Anda mengonfigurasi SafetySettings saat membuat instance GenerativeModel.

Contoh dengan satu setelan keamanan:


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)
  ]
)

// ...

Contoh dengan beberapa setelan keamanan:


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

Anda mengonfigurasi SafetySettings saat membuat instance GenerativeModel.

Contoh dengan satu setelan keamanan:


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)
    )
)

// ...

Contoh dengan beberapa setelan keamanan:


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

Anda mengonfigurasi SafetySettings saat membuat instance GenerativeModel.


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)
                );
);

// ...

Contoh dengan beberapa setelan keamanan:


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

Anda mengonfigurasi SafetySettings saat membuat instance GenerativeModel.

Contoh dengan satu setelan keamanan:


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 });

// ...

Contoh dengan beberapa setelan keamanan:


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

Anda mengonfigurasi SafetySettings saat membuat instance GenerativeModel.

Contoh dengan satu setelan keamanan:


// ...

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,
);

// ...

Contoh dengan beberapa setelan keamanan:


// ...

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

Anda mengonfigurasi SafetySettings saat membuat instance GenerativeModel.

Contoh dengan satu setelan keamanan:


// ...

// 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)
  }
);

// ...

Contoh dengan beberapa setelan keamanan:


// ...

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 }
);

// ...

Setelan keamanan untuk model Imagen

Klik penyedia Gemini API untuk melihat konten dan kode khusus penyedia di halaman ini.

Pelajari semua setelan keamanan yang didukung dan nilai yang tersedia untuk model Imagen dalam dokumentasi Google Cloud.

Swift

Anda mengonfigurasi ImagenSafetySettings saat membuat instance ImagenModel.


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

Anda mengonfigurasi ImagenSafetySettings saat membuat instance ImagenModel.


// 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

Anda mengonfigurasi ImagenSafetySettings saat membuat instance ImagenModel.


// 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

Anda mengonfigurasi ImagenSafetySettings saat membuat instance ImagenModel.


// ...

// 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

Anda mengonfigurasi ImagenSafetySettings saat membuat instance ImagenModel.


// ...

// 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

Penggunaan Imagen belum didukung untuk Unity, tetapi periksa kembali nanti.

Opsi lain untuk mengontrol pembuatan konten

  • Pelajari lebih lanjut desain perintah agar Anda dapat memengaruhi model untuk menghasilkan output yang spesifik untuk kebutuhan Anda.
  • Konfigurasikan parameter model untuk mengontrol cara model menghasilkan respons. Untuk model Gemini, parameter ini mencakup token output maksimum, suhu, topK, dan topP. Untuk model Imagen, hal ini mencakup rasio aspek, pembuatan orang, watermark, dsb.
  • Tetapkan petunjuk sistem untuk mengarahkan perilaku model. Fitur ini seperti preamble yang Anda tambahkan sebelum model diekspos ke petunjuk lebih lanjut dari pengguna akhir.
  • Teruskan skema respons bersama dengan perintah untuk menentukan skema output tertentu. Fitur ini paling sering digunakan saat membuat output JSON, tetapi juga dapat digunakan untuk tugas klasifikasi (seperti saat Anda ingin model menggunakan label atau tag tertentu).