Understand and use safety settings


You can use safety settings to adjust the likelihood of getting responses that may be considered harmful. By default, safety settings block content with medium and/or high probability of being unsafe content across all dimensions.

Learn more about safety settings in the Google Cloud documentation.

You configure SafetySettings during initialization of the model. Here are some basic examples.

Here's how to set one safety setting:

Kotlin+KTX 

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

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

// ...

Java 

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

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

GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// ...

You can also set more than one safety setting:

Kotlin+KTX 

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

val harassmentSafety = SafetySetting(HarmCategory.HARASSMENT, BlockThreshold.ONLY_HIGH)

val hateSpeechSafety = SafetySetting(HarmCategory.HATE_SPEECH, BlockThreshold.MEDIUM_AND_ABOVE)

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

// ...

Java 

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

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

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

GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// ...

Other options to control content generation

  • Learn more about prompt design so that you can influence the model to generate output specific to your needs.
  • Configure model parameters to control how the model generates a response. These parameters include max output tokens, temperature, topK, and topP.
  • Set system instructions to steer the behavior of the model. This feature is like a "preamble" that you add before the model gets exposed to any further instructions from the end user.
  • Pass a response schema along with the prompt to specify a specific output schema. This feature is most commonly used when generating JSON output, but it can also be used for classification tasks (like when you want the model to use specific labels or tags).