# Class SafetySettings (2.6.0)

2.6.0 (latest) 2.1.0 2.0.0 1.43.0 1.42.0 1.41.1 1.40.0 1.39.0 1.38.0 1.37.0 1.36.0 1.35.0 1.34.1 1.33.0 1.32.1 1.31.1 1.30.1 1.29.0 1.28.0 1.27.0 1.26.0 1.25.0 1.24.0 1.23.1 1.22.0 1.21.0 1.20.1 1.19.0 1.18.0 1.17.1 1.16.0 1.15.0 1.14.1 1.13.5 1.12.1 1.11.0 1.10.0 1.9.1 1.8.0 1.7.0 1.6.0 1.5.0 1.4.0 1.3.2 1.2.0 1.1.1 1.0.0 0.8.2 0.7.1 0.6.0 0.5.0 0.4.1 0.3.0 0.2.0 0.1.1

    SafetySettings(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Settings for Generative Safety.

| ## Attributes ||
|---|---|
| **Name** | **Description** |
| `default_banned_phrase_match_strategy` | `https://docs.cloud.google.com/python/docs/reference/dialogflow-cx/latest/google.cloud.dialogflowcx_v3.types.SafetySettings.PhraseMatchStrategy` Optional. Default phrase match strategy for banned phrases. |
| `banned_phrases` | `MutableSequence[https://docs.cloud.google.com/python/docs/reference/dialogflow-cx/latest/google.cloud.dialogflowcx_v3.types.SafetySettings.Phrase]` Banned phrases for generated text. |
| `rai_settings` | `https://docs.cloud.google.com/python/docs/reference/dialogflow-cx/latest/google.cloud.dialogflowcx_v3.types.SafetySettings.RaiSettings` Optional. Settings for Responsible AI checks. |
| `default_rai_settings` | `https://docs.cloud.google.com/python/docs/reference/dialogflow-cx/latest/google.cloud.dialogflowcx_v3.types.SafetySettings.RaiSettings` Optional. Immutable. Default RAI settings to be annotated on the agent, so that users will be able to restore their RAI configurations to the default settings. Read-only field for the API proto only. |
| `prompt_security_settings` | `https://docs.cloud.google.com/python/docs/reference/dialogflow-cx/latest/google.cloud.dialogflowcx_v3.types.SafetySettings.PromptSecuritySettings` Optional. Settings for prompt security checks. |

## Classes

### Phrase

    Phrase(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Text input which can be used for prompt or banned phrases.

### PhraseMatchStrategy

    PhraseMatchStrategy(value)

Strategy for matching phrases.

### PromptSecuritySettings

    PromptSecuritySettings(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Settings for prompt security checks.

### RaiSettings

    RaiSettings(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Settings for Responsible AI.