0.20.1 (latest) 0.20.0 0.19.0 0.18.0 0.17.0 0.16.0 0.15.0 0.14.0 0.13.12 0.12.3 0.11.14 0.10.0 0.9.1 0.8.1 0.7.0 0.6.0 0.5.0 0.4.1 0.3.1 0.2.1 0.1.1

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

Customer-defined policy for the assistant.

| ## Attributes ||
|---|---|
| **Name** | **Description** |
| `banned_phrases` | `MutableSequence[https://docs.cloud.google.com/python/docs/reference/discoveryengine/latest/google.cloud.discoveryengine_v1beta.types.Assistant.CustomerPolicy.BannedPhrase]` Optional. List of banned phrases. |
| `model_armor_config` | `https://docs.cloud.google.com/python/docs/reference/discoveryengine/latest/google.cloud.discoveryengine_v1beta.types.Assistant.CustomerPolicy.ModelArmorConfig` Optional. Model Armor configuration to be used for sanitizing user prompts and assistant responses. |

## Classes

### BannedPhrase

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

Definition of a customer-defined banned phrase. A banned
phrase is not allowed to appear in the user query or the LLM
response, or else the answer will be refused.

### ModelArmorConfig

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

Configuration for customer defined Model Armor templates to
be used for sanitizing user prompts and assistant responses.