Apex Reference Guide
jNote: This release is in preview. Features described here don’t become generally available until the latest general availability date that Salesforce announces for this release. Before then, and where features are noted as beta, pilot, or developer preview, we can’t guarantee general availability within any particular time frame or at all. Make your purchase decisions only on the basis of generally available products and features.
ConnectApi.EinsteinLlmAdditionalConfigInput
Additional configuration information for the LLM provider.
| Property | Type | Description | Required or Optional | Available Version |
|---|---|---|---|---|
| additionalParameters | Map<String, ConnectApi.WrappedValue> | Map of parameters and values for the LLM provider. | Optional | 60.0 |
| applicationName | String | Name of the application. | Required | 60.0 |
| enablePiiMasking | Boolean | Specifies whether to mask personally identifiable information (PII) (true) or not (false). | Optional | 60.0 |
| frequencyPenalty | Double | Use to reduce the repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they already appeared in the prompt or in prior generations. Minimum value is 0.0. Maximum value is 1.0. | Optional | 60.0 |
| maxTokens | Integer | Maximum number of tokens to generate. | Optional | 60.0 |
| numGenerations | Integer | Number of generation requests to send to the LLM provider. | Optional | 60.0 |
| presencePenalty | Double | Use to reduce the repetitiveness of generated tokens. This value is similar to frequency penalty, except that this penalty is applied equally to all tokens that already appeared, regardless of their exact frequencies. Minimum value is 0.0, and maximum value is 1.0. | Optional | 60.0 |
| stopSequences | List<String> | Generated text is cut at the end of the earliest occurrence of a stop sequence. | Optional | 60.0 |
| temperature | Double | Sampling temperature to use. Higher values mean the model takes more risks. Lower temperatures mean that generations are less random. Minimum value is 0.0, and maximum value is 1.0 | Optional | 60.0 |