Generative AI model configuration form

The Generative AI model configuration form contains information about a custom embedding model that your AI Search Retrieval Augmented Generation (RAG) application uses to generate embeddings for semantic indexing. Use this form when creating or modifying a custom embedding model.

For details on creating or modifying a custom embedding model, see Create a custom embedding model.

Table 1. Generative AI Model Configuration

Field	Description
Active	Option to activate the embedding model.
Model	Unique name for the embedding model.
Domain	Domain that you want to associate the model with. For example, AI Search RAG.
External	Option to make this model to be used externally.
Connection and Credential Alias	Connection and credential alias that you created on your own for the custom embedding model.
Supported Language	Languages that are supported for this model. By default, the supported language is English. The current available languages for your third party supported custom embedding model are as follows: Brazilian Portuguese, Chinese, Chinese (traditional), Dutch, English, Finnish, French, French Canadian, German, Estonian, Italian, Japanese, Korean, Norwegian, Arabic, Pseudo, Polish, Portuguese, Russian, Turkish, Hebrew, Hungarian, Czech, Thai, Spanish, and Swedish.
Model Type	Type of model that is used for a specific purpose. For example, Embedding Model.
Vector Dimension	Vector dimension value that shouldn't exceed 4096. This field appears only if you have selected Embedding Model in the Model Type field.
Application	Name of the application that this model is configured for.
Provider	Name of the generative AI provider mapping. For example, Generic Embedder.
Max Tokens	Maximum limit to generate embeddings.