Connect your custom embedding model with the Generative AI application

Integrate your custom embedding model with a capability definition to help the Generative AI application understand your data better and deliver more relevant, tailored responses.

Before you begin

Role required: admin

Procedure

1. Navigate to All, and then enter sys_generative_ai_config.list in the filter to go to the Generative AI Configurations [sys_generative_ai_config] table.
2. Select New.
3. Verify that Definition Table field is prepopulated with sys_one_extend_capability_definition.
4. In the Definition field, select the search icon ()to select the definition document.
   1. In the Table name field, select One API System Executor [one_api_system_executor].
   2. In the Document field, select the OneExtend capability definition that you want to integrate with the embedding model.
   3. Select OK.
5. In the Model field, select an embedding model of your choice.
6. Select the Active option.
7. Populate the Additional Configurations field.
   • In the Name field, enter resource _path.
   • In the Value field, enter the end point path for the connection alias URL that you created for your embedding model.

     For example, /text-embedding-3-large/embeddings?api-version=2023-05-15.

8. Select Submit.