Skip to main content
Add a Custom Model

Learn how how to set up custom large language models to be used within CalypsoAI.

Updated over a week ago

The CalypsoAI platform enables the use of custom models, such as internal models, open-source models, and others via the Custom Model Configuration feature.

Super Admins can configure custom models for managed use globally across the organization. Group Admins can configure custom models for use by the groups they manage.

Steps

Click Model Configurations in the navigation panel.

Depending on who will have access to the model, click the Global or Groups link. If configuring the model for a group, select the group name from the drop-down list.

Click Add other providers.

Select a provider from the Provider display name drop-down list or enter a new provider in the field to create a new set of models.

Optional Steps & Attributes

  • Example Configuration (Recommended): Open the Select config drop-down list and select the provider. Enter a name for the model in the Model display name text box. The Inputs and Configuration windows will display the model parameters and outputs, respectively.

Secrets: If a provider requires a secret, such as an API key, to be provided via an authentication header, we can supply this securely through the Secret section in the Configuration window and paste it into the Key field. The value of the key will be displayed in the Value field.

  • Input: Enter changes to the model parameters via the Input window.

  • Configuration: Enter changes to the model configuration via the Configuration window.

Finalize Changes

When the preferred changes have been made, click Test and Connect. An error message appears if the test and/or connection was not successful.

Please note that the CalypsoAI Team is available for assistance with configuration changes for custom models.

Did this answer your question?