Note: This article covers adding a pre-configured LLM provider or model to the platform. To learn how to add a custom model, see Add a Custom Model to the Platform.
Add a Model from an Existing LLM Provider
Click Model Configurations in the navigation panel.
The Model Configurations screen opens. Click the Global or Groups tab.
Note: To add a chatbot to a pre-configured model or provider, see TBD.
The list of pre-configured LLM providers appears. Each tile displays one provider. Click Add on a tile to add a model supported by that provider.
The provider window opens. Enter the required information, then click Test and Connect.
Add an LLM Provider
From the Global or Groups screen, click Add other providers. The Other models screen opens. Enter a provider display name in the text box. Use the drop-down list to review existing provider display names. Scroll to the next section on the screen.
Connect to Model Provider
Open the Select config drop-down list and select the provider.
Enter a name for the model in the Model Display Name text box. Scroll to the next section on the screen.
Secrets
If the 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. Scroll to the next section on the screen.
Input
The Inputs and Configuration windows display the model parameters and outputs, respectively, for the identified model. Enter changes to the model parameters via the Input window.
Configuration
Enter changes to the model configuration via the Configuration window.
Model Configuration Error Messaging
If an error occurs when configuring a model, the full error message appears beneath the configuration form. This provides more context about what went wrong and allows users to keep the error in view until it has been fixed.
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.
