On This Page

Home / Cribl Copilot/ Custom AI Providers/Configure Custom AI Providers

Configure Custom AI Providers

The Custom AI Providers feature enables a Bring Your Own Model (BYOM) approach, letting you connect your own large language model (LLM) backend to Cribl AI features in Cribl Copilot instead of using the default Cribl-managed LLMs. This topic describes how to enable or disable a BYOM, edit it, and switch back to the Cribl-managed LLM provider defaults.

Prerequisites
​

Before you start, make sure that:

  • You have Owner or Admin permissions for the on-prem deployment or Cribl.Cloud Workspace.
  • Cribl Copilot is enabled for your deployment (Cribl.Cloud or on-prem).
  • You have decided which Cribl Copilot features you want enabled or disabled in AI Settings.
  • For on-prem deployments, you are configuring your LLM on the Leader Node (not on a Worker/Edge Node), and the Leader Node has network access to your LLM endpoints.
  • You have at least one supported LLM account, with:
    • A deployment identifier (such as the Deployment URL).
    • Credentials (for example, an API key or cloud access keys) with permission to invoke the model.

Open AI Settings
​

  1. Sign in to Cribl:
    • Cribl.Cloud: Open the Workspace where you want to configure Copilot.
    • On-prem: Open the Leader.
  2. Select Settings (⚙).
  3. If available for your deployment, open the Global tab.
  4. Select AI Settings.

On the AI Settings page you can:

  • Enable or disable Cribl Copilot.
  • See whether a custom AI provider is configured for the deployment.
  • Open the custom AI provider configuration modal to add, edit, or stop using your own LLM.

Add a Custom AI Provider
​

You can start the configuration from either of these entry points on the AI Settings page:

  • The Try it! button in the custom AI providers banner.
  • The Use Custom AI Provider button.

In the Custom AI provider configuration modal:

  1. Enter a custom AI provider ID and optional Description.
  2. Choose the provider type.
  3. Fill in the custom AI provider-specific fields:
    • Deployment URL
    • API Key
  4. (Recommended) Select Test Connection to determine whether the configuration is valid and reachable. If the test fails, adjust the values and test again.
  5. When all required fields are valid and (ideally) the test passes, select Save.

After you Save:

  • The configuration is stored in the Cribl secret store.
  • A Custom AI provider card appears at the top of AI Settings showing the provider name and type.
  • Supported Copilot capabilities in that deployment begin using your custom provider for new requests.

Edit an Existing Custom AI Provider
​

You can update a configured provider if any details change (for example, keys rotate or you want to switch models).

  1. Open Settings > AI Settings:
  2. Locate the Custom AI provider card at the top of the page.
  3. Select the gear icon (⚙) on that card.
  4. In the modal:
    • Update the relevant fields.
    • (Optional) Select Test Connection to validate the updated configuration.
  5. Select Save to apply the changes, or Cancel to discard them.

New AI requests use the updated configuration immediately.

Stop Using a Custom AI Provider
​

You might need to stop using your own LLM temporarily (for example, during an outage or while rotating credentials). The supported way to do this is to switch back to the default Cribl LLM provider.

  1. Go to Settings > AI settings.
  2. Select Use Cribl AI Provider.
  3. Confirm the change in the modal.

After confirmation, the deployment stops sending supported Copilot requests to your LLM.

If you want to use your own LLM again later, repeat the Add a Custom AI Provider steps and save a new configuration.

Troubleshoot common errors
​

If there is a problem with your custom AI provider, you may see:

  • Connection failures in the Test Connection step.
  • Provider-specific errors surfaced in Copilot features.

Typical issues include:

  • Invalid or expired credentials - Rotate or correct keys, then re-test.
  • Wrong Deployment URL - Ensure the model exists and is reachable where you’ve configured it.
  • Incorrect model or deployment name - Confirm the identifier exactly matches what your provider shows.
  • Rate limits or quotas exceeded - Check usage and raise limits or use a different deployment.

If you cannot resolve the issue quickly, use Use Cribl AI Provider on the AI Settings page to fall back to Cribl-managed LLMs while you investigate.