Cloudera Docs

Registering models in Agent Studio

Register Large Language Models (LLMs) in Agent Studio to connect to model providers and establish a default model for agent operations.

  1. In the Cloudera console, click the Cloudera AI tile.
    The Cloudera AI Home page is displayed.
  2. Click on the name of the workbench.
    The Cloudera AI Workbench Home page is displayed.
  3. In the left navigation pane, click AI Studios.
    The AI Studios page is displayed.
  4. On the Agent Studio tile, click Open.
    The Agent Studio page is displayed.
  5. Click the LLMs tab.
    The Models window is displayed.
  6. Click Register New Model.
    The Register Model window is displayed.
    Figure 1. Register Model window
  7. Specify the following fields:
    1. Model Provider - Select one of the following supported providers:
      • Cloudera AI Inference
      • OpenAI
      • Azure OpenAI
      • Google Gemini
      • Anthropic
      • AWS Bedrock
      • OpenAI compatible providers - This option allows you to connect to any model endpoint that adheres to the OpenAI API specifications.
    2. Model Alias - Enter a unique name for your model to reference it within the studio.
    3. Model Identifier - Enter the identifier corresponding to the selected Model Provider.
    4. API Base - Enter the base URL for the model API.
    5. API Key - Enter the API key for accessing the model service.
    6. Default Model - Click the Set as Default toggle to set this as the default model for the studio.
  8. Click on Register.