Cloudera Docs

Launching RAG Studio within a project

RAG Studio is compatible with Cloudera AI Inference service, AWS Bedrock, and Azure OpenAI, enabling you to select different LLM and embedding models tailored to your specific needs.

RAG Studio integrates with three major enterprise inference serviceservices:

  • AWS Bedrock: It provides scalable cloud-based inference.
  • Cloudera AI Inference Service: It offers enterprise-grade deployment options.

  • Azure OpenAI: It enables the use of natural language processing models provided by OpenAI.

  • Host names: For air-gapped installations that use a proxy setup, it is essential to whitelist the necessary URLs in your firewall rules. For a list of hostnames to whitelist, see Host names and endpoints required for AI Studios .
  1. In the Cloudera console, click the Cloudera AI tile.

    The Cloudera AI Workbenches page displays.

  2. Click on the name of the workbench.

    The workbenches Home page displays.

  3. Click Projects, and then click New Project to create a new project.

    In the left navigation pane, the new AI Studios option is displayed.

  4. Click AI Studios.
  5. Click the Launch button in the RAG Studio box. The Configure Studio: RAG Studio page is displayed.
  6. Select the Runtime version.
  7. Click Launch AI Studio.

    The AI Studio Setup Steps page is displayed.

    After launching, you can view the list of tasks being executed as part of the AI studio deployment.