Skip to content

On-premise users: click in-app to access the full platform documentation for your version of DataRobot.

Use Google Gemini with DataRobot

Access this AI accelerator on GitHub

DataRobot allows you to leverage LLMs proposed by hyperscalers via the Custom Model Workshop.

This AI Accelerator demonstrates how to implement a Streamlit application based on the Google Gemini LLM and host it on the DataRobot platform. The user of this AI Accelerator is expected to be familiar with the custom model deployment process and custom metrics creation in DataRobot as well as with Google Vertex AI.

This accelerator requires the service account for the Vertex AI project. The following steps outline the accelerator workflow.

  1. Create credentials with a GCP service account (base64 encoded).

  2. Optional. Deploy a guard model from the DataRobot global models.

  3. Deploy a text model (Gemini Pro).

  4. Deploy a multimodal model (Gemini Pro Vision).

  5. Create custom metrics for both deployments (text and multimodal).

  6. Deploy a Streamlit app to DataRobot.

Updated April 26, 2024