Google Vertex AI¶

Configure HolmesGPT to use Google Vertex AI with Gemini models.

Setup¶

Create a Google Cloud project with Vertex AI API enabled
Create a service account with Vertex AI User role
Download the JSON key file

Configuration¶

export VERTEXAI_PROJECT="your-project-id"
export VERTEXAI_LOCATION="us-central1"
export GOOGLE_APPLICATION_CREDENTIALS="path/to/service-account-key.json"

holmes ask "what pods are failing?" --model="vertex_ai/<your-vertex-model>"

Using CLI Parameters¶

You can also pass credentials directly as command-line parameters:

holmes ask "what pods are failing?" --model="vertex_ai/<your-vertex-model>" --api-key="your-service-account-key"

Additional Resources¶

HolmesGPT uses the LiteLLM API to support Google Vertex AI provider. Refer to LiteLLM Google Vertex AI docs for more details.