Skip to main content

​
Vertex AI Configuration

Vertex AI is Google Cloud’s managed platform for running Gemini and other foundation models. Choose it over the direct Gemini provider when you need requests billed to a Google Cloud project, kept inside a specific region, or governed by your existing IAM policies. Vertex AI authenticates with a service account JSON key that you upload in PipesHub. It does not use an API key, and it does not read credentials from environment variables.

​
Before you start

  1. In the Google Cloud Console, select or create a project.
  2. Enable the Vertex AI API for that project.
  3. Go to IAM & Admin → Service Accounts and create a service account.
  4. Grant it the Vertex AI User role, or a role that includes it.
  5. Open the service account, go to the Keys tab, and create a new JSON key. The file downloads once — keep it safe.

​
Required Fields

​
GCP Project ID *

The Google Cloud project that hosts Vertex AI. This must match the project_id field inside your service account JSON file.

​
Service Account JSON *

Upload the JSON key file you created above. PipesHub validates the file before saving and will reject it if:
  • the file is not valid JSON,
  • it is missing type, project_id, or private_key, or
  • its type field is not service_account — which usually means an OAuth client secret was uploaded by mistake.
The key is stored encrypted and is used only to authenticate requests to Vertex AI.

​
Model Name *

The Vertex AI model to call, for example gemini-2.5-flash or gemini-2.5-pro. Check Google’s Vertex AI model reference for the current list, and confirm the model is available in the region you chose.

​
Optional Fields

​
Region

The Vertex AI region requests are sent to, for example us-central1 or europe-west4. Default: us-central1 Pick a region close to your users for lower latency, or one that satisfies your data residency requirements. Not every model is offered in every region.

​
Model Friendly Name

A label shown in the PipesHub interface so you can tell several configurations apart. If you leave it blank, the model name is used.

​
Context Length

The size of the model’s context window, in tokens. PipesHub uses this number to decide how much retrieved content it can safely include in a prompt. Set it to the value published for your model. If you leave it blank, PipesHub uses a conservative default.

​
Is Multimodal

Turn this on if the model accepts images as well as text. It is on by default.

​
Is Reasoning

Turn this on if the model performs extended reasoning before answering. It is on by default.

​
Troubleshooting

“Permission denied”. The service account is missing the Vertex AI User role, or the Vertex AI API is not enabled on the project. “Model not found” in a specific region. The model is not offered there. Try us-central1, which carries the widest selection. The upload is rejected. You uploaded an OAuth client secret rather than a service account key. Open the file and confirm "type": "service_account".