Generate
vertex_ai.generate_content
ActionGoogle Cloudconnection required
Calls the Vertex generateContent endpoint for a Gemini model.
Invoke a Gemini foundation model on Google Vertex AI.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- OAuth 2.0
- Providers
- Google Vertex AI
- Secret shape
- {"client_id", "client_secret", "refresh_token"}
- Config it needs
- project_id, region
- Resolved by
- config.connection_id, else node.connection_id
Configuration
6 fields, 2 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.
| Field | Type | Required | Default | Constraints | Example |
|---|---|---|---|---|---|
project_id GCP project id (overrides connection). | string | No | — | — | — |
region Region (default us-central1, overrides connection). | string | No | — | — | — |
model Model id, e.g. gemini-1.5-flash-002. | string | Yes | — | — | — |
prompt User prompt. Supports {{ }}. | string | Yes | — | — | — |
system Optional system instruction. | string | No | — | — | — |
max_tokens Max output tokens. | number | No | 1024 | ≥ 1 | — |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"max_tokens": 1024
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
text | string | — |
output_tokens | number | — |
finish_reason | string | — |
{
"finish_reason": "",
"output_tokens": 0,
"text": ""
}Related Google Vertex AI nodes
See Generate run in a workflow.
In a technical demo we add the Google Vertex AI connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.