Annotate Image
google_vision.annotate
ActionGoogle Cloudconnection required
Calls the Vision API POST /v1/images:annotate.
Detect labels, text (OCR), objects and more in an image with Cloud Vision.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- OAuth 2.0
- Providers
- Google Cloud Vision
- Secret shape
- {"client_id", "client_secret", "refresh_token"}
- Resolved by
- config.connection_id, else node.connection_id
Configuration
3 fields, 1 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 |
|---|---|---|---|---|---|
image_uri Public or gs:// image URL. Supports {{ }}. | string | Yes | — | — | — |
features Comma-separated: labels,text,faces,objects,safe_search,landmarks,logos. | string | No | labels | — | — |
max_results Max results per feature. | number | No | 10 | ≥ 1 | — |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"features": "labels",
"max_results": 10
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
labels | array | — |
text | string | — |
{
"labels": [],
"text": ""
}See Annotate Image run in a workflow.
In a technical demo we add the Google Cloud Vision connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.