Embed Text
vertex_ai.embed_text
ActionGoogle Cloudconnection required
Calls the Vertex AI publishers/google/models/{model}:predict endpoint.
Create vector embeddings for one or more texts with a Google embedding model.
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
5 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 |
|---|---|---|---|---|---|
project_id GCP project id (overrides connection). | string | No | — | — | — |
region Region (default us-central1). | string | No | — | — | — |
text Text to embed (or a JSON array of texts). Supports {{ }}. | string | Yes | — | — | — |
model Embedding model id. | string | No | text-embedding-005 | — | — |
task_type Optional task type hint. | string | No | — | one of "RETRIEVAL_QUERY", "RETRIEVAL_DOCUMENT", "SEMANTIC_SIMILARITY", "CLASSIFICATION", "CLUSTERING", "QUESTION_ANSWERING", "FACT_VERIFICATION" | — |
Example configuration
Every value below is the contract’s own example or default — nothing invented.
{
"model": "text-embedding-005"
}Output
One shape.
result
| Field | Type | Example |
|---|---|---|
embeddings | array | — |
count | number | — |
dims | number | — |
model | string | — |
{
"count": 0,
"dims": 0,
"embeddings": [],
"model": ""
}Related Google Vertex AI nodes
See Embed Text 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.