ActionGoogle Vertex AIUpdated May 2026

How do I generate embeddings on Vertex AI?

Short answer: Drop the "Google Vertex AI → Embed Text" action anywhere in your workflow, map the inputs from upstream nodes, and publish.

Use this action All 3 Google Vertex AI actions

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Model model	options	Optional	Model. Options: Text Embedding 005, Gemini Embedding 001, Multilingual Embedding 002
Text text	string	Required	Text (required)
Task Type task_type	options	Optional	Task Type. Options: Retrieval Document, Retrieval Query, Semantic Similarity …

Sample request

{
  "model": "{{trigger.model}}",
  "text": "{{trigger.text}}",
  "task_type": "{{trigger.task_type}}"
}

Returns

{
  "predictions": [
    {
      "embeddings": {
        "values": [
          0.012
        ],
        "statistics": {
          "token_count": 5
        }
      }
    }
  ]
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Embed Text.

Any of these apps can fire this action as part of a workflow.

Gmail → Google Vertex AI

1 Gmail triggers

Slack → Google Vertex AI

13 Slack triggers

Google Sheets → Google Vertex AI

2 Google Sheets triggers

HubSpot → Google Vertex AI

18 HubSpot triggers

FAQ

Questions about Embed Text.

What does the Embed Text action do in Google Vertex AI?

Generates text embeddings on Vertex AI using Gemini Embedding or text-embedding-005. Use for RAG, semantic search, or clustering inside your GCP project (with the data-residency/retention controls that come with Vertex).

What inputs does Embed Text require?

Required: Text. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if Google Vertex AI returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does Embed Text support batch operations?

Yes. Run Embed Text inside a Loop node to process arrays. Tiny Command handles Google Vertex AI's rate limits automatically so you don't have to throttle manually.

More actions