ActionGoogle Vertex AIUpdated September 2026

How do I generate embeddings on Vertex AI?

Short answer: You can embed text in Google Vertex AI by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Google Vertex AI Embed Text action to a workflow, map its 3 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Embed Text in Google Vertex AI — start free All 3 Google Vertex AI actions

Embed Text in Google Vertex AI — start free

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 run history shows the failed step with its input and the error message Google Vertex AI returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.

Does Embed Text support batch operations?

Run Embed Text inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Google Vertex AI's rate limits.

More actions

Other Google Vertex AI actions.

Action

Generate Content (Gemini)

Calls Gemini models on Vertex AI using your GCP project, region, and IAM. Same model family as the public Gemini API but with enterprise governance: VPC-SC, CMEK, audit logs, and data-residency.

Action

Imagen Generate

Generates images using Imagen on Vertex AI, the enterprise-tier image model with prompt-rewriting controls, safety filters, and retention controls suitable for regulated workloads.

Embed Text in Google Vertex AI — start free