Google Vertex AI

Run predictions and generate text using models on Google Cloud Vertex AI.

On this page

Connect
Call it from a workflow
Actions (3)
generate_content
generate_image
custom_api_call
Details

Connect

Auth type: OAuth (oauth2). Click Connect and approve access on the provider's page. Appbricx runs the OAuth flow (signed single-use state, PKCE where the provider supports it), stores the tokens encrypted and refreshes them before they expire.

Scopes requested: https://www.googleapis.com/auth/cloud-platform

OAuth needs an OAuth app: the platform's when the operator configured one, or your own (admin panel, Integrations, Configure). You can also bring your own credentials.

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("google_vertexai", "generate_content", {
    "location": "<location>",
    "model": "<model>",
    "userMessage": "<user message>"
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("Google Vertex AI answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "google-vertexai-generate-content",
  name: "Google Vertex AI: Generate Content",
  description: "Calls Google Vertex AI when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("google_vertexai", {
      "action": "generate_content",
      "location": "<location>",
      "model": "<model>",
      "userMessage": "<user message>"
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/google_vertexai/generate_content" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"location":"<location>","model":"<model>","userMessage":"<user message>"}}'

Actions

generate_contentin catalog

Generate Content. Call a Gemini model on Vertex AI to generate a text response.

Input	Type	Description
`location`required	id (picked from your account)	Google Cloud region where your Vertex AI resources are hosted.
`model`required	id (picked from your account)	Gemini model to use for content generation.
`systemMessage`optional	long text	Instructions that guide the model's behavior throughout the conversation.
`userMessage`required	long text	The prompt to send to the model.
`files`optional	array	Optional files to include in the prompt (images, PDFs, text, audio, video)
`youtubeUrl`optional	text	Optional public YouTube video URL for the AI to use as a reference.
`imageUrls`optional	array	Public image URLs to include alongside the user message. The model will analyze these images.
`temperature`optional	number	Controls randomness. Lower values are more deterministic (0–2). Leave empty to use the model default.
`maxOutputTokens`optional	number	Maximum number of tokens to generate. Leave empty to use the model default.
`thinkingLevel`optional	one of "LOW" \| "MEDIUM" \| "HIGH"	Controls how much the model thinks before responding. Supported on Gemini 2.5 and later models.
`thinkingBudget`optional	number	Maximum number of tokens the model can use for internal reasoning. Set to 0 to disable thinking. Supported on Gemini 2.5 and later models.
`includeThoughts`optional	boolean	When enabled, the model's reasoning is returned alongside the final response. Supported on Gemini 2.5 and later models.

generate_imagein catalog

Generate Image. Generate an image from a text prompt using Google Imagen models on Vertex AI.

Input	Type	Description
`location`required	id (picked from your account)	Google Cloud region where your Vertex AI resources are hosted.
`model`required	id (picked from your account)	Model to use for image generation.
`prompt`required	long text	A text description of the image you want to generate.
`modelOptions`required	object (depends on other props)	Model Configurations

custom_api_call

Custom API Call. Make a custom API call to a specific endpoint

Input	Type	Description
`url`required	object (depends on other props)	url
`method`required	one of "GET" \| "POST" \| "PATCH" \| "PUT" \| "DELETE" \| "HEAD"	Method
`headers`required	object	Authorization headers are injected automatically from your connection.
`queryParams`required	object	Query Parameters
`body_type`optional	one of "none" \| "json" \| "form_data" \| "raw"	Body Type
`body`optional	object (depends on other props)	Body
`response_is_binary`optional	boolean	Enable for files like PDFs, images, etc.
`failsafe`optional	boolean	No Error on Failure
`timeout`optional	number	Timeout (in seconds)
`followRedirects`optional	boolean	Follow redirects

Details

Id: google_vertexai
Category: AI and ML
Tags: ai, google, vertex, gcp, enterprise, ml
Package: @activepieces/piece-google-vertexai@0.1.1
Tier: Built in