---
title: "Google Cloud Vision integration for LuumenAI"
url: "https://www.luumen.ai/integrations/google-cloud-vision/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Google Cloud Vision integration for LuumenAI

Read Vision annotations and product catalogs, then make changes with approval

## What LuumenAI can do with Google Cloud Vision

LuumenAI connects to Google Cloud Vision with an API token and exposes 29 tools (13 read-only · 10 write · 6 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 29 tools (13 read-only · 10 write · 6 destructive)
- Plan: available on all plans
- Category: AI & automation

## About Google Cloud Vision with LuumenAI

Connect Google Cloud Vision and your agent can run label, text, and landmark detection on images, check the state of long-running annotation jobs, and inspect Product Search catalogs. Catalog changes — creating products, updating product sets, importing from Cloud Storage, deleting — run as previewed steps you approve. Luumen authenticates with an API key.

## Example tools

Read-only (13 in total):

- `GOOGLE_CLOUD_VISION_ANNOTATE_FILES` — Perform image detection and annotation for batch files in Google Cloud Vision.
- `GOOGLE_CLOUD_VISION_ANNOTATE_IMAGES` — Run image detection and annotation for a batch of images using Google Cloud Vision API.
- `GOOGLE_CLOUD_VISION_ANNOTATE_LOCATION_IMAGES` — Run image detection and annotation for a batch of images scoped to a specific project and location.
- `GOOGLE_CLOUD_VISION_GET_PRODUCT` — Get information associated with a Product.
- `GOOGLE_CLOUD_VISION_GET_PRODUCT_SET` — Get a ProductSet.
- `GOOGLE_CLOUD_VISION_LIST_INDEX_ENDPOINTS` — Lists IndexEndpoints in Vertex AI Vision for a given project and location.
- `GOOGLE_CLOUD_VISION_LIST_LOCATIONS` — List available Vision AI service locations for a project.
- `GOOGLE_CLOUD_VISION_LIST_OPERATIONS` — List operations that match the specified filter.

Write and destructive (16 in total, approval required by default):

- `GOOGLE_CLOUD_VISION_ANNOTATE_FILES_ASYNC_BATCH` — Run asynchronous image detection and annotation for a list of generic files (PDF, TIFF, GIF).
- `GOOGLE_CLOUD_VISION_ANNOTATE_IMAGES_ASYNC_BATCH` — Run asynchronous image detection and annotation for a batch of images.
- `GOOGLE_CLOUD_VISION_CREATE_PRODUCT` — Creates a new Product resource in Google Cloud Vision Product Search.
- `GOOGLE_CLOUD_VISION_CREATE_PRODUCT_SET` — Creates a new ProductSet resource in Google Cloud Vision Product Search.
- `GOOGLE_CLOUD_VISION_CREATE_REFERENCE_IMAGE` — Create a ReferenceImage under a product.
- `GOOGLE_CLOUD_VISION_DELETE_PRODUCT` — Permanently deletes a Product and its associated reference images from Google Cloud Vision API.
- `GOOGLE_CLOUD_VISION_IMPORT_PRODUCT_SETS` — Asynchronously imports product sets and reference images from a CSV file stored in Google Cloud Storage.
- `GOOGLE_CLOUD_VISION_PURGE_PRODUCTS` — Asynchronously delete products in a ProductSet or orphan products.

## Frequently asked questions

### How does LuumenAI connect to Google Cloud Vision?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Google Cloud Vision on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 6 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to Google Cloud Vision — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/google-cloud-vision/