Google Cloud Vision
for LuumenAI

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

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.

The Google Cloud Vision toolbox

29 tools: 13 read, 16 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadAnnotate Files with Vision APIPerform image detection and annotation for batch files in Google Cloud Vision.
  • ReadAnnotate ImagesRun image detection and annotation for a batch of images using Google Cloud Vision API.
  • ReadAnnotate Location ImagesRun image detection and annotation for a batch of images scoped to a specific project and location.
  • ReadGet ProductGet information associated with a Product.
  • ReadGet Product SetGet a ProductSet.
  • ReadList Vision AI IndexEndpointsLists IndexEndpoints in Vertex AI Vision for a given project and location.
  • ReadList LocationsList available Vision AI service locations for a project.
  • ReadList Vision API OperationsList operations that match the specified filter.
  • ReadGet Vision API OperationRetrieves the latest state of a long-running Vision API operation.
  • ReadGet Reference ImageGet information associated with a ReferenceImage.
  • ReadList Products in ProductSetList Products in a specified ProductSet.
  • ReadList ProjectsList Google Cloud projects accessible to the authenticated user via Cloud Resource Manager API.
  • ReadList Reference ImagesList reference images for a product.
  • WriteAsync Batch Annotate FilesRun asynchronous image detection and annotation for a list of generic files (PDF, TIFF, GIF). Approval by default
  • WriteAnnotate Images Async BatchRun asynchronous image detection and annotation for a batch of images. Approval by default
  • WriteCreate Vision ProductCreates a new Product resource in Google Cloud Vision Product Search. Approval by default
  • WriteCreate Product SetCreates a new ProductSet resource in Google Cloud Vision Product Search. Approval by default
  • WriteCreate ReferenceImageCreate a ReferenceImage under a product. Approval by default
  • WriteDelete ProductPermanently deletes a Product and its associated reference images from Google Cloud Vision API. Approval by default
  • WriteImport Product SetsAsynchronously imports product sets and reference images from a CSV file stored in Google Cloud Storage. Approval by default
  • WritePurge ProductsAsynchronously delete products in a ProductSet or orphan products. Approval by default
  • WriteUpdate ProductUpdate a Product's mutable fields: displayName, description, and productLabels. Approval by default
  • WriteUpdate Product SetUpdate a ProductSet resource. Approval by default
  • WriteAdd Product to ProductSetAdd a Product to a ProductSet in Google Cloud Vision Product Search. Approval by default
  • WriteCancel Vision OperationStarts asynchronous cancellation of a long-running Vision API operation. Approval by default
  • WriteDelete Vision API OperationDelete a long-running Vision API operation. Approval by default
  • WriteDelete Product SetPermanently delete a ProductSet. Approval by default
  • WriteDelete Reference ImagePermanently removes a reference image from a product in Google Cloud Vision Product Search. Approval by default
  • WriteRemove Product from ProductSetRemoves a Product from a specified ProductSet in Google Cloud Vision API. Approval by default

One prompt, start to finish

What a governed Google Cloud Vision run looks like inside Luumen.

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 — async batch annotate files, annotate images async batch, create vision product, create product set, and more — is shown as a plan and requires approval by default, including the 6 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.

Who gets access to the integration?

You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.

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, and can be linked to the ticket or change record.

Put Google Cloud Vision to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.