AI & Machine Learning

Connect Google Cloud Vision to Your AI Agents

Google Cloud Vision is Google's vision-AI API for extracting insights from images and documents — labeling, text and logo detection, and more. Through this integration, WKIL agents can run image and batch-file annotation jobs and manage Vision Product Search resources (products, product sets, and reference images) using verified actions.

Authentication: API key

Build with Google Cloud Vision

What you can do

Detect and annotate images or batch files — labels, objects, text, and more — through Google Cloud Vision.
Run asynchronous annotation jobs for large batches of images or generic document files (PDF, TIFF, GIF).
Scope image annotation to a specific Google Cloud project and location.
Create and manage Vision Product Search resources — products, product sets, and reference images.

Available capabilities may vary by authentication and workspace configuration.

Actions supported by the connector

29 verified tools

Annotate Files with Vision API

Tool to perform image detection and annotation for batch files in Google Cloud Vision.

Async Batch Annotate Files

Tool to run asynchronous image detection and annotation for a list of generic files (PDF, TIFF, GIF).

Annotate Images

Run image detection and annotation for a batch of images using Google Cloud Vision API.

Annotate Images Async Batch

Tool to run asynchronous image detection and annotation for a batch of images.

Annotate Location Images

Tool to run image detection and annotation for a batch of images scoped to a specific project and location.

Create Vision Product

Creates a new Product resource in Google Cloud Vision Product Search.

Create Product Set

Creates a new ProductSet resource in Google Cloud Vision Product Search.

Create ReferenceImage

Tool to create a ReferenceImage under a product.

View all verified tools (search)

Annotate Files with Vision APIAsync Batch Annotate FilesAnnotate ImagesAnnotate Images Async BatchAnnotate Location ImagesCreate Vision ProductCreate Product SetCreate ReferenceImageDelete ProductGet ProductGet Product SetImport Product SetsList Vision AI IndexEndpointsList LocationsList Vision API OperationsPurge ProductsUpdate ProductUpdate Product SetAdd Product to ProductSetCancel Vision OperationDelete Vision API OperationDelete Product SetDelete Reference ImageGet Vision API OperationGet Reference ImageList Products in ProductSetList ProjectsList Reference ImagesRemove Product from ProductSet

Practical agent use cases

A content team can have a WKIL agent batch-annotate a folder of product images to extract labels and text before publishing.
A catalog team can use the Vision Product Search actions to register reference images so visually similar products can be matched later.

How it works with WKIL

1
Choose the integration
Add Google Cloud Vision to your agent from inside the WKIL platform.
2
Grant the permissions it needs
Define precisely what the agent can access and perform.
3
Test, then run it
Test actions before they go live, with human approval where needed.

Permissions always stay in your control — you can scope access and require human approval before any sensitive action.

Related integrations

FAQ

What is Google Cloud Vision?

Google Cloud Vision is Google's vision-AI API that detects and annotates content in images and documents — labels, text, faces, logos, and more.

What does the Google Cloud Vision integration support?

The WKIL integration exposes 29 verified Google Cloud Vision actions covering image and batch-file annotation and Vision Product Search management. It does not currently support real-time streaming annotation or Vision's video-analysis features.

Does WKIL need access to a Google Cloud Vision account?

Yes. The integration requires the appropriate Google Cloud Vision authentication and should be scoped to the permissions your workflow needs.