Google Cloud Vision integration: operations for AI agents
Google Cloud Vision connects to Type.com as an integration. This page lists the 23 operations documented for Claude and Codex in Type.com: 5 read, 16 write, 2 destructive.
About Google Cloud Vision
Google Cloud Vision API enables developers to integrate vision detection features into applications, including image labeling, face and landmark detection, optical character recognition (OCR), and explicit content tagging.
Categories: Design & Media
How to connect Google Cloud Vision to Type.com
- Access
- Organization connection: one shared account for the workspace.
To add the connection, follow the steps in Space connections.
Documented operations
23 operations. Your connection's permissions determine which operations are available. API references describe the vendor surface; they do not expand your connection's credentials or access.
23 operations listed.
Files
- Write
Vision.files.annotate
Service that performs image detection and annotation for a batch of files. Now only "application/pdf", "image/tiff" and "image/gif" are supported.
- Write
Vision.files.async Batch Annotate
Run asynchronous image detection and annotation for a list of generic files, such as PDF files, which may contain multiple pages and multiple images per page. Progress and results can be retrieved through the google.longrunning.Operations interface.
Images
- Write
Vision.images.annotate
Run image detection and annotation for a batch of images.
- Write
Vision.images.async Batch Annotate
Run asynchronous image detection and annotation for a list of images. Progress and results can be retrieved through the google.longrunning.Operations interface. Operation.metadata contains OperationMetadata (metadata).
Projects
- Read
Vision.projects.operations.get
Gets the latest state of a long-running operation. Clients can use this method to poll the operation result at intervals as recommended by the API service.
- Read
Vision.projects.locations.product Sets.products.list
Lists the Products in a ProductSet, in an unspecified order. If the ProductSet does not exist, the products field of the response will be empty. Possible errors: Returns INVALIDARGUMENT if pagesize is greater than 100 or less than 1.
- Read
Vision.projects.locations.product Sets.list
Lists ProductSets in an unspecified order. Possible errors: Returns INVALIDARGUMENT if pagesize is greater than 100, or less than 1.
- Read
Vision.projects.locations.products.list
Lists products in an unspecified order. Possible errors: Returns INVALIDARGUMENT if pagesize is greater than 100 or less than 1.
- Read
Vision.projects.locations.products.reference Images.list
Lists reference images. Possible errors: Returns NOTFOUND if the parent product does not exist. Returns INVALIDARGUMENT if the pagesize is greater than 100, or less than 1.
- Write
Vision.projects.locations.product Sets.patch
Makes changes to a ProductSet resource. Only displayname can be updated currently. Possible errors: Returns NOTFOUND if the ProductSet does not exist. Returns INVALIDARGUMENT if displayname is present in updatemask but missing from the request or longer than 4096 characters.
- Write
Vision.projects.locations.product Sets.add Product
Adds a Product to the specified ProductSet. If the Product is already present, no change is made. One Product can be added to at most 100 ProductSets. Possible errors: Returns NOTFOUND if the Product or the ProductSet doesn't exist.
- Write
Vision.projects.locations.product Sets.remove Product
Removes a Product from the specified ProductSet.
- Write
Vision.projects.locations.files.annotate
Service that performs image detection and annotation for a batch of files. Now only "application/pdf", "image/tiff" and "image/gif" are supported.
- Write
Vision.projects.locations.files.async Batch Annotate
Run asynchronous image detection and annotation for a list of generic files, such as PDF files, which may contain multiple pages and multiple images per page. Progress and results can be retrieved through the google.longrunning.Operations interface.
- Write
Vision.projects.locations.images.annotate
Run image detection and annotation for a batch of images.
- Write
Vision.projects.locations.images.async Batch Annotate
Run asynchronous image detection and annotation for a list of images. Progress and results can be retrieved through the google.longrunning.Operations interface. Operation.metadata contains OperationMetadata (metadata).
- Write
Vision.projects.locations.product Sets.create
Creates and returns a new ProductSet resource. Possible errors: Returns INVALIDARGUMENT if displayname is missing, or is longer than 4096 characters.
- Write
Vision.projects.locations.product Sets.import
Asynchronous API that imports a list of reference images to specified product sets based on a list of image information. The google.longrunning.Operation API can be used to keep track of the progress and results of the request. Operation.metadata contains BatchOperationMetadata.
- Write
Vision.projects.locations.products.create
Creates and returns a new product resource. Possible errors: Returns INVALIDARGUMENT if displayname is missing or longer than 4096 characters. Returns INVALIDARGUMENT if description is longer than 4096 characters. Returns INVALIDARGUMENT if productcategory is missing or invalid.
- Write
Vision.projects.locations.products.reference Images.create
Creates and returns a new ReferenceImage resource. The boundingpoly field is optional. If boundingpoly is not specified, the system will try to detect regions of interest in the image that are compatible with the productcategory on the parent product.
- Destructive
Vision.projects.locations.product Sets.delete
Permanently deletes a ProductSet. Products and ReferenceImages in the ProductSet are not deleted. The actual image files are not deleted from Google Cloud Storage.
- Destructive
Vision.projects.locations.products.purge
Asynchronous API to delete all Products in a ProductSet or all Products that are in no ProductSet. If a Product is a member of the specified ProductSet in addition to other ProductSets, the Product will still be deleted.
Operations
- Write
Vision.operations.cancel
Starts asynchronous cancellation on a long-running operation. The server makes a best effort to cancel the operation, but success is not guaranteed. If the server doesn't support this method, it returns google.rpc.Code.UNIMPLEMENTED.
No operations match.
See How connections work for access and permissions, or browse all integrations.
Reference date: October 27, 2026. Google Cloud Vision API docs.