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.
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. On Nagent, Google Cloud Vision is exposed as a fully-configurable artificial intelligence integration that any agent can call — 29 actions, and API key authentication. No code is required to wire Google Cloud Vision into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Google Cloud Vision to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Google Cloud Vision into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Google Cloud Vision, with input parameters and output schema. Drop these into any step of an agent built in Helix.
GOOGLE_CLOUD_VISION_ANNOTATE_FILESTool to perform image detection and annotation for batch files in Google Cloud Vision. Supports PDF, TIFF, and GIF files. Extracts up to 5 frames (GIF) or pages (PDF/TIFF) from each file and performs detection for each image. Use when you need to analyze documents or multi-page images with features like text detection, label detection, face detection, or other Vision API capabilities.
Input parameters
Required. Target project and location for the request. Format: projects/{project-id}/locations/{location-id}. Supported locations: us, asia, eu.
Required. Array of individual file annotation requests. Each request specifies input file configuration and desired features. At least one request is required.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_ANNOTATE_FILES_ASYNC_BATCHTool to run asynchronous image detection and annotation for a list of generic files (PDF, TIFF, GIF). Use when processing multi-page documents that may contain multiple images per page. Results are written to Google Cloud Storage and progress can be tracked via the returned operation name using VisionGetOperation.
Input parameters
Optional target project and location. Format: projects/{project-id}/locations/{location-id}. Supported locations: us, eu. If not specified, the service will auto-select a location.
Individual async file annotation requests for this batch. Must include at least one request.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_ANNOTATE_IMAGESRun image detection and annotation for a batch of images using Google Cloud Vision API. Performs various types of image analysis including face detection, landmark detection, logo detection, label detection, text detection (OCR), safe search detection, image properties, crop hints, web detection, product search, and object localization. Supports up to 16 images in a single batch request. Each image can have multiple feature types analyzed simultaneously.
Input parameters
Optional parent resource name in format projects/{project_id}/locations/{location_id}. Typically not required for standard image annotation.
Array of individual image annotation requests. Each request specifies an image and features to detect. The API supports up to 16 images in a single batch request for most features (specify 1-16 requests).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_ANNOTATE_IMAGES_ASYNC_BATCHTool to run asynchronous image detection and annotation for a batch of images. Use when processing multiple images or large images that require longer processing time. Results are written to Google Cloud Storage as JSON files.
Input parameters
Required location specification in format: projects/{project-id}/locations/{location-id}. Supported locations: 'us', 'asia', 'eu'. This controls where the async batch annotation operation runs and where data is processed.
List of image annotation requests. Must contain at least one request. Each request specifies an image (via GCS URI) and the features to detect. You can process multiple images in a single batch operation.
Configuration specifying where to write the annotation results. Results are written to Google Cloud Storage as JSON files. You must have write access to the specified GCS bucket.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_ANNOTATE_LOCATION_IMAGESTool to run image detection and annotation for a batch of images scoped to a specific project and location. Performs various types of image analysis including label detection, face detection, landmark detection, logo detection, OCR text detection, safe search detection, image properties, crop hints, web detection, product search, and object localization. Supports processing up to 16 images per request with regional endpoint routing (us, asia, eu). Use this when you need to analyze images with location-specific processing for content extraction, text recognition, object detection, face identification, or landmark/logo recognition.
Input parameters
Target project and location for the annotation request. Format: projects/{project-id}/locations/{location-id}. Supported locations: us, asia, eu. Example: projects/my-project/locations/us
Array of individual image annotation requests. Each request specifies an image and the features to detect on it. Maximum 16 requests per batch.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_CREATE_PRODUCTCreates a new Product resource in Google Cloud Vision Product Search. A Product represents a physical item that can be visually searched using reference images. After creating a product, you can add reference images to it and include it in product sets for visual search capabilities. Prerequisites: - Vision API must be enabled in your Google Cloud project - Product Search must be enabled - Valid project ID and location (us-west1, us-east1, europe-west1, or asia-east1) Use this action to: - Register a new product for visual search - Set up product metadata (display name, description, category, labels) - Obtain a product resource name for adding reference images
Input parameters
Required. The parent resource where the product will be created. Must be in format: projects/{PROJECT_ID}/locations/{LOC_ID}. Valid locations for Product Search: us-west1, us-east1, europe-west1, asia-east1.
Optional. User-defined ID for the product. If not provided, the system generates one. Maximum 128 characters. Must not contain forward slashes ('/'). Use lowercase alphanumeric characters, hyphens, and underscores only.
Optional. User-provided description of the product. Maximum 4096 characters. Provides additional context about the product.
Required. Display name for the product. Must be non-empty. Maximum 4096 characters. This is the human-readable name shown to users.
Optional. Key-value pairs for organizing and filtering products. Maximum 500 labels per product. Each key and value must be non-empty and ≤128 bytes. Useful for categorization (e.g., color:red, size:large, brand:acme).
Required. Immutable product category. Cannot be changed after creation. Valid values: 'homegoods-v2', 'apparel-v2', 'toys-v2', 'packagedgoods-v1', 'general-v1'. Choose 'general-v1' for products that don't fit other categories.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_CREATE_PRODUCT_SETCreates a new ProductSet resource in Google Cloud Vision Product Search. A ProductSet is a container for grouping related products together for visual search. After creating a product set, you can add products to it using the AddProductToProductSet action. Prerequisites: - Vision API must be enabled in your Google Cloud project - Product Search must be enabled - Valid project ID and location (us-west1, us-east1, europe-west1, or asia-east1) Use this action to: - Create a new product set container - Organize products into logical groups - Obtain a product set resource name for adding products
Input parameters
Required. The parent resource where the product set will be created. Must be in format: projects/{PROJECT_ID}/locations/{LOC_ID}. Valid locations for Product Search: us-west1, us-east1, europe-west1, asia-east1.
Required. Display name for the product set. Must be non-empty. Maximum 4096 characters. This is the human-readable name shown to users.
Optional. User-defined ID for the product set. If not provided, the system generates one. Maximum 128 characters. Must not contain forward slashes ('/'). Use lowercase alphanumeric characters, hyphens, and underscores only.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_CREATE_REFERENCE_IMAGETool to create a ReferenceImage under a product. Use when adding a new image to a product for detection.
Input parameters
Google Cloud Storage URI of the image; must start with gs://
Resource name of the product to add the reference image under. Format: projects/{PROJECT_ID}/locations/{LOC_ID}/products/{PRODUCT_ID}
Optional list of up to 10 regions of interest. If omitted, service auto-detects regions.
Client-specified ID for the new ReferenceImage; max 128 chars, no '/'. If already in use, returns ALREADY_EXISTS.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_DELETE_PRODUCTPermanently deletes a Product and its associated reference images from Google Cloud Vision API. This is a destructive operation that cannot be undone. The product metadata and all images are deleted immediately, though search queries against ProductSets may temporarily return cached results until caches refresh. Use this tool when you need to remove a product that is no longer needed. Ensure you have the correct product resource name before deletion.
Input parameters
Resource name of the Product to delete. Format: projects/{project_id}/locations/{location_id}/products/{product_id}. Supported locations: us-west1, us-east1, europe-west1, asia-east1.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_GET_PRODUCTTool to get information associated with a Product. Use when you have the product resource name and need its details.
Input parameters
Resource name of the Product to retrieve. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}/products/{PRODUCT_ID}. Supported locations: us-west1, us-east1, asia-east1, europe-west1.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_GET_PRODUCT_SETTool to get a ProductSet. Use when you need metadata details of an existing ProductSet by its full resource name. Use after obtaining the resource name.
Input parameters
Resource name of the ProductSet to get. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}/productSets/{PRODUCT_SET_ID}
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_IMPORT_PRODUCT_SETSAsynchronously imports product sets and reference images from a CSV file stored in Google Cloud Storage. This bulk import operation creates ProductSets, Products, and ReferenceImages from a properly formatted CSV file. Returns a long-running Operation that can be polled for completion status. The import automatically creates new ProductSets and Products if they don't exist based on the IDs in the CSV. Use this when you need to: - Bulk import multiple products and images at once - Create product catalogs from existing CSV data - Set up initial product search datasets Note: Requires OAuth authentication with cloud-platform or cloud-vision scope, and read access to the GCS bucket.
Input parameters
Project and location resource name. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}.
The input configuration for the import request.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_LIST_INDEX_ENDPOINTSLists IndexEndpoints in Vertex AI Vision for a given project and location. IndexEndpoints are deployed instances of image indexes used for visual search and retrieval in Vision AI's media warehouse. Use this tool to discover existing endpoints before querying them or to manage deployed indexes. IMPORTANT: Requires OAuth2 authentication (API keys are NOT supported). Needs 'visionai.indexEndpoints.list' IAM permission.
Input parameters
Filter expression supports filtering by deployedImageIndex.image_index or deployedImageIndex.corpus.
The parent resource name. Format: projects/{project}/locations/{location}.
Maximum number of items to return; default 50; maximum 1000 (higher coerced to 1000).
The nextPageToken from a previous call to retrieve the subsequent page.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_LIST_LOCATIONSTool to list available Vision AI service locations for a project. Use when you need to discover supported regions before making region-specific API calls.
Input parameters
The project resource name that owns the locations collection. Format: projects/{project_id}
Filter expression to narrow results, e.g., 'displayName=tokyo'.
Maximum number of locations to return; between 1 and 1000.
Pagination token from previous ListLocations call to retrieve next page of results.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_LIST_OPERATIONSTool to list operations that match the specified filter. Use when you need to retrieve all operations under a specific project and location.
Input parameters
The name of the operation's parent resource. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}
The standard list filter.
The standard list page size.
The standard list page token.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_PURGE_PRODUCTSTool to asynchronously delete products in a ProductSet or orphan products. Use when you need to clean up products at scale; ensure `force` is true to execute.
Input parameters
Must be true to actually perform the purge.
Project and location path. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}
If true, delete all products not in any ProductSet.
Configuration to specify a ProductSet whose products should be deleted.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_UPDATE_PRODUCTTool to update a Product's mutable fields: displayName, description, and productLabels. Use after confirming the product resource name.
Input parameters
Resource name of the Product. Format: projects/{PROJECT_ID}/locations/{LOC_ID}/products/{PRODUCT_ID}.
Comma-separated list of fields to update. Valid mask paths: displayName,description,productLabels. If omitted, all mutable fields are updated.
Product description; max 4096 characters.
Product display name; non-empty; max 4096 characters.
List of labels to update; each key/value pair non-empty with max 128 bytes.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_UPDATE_PRODUCT_SETTool to update a ProductSet resource. Use when you need to modify the displayName of an existing ProductSet.
Input parameters
Resource name of the ProductSet to update. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}/productSets/{PRODUCT_SET_ID}
Comma-separated list of fields to update; only 'displayName' is supported.
New display name for the ProductSet (non-empty, max 4096 chars).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_ADD_PRODUCT_TO_PRODUCT_SETAdd a Product to a ProductSet in Google Cloud Vision Product Search. This action associates a Product with a ProductSet, enabling the product to be included in product search queries against that set. Both resources must exist in the same Google Cloud project and location before calling this action. Key characteristics: - Idempotent: If the Product is already in the ProductSet, no change is made and no error occurs - Constraint: One Product can be added to at most 100 ProductSets - The Product and ProductSet must be in the same project and location - Valid locations: us-west1, us-east1, europe-west1, asia-east1 Use this after creating both a Product and a ProductSet to establish their association. Returns an empty response on success.
Input parameters
The ProductSet resource name to add the product to. Format: projects/{project_id}/locations/{location_id}/productSets/{product_set_id}. Valid locations: us-west1, us-east1, europe-west1, asia-east1. Example: 'projects/my-project/locations/us-west1/productSets/my-product-set'
The Product resource name to add to the ProductSet. Must be in the same project and location as the ProductSet. Format: projects/{project_id}/locations/{location_id}/products/{product_id}. Example: 'projects/my-project/locations/us-west1/products/my-product'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_CANCEL_OPERATIONStarts asynchronous cancellation of a long-running Vision API operation. Returns an empty response on successful cancellation request. Note that the server makes a best effort to cancel the operation, but success is not guaranteed. Use the Get Operation action to check if cancellation succeeded or if the operation completed despite the cancellation attempt. The server may return UNIMPLEMENTED if the operation does not support cancellation.
Input parameters
The server-assigned name of the operation resource to cancel. Format: operations/{operation_id} or projects/{project}/locations/{location}/operations/{operation_id}. This name is returned when creating long-running operations like importProductSets or purgeProducts.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_DELETE_OPERATIONTool to delete a long-running Vision API operation. Use after confirming the operation name.
Input parameters
The resource name of the operation to delete, e.g. 'operations/12345'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_DELETE_PRODUCT_SETTool to permanently delete a ProductSet. Use after confirming the ProductSet's resource name.
Input parameters
The resource name of the ProductSet to delete. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}/productSets/{PRODUCT_SET_ID}
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_DELETE_REFERENCE_IMAGEPermanently removes a reference image from a product in Google Cloud Vision Product Search. This action deletes the reference image association from the specified product. The image will be marked for deletion and removed during the next indexing operation. Note that the actual image file in Google Cloud Storage is not deleted. Use this when you need to: - Remove outdated or incorrect product reference images - Clean up test images from products - Update product imagery by removing old references Prerequisites: - The product must exist - The reference image must have been previously created under the product - You need the full resource path of the reference image (use List Reference Images if unknown)
Input parameters
The full resource path of the reference image to delete. Must follow the format: projects/{PROJECT_ID}/locations/{LOCATION_ID}/products/{PRODUCT_ID}/referenceImages/{IMAGE_ID}. Valid locations: us-west1, us-east1, europe-west1, asia-east1. Use the List Reference Images action to find available image IDs if needed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_GET_OPERATIONRetrieves the latest state of a long-running Vision API operation. Use this to poll the status of asynchronous operations like importProductSets or purgeProducts. The operation name is returned when you start an async operation.
Input parameters
The full resource name of the operation to retrieve. Must be in one of these formats: (1) 'projects/{project}/operations/{operation_id}' or (2) 'projects/{project}/locations/{location}/operations/{operation_id}'. Use format (2) for location-specific operations like import and purge.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_GET_REFERENCE_IMAGETool to get information associated with a ReferenceImage. Use when you have the full resource name and need its metadata.
Input parameters
Full resource name of the ReferenceImage to retrieve. Format: projects/{PROJECT_ID}/locations/{LOCATION_ID}/products/{PRODUCT_ID}/referenceImages/{REFERENCE_IMAGE_ID}
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_LIST_PRODUCTS_IN_PRODUCT_SETTool to list Products in a specified ProductSet. Use when you need to retrieve Products associated with a ProductSet after confirming it exists, with optional pagination.
Input parameters
Resource name of the ProductSet to list Products from. Format: projects/{project_id}/locations/{location_id}/productSets/{product_set_id}
Maximum number of items to return; default 10; maximum 100. Requests outside 1-100 return INVALID_ARGUMENT.
The nextPageToken from a previous call to retrieve the next page of results.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_LIST_PROJECTSList Google Cloud projects accessible to the authenticated user via Cloud Resource Manager API. This action queries the Cloud Resource Manager API (not Vision API directly) to enumerate projects. It requires OAuth 2.0 authentication - API key auth is insufficient. Use this when you need to discover available project IDs before making Vision API calls that require project identifiers. Note: Returns projects you have 'resourcemanager.projects.get' permission on.
Input parameters
Filter expression (case-insensitive). Supported fields: name, id (or projectId), labels.<key>, parent.type, parent.id, lifecycleState. Examples: 'name:how*', 'lifecycleState:ACTIVE', 'labels.color:red'
Maximum number of projects to return; server may return fewer.
Token from a previous list call to retrieve the next page of results.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_LIST_REFERENCE_IMAGESTool to list reference images for a product. Use when you need to retrieve stored reference images under a specified product resource name, with optional pagination.
Input parameters
Resource name of the product to list reference images for. Format: projects/{PROJECT_ID}/locations/{LOC_ID}/products/{PRODUCT_ID}.
Maximum number of images to return; default 10, maximum 100.
Token for fetching the next page of results from a previous list call.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
GOOGLE_CLOUD_VISION_VISION_REMOVE_PRODUCT_FROM_PRODUCT_SETRemoves a Product from a specified ProductSet in Google Cloud Vision API. This operation unlinks a product from a product set but does not delete either resource. Both the product and product set must exist in the same Google Cloud project and location. The product must have been previously added to the product set for this operation to succeed. Use this when you need to reorganize products across product sets or remove a product from a set without deleting the product itself.
Input parameters
Resource name of the ProductSet to modify. Format: projects/{project_id}/locations/{location_id}/productSets/{product_set_id}
Resource name of the Product to remove. Format: projects/{project_id}/locations/{location_id}/products/{product_id}
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 90 agents privately built on Nagent that already use Google Cloud Vision.
Build on Nagent
Connect Google Cloud Vision to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Google Cloud Vision, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Google Cloud Vision is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Google Cloud Vision is connected, you configure its 29 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Google Cloud Vision steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Google Cloud Vision event fires, the agent kicks off automatically.
Every Google Cloud Vision action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Google Cloud Vision ships with 29 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Google Cloud Vision together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Google Cloud Vision-based workflows tailored to your business.