Google Cloud Vision API

Google Cloud Vision API

The GCP Image Vision function allows you to enable powerful content discovery and analysis in your images.

Deploy now
Ready to go in minutes
Ready to go in minutes

Deploy the Google Cloud Vision API function on your processing stack in no time. Koyeb functions are pre-configured processing application to analyze, transform and optimize your data.

Infinite combinations
Infinite combinations

Compose processing workflows with ready to use integrations and your own code if needed. Build your business logic with our SDKs in Golang, Node.js, and Python or using Docker images.

No infrastructure management
No infrastructure management

Koyeb's all-in-one platform is backed by a highly available infrastructure. Build advanced operation pipelines for your data with zero server maintenance.



GCP Image Vision is an image detection service that allows you to add Google image analysis technology to your applications. The GCP Image Vision function allows you to detect people, faces, explicit content, logos, objects, text, and labels such as locations and activities in images.

This function comes with the following variants:

  • Image properties, to detect general attributes of the image, such as dominant color.
  • Label Detection, to return labels about an image. It will detect general objects, locations, activities, animal species, products and more. Labels are returned in English.
  • Logo Detection, to identify popular logos within an image. It returns their coordinates and description.
  • Object Detection, to detect multiple objects in an image and provides information for each object in the image. For each object, you will get the position of the object, and rectangular bounds for the region of the image that contains the object.
  • Image explicit content detection, to detect content such as adult or violent content within an image. It can be used in automated moderation systems.
  • Image OCR, to detect the text in the image. You will get the entire extracted string, as well as individual words, and their bounding boxes.
  • Image Web Detection, to find similar images on the web. With this variant, you can find duplicate images or similar images on the internet.

Advantages of using Koyeb's GCP image vision Function

With Koyeb, you can run the GCP Image Vision function to add image analysis and content discovery to your applications in seconds. Additional benefits: * Store the result on the cloud service provider of your choice * Enjoy a ready to use function that requires no code or complex configuration to get started * Combine additional processing actions that immediately use the results of the GCP image vision function

  • Create image libraries that are easier to search
  • Conduct demographic analysis
  • Detect explicit content
  • Identify duplicate or similiar images on the internet
  • Enrich your application database
  • Extract text from images

How the GCP Image Vision Function Works with Koyeb

To get started with the GCP image vision function, you have to copy the configuration snippet below and replace the required values with yours. This function is triggered each time an object of type type what is created in the Store you use.

Below is what you need to use this function: * A Koyeb account * Valid GCP credentials with permissions configured to access the GCP Vision API * A Store to upload images and save the function result









Seconds to deploy

Configure Google Cloud Vision API

Additional information to get started with the Google Cloud Vision API integration.

Available settings

  • STORE — The store to watch to trigger the function and save the generated watermark image.Default value: - Required: Yes
  • GCP_KEY_SECRET — The name of the secret in which the GCP Key will be stored.Default value: - Required: Yes
  • GCP_VISION_OPERATION — The name of the vision operation you want to perform. It can be any of face-detection image-properties label-detection landmark-detection logo-detection object-localization safe-search-detection web-detection text-detection document-text-detection.Default value: - Required: Yes
  • IMAGE_PREFIX — Only analyse images which start with this file prefix.Default value: - Required: No

Ready to get started?

Get in touch or create an account and deploy your serverless stack in minutes.