Skip to content
NEWMarketplace and your team: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / Building Blocks & Utilities

Building Blocks & Utilities

Classify land-type images with Voyage.ai embeddings and Qdrant KNN voting

Called by other workflows, it takes an image URL, gets a Voyage.ai multimodal embedding, finds similar labeled images in Qdrant and returns the majority-vote land class.

What it does

## KNN classification workflow-tool ### This n8n template takes an image URL (as anomaly detection tool does), and as output, it returns a class of the object on the image (out of land types list) * An image URL is received via the Execute Workflow Trigger, which is then sent to the Voyage.ai Multimodal Embeddings API to fetch its embedding. * The image's embedding vector is then used to query Qdrant, returning a set of X similar images with pre-labeled classes. * Majority voting is done for classes of neighbouring images. * A loop is used to resolve scenarios where there is a tie in Majority Voting (for example, we have 5 "forest" and 5 "beach"), and we increase the number of neighbours to retrieve. * When the loop finally resolves, the identified class is returned to the calling workflow.

The steps

  1. Embed image
  2. Query Qdrant
  3. Majority Vote
  4. Increase limitKNN
  5. Propagate loop variables
  6. Image Test URL
  7. Return class
  8. Check tie
  9. Qdrant variables + embedding + KNN neigbours
  10. Execute Workflow Trigger

Similar automations