Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Embed Image Datasets into Qdrant for Anomaly Detection

When you run it, it loads image crops from Google Cloud Storage, embeds them and uploads them to Qdrant for KNN classification.

Import it free Sign in to open it

What it does

Now it's time to embed & upload to Qdrant our image datasets; Both of them, crops (you should replace it with your image datasets) Datasets consist of image URLs; images are grouped by folders based on their class. For example, we have a system of subfolders like *"tomato"* and *"cucumber"* for the crops dataset with image URLs of the respective class.

The steps

  1. When clicking ‘Test workflow’
  2. Google Cloud Storage
  3. Get fields for Qdrant
  4. Qdrant cluster variables
  5. Embed crop image
  6. Create Qdrant Collection
  7. Check Qdrant Collection Existence
  8. Batches in the API's format
  9. Batch Upload to Qdrant
  10. Split in batches, generate uuids for Qdrant points
  11. If collection exists
  12. Payload index on crop_name
  13. Filtering out tomato to test anomalies
  14. Error Handler

60 steps in total.

Similar automations

RAG & Knowledge BasesEmbed Image Datasets into Qdrant for Anomaly Detection13 stepsRAG & Knowledge BasesEmbed Image Datasets into Qdrant for Anomaly Detection60 stepsRAG & Knowledge BasesUpload Crop Images to Qdrant for Anomaly Detection13 stepsRAG & Knowledge BasesSet Up Medoids for Crop Anomaly Detection26 steps