Intelligent Image Classification with KNN and Voyage AI

This n8n workflow provides a robust solution for image classification, seamlessly integrating advanced AI models and vector search capabilities. It begins by embedding an input image using Voyage AI's voyage-multimodal-3 model, capturing its visual essence. This embedding is then used to query a Qdrant vector database, retrieving the most similar image embeddings based on a configurable KNN approach. A majority vote mechanism is employed on the landscape_name payload of the nearest neighbors to determine the final classification. The workflow intelligently handles potential ties by iteratively increasing the KNN search limit until a definitive classification is achieved, ensuring accuracy and reliability.