Automate KNN Image Classification with Qdrant and Voyage AI
This workflow automates the classification of images using the k-nearest neighbors (KNN) algorithm. It leverages Qdrant for vector database management and Voyage AI for embedding generation, providing a robust solution for image classification tasks.
This workflow is designed to classify images based on a pre-uploaded dataset in Qdrant. It starts by receiving an image URL, which is then processed through the Voyage AI Multimodal Embeddings API to obtain an embedding vector. This vector is used to query Qdrant for similar images, and a majority voting mechanism determines the most likely class of the input image. In case of a tie, the workflow dynamically adjusts the number of neighbors considered until a clear classification is achieved or a
- Platform
- n8n
- Category
- AI & Machine Learning
- Price
- $14.99
- Creator
- Lily Zhang
- classifier
- if
- set
- code
- stickyNote
- httpRequest
- executeWorkflowTrigger
How to import this workflow into n8n
- 1Purchase or download the workflow to get the n8n workflow JSON file.
- 2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
- 3Open each node marked with a credential warning and connect your own accounts and API keys.
- 4Run the workflow once manually to verify the data flow, then toggle it to Active.
Related AI & Machine Learning workflows
- Create an AI Data Analyst Chatbot for Automated Data Retrieval and Analysis$19.99
- Perform Hybrid Search on Legal Datasets Using Qdrant and BM25/mxbai$14.99
- Automate Weekly AI Research Summaries with arXiv and Weaviate$19.99
- Build a PDF Document RAG System with Mistral OCR, Qdrant, and Gemini AI$24.99
- Index Legal Documents for Hybrid Search Using Qdrant, OpenAI, and BM25$19.99
- Automate Legal Q&A with AI and Document Retrieval via Telegram$9.99
More from Lily Zhang
Need this deployed? We'll set it up for you.
Our automation experts deploy this workflow in your stack, connect your accounts, and verify it works — or build a custom solution from scratch.