Image Analysis and Embedding Workflow for Search

This n8n workflow automates the process of analyzing an image from Google Drive to generate semantic keywords and color information, then creates an embedding document to facilitate image search via a vector store. The workflow begins with a manual trigger, allowing users to activate the process. It downloads an image from Google Drive, extracts color channel information, and uses OpenAI’s vision model to generate descriptive keywords. These data points are merged and formatted into a document with relevant metadata. The document is then stored in an in-memory vector database, making it possible to perform similarity searches based on textual prompts. This workflow is practical for image cataloging, searching, and managing large image datasets efficiently, especially useful in digital asset management, content tagging, and AI-powered image retrieval systems.