{"product_id":"n8n-image-embeddings-workflow-text-summarisation-search","title":"n8n Image Embeddings Workflow: Text Summarisation Search","description":"\u003ch3\u003eFind the right image instantly with n8n image embeddings—powered by Vision + vector search\u003c\/h3\u003e\n\u003cp\u003eThis n8n template ingests photos from Google Drive, builds semantic image embeddings using both color metadata and vision-based descriptions, and then lets you query your image library like text. In short: type a phrase, and the workflow returns the relevant image references and\/or links from your vector store.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eImports a photo from Google Drive\u003c\/strong\u003e into the workflow.\u003c\/li\u003e\n  \u003cli\u003eUses the \u003cstrong\u003eEdit Image\u003c\/strong\u003e node to \u003cstrong\u003eextract colour information\u003c\/strong\u003e, which becomes part of the image’s semantic metadata.\u003c\/li\u003e\n  \u003cli\u003eProcesses the same photo with a \u003cstrong\u003evision-capable model\u003c\/strong\u003e to generate a \u003cstrong\u003eshort description and semantic keywords\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eMerges the colour metadata + vision output\u003c\/strong\u003e with the document metadata to create a single “image document”.\u003c\/li\u003e\n  \u003cli\u003eInserts that document into a \u003cstrong\u003evector store\u003c\/strong\u003e as a \u003cstrong\u003etext embedding associated with the image\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003eEnables \u003cstrong\u003equerying the vector store\u003c\/strong\u003e like a normal document search—returning the relevant image references\/links.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003ePersonal photo library search\u003c\/strong\u003e: find images by meaning (e.g., “sunset beach”, “red car”).\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eProduct recommendations\u003c\/strong\u003e: retrieve visually similar products using semantic queries.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eVideo footage exploration\u003c\/strong\u003e: index frames or extracted images and search via descriptive prompts.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIntegrations \/ nodes:\u003c\/strong\u003e \u003cem\u003eset\u003c\/em\u003e, \u003cem\u003emerge\u003c\/em\u003e, \u003cem\u003eedit image\u003c\/em\u003e, \u003cem\u003esticky note\u003c\/em\u003e, \u003cem\u003eGoogle Drive\u003c\/em\u003e, \u003cem\u003emanual trigger\u003c\/em\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eAI requirements:\u003c\/strong\u003e an \u003cstrong\u003eOpenAI account\u003c\/strong\u003e for the vision-capable model and \u003cstrong\u003eembedding models\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eStorage:\u003c\/strong\u003e image documents are stored as \u003cstrong\u003etext embeddings in a vector store\u003c\/strong\u003e to support contextual retrieval.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003cp\u003e\u003cstrong\u003eNote:\u003c\/strong\u003e The workflow is designed for creating image embeddings via text summarisation + metadata. If you want to improve results, you can swap in dedicated multimodal embedding approaches (e.g., \u003ca href=\"https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/embeddings\/get-multimodal-embeddings\"\u003eGoogle Vertex AI multimodal embeddings\u003c\/a\u003e).\u003c\/p\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":45837247709363,"sku":"N8N-2344","price":36.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/Y1i9gaoJj0LdaLUfTyo03_E8rYbKpF.png?v=1786792511","url":"https:\/\/buyflowscripts.com\/products\/n8n-image-embeddings-workflow-text-summarisation-search","provider":"N8N Commerce","version":"1.0","type":"link"}