{"product_id":"n8n-workflow-gemini-embeddings-category-mapper-review-queue","title":"n8n Workflow: Gemini Embeddings Category Mapper + Review Queue","description":"\u003ch3\u003eAutomatically map product listings to the best marketplace category with Gemini embeddings—high-confidence matches go through, uncertain ones go to review\u003c\/h3\u003e\n\u003cp\u003eThis n8n workflow uses \u003cstrong\u003eGoogle Gemini embeddings\u003c\/strong\u003e to compare your products against a category tree, select the best \u003cstrong\u003ecategory_id\u003c\/strong\u003e, and either \u003cstrong\u003emap\u003c\/strong\u003e the product automatically or route it to a \u003cstrong\u003ehuman review queue\u003c\/strong\u003e when confidence is low.\u003c\/p\u003e\n\n\u003ch3\u003eWhat this workflow does\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eRun once: create tables and demo data\u003c\/strong\u003e to initialize two n8n \u003cstrong\u003eData Tables\u003c\/strong\u003e: one for \u003cem\u003emarketplace_categories\u003c\/em\u003e and one for \u003cem\u003eproducts_to_map\u003c\/em\u003e (you’ll replace the demo rows with your own category tree and products).\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIndex the category tree\u003c\/strong\u003e by reading all category paths, generating \u003cstrong\u003eGoogle Gemini embeddings\u003c\/strong\u003e, and storing them in an \u003cstrong\u003ein-memory vector store\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eMap pending products one at a time\u003c\/strong\u003e: for each product, generate an embedding, retrieve a shortlist of similar categories from the vector store, and use the \u003cstrong\u003eGoogle Gemini chat model\u003c\/strong\u003e to choose a single \u003cstrong\u003ecategory_id\u003c\/strong\u003e (or \u003cstrong\u003eNONE\u003c\/strong\u003e) with a structured reason.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eValidate and update status\u003c\/strong\u003e against the shortlist and a similarity threshold:\n    \u003cul\u003e\n      \u003cli\u003eIf high-confidence: update the product row with the selected category details.\u003c\/li\u003e\n      \u003cli\u003eIf uncertain: set the product row to \u003cstrong\u003eneeds_review\u003c\/strong\u003e with candidate categories and the review reason.\u003c\/li\u003e\n    \u003c\/ul\u003e\n  \u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eUse cases\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003eMapping e-commerce or marketplace listings to the correct taxonomy using \u003cstrong\u003en8n automation\u003c\/strong\u003e and \u003cstrong\u003eGemini embeddings\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003eMaintaining category accuracy at scale by sending ambiguous items to a \u003cstrong\u003ereview queue\u003c\/strong\u003e instead of forcing incorrect mappings.\u003c\/li\u003e\n  \u003cli\u003eOperational workflows for SaaS teams that need consistent category assignment across thousands of products.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical details\u003c\/h3\u003e\n\u003cul\u003e\n  \u003cli\u003e\n\u003cstrong\u003eIntegrations:\u003c\/strong\u003e Google Gemini (PaLM) for \u003cstrong\u003eembeddings\u003c\/strong\u003e and the \u003cstrong\u003eGemini chat model\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eCore workflow components:\u003c\/strong\u003e \u003ccode\u003eif\u003c\/code\u003e, \u003ccode\u003eset\u003c\/code\u003e, \u003ccode\u003ecode\u003c\/code\u003e, \u003ccode\u003eaggregate\u003c\/code\u003e, \u003cstrong\u003edata table\u003c\/strong\u003e, and \u003cstrong\u003esticky note\u003c\/strong\u003e.\u003c\/li\u003e\n  \u003cli\u003e\n\u003cstrong\u003eSetup steps:\u003c\/strong\u003e create a Google Gemini API credential, select it for both Gemini embedding nodes and the chat model node, then import your category tree and products into the two Data Tables.\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"N8N Commerce","offers":[{"title":"Default Title","offer_id":46275670474931,"sku":"N8N-21467","price":23.99,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0749\/6279\/6723\/files\/I1BL1O7jDeDxxkhb4K8KY_Ir6RFfFY.png?v=1792833160","url":"https:\/\/buyflowscripts.com\/products\/n8n-workflow-gemini-embeddings-category-mapper-review-queue","provider":"N8N Commerce","version":"1.0","type":"link"}