Generating Image Embeddings via Textual Summarisation
Automates image embeddings by extracting color data and AI-generated descriptions from photos, storing them as text vectors for semantic search in photo libraries or product recommendations.
This n8n workflow enables quick image contextual search by converting images into searchable text embeddings. It processes photos from Google Drive, extracts visual metadata like colors, and uses a vision AI model to generate semantic descriptions, combining them into a document embedded in a vector store.
The workflow starts with a manual trigger or image import from Google Drive. An Edit Image node extracts color information for semantic metadata. A vision-capable OpenAI model analyzes the im
- Platform
- n8n
- Category
- Sales
- Price
- $18.99
- Creator
- Pablo Ulrich
- image embeddings
- AI vision
- semantic search
- Google Drive
- OpenAI
- vector store
- photo library
- product recommendations
- text summarization
- image processing
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 Sales workflows
- Automate B2B Lead Generation from Company Websites Using Brightdata and OpenRouter AI$14.99
- Automate Cold Calling Pipeline with Apify, OpenAI, and WhatsApp$19.99
- Automate Lead Generation and Enrichment Using Google My Business and Supabase$13.57
- Automate Sales Outreach with OpenAI, Airtable & Google Sheets for Prospect Research$9.99
- AI-Powered Lead Research & Personalized Email Generation with Groq & Google Sheets$14.99
- Automate Spare Parts Quotation with Gmail, Google Sheets, and Gemini AI$14.99
More from Pablo Ulrich
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.