Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Create Image Embeddings from Text Summaries with OpenAI

When you run it, the workflow reads images from Google Drive, extracts color information, has OpenAI describe them, and embeds the summaries in a vector store.

Import it free Sign in to open it

What it does

## 2. Image Embedding Methods Read more about working with images in n8n There are a myriad of image embedding techniques some which involve specialised models and some which do a simplified image-to-text representation. In this demo, we'll use the simplified text representation methods: collecting color channel information and using Multimodal LLMs to produce keywords for the image. Together, these will form the document we'll embed to represent our image for search.

The steps

  1. When clicking "Test workflow"
  2. Google Drive
  3. Get Color Information
  4. Resize Image
  5. Default Data Loader
  6. Recursive Character Text Splitter
  7. Combine Image Analysis
  8. Document for Embedding
  9. Embeddings OpenAI1
  10. Get Image Keywords
  11. In-Memory Vector Store
  12. Embeddings OpenAI
  13. Search for Image

Similar automations

RAG & Knowledge BasesIndex Google Drive Files into Pinecone with OpenAI Embeddings6 stepsRAG & Knowledge BasesChat with Google Drive Files Using OpenAI Embeddings23 stepsRAG & Knowledge BasesLoad Google Drive Files into a PGVector Database22 stepsRAG & Knowledge BasesEmbed Google Drive Images with OpenAI and Color Data18 steps