I have cleaned text content (from scraping) which I want to get text embeddings for. The input text could come from BigQuery or Google Sheets, and I want to use an Google vertex embedding function in n8n.
According to the n8n integrations page, the Google Vertex AI Embeddings node is available as a regular node:
Interestingly, when I try the n8n cloud version, the Vertex AI Embeddings integration does appear, but it’s available as a “tool”, not a typical workflow node - it doesn’t connect to other nodes.
The embeddings tool nodes are intended to be connected to AI agent nodes or other nodes that support automatically calling the embeddings tool, like the vector store nodes.
What were you going to do with the embeddings data at your workflow? If you’re for instance trying to build for instance an integration from BigQuery to a vector database, you could use the Google Vertex embeddings by building something like this:
That integrations page does seem a bit misleading, as we don’t currently have a standalone embeddings node like shown on the screenshot there. I’ll raise this up.
Hi @Jaakko
My objective here is to calculate similarity scores using text embedding between different documents I have gathered. What I gather from your response is that, I will have to use custom http request to call text embedding APIs manually.
Yeah, there were several similar instances in integrations section where things were not that clear straightaway. They might need some reviewing.
