Using Zep and Hugging Face 🤗 embeddings with n8n LangChain nodes

Hey :wave:

From the moment that in n8n we have a possibility to use AI nodes, I just couldn’t resist creating a tutorial about connecting it with the Zep vector store and embedding models available on HuggingFace.

In this tutorial, I go step-by-step through the process of setting up Zep and integrating it with n8n AI nodes.

2 Likes

hey i’m trying to follow your video and i’m running into this: N8n cloud / Zep error
any thoughts?

Hey, what embedding model are you using? Please note that in this tutorial I use model BAAI/bge-small-en-v1.5 with 384 dimensions. If you use other embedding model (e.g. text-embedding-3-small from OpenAI) you may need to change this value according to documentation (for text-embedding-3-small it will be 1536).

Thanks for the reply. Yes i am also using BAAI/bge-small-en-v1.5 with embedding dimension 384 - I am doing everything exactly as you do in your video. Is it possible Zep is somehow not configured properly? I am running Zep on AWS EC2, the dashboard is accessible through my browser, and n8n accepts the Zep credentials as correct but maybe there something else Zep is missing?