I’ve built a Voyage AI Embeddings node for n8n (and it passed 1,000 installs in under 24 hours)

Built with n8n
1

I’ve just released a new n8n community node that finally makes it easy to use Voyage AI Embeddings inside n8n’s AI workflows.

If you’ve tried integrating Voyage into n8n before, you might have hit at least one of these issues:

  • n8n doesn’t ship an official Voyage AI Embeddings node yet

  • The existing Voyage-related community node fails with errors like
    "Tokenizer requires @huggingface/transformers. Install: npm i @huggingface/transformers onnxruntime-node...",
    which is not ideal for production environments

Since I needed Voyage for my own RAG and AI Agent workflows, I decided to build a clean, dependency-free community node instead of waiting for a fix.

Node: n8n-nodes-embeddings-voyageai on npm
It integrates with n8n’s vector store ecosystem and behaves like other native embeddings nodes: you attach it under a Vector Store, feed in text, and it returns embeddings ready for similarity search and RAG.

Key highlights:

  • Supports major Voyage embedding models like voyage-4-large, voyage-4, voyage-4-lite, voyage-code-3, voyage-finance-2, voyage-law-2

  • No heavy dependencies like @huggingface/transformers or onnxruntime-node

  • Configurable dimensions (256 / 512 / 1024 / 2048) so you can balance quality vs storage

  • Works smoothly with existing Vector Store nodes in n8n (Supabase, Pinecone, Qdrant, PGVector, etc.)

I originally built it just to unblock my own projects, but within the first 24 hours it had already passed 1,000+ installs and the feedback so far has been really positive around speed, stability, and “native” feel in n8n.

If you’re running RAG or AI agents on n8n and want to try Voyage AI Embeddings without dependency headaches, give n8n-nodes-embeddings-voyageai a spin and let me know how it works for you.

1 Like