How can I efficiently run a RAG pipeline fully in Node.js using OpenAI embeddings and FAISS without relying on Python?

I am working with a small Retrieval-Augmented Generation (RAG) setup and I want to run the entire pipeline purely in Node.js without using any Python-based services.

Workflow i am going to follow :

• Generate embeddings using openai.embeddings.create()

• Store them in an efficient vector database probably fiass

• Retrieve relevant chunks for user queries

• Pass them into a prompt for gpt or avilable free LLMs

Many tutorials use Python + FAISS (or LangChain’s Python bindings). In Node.js, FAISS doesn’t have official bindings and libraries like faiss-node or vectordb seem incomplete or outdated.

Question: What’s the best way to implement a RAG in pure Node.js that supports embedding storage, similarity search and retrieval without calling a Python backend?