A RAG pipeline that indexes n8n documentation into a vector store for accurate, context-grounded chatbot responses using embeddings and Gemini.
This workflow creates a Retrieval-Augmented Generation (RAG) system turning an AI into an n8n documentation expert. Part 1 handles one-time indexing: it scrapes all n8n docs pages, splits them into chunks, generates embeddings with an AI model, and stores them in n8n's Simple Vector Store. This builds a searchable knowledge base like detailed index cards for every doc section.
Part 2 is the interactive chatbot. On query, it retrieves the most relevant chunks from the vector store, feeds them to
Platform
n8n
Category
Media & Entertainment
Price
$22.99
Creator
Maxim Luong
RAG
Chatbot
n8n
Documentation
Vector Store
Embeddings
AI Agent
Gemini
Web Scraping
Knowledge Base
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.