🤖 Build a Documentation Expert Chatbot with Gemini RAG Pipeline
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 23 nodes and runs manually, when you click “Execute workflow” (plus 2 other triggers). Along the way it connects Google Gemini Chat Model and Embeddings Google Gemini. It also calls docs.n8n.io over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 2 other triggers).
- Get All n8n Documentation Links (HTTP Request): calls docs.n8n.io
- Get Documentation Page (HTTP Request): calls an HTTP API
- n8n Docs AI Agent (AI Agent): runs an AI agent, with model: Gemini 2.5 Flash; 1 tool (Official n8n Documentation); memory: Simple Memory
- Extract Links from HTML (HTML): parses or builds HTML
- Extract Documentation Content (HTML): parses or builds HTML
- Split Out: splits a list into separate items
- Clean Documentation (Edit Fields (Set)): sets 1 field: documentation
- Remove Duplicate Links (Remove Duplicates): removes duplicate items
- Remove Duplicate Documentation Content (Remove Duplicates): removes duplicate items
- Only Keep Doc Paths (Filter): keeps only the items that match a condition
…plus 3 more steps. See the full node list below.
Services it uses
HTTP calls to: docs.n8n.io
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (18)
- Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Remove Duplicates
n8n-nodes-base.removeDuplicates - Filter
n8n-nodes-base.filter - Edit Fields (Set)
n8n-nodes-base.set - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - HTTP Request
n8n-nodes-base.httpRequest - HTML
n8n-nodes-base.html - Split Out
n8n-nodes-base.splitOut - Execute Sub-workflow
n8n-nodes-base.executeWorkflow - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - AI Agent
@n8n/n8n-nodes-langchain.agent - Manual Trigger
n8n-nodes-base.manualTrigger - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory
From the author
How it works This template is a complete, hands-on tutorial for building a RAG (Retrieval-Augmented Generation) pipeline. In simple terms, you'll teach an AI to become an expert on a specific topic—in this case, the official n8n documentation—and then build a…