Build a cost-efficient Lookio RAG chatbot with GPT-4.1 models for knowledge Q&A
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 13 nodes and runs when a chat message arrives. Along the way it connects OpenAI Chat Model.
How it runs
Trigger: When a chat message arrives.
- Find past messages (Chat Memory Manager): uses Chat Memory Manager, with memory: Simple Memory
- Intent router (Text Classifier): classifies text into categories with AI, with model: Very small model
- Simple response (Basic LLM Chain): sends a prompt to an LLM, with model: Very small model
- Prepare retrieval query (Basic LLM Chain): sends a prompt to an LLM, with model: Mini model
- Respond to Chat (Chat): uses Chat
- RAG via Lookio (HTTP Request): calls an HTTP API (POST)
- Store messages (Chat Memory Manager): uses Chat Memory Manager, with memory: Simple Memory
- Write the final response (Basic LLM Chain): sends a prompt to an LLM, with model: Large model
Services it uses
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 (8)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - HTTP Request
n8n-nodes-base.httpRequest - Text Classifier
@n8n/n8n-nodes-langchain.textClassifier - Chat
@n8n/n8n-nodes-langchain.chat - Chat Memory Manager
@n8n/n8n-nodes-langchain.memoryManager - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow
From the author
This template provides a high-performance, cost-optimized alternative to standard AI Agents for building RAG (Retrieval-Augmented Generation) chatbots. Instead of relying on a single expensive model to decide every action, this workflow uses a modular…