Build a knowledge base chatbot with OpenAI, RAG and MongoDB vector embeddings
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 12 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Embeddings OpenAI, MongoDB Atlas Vector Store and Google Docs.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Google Docs: get
- Knowledge Base Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (MongoDB Vector Search); memory: Simple Memory
- MongoDB Vector Store Inserter (MongoDB Atlas Vector Store): stores documents in the MongoDB Atlas vector store, with embeddings: OpenAI Embeddings Generator; document loader: Document Section Loader
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Knowledge Base Agent (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Knowledge Base Agent (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (10)
- AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Manual Trigger
n8n-nodes-base.manualTrigger - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - MongoDB Atlas Vector Store
@n8n/n8n-nodes-langchain.vectorStoreMongoDBAtlas - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Google Docs
n8n-nodes-base.googleDocs - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger
From the author
Who is this for? This template is designed for internal support teams, product specialists, and knowledge managers in technology companies who want to automate ingestion of product documentation and enable AI-driven, retrieval-augmented question answering.…