Document-based AI chatbot with RAG, OpenAI and Cohere reranker
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 (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Embeddings OpenAI, Google Drive and Supabase Vector Store and 1 more.
How it runs
Trigger: When a chat message arrives (plus 1 other trigger).
- RAG Agent (AI Agent): runs an AI agent, with model: AI Model (OpenAI); 1 tool (Knowledge Base Search); memory: Conversation Memory
- Download PDF from Drive (Google Drive): download
- Extract PDF Content (Extract from File): extracts data from a file (pdf)
- Store in Vector Database (Supabase Vector Store): stores documents in the Supabase vector store, with embeddings: Document Embeddings; document loader: Process Document Text
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 (11)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Manual Trigger
n8n-nodes-base.manualTrigger - Google Drive
n8n-nodes-base.googleDrive - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Extract from File
n8n-nodes-base.extractFromFile - Reranker Cohere
@n8n/n8n-nodes-langchain.rerankerCohere
From the author
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Build intelligent AI chatbot with RAG and Cohere Reranker Who is it for? This template is perfect for developers, businesses, and automation enthusiasts who…