Run a RAG support copilot with Claude Sonnet and OpenAI embeddings
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 someone submits an n8n form (“Add to Knowledge Base”) (plus 1 other trigger). Along the way it connects Embeddings OpenAI, Anthropic Chat Model and Gmail.
How it runs
Trigger: When someone submits an n8n form (“Add to Knowledge Base”) (plus 1 other trigger).
- Company Knowledge Base (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Ingest Embeddings; document loader: Document Loader
- AI Support Agent (AI Agent): runs an AI agent, with model: Claude Sonnet 4.; 2 tools (Escalate to Human, Knowledge Base Search); memory: Conversation Memory
- Log Q&A (Data table): uses Data table
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)
- n8n Form Trigger
n8n-nodes-base.formTrigger - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Gmail Tool
n8n-nodes-base.gmailTool - Data table
n8n-nodes-base.dataTable
From the author
Quick overview This template ingests internal docs into an in-memory vector knowledge base using OpenAI embeddings, then runs a public support chat powered by Anthropic Claude that answers only from that knowledge and escalates unanswered requests to a Gmail…