Draft grounded Gmail support replies from a Notion KB with Groq and Cohere
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 1 other trigger). Along the way it connects Notion, Gmail, Groq Chat Model and Embeddings Cohere and 1 more.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Get KB Articles (Notion): get many (database page)
- Normalize Email (Edit Fields (Set)): sets 8 fields: emailSubject, emailBody, senderEmail…
- Check If Published (If): checks a condition and branches into true / false
- Classify Inquiry (Text Classifier): classifies text into categories with AI, with model: Groq Triage Model
- Get Article Body (Notion): get many (block)
- Retrieve From KB (Simple Vector Store): searches the Simple vector store, with embeddings: Embed Query With Cohere
- Assemble Article Documents (Code): runs custom JavaScript code
- Bundle Retrieved Sources (Code): runs custom JavaScript code
- Store KB Vectors (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Embed Articles With Cohere; document loader: Load Article Text
- Check Retrieval Confidence (If): checks a condition and branches into true / false
…plus 4 more steps. See the full node list below.
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 (15)
- Manual Trigger
n8n-nodes-base.manualTrigger - Notion
n8n-nodes-base.notion - If
n8n-nodes-base.if - Code
n8n-nodes-base.code - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Gmail Trigger
n8n-nodes-base.gmailTrigger - Edit Fields (Set)
n8n-nodes-base.set - Text Classifier
@n8n/n8n-nodes-langchain.textClassifier - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Gmail
n8n-nodes-base.gmail - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq - Embeddings Cohere
@n8n/n8n-nodes-langchain.embeddingsCohere - Reranker Cohere
@n8n/n8n-nodes-langchain.rerankerCohere
From the author
Quick Overview This workflow ingests published Notion knowledge base articles into an in-memory vector store using Cohere embeddings, then monitors a support Gmail inbox and uses Groq to draft grounded reply emails based only on retrieved KB sources, saving…