Gmail assistant with full Gmail history RAG using OpenAI
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 20 nodes and runs when a chat message arrives (plus 2 other triggers). Along the way it connects OpenAI Chat Model, Embeddings OpenAI, Qdrant Vector Store and Gmail.
How it runs
Trigger: When a chat message arrives (plus 2 other triggers).
- RAG Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 1 tool (Qdrant Email Vector Store); memory: Simple Memory
- Get new Email Body (Gmail): get
- Get all emails (Gmail): get many
- Store Emails in Vector DB (Qdrant Vector Store): stores documents in the Qdrant vector store, with embeddings: Embeddings OpenAI; document loader: Set proper metadata
- Refactor Email Body data (Code): runs custom JavaScript code
- Loop over all emails (Loop Over Items (Split in Batches)): loops over the items in batches
- Store Emails in Vector DB (Qdrant Vector Store): stores documents in the Qdrant vector store, with embeddings: Embeddings OpenAI; document loader: Set proper metadata
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 RAG Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- Also check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) RAG Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (13)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Manual Trigger
n8n-nodes-base.manualTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Gmail Trigger
n8n-nodes-base.gmailTrigger - Gmail
n8n-nodes-base.gmail - Code
n8n-nodes-base.code - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter
From the author
🧠 RAG with Full Gmail history + Real time email updates in RAG using OpenAI & Qdrant > Summary: > This workflow listens for new Gmail messages, extracts and cleans email content, generates embeddings via OpenAI, stores them in a Qdrant vector database,…