Gmail customer support auto-responder with Ollama LLM and Pinecone RAG
Needs changesWhat this workflow does
This AI workflow has 10 nodes and runs on Gmail events. Along the way it connects Gmail, Pinecone Vector Store, Ollama Model and Embeddings Ollama and 1 more.
How it runs
Trigger: On Gmail events.
- Text Classifier: classifies text into categories with AI, with model: Ollama Model
- AI Agent: runs an AI agent, with model: Ollama Chat Model; 1 tool (Pinecone Vector Store); memory: Simple Memory
- Label (Gmail): uses Gmail
- Send (Gmail): uses Gmail
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 AI Agent (v1.8): 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).
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- Gmail Trigger
n8n-nodes-base.gmailTrigger - Text Classifier
@n8n/n8n-nodes-langchain.textClassifier - AI Agent
@n8n/n8n-nodes-langchain.agent - Pinecone Vector Store
@n8n/n8n-nodes-langchain.vectorStorePinecone - Gmail
n8n-nodes-base.gmail - Ollama Model
@n8n/n8n-nodes-langchain.lmOllama - Embeddings Ollama
@n8n/n8n-nodes-langchain.embeddingsOllama - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow
From the author
Gmail Customer Support Auto-Responder with Ollama LLM and Pinecone RAG Built by Setidure Technologies Automate intelligent, friendly replies to customer queries using AI, vector search, and Gmail — all without human effort. --- Overview This is a…