Automated Gmail support agent with Gemini 2.5, RAG & Cohere reranking
n8n8 modulesv1.0AI Email Support Agent with RAG & Cohere Reranking Transform your inbox into an intelligent support system: automatically detect new emails, retrieve relevant knowledge from Pinecone, rerank with Cohere for precision, generate contextual replies using Gemini AI, and respond—all while maintaining conversation history. What It Does This workflow triggers on incoming Gmail messages, leverages a LangChain agent with PostgreSQL memory for context, queries a Pinecone vector store (RAG) enhanced by Coh
At a glance
Automated Gmail support agent with Gemini 2.5, RAG & Cohere reranking is a ready-made n8n workflow you import as a workflow JSON file — no build required. It connects agent, embeddingsOpenAi, gmail, gmailTrigger. It's free to download. Follow the 5-step import below to go live in minutes.
- Platform
- n8n
- Connects
- agent, embeddingsOpenAi, gmail, gmailTrigger, lmChatGoogleGemini, memoryPostgresChat
- Modules
- 8
- Price
- Free
- Version
- v1.0
About this workflow
AI Email Support Agent with RAG & Cohere Reranking Transform your inbox into an intelligent support system: automatically detect new emails, retrieve relevant knowledge from Pinecone, rerank with Cohere for precision, generate contextual replies using Gemini AI, and respond—all while maintaining conversation history. What It Does This workflow triggers on incoming Gmail messages, leverages a LangChain agent with PostgreSQL memory for context, queries a Pinecone vector store (RAG) enhanced by Cohere reranking and OpenAI embeddings, crafts personalized responses via Gemini 2.5, and auto-replies to keep support flowing. Key Features - Gmail Integration - Real-time polling for new emails every minute - RAG with Pinecone - Retrieves top 10 relevant docs from "agency-info" index as agent tool - Cohere Reranking - Boosts retrieval accuracy by reordering results semantically - Persistent Memory - Postgres chat history keyed by email ID for ongoing threads - Gemini-Powered Agent - Handles queries with custom system prompt for agency support - Seamless Auto-Reply - Sends formatted text responses directly in Gmail Perfect For - Agencies: Automate client FAQs on services, pricing, and ownership - Support Teams: Scale responses without losing conversation context - Small Businesses: Handle inquiries 24/7 with AI-driven accuracy - Developers: Prototype RAG agents with vector stores and rerankers - Marketers: Personalize outreach replies based on knowledge base - Consultants: Quick, informed answers from internal docs Technical Highlights Built on n8n's LangChain ecosystem, this workflow highlights: - Trigger-to-response pipeline with polling and webhooks - Hybrid retrieval: Embeddings + vector search + semantic reranking - Stateful agents with database-backed memory for multi-turn chats - Multi-provider setup: OpenAI (embeddings), Cohere (rerank), Google (LLM) - Scalable for production with configurable topK and session keys Setup Instructions Prerequisites - n8n instance with LangChain nodes enabled - Accounts for: Gmail (OAuth2), OpenAI (API key), Cohere (API key), Google Gemini (API key), Pinecone (API key and index), Postgres (database connection, e.g., Neon or Supabase) Required Credentials Gmail OAuth2 1. Enable Gmail API in Google Cloud Console 2. Create OAuth2 credential in n8n with scopes: OpenAI API 1. Get API key from platform.openai.com 2. Add as OpenAI credential in n8n Cohere API 1. Sign up at cohere.com 2. Copy API key to n8n Cohere credential Google Gemini API 1. Generate key at 2. Add as Google PaLM credential in n8n (compatible with Gemini) Pinecone API 1. Create index "agency-info" with dimension 1024 2. Add API key to n8n Pinecone credential Postgres 1. Set up database (e.g., Neon/Supabase) with a table for chat history 2. Add connection details (host, database, user, password) to n8n Postgres credential Configuration Steps 1. Import the workflow JSON into your n8n instance 2. Assign all required credentials to the respective nodes 3. Populate the Pinecone "agency-info" index with your knowledge base documents (use a separate upsert workflow or Pinecone dashboard) 4. Customize the tableName in the Postgres Memory node if needed (default: "emailsupportagent") 5. Adjust the agent's system prompt or topK retrieval if required for your use case 6. Activate the workflow and test by sending a sample email to trigger it Troubleshooting - No trigger firing: Verify Gmail scopes and polling interval - Empty retrieval: Check Pinecone index population, dimensions (must be 1024), and document embeddings - Rerank errors: Ensure Cohere API key is valid and has sufficient quota - Memory issues: Confirm Postgres connection and that sessionKey uses email ID Perfect for deploying hands-off email automation. Import, connect credentials, and activate!
How to import this n8n workflow
- 1
Download the workflow JSON file after purchase.
- 2
Open n8n → click the menu → Import from File.
- 3
Select the downloaded JSON and import.
- 4
Set up credentials for each node that requires them.
- 5
Click Execute Workflow to test, then activate.
Setup guide
Setup guide included
Purchase to unlock the full step-by-step guide
Related N8n workflows
Interactive recruitment customer service with WhatsApp, Google Sheets CRM
Create an automated customer support assistant with GPT-4o and GoHighLevel SMS
Create stunning AI images directly from WhatsApp with Gemini
Automate newsletter creation & client delivery with GPT-4O, Google Sheets
Fetch Threads analytics for your latest posts and email an HTML report
Create a context-aware Slack assistant with Google Sheets, Pinecone & GPT-4o
Jarvis: productivity AI agent for tasks, calendar, email & expense using MCPs
Generate Images with OpenAI new GPT-Image-1 Model via User-Friendly Form
Reviews
No reviews yet
Be the first to buy and share your experience.
Leave a review
Sign in to share your experience with this workflow.
Create a free account to purchase workflows.
- JSON blueprint — instant download
- Setup guide PDF included
- 5 downloads · valid 30 days
- Works with n8n
Need help setting this up?
Book a 3-hour live setup session with an Agility consultant.
- Configure live on Google Meet / Zoom
- Free follow-up if workflow has defects
- Platform expert assigned to you