Route RAG customer support across WhatsApp and Outlook with Pinecone and OpenRouter

by Salman Mehboob ✓ · 211 views · created 2026-06-22 · Support Chatbot, AI RAG

What this workflow does

This AI workflow has 41 nodes and runs when someone submits an n8n form (“Knowledge Base Document Upload”) (plus 3 other triggers). Along the way it connects Pinecone Vector Store, Embeddings Google Gemini, WhatsApp Business Cloud and Slack and 3 more.

How it runs

Trigger: When someone submits an n8n form (“Knowledge Base Document Upload”) (plus 3 other triggers).

1. Insert into Vector Store (Pinecone Vector Store): stores documents in the Pinecone vector store, with embeddings: Embeddings Model; document loader: Document Loader
2. Normalize WhatsApp (Edit Fields (Set)): sets 7 fields: channel, contact_id, contact_name…
3. Normalize Email (Edit Fields (Set)): sets 7 fields: channel, contact_id, contact_name…
4. Extract Contact ID (Edit Fields (Set)): sets 3 fields: contact_id, resolved_by, channel_id
5. Ingestion Success (Edit Fields (Set)): sets 3 fields: status, message, ingested_at
6. Merge (Edit Fields (Set)): sets 7 fields: channel, contact_id, contact_name…
7. Contact ID Provided? (If): checks a condition and branches into true / false
8. Check Handoff (Google Sheets): uses Google Sheets
9. Respond to Slack (OK) (Respond to Webhook): sends the response back to the webhook caller
10. Respond to Slack (Error) (Respond to Webhook): sends the response back to the webhook caller

…plus 19 more steps. See the full node list below.

Services it uses

Pinecone Vector StoreEmbeddings Google GeminiWhatsApp Business CloudSlackMicrosoft OutlookOpenRouter Chat ModelGoogle Sheets

Before you upgrade to n8n 3.0

Nodes used (20)

• n8n Form Triggern8n-nodes-base.formTrigger
• Pinecone Vector Store@n8n/n8n-nodes-langchain.vectorStorePinecone
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Edit Fields (Set)n8n-nodes-base.set
• Embeddings Google Gemini@n8n/n8n-nodes-langchain.embeddingsGoogleGemini
• Token Splitter@n8n/n8n-nodes-langchain.textSplitterTokenSplitter
• WhatsApp Triggern8n-nodes-base.whatsAppTrigger
• AI Agent@n8n/n8n-nodes-langchain.agent
• Simple Memory@n8n/n8n-nodes-langchain.memoryBufferWindow
• Structured Output Parser@n8n/n8n-nodes-langchain.outputParserStructured
• Ifn8n-nodes-base.if
• Slackn8n-nodes-base.slack
• Switchn8n-nodes-base.switch
• WhatsApp Business Cloudn8n-nodes-base.whatsApp
• Microsoft Outlookn8n-nodes-base.microsoftOutlook
• Microsoft Outlook Triggern8n-nodes-base.microsoftOutlookTrigger
• OpenRouter Chat Model@n8n/n8n-nodes-langchain.lmChatOpenRouter
• Google Sheetsn8n-nodes-base.googleSheets
• Webhookn8n-nodes-base.webhook
• Respond to Webhookn8n-nodes-base.respondToWebhook

From the author

Quick overview A production-ready 3-workflow system that handles customer support across WhatsApp and Email using RAG-powered AI. Automatically routes queries, detects escalation intent, logs handoffs to Google Sheets, alerts your team via Slack, and lets…

View the original on n8n.io → Check your own copy