Build a multi-tenant RAG search engine with Qdrant and OpenAI GPT-4o

by Alfaz Mahmud Rizve ✓ · 27 views · created 2026-08-24 · Internal Wiki, AI RAG

What this workflow does

This workflow has 11 nodes and runs when an HTTP POST request hits its webhook URL. It uses only n8n's built-in nodes. It also calls api.openai.com over HTTP.

How it runs

Trigger: When an HTTP POST request hits its webhook URL.

1. Tenant Auth & Payload Middleware (Code): runs custom JavaScript code
2. Is Tenant Authenticated? (If): checks a condition and branches into true / false
3. Generate Vector Embeddings (HTTP Request): calls api.openai.com (POST)
4. Respond Unauthorized (Respond to Webhook): sends the response back to the webhook caller
5. Build Qdrant Tenant Filter (Code): runs custom JavaScript code
6. Qdrant Vector Search (HTTP Request): calls an HTTP API (POST)
7. Format Context & Citations (Code): runs custom JavaScript code
8. OpenAI RAG Synthesis Agent (HTTP Request): calls api.openai.com (POST)
9. Assemble RAG Response (Code): runs custom JavaScript code
10. Respond to RAG Client (Respond to Webhook): sends the response back to the webhook caller

HTTP calls to: api.openai.com

Before you upgrade to n8n 3.0

Nodes used (5)

• Webhookn8n-nodes-base.webhook
• Coden8n-nodes-base.code
• Ifn8n-nodes-base.if
• HTTP Requestn8n-nodes-base.httpRequest
• Respond to Webhookn8n-nodes-base.respondToWebhook

From the author

Quick overview This workflow exposes a POST webhook that authenticates a tenant, embeds the user query with OpenAI, searches tenant-scoped vectors in Qdrant, and uses GPT-4o to return a grounded answer with bracketed citations and usage metrics. How it works…

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