Build an advanced multi-query RAG system with Supabase and GPT-5
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 18 nodes and runs when a chat message arrives (plus 1 other trigger). Along the way it connects OpenAI Chat Model, Supabase Vector Store and Embeddings OpenAI.
How it runs
Trigger: When a chat message arrives (plus 1 other trigger).
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 2 tools (Think, Query knowledge base); memory: Simple Memory
- Split Out: splits a list into separate items
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Aggregate: combines items into one
- Supabase Vector Store: searches the Supabase vector store, with embeddings: Embeddings OpenAI
- Clean RAG output (Edit Fields (Set)): sets 1 field: Chunk content
- Keep score over 0. (Filter): keeps only the items that match a condition
- Any chunk? (If): checks a condition and branches into true / false
- Aggregate: combines items into one
- Say no chunk match (Edit Fields (Set)): sets 1 field: Retrieval output
…plus 1 more step. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (15)
- AI Agent
@n8n/n8n-nodes-langchain.agent - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Split Out
n8n-nodes-base.splitOut - Aggregate
n8n-nodes-base.aggregate - If
n8n-nodes-base.if - Edit Fields (Set)
n8n-nodes-base.set - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Think Tool
@n8n/n8n-nodes-langchain.toolThink - Filter
n8n-nodes-base.filter
From the author
Go beyond basic Retrieval-Augmented Generation (RAG) with this advanced template. While a simple RAG setup can answer straightforward questions, it often fails when faced with complex queries and can be polluted by irrelevant information. This workflow…