Smarter RAG agents with enriched retrieval and modular workflows
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 24 nodes and runs when a chat message arrives (plus 2 other triggers). Along the way it connects Supabase, Supabase Vector Store, Embeddings Google Gemini and Google Gemini and 3 more.
How it runs
Trigger: When a chat message arrives (plus 2 other triggers).
- Query Builder (Google Gemini): uses Google Gemini
- Extract from File: extracts data from a file (pdf)
- Get many rows (Supabase): get many
- RAG Agent (AI Agent): runs an AI agent, with model: Google Gemini 2.0 Flash; 1 tool (Supabase Vector Store); memory: Postgres Chat Memory
- Set File Data (Edit Fields (Set)): sets 4 fields: doc_id, doc_title, doc_type…
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Delete Old Doc Rows (Supabase): delete
- Merge: merges the data from its input branches
- Edit Fields (Edit Fields (Set)): sets 1 field: row_id
- Insert into Supabase Vectorstore (Supabase Vector Store): stores documents in the Supabase vector store, with embeddings: Embeddings Google Gemini; document loader: Default Data Loader
…plus 3 more steps. 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 (18)
- Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Supabase
n8n-nodes-base.supabase - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - n8n Form Trigger
n8n-nodes-base.formTrigger - Extract from File
n8n-nodes-base.extractFromFile - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Merge
n8n-nodes-base.merge - Wait
n8n-nodes-base.wait - Edit Fields (Set)
n8n-nodes-base.set - Google Gemini
@n8n/n8n-nodes-langchain.googleGemini - Schedule Trigger
n8n-nodes-base.scheduleTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Reranker Cohere
@n8n/n8n-nodes-langchain.rerankerCohere - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat
From the author
An extendable RAG template to build powerful, explainable AI assistants — with query understanding, semantic metadata, and support for free-tier tools like Gemini, Gemma and Supabase. Description This workflow helps you build smart, production-ready RAG…