Chat with documents via RAG: Google Drive to GPT-5 with Supabase vector database
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 23 nodes and runs on Telegram events (plus 5 other triggers). Along the way it connects Google Drive, Embeddings OpenAI, Supabase Vector Store and Postgres Chat Memory and 5 more.
How it runs
Trigger: On Telegram events (plus 5 other triggers).
- Edit Fields (Edit Fields (Set)): sets or maps fields
- RAG Agent (AI Agent): runs an AI agent, with model: GPT; 1 tool (Supabase Vector Store); memory: Chat Memory
- Download File (Google Drive): uses Google Drive
- Send a text message (Telegram): uses Telegram
- Send message (WhatsApp Business Cloud): uses WhatsApp Business Cloud
- Send a message (Slack): uses Slack
- Send a message (Gmail): uses Gmail
- OCR (Mistral AI): uses Mistral AI
- Split Out: splits a list into separate items
- Insert into Supabase Vectorstore (Supabase Vector Store): uses the Supabase vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in RAG Agent (v1.6): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- Also check Slack Trigger requires a signing secret on the Slack API credential.
- Also check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll).
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) RAG Agent (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (21)
- Google Drive
n8n-nodes-base.googleDrive - Split Out
n8n-nodes-base.splitOut - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Mistral AI
n8n-nodes-base.mistralAi - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - AI Agent
@n8n/n8n-nodes-langchain.agent - Slack Trigger
n8n-nodes-base.slackTrigger - Telegram Trigger
n8n-nodes-base.telegramTrigger - Gmail Trigger
n8n-nodes-base.gmailTrigger - WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - Edit Fields (Set)
n8n-nodes-base.set - Telegram
n8n-nodes-base.telegram - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - Slack
n8n-nodes-base.slack - Gmail
n8n-nodes-base.gmail
From the author
📄 n8n RAG Ingestion & Query Workflow Overview This workflow is your all-in-one pipeline to turn any document into a powerful searchable knowledge base using RAG (Retrieval-Augmented Generation). From the moment a file lands in your Google Drive, it’s…