Provide academic OCR and RAG answers on Telegram with Gemini, GPT-4 mini and Supabase
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 28 nodes and runs on Google Drive events (file created) (plus 2 other triggers). Along the way it connects Telegram, Google Sheets, OpenAI Chat Model and Google Drive and 5 more.
How it runs
Trigger: On Google Drive events (file created) (plus 2 other triggers).
- Download file (Google Drive): download
- Get many rows (Supabase): get many
- Switch: routes items into 4 branches
- Supabase Vector Store: stores documents in the Supabase vector store, with embeddings: Embeddings OpenAI; document loader: Default Data Loader
- Append or update row in sheet (Google Sheets): append or update
- AI Agent: runs an AI agent, with model: OpenAI Chat Model; 1 tool (Supabase Vector Store); memory: Postgres Chat Memory
- from File (Extract from File): extracts data from a file (binary to propery)
- Telegram: uses Telegram
- Get row(s) in sheet (Google Sheets): uses Google Sheets
- Send a text message (Telegram): uses Telegram
…plus 7 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 (19)
- Telegram Trigger
n8n-nodes-base.telegramTrigger - Switch
n8n-nodes-base.switch - If
n8n-nodes-base.if - HTTP Request
n8n-nodes-base.httpRequest - Telegram
n8n-nodes-base.telegram - Google Sheets
n8n-nodes-base.googleSheets - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - AI Agent
@n8n/n8n-nodes-langchain.agent - Google Sheets Tool
n8n-nodes-base.googleSheetsTool - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Google Drive
n8n-nodes-base.googleDrive - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Supabase
n8n-nodes-base.supabase - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - Extract from File
n8n-nodes-base.extractFromFile - Embeddings Hugging Face Inference
@n8n/n8n-nodes-langchain.embeddingsHuggingFaceInference
From the author
🛠️ How It Works: System Architecture Workflow ini bekerja melalui empat lapisan proses utama yang terintegrasi secara otomatis: 1. Input Processing & Routing Telegram Trigger: Menangkap setiap pesan masuk dari mahasiswa. Smart Routing (Switch): Node Switch…