Multi-language Telegram RAG chatbot with supervisor AI & automated Google Drive pipeline
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 112 nodes and runs manually, when you click “Execute workflow” (plus 7 other triggers). Along the way it connects Google Docs, OpenAI Chat Model, Google Sheets and Google Drive and 6 more.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 7 other triggers).
- Edit Fields (Set): sets 1 field: Crawl4ai End Point
- Loop Over Files (Loop Over Items (Split in Batches)): loops over the items in batches
- Set File Get Data (Edit Fields (Set)): sets 5 fields: id, mimeType, name…
- Google Sheets: uses Google Sheets
- Google Sheets: uses Google Sheets
- Edit Fields Telegram Message (Edit Fields (Set)): sets 3 fields: Chat Input, Session Id, Chat Id
- RAG AI Agent - Product (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (Query Products, Supabase Vector Store)
- Google Sheets: uses Google Sheets
- Set File Data (Edit Fields (Set)): sets 4 fields: file_id, file_type, file_title…
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
…plus 63 more steps. See the full node list below.
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 Content Formatter (v1.8), Supervisor AI Agent1 (v1.6), Output First Translator (v1.6)…: replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Content Formatter (v1.8), Supervisor AI Agent1 (v1.6), Output First Translator (v1.6), Translator1 (v1.6), Output Translator (v1.6), RAG AI Agent - Product (v1.6), RAG AI Agent - Academy (v1.6), RAG AI Agent - News (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (31)
- Manual Trigger
n8n-nodes-base.manualTrigger - Wait
n8n-nodes-base.wait - Google Docs
n8n-nodes-base.googleDocs - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - AI Agent
@n8n/n8n-nodes-langchain.agent - Google Sheets
n8n-nodes-base.googleSheets - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - If
n8n-nodes-base.if - Filter
n8n-nodes-base.filter - Merge
n8n-nodes-base.merge - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set - Google Drive
n8n-nodes-base.googleDrive - Supabase
n8n-nodes-base.supabase - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterCharacterTextSplitter - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Switch
n8n-nodes-base.switch - Extract from File
n8n-nodes-base.extractFromFile - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Aggregate
n8n-nodes-base.aggregate - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Telegram Trigger
n8n-nodes-base.telegramTrigger - Telegram
n8n-nodes-base.telegram - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Postgres Tool
n8n-nodes-base.postgresTool - Google Sheets Tool
n8n-nodes-base.googleSheetsTool
From the author
N8N Hybrid RAG Chatbot with Multiple AI Agents One of the most powerful system in the market, this template creates a sophisticated, multi-agent hybrid RAG (Retrieval-Augmented Generation) chatbot that can handle diverse user queries by routing them to a…