Document Q&A chatbot with Google Drive, GPT-4-mini & Telegram (RAG system)
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 11 nodes and runs on Google Drive events (plus 1 other trigger). Along the way it connects Google Drive, Embeddings OpenAI, OpenAI Chat Model and Telegram.
How it runs
Trigger: On Google Drive events (plus 1 other trigger).
- Download file (Google Drive): uses Google Drive
- AI Agent: runs an AI agent, with model: Model; 1 tool (Retrieve documents); memory: Simple Memory
- Insert documents (Simple Vector Store): uses the Simple vector store, with embeddings: Embedding model; document loader: Default Data Loader
- Telegram: uses Telegram
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 (10)
- Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Google Drive
n8n-nodes-base.googleDrive - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Telegram Trigger
n8n-nodes-base.telegramTrigger - Telegram
n8n-nodes-base.telegram
From the author
Description 📌 Overview This workflow creates a chat-based Retrieval-Augmented Generation (RAG) agent that lets you upload documents to Google Drive and then query them directly through Telegram. It uses embeddings, vector storage, and an AI agent to…