Answer HR policy questions in Telegram with Groq, Gemini and Google Drive
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 12 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Google Drive, Embeddings Google Gemini, Telegram and Groq Chat Model.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Download PDF from Google Drive (Google Drive): download
- HR Q&A Agent (AI Agent): runs an AI agent, with model: Groq Chatbot Model; 1 tool (HR Policy Vector Storage); memory: Memory Buffer for Chat
- Store in Vector Database (Simple Vector Store): stores documents in the Simple vector store, with embeddings: Generate Gemini Embeddings; document loader: Load PDF Data
- Send Reply on Telegram (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)
- Manual Trigger
n8n-nodes-base.manualTrigger - Google Drive
n8n-nodes-base.googleDrive - Simple Vector Store
@n8n/n8n-nodes-langchain.vectorStoreInMemory - Embeddings Google Gemini
@n8n/n8n-nodes-langchain.embeddingsGoogleGemini - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Telegram Trigger
n8n-nodes-base.telegramTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Telegram
n8n-nodes-base.telegram - Groq Chat Model
@n8n/n8n-nodes-langchain.lmChatGroq - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow
From the author
Quick overview This workflow indexes an HR policy PDF from Google Drive into an in-memory vector store using Google Gemini embeddings, then answers employee questions sent via Telegram using a Groq chat model with retrieval-augmented generation. How it works…