Telegram Document Q&A Bot with Gemini AI & Supabase Vector Search

Build a Telegram AI chatbot that answers questions from uploaded PDFs using Gemini for embeddings and Supabase for vector search, with rich HTML formatting.

This n8n workflow creates an intelligent Telegram bot for document-based Q&A. Users upload PDFs, which are processed to generate embeddings via Google Gemini and stored in a Supabase vector database. When users ask questions, the bot performs vector similarity search to retrieve relevant chunks, then Gemini generates context-aware responses formatted with HTML for Telegram. Key features include adaptive message chunking for long responses and intelligent post-processing for rich Telegram format
Platform
n8n
Category
Development & IT
Price
$24.99
Creator
Bruno Jonsson

How to import this workflow into n8n

  1. 1Purchase or download the workflow to get the n8n workflow JSON file.
  2. 2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
  3. 3Open each node marked with a credential warning and connect your own accounts and API keys.
  4. 4Run the workflow once manually to verify the data flow, then toggle it to Active.

Related Development & IT workflows

More from Bruno Jonsson

All Development & IT workflows →All n8n workflows →

Need this deployed? We'll set it up for you.

Our automation experts deploy this workflow in your stack, connect your accounts, and verify it works — or build a custom solution from scratch.

Get It DeployedCustom Build