Create a Multi-Modal Telegram Support Bot with GPT-4 and Supabase RAG

This n8n workflow transforms your Telegram bot into an intelligent, multi-modal AI assistant. It processes text, documents, images, and audio messages using OpenAI models and responds with context-aware answers. The integration with Supabase enables a Retrieval-Augmented Generation (RAG) experience by storing document embeddings and retrieving relevant information.

The workflow enhances traditional support bots by supporting multiple input formats, dynamically extracting and processing data from uploaded files. It implements RAG by combining user input with relevant memory or vector-based context, delivering more accurate, relevant, and human-like AI responses. Ideal for businesses automating support, freelancers offering AI chatbots, and developers exploring AI with multi-format input and vector memory.
Platform
n8n
Category
Customer Support
Price
$24.99
Creator
Chloe Dubois

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 Customer Support workflows

More from Chloe Dubois

All Customer Support 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