Customer Support involved to set up

RAG Chatbot with Supabase and TogetherAI

Ingests Google Docs into a vector database via Together AI and answers Telegram questions using only that retrieved context.

Verified 2026-07-07

Developer-EngineeringPersonal-Consumer

What it does

Get instant answers to your questions via Telegram by asking about content stored in your Google Docs. The agent pulls only the relevant information from those documents to provide accurate responses without needing external knowledge.

How it works

When it runs: Triggered by an event · Event · on new Telegram message
How hands-off: Assists you, you do the final step
Setup: A bigger project · a few focused days
Works with: Telegram, Google Docs, Supabase, Together AI, OpenRouter Chat Model

Tools that fit

Services

Telegram : User interaction trigger and response delivery

Google Docs : Source document retrieval for training data

Supabase : Storing text chunks and vector embeddings

api

Together AI : Generating vector embeddings for text

LLM

OpenRouter Chat Model : LLM inference to generate answers from context

Watch out for

Supabase vector search performance degrades without a proper index, so add an IVFFlat or HNSW index on the embedding column.
Google Docs API may return rich text HTML instead of plain text, so strip all HTML tags before chunking to avoid noise in embeddings.
Together AI rate limits can block the ingestion pipeline, add exponential backoff logic to your HTTP request step.
Context window overflow occurs if too many chunks are retrieved, implement a relevance score threshold to filter out weak matches.

Seen in the wild

n8n: RAG Chatbot with Supabase + TogetherAI + Openrouter template

Want this running in your business?

This is what I do. I design and build AI agents like this one, and keep them running. If you want it set up for your team instead of doing it yourself, get in touch.

Get in touch

Who it's for

Built for developers who want the busywork around code automated, not the code itself.

Works just as well for personal use, no business context needed.

Frequently asked questions

Who is this for?

developers and engineers and anyone managing their own day, or anyone doing customer support work who wants this handled automatically rather than manually.

How long does it take to set up?

A bigger project: plan for a few focused days to get it running end to end.

Related use cases

← Back to directory