# Build a website AI chatbot with Gemini and Supabase RAG: n8n workflow

> Started by someone opening a chat with it, and works across Google Drive, Supabase and Supabase vectors.

Source: https://millionrounds.com/workflow/build-a-website-ai-chatbot-with-gemini-and-supabase-rag (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Lead generation](https://millionrounds.com/workflows?category=Lead+generation#library)

# Build a website AI chatbot with Gemini and Supabase RAG

Started by someone opening a chat with it, and works across Google Drive, Supabase and Supabase vectors. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 19 steps, 1 loop or waits: a working afternoon to understand properly.

Medium Calls a model: Gemini, OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-website-ai-chatbot-with-gemini-and-supabase-rag)

**19 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**1** Loop or waits

**3** Services it connects to

## The flow

Starts it 3 Model 11 Logic 3 Service 2

The steps in the order they run, from what starts it.

- 1 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 2 **Google Drive Trigger** Google Drive trigger *Starts it*
- 3 **Google Drive Trigger1** Google Drive trigger *Starts it*
- 4 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 5 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 6 **Think** Tool Think *Model*
- 7 **Calculator** Tool Calculator *Model*
- 8 **conversation buffer** Memory Buffer Window *Model*
- 9 **When chat message received** Chat trigger *Starts it*
- 10 **Code Tool** Tool Code *Model*
- 11 **Support Agent** Agent *Model*
- 12 **Set the fields for mapping** Set *Logic*
- 13 **Default Data Loader** Document Default Data Loader *Model*
- 14 **Supabase Vector Store** Vector Store Supabase *Model*
- 15 **Knowledgebase** Vector Store Supabase *Model*
- 16 **Data Normalizer** Code *Logic*
- 17 **Deletes old records** Supabase *Service*
- 18 **Loop Over Items** Split In Batches *Logic*
- 19 **Download file** Google Drive *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 19, 1 loop or waits
- **Size:** Medium: a working afternoon
- **Connects to:** Google Drive, Supabase, Supabase vectors
- **Model:** Gemini, OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, plus your own Google Drive, Supabase and Supabase vectors accounts, and a key for Gemini and OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls Gemini and OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 19 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 19 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-website-ai-chatbot-with-gemini-and-supabase-rag)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[Supabase](https://millionrounds.com/workflows?service=Supabase#library)[Supabase vectors](https://millionrounds.com/workflows?service=Supabase+vectors#library)

## Workflows like it

Also lead generation, with the same services where possible, closest in size first.

- [**Create Gmail drafts from business cards with Google Drive** 19 steps · calls a model · Discord, Gmail](https://millionrounds.com/workflow/create-gmail-drafts-from-business-cards-with-google-drive)
- [**Automated lead capture & AI-personalized audio follow-up** 18 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/automated-lead-capture-and-ai-personalized-audio-follow-up)
- [**Create AI personalized video & voice outreach with HeyGen** 18 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/create-ai-personalized-video-and-voice-outreach-with-heygen)
- [**LinkedIn lead personalization with Google Drive and Apify** 18 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/linkedin-lead-personalization-with-google-drive-and-apify)
- [**AI-powered lead generation with Apollo and OpenAI** 21 steps · calls a model · Apify, Postgres](https://millionrounds.com/workflow/ai-powered-lead-generation-with-apollo-and-openai)
- [**Analyze sales calls & route leads with OpenAI and Airtable** 17 steps · calls a model · Airtable, Gmail](https://millionrounds.com/workflow/analyze-sales-calls-and-route-leads-with-openai-and-airtable)