# Websites into a conversational knowledge base with OpenAI RAG: n8n workflow

> Started by someone submitting a form, and works across Supabase and Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/websites-into-a-conversational-knowledge-base-with-openai-ra (Millionrounds; every figure on the page links to its filing or article)

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

# Websites into a conversational knowledge base with OpenAI RAG

Started by someone submitting a form, and works across Supabase and Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 34 steps, 7 branches, 4 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fwebsites-into-a-conversational-knowledge-base-with-openai-ra)

**34 steps** Large: read it before trusting it with anything live

**7** Branches: places the flow splits

**4** Loops or waits

**2** Services it connects to

## The flow

Starts it 2 Model 4 Logic 16 Service 12

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

- 1 **On form submission** Form trigger *Starts it*
- 2 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 3 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 4 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 5 **Add to Supabase** Supabase *Service*
- 6 **Supabase Vector Store** Vector Store Supabase *Model*
- 7 **Default Data Loader** Document Default Data Loader *Model*
- 8 **Check Supabase Errors** Supabase *Service*
- 9 **Check Supabase** Supabase *Service*
- 10 **Update Supabase** Supabase *Service*
- 11 **If ERRORs Exist** If *Logic*
- 12 **If** If *Logic*
- 13 **Slow down** Wait *Logic*
- 14 **Limit One Error** Limit *Logic*
- 15 **Limit** Limit *Logic*
- 16 **Check Page** Http Request *Service*
- 17 **Get page** Http Request *Service*
- 18 **If Page Exist** If *Logic*
- 19 **If SUCCESS** If *Logic*
- 20 **Supabase Reactivate Page** Supabase *Service*
- 21 **Supabase Deactivate Page** Supabase *Service*
- 22 **If PDF** If *Logic*
- 23 **Supabase** Supabase *Service*
- 24 **Extract from PDF** Extract From File *Service*
- 25 **Extract Text & Links & Emails** Code *Logic*
- 26 **Tea time** Wait *Logic*
- 27 **If1** If *Logic*
- 28 **Split Out** Split Out *Logic*
- 29 **Prepare Content** Set *Logic*
- 30 **Loop Over Items** Split In Batches *Logic*
- 31 **Check Already in Supabase** Supabase *Service*
- 32 **If NOT EXIST** If *Logic*
- 33 **Wait** Wait *Logic*
- 34 **Save to Supabase** Supabase *Service*

## How it's built

- **Starts on:** Someone submitting a form
- **Steps:** 34, with 7 branches, 4 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Supabase, Supabase vectors
- **Model:** 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 Supabase and Supabase vectors accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone submitting a form.

Does it use AI?

Yes. It calls 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?

Take your time. At 34 steps it is large: read it before trusting it with anything live.

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 34 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%2Fwebsites-into-a-conversational-knowledge-base-with-openai-ra)
- **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.

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

## Workflows like it

Also data collection, with the same services where possible, closest in size first.

- [**Create a self-updating RAG chatbot with Google Drive** 34 steps · calls a model · Google Drive, Postgres](https://millionrounds.com/workflow/create-a-self-updating-rag-chatbot-with-google-drive)
- [**From sitemap crawling to vector storage: Creating an efficient** 35 steps · calls a model · Postgres, Supabase](https://millionrounds.com/workflow/from-sitemap-crawling-to-vector-storage-creating-an-efficien)
- [**Google Drive to Pinecone vector storage workflow with OpenAI** 32 steps · calls a model · Google Drive, Supabase](https://millionrounds.com/workflow/google-drive-to-pinecone-vector-storage-workflow-with-openai)
- [**Automate viral video generation with Shotstack, OpenAI, and S3** 30 steps · calls a model · S3, Supabase](https://millionrounds.com/workflow/automacao-gerar-videos-virais-shotstack-with-openai-and-s3)
- [**Adaptive email auto-responder with OpenAI and Gmail** 29 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/adaptive-email-auto-responder-with-openai-and-gmail)
- [**Autonomous AI crawler with OpenAI and Supabase** 28 steps · calls a model · Supabase](https://millionrounds.com/workflow/autonomous-ai-crawler-with-openai-and-supabase)