# Build a website RAG support chatbot with Firecrawl: n8n workflow

> Started by someone opening a chat with it, and works across Pinecone. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents...

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

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

# Build a website RAG support chatbot with Firecrawl

Started by someone opening a chat with it, and works across Pinecone. It puts Gemini and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 22 steps, 1 branch, 2 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini, OpenAI Retrieval

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

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

**1** Branch: places the flow splits

**2** Loops or waits

**1** Service it connects to

## The flow

Starts it 2 Model 8 Logic 8 Service 4

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

- 1 **Document Loader** Document Default Data Loader *Model*
- 2 **When chat message received** Chat trigger *Starts it*
- 3 **Chat Memory** Memory Buffer Window *Model*
- 4 **OpenAI Embeddings** Embeddings Open Ai *Model*
- 5 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 6 **Embeddings Google Gemini** Embeddings Google Gemini *Model*
- 7 **Website URL Form** Form trigger *Starts it*
- 8 **Store in Vector Database** Vector Store Pinecone *Model*
- 9 **Customer Support Agent** Agent *Model*
- 10 **Pinecone Vector Storage** Vector Store Pinecone *Model*
- 11 **Normalize Website URL** Set *Logic*
- 12 **Process URLs One by One** Split In Batches *Logic*
- 13 **Get Pinecone Index Host** Http Request *Service*
- 14 **Rate Limit Delay** Wait *Logic*
- 15 **Clear Pinecone Namespace (Prevent Duplicates)** Http Request *Service*
- 16 **Fetch Page Content** Http Request *Service*
- 17 **Map Website URLs** Firecrawl *Service*
- 18 **Extract HTML and URL** Set *Logic*
- 19 **Filter and Normalize URLs** Code *Logic*
- 20 **Clean HTML to Text** Code *Logic*
- 21 **Check Text Length** If *Logic*
- 22 **Split Text into Chunks** Code *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 22, with 1 branch, 2 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Pinecone
- **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 Pinecone account, 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?

Take your time. At 22 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 22 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-rag-support-chatbot-with-firecrawl)
- **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.

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

## Workflows like it

Also customer support, with the same services where possible, closest in size first.

- [**Build a website-powered customer support chatbot with Decodo** 22 steps · calls a model · Pinecone](https://millionrounds.com/workflow/build-a-website-powered-customer-support-chatbot-with-decodo)
- [**AI email support system: Gmail, Gemini, GPT-4, Slack & Google** 23 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/ai-email-support-system-gmail-gemini-gpt-4-slack-and-google)
- [**Build RAG-powered support agent for Jira issues with Pinecone** 23 steps · calls a model · Pinecone](https://millionrounds.com/workflow/build-rag-powered-support-agent-for-jira-issues-with-pinecon)
- [**Automate Airbnb guest support with OpenAI and Google Drive** 24 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/automate-airbnb-guest-support-with-openai-and-google-drive)
- [**Route SaaS helpdesk chats with SoterAI and Groq** 20 steps · calls a model · Pinecone](https://millionrounds.com/workflow/route-saas-helpdesk-chats-with-soterai-and-groq)
- [**Answer Slack knowledge questions with Notion and Google Drive** 25 steps · calls a model · Google Drive, Notion](https://millionrounds.com/workflow/answer-slack-knowledge-questions-with-notion-and-google-driv)