# Create an customer support assistant with OpenAI: n8n workflow

> Started by another system calling it, and works across GoHighLevel and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from...

Source: https://millionrounds.com/workflow/create-an-customer-support-assistant-with-openai (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)

# Create an customer support assistant with OpenAI

Started by another system calling it, and works across GoHighLevel and in-memory vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 34 steps, 1 branch, 2 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%2Fcreate-an-customer-support-assistant-with-openai)

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

**1** Branch: places the flow splits

**2** Loops or waits

**2** Services it connects to

## The flow

Starts it 2 Model 10 Logic 15 Service 7

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

- 1 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 2 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 3 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 4 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 5 **Redis Chat Memory** Memory Redis Chat *Model*
- 6 **Schedule Trigger** Schedule trigger *Starts it*
- 7 **Webhook from GHL - SMS Reply Trigger** Webhook *Starts it*
- 8 **Direct API access via HTTP** Http Request *Service*
- 9 **Direct API access via HTTP1** Http Request *Service*
- 10 **Simple Vector Store** Vector Store In Memory *Model*
- 11 **Simple Vector Store2** Vector Store In Memory *Model*
- 12 **Default Data Loader** Document Default Data Loader *Model*
- 13 **AI Agent** Agent *Model*
- 14 **Simple Vector Store1** Vector Store In Memory *Model*
- 15 **Set Website URL** Set *Logic*
- 16 **If** If *Logic*
- 17 **Wait** Wait *Logic*
- 18 **Send SMS via GHL** Http Request *Service*
- 19 **BrightData** Bright Data *Service*
- 20 **Look Up GHL Contact by ID** High Level *Service*
- 21 **Loop Over Items** Split In Batches *Logic*
- 22 **HTML** Html *Logic*
- 23 **Set Website URL1** Set *Logic*
- 24 **BrightData1** Bright Data *Service*
- 25 **Get sitemap** Http Request *Service*
- 26 **Split Out** Split Out *Logic*
- 27 **HTML1** Html *Logic*
- 28 **Get XML file** Xml *Logic*
- 29 **Merge** Merge *Logic*
- 30 **Filter** Filter *Logic*
- 31 **Split out links** Split Out *Logic*
- 32 **Remove Duplicates1** Remove Duplicates *Logic*
- 33 **Edit Links** Set *Logic*
- 34 **Edit Links1** Set *Logic*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 34, with 1 branch, 2 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** GoHighLevel, in-memory 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 GoHighLevel and in-memory vectors accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

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%2Fcreate-an-customer-support-assistant-with-openai)
- **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.

[GoHighLevel](https://millionrounds.com/workflows?service=GoHighLevel#library)[in-memory vectors](https://millionrounds.com/workflows?service=in-memory+vectors#library)

## Workflows like it

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

- [**Draft grounded Gmail support replies from a Notion KB** 23 steps · calls a model · Gmail, Notion](https://millionrounds.com/workflow/draft-grounded-gmail-support-replies-from-a-notion-kb)
- [**Run a customer support RAG chatbot with OpenAI** 21 steps · calls a model · Google Drive, Telegram](https://millionrounds.com/workflow/run-a-customer-support-rag-chatbot-with-openai)
- [**Draft customer support email replies with Gmail** 17 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/draft-customer-support-email-replies-with-gmail)
- [**Answer customer questions and book jobs with OpenAI RAG** 16 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/answer-customer-questions-and-book-jobs-with-openai-rag-2)
- [**Answer customer questions and book jobs with OpenAI RAG** 16 steps · calls a model · Gmail, Google Calendar](https://millionrounds.com/workflow/answer-customer-questions-and-book-jobs-with-openai-rag)
- [**Dual-path customer support system with Google Sheets** 15 steps · calls a model · Google Sheets, in-memory vectors](https://millionrounds.com/workflow/dual-path-customer-support-system-with-google-sheets)