# Chatbot Workflow with Vector Store: n8n workflow template

> Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/chatbot-workflow-with-vector-store (Millionrounds; every figure on the page links to its filing or article)

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

# Chatbot Workflow with Vector Store

Started by someone opening a chat with it. It calls services over plain HTTP rather than through connectors. It puts Gemini behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 21 steps, 1 loop or waits: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fchatbot-workflow-with-vector-store)

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

**0** Branches: places the flow splits

**1** Loop or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 2 Model 12 Logic 5 Service 2

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

- 1 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 2 **Google Gemini Chat Model2** Lm Chat Google Gemini *Model*
- 3 **Google Gemini Chat Model3** Lm Chat Google Gemini *Model*
- 4 **Embeddings Google Gemini3** Embeddings Google Gemini *Model*
- 5 **Embeddings Google Gemini1** Embeddings Google Gemini *Model*
- 6 **Recursive Character Text Splitter1** Text Splitter Recursive Character Text Splitter *Model*
- 7 **Redis Chat Memory** Memory Redis Chat *Model*
- 8 **Structured Output Parser** Output Parser Structured *Model*
- 9 **When chat message received** Chat trigger *Starts it*
- 10 **HTTP Request** Http Request *Service*
- 11 **AI Agent1** Agent *Model*
- 12 **kb_tool** Tool Vector Store *Model*
- 13 **Redis Vector Store1** Vector Store Redis *Model*
- 14 **Redis Vector Store** Vector Store Redis *Model*
- 15 **Default Data Loader1** Document Default Data Loader *Model*
- 16 **XML** Xml *Logic*
- 17 **Loop URLs** Split In Batches *Logic*
- 18 **Split Out** Split Out *Logic*
- 19 **Scrape Page** Http Request *Service*
- 20 **Code in JavaScript** Code *Logic*
- 21 **HTML** Html *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 21, 1 loop or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Gemini
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, and a key for Gemini. 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. 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 21 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 21 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%2Fchatbot-workflow-with-vector-store)
- **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.

## Workflows like it

Also ai assistants, with the same services where possible, closest in size first.

- [**Agile project generator with ClickUp and OpenAI** 21 steps · calls a model · ClickUp, Gmail](https://millionrounds.com/workflow/agile-project-generator-with-clickup-and-openai)
- [**Assess credential risk and route mitigation actions** 21 steps · calls a model](https://millionrounds.com/workflow/assess-credential-risk-and-route-mitigation-actions)
- [**Beginner's Guide to Workflow Automation with OpenAI** 21 steps · calls a model](https://millionrounds.com/workflow/beginner-s-guide-to-workflow-automation-with-openai)
- [**Build an on-premises AI Kaggle competition assistant** 21 steps · calls a model · Qdrant](https://millionrounds.com/workflow/build-an-on-premises-ai-kaggle-competition-assistant)
- [**Create AI-powered YouTube shorts with OpenAI** 21 steps · calls a model](https://millionrounds.com/workflow/create-ai-powered-youtube-shorts-with-openai)
- [**Cybersecurity Intelligence: Create Daily Digest & Viral Topics** 21 steps · calls a model · Baserow, Email](https://millionrounds.com/workflow/cybersecurity-intelligence-create-daily-digest-and-viral-top)