# Vector database as a big data analysis tool for AI agents [2/3: n8n workflow

> Started by an event in a connected app. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/vector-database-as-a-big-data-analysis-tool-for-ai-agents-2- (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Research and reporting](https://millionrounds.com/workflows?category=Research+and+reporting#library)

# Vector database as a big data analysis tool for AI agents [2/3

Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. 26 steps: large, and worth reading before you trust it with anything live.

Large

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fvector-database-as-a-big-data-analysis-tool-for-ai-agents-2-)

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

**0** Branches: places the flow splits

**0** Loops or waits

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

## The flow

Starts it 1 Logic 13 Service 12

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

- 1 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 2 **Qdrant cluster variables** Set *Logic*
- 3 **Medoids Variables** Set *Logic*
- 4 **Text Medoids Variables** Set *Logic*
- 5 **Total Points in Collection** Http Request *Service*
- 6 **Textual (visual) crop descriptions** Set *Logic*
- 7 **Crop Counts** Http Request *Service*
- 8 **Split Out1** Split Out *Logic*
- 9 **Info About Crop Clusters** Set *Logic*
- 10 **Merge** Merge *Logic*
- 11 **Split Out** Split Out *Logic*
- 12 **Embed text** Http Request *Service*
- 13 **Cluster Distance Matrix** Http Request *Service*
- 14 **Get Medoid by Text** Http Request *Service*
- 15 **Scipy Sparse Matrix** Code *Logic*
- 16 **Set text medoid id** Http Request *Service*
- 17 **Prepare for Searching Threshold1** Set *Logic*
- 18 **Set medoid id** Http Request *Service*
- 19 **Get Medoid Vector** Http Request *Service*
- 20 **Searching Text Medoid Score** Http Request *Service*
- 21 **Prepare for Searching Threshold** Set *Logic*
- 22 **Threshold Score1** Set *Logic*
- 23 **Searching Score** Http Request *Service*
- 24 **Set text medoid threshold score** Http Request *Service*
- 25 **Threshold Score** Set *Logic*
- 26 **Set medoid threshold score** Http Request *Service*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 26
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** None. This is plumbing, not judgement

## Questions

What does it need to run?

An n8n account. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Take your time. At 26 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 26 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%2Fvector-database-as-a-big-data-analysis-tool-for-ai-agents-2-)
- **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 research and reporting, with the same services where possible, closest in size first.

- [**Build a self-hosted URL shortener with Airtable** 26 steps · Airtable](https://millionrounds.com/workflow/build-a-self-hosted-url-shortener-with-airtable)
- [**Generate AI Facebook ad variants from competitors** 26 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/generate-ai-facebook-ad-variants-from-competitors)
- [**Generate comprehensive financial reports with OpenAI and Gmail** 26 steps · calls a model · Gmail, Google Docs](https://millionrounds.com/workflow/generate-comprehensive-financial-reports-with-openai-and-gma)
- [**Generate weekly AI equity research reports with Google Sheets** 26 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/generate-weekly-ai-equity-research-reports-with-google-sheet)
- [**Track npm package downloads with Telegram** 25 steps · Telegram](https://millionrounds.com/workflow/track-npm-package-downloads-with-telegram)
- [**AI Forex Trader with News Sentiment Analysis** 27 steps · calls a model · Discord](https://millionrounds.com/workflow/ai-forex-trader-with-news-sentiment-analysis)