# Scrape query from Serper API than add Airtable and ZEP: n8n workflow

> Started by an event in a connected app, and works across Airtable. It puts a language model behind a retrieval step, so answers are drawn from documents you...

Source: https://millionrounds.com/workflow/scrape-query-from-serper-api-than-add-airtable-and-zep (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)

# Scrape query from Serper API than add Airtable and ZEP

Started by an event in a connected app, and works across Airtable. It puts a language model behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 43 steps, 2 branches, 6 loops or waits: large, and worth reading before you trust it with anything live.

Large Calls a model Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fscrape-query-from-serper-api-than-add-airtable-and-zep)

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

**2** Branches: places the flow splits

**6** Loops or waits

**1** Service it connects to

## The flow

Starts it 1 Model 17 Logic 16 Service 9

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

- 1 **On new manual Chat Message** Manual Chat trigger *Starts it*
- 2 **Embeddings HuggingFace Inference** Embeddings Hugging Face Inference *Model*
- 3 **Token Splitter** Text Splitter Token Splitter *Model*
- 4 **Embeddings HuggingFace Inference1** Embeddings Hugging Face Inference *Model*
- 5 **Token Splitter1** Text Splitter Token Splitter *Model*
- 6 **Embeddings HuggingFace Inference2** Embeddings Hugging Face Inference *Model*
- 7 **Token Splitter2** Text Splitter Token Splitter *Model*
- 8 **Embeddings HuggingFace Inference3** Embeddings Hugging Face Inference *Model*
- 9 **Token Splitter3** Text Splitter Token Splitter *Model*
- 10 **IF** If *Logic*
- 11 **Zep Insert sitelinks records** Vector Store Zep *Model*
- 12 **Default Data Loader** Document Default Data Loader *Model*
- 13 **Insert Records ZEP Vector peopleAlsoAsk** Vector Store Zep *Model*
- 14 **peopleAlsoAsk Data Loader** Document Default Data Loader *Model*
- 15 **Zep Vector Store2** Vector Store Zep *Model*
- 16 **organicSearch Data Loader** Document Default Data Loader *Model*
- 17 **Insert Records ZEP Vector relatedSearch** Vector Store Zep *Model*
- 18 **relatedSearch Data Loader** Document Default Data Loader *Model*
- 19 **Add record Chat Input** Airtable *Service*
- 20 **Loop Over Sitelinks** Split In Batches *Logic*
- 21 **Loop Over Items** Split In Batches *Logic*
- 22 **Loop organicSearch** Split In Batches *Logic*
- 23 **HTTP Request** Http Request *Service*
- 24 **AI Agent** Agent *Model*
- 25 **Add Record Sitelinks Table** Airtable *Service*
- 26 **Add records peopleAlsoAsk** Airtable *Service*
- 27 **Add Record organicSearch** Airtable *Service*
- 28 **Split Out Organic Search Results** Split Out *Logic*
- 29 **Split Out peopleAlsoAsk Fields** Split Out *Logic*
- 30 **Split Out relatedSearches** Split Out *Logic*
- 31 **Split Out organicSearch** Split Out *Logic*
- 32 **Wait1** Wait *Logic*
- 33 **Wait** Wait *Logic*
- 34 **Wait2** Wait *Logic*
- 35 **Edit Fields** Set *Logic*
- 36 **Aggregate relatedSearches keywords** Aggregate *Logic*
- 37 **PATCH connections Airtable Chat Input Records** Http Request *Service*
- 38 **PATCH connections Airtable Chat Input Records peopleAlsoAsk** Http Request *Service*
- 39 **PATCH connections Airtable Chat Input Records organicSearch** Http Request *Service*
- 40 **Exclude Youtube Links** Filter *Logic*
- 41 **Add Records relatedSearches** Airtable *Service*
- 42 **IF sitelinks not empty** If *Logic*
- 43 **Split Out Sitelinks** Split Out *Logic*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 43, with 2 branches, 6 loops or waits
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Airtable
- **Model:** A language model, family not declared
- **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 Airtable account, and a key for a language model. 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?

Yes. It calls a language model. 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 43 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 43 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%2Fscrape-query-from-serper-api-than-add-airtable-and-zep)
- **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.

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

## Workflows like it

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

- [**AI data extraction with Airtable** 36 steps · calls a model · Airtable](https://millionrounds.com/workflow/ai-data-extraction-with-airtable)
- [**Facebook ads generator with Gemini and OpenAI** 51 steps · calls a model · Airtable](https://millionrounds.com/workflow/facebook-ads-generator-with-gemini-and-openai)
- [**Daily agenda reminder in Airtable - WhatsApp - Evolution** 33 steps · calls a model · Airtable](https://millionrounds.com/workflow/aviso-de-agenda-diaria-en-airtable-whatsapp-evolution)
- [**Extract information from a logo sheet with Airtable** 33 steps · calls a model · Airtable](https://millionrounds.com/workflow/extract-information-from-a-logo-sheet-with-airtable)
- [**Fetch hierarchical data records from Airtable** 32 steps · Airtable](https://millionrounds.com/workflow/fetch-hierarchical-data-records-from-airtable)
- [**AI agent to chat with Airtable** 30 steps · calls a model · Airtable](https://millionrounds.com/workflow/ai-agent-to-chat-with-airtable)