# Search & summarize web data with Perplexity and Gemini: n8n workflow

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

Source: https://millionrounds.com/workflow/search-and-summarize-web-data-with-perplexity-and-gemini (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)

# Search & summarize web data with Perplexity and Gemini

Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Gemini. 15 steps, 2 branches, 1 loop or waits: a working afternoon to understand properly.

Medium Calls a model: Gemini

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fsearch-and-summarize-web-data-with-perplexity-and-gemini)

**15 steps** Medium: a working afternoon

**2** Branches: places the flow splits

**1** Loop or waits

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

## The flow

Starts it 1 Model 6 Logic 4 Service 4

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

- 1 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 2 **Google Gemini Chat Model** Lm Chat Google Gemini *Model*
- 3 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 4 **Google Gemini Chat Model1** Lm Chat Google Gemini *Model*
- 5 **Perplexity Search Request** Http Request *Service*
- 6 **Summarization of search result** Chain Summarization *Model*
- 7 **Default Data Loader** Document Default Data Loader *Model*
- 8 **Readable Data Extractor** Information Extractor *Model*
- 9 **Set Snapshot Id** Set *Logic*
- 10 **Webhook Notifier** Http Request *Service*
- 11 **Check Snapshot Status** Http Request *Service*
- 12 **If** If *Logic*
- 13 **Check on the errors** If *Logic*
- 14 **Wait** Wait *Logic*
- 15 **Download Snapshot** Http Request *Service*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 15, with 2 branches, 1 loop or waits
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Gemini

## 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 an event in a connected app.

Does it use AI?

Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 15 steps is enough that you should read each one before running it.

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 15 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%2Fsearch-and-summarize-web-data-with-perplexity-and-gemini)
- **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.

- [**AI trading assistant: Telegram + TradingView charts + technical** 15 steps · calls a model · Telegram](https://millionrounds.com/workflow/ai-trading-assistant-telegram-tradingview-charts-technical)
- [**AI-powered Bitcoin and crypto market intelligence report** 15 steps · calls a model · Supabase, WordPress](https://millionrounds.com/workflow/ai-powered-bitcoin-and-crypto-market-intelligence-report)
- [**AI-powered RAG workflow for stock earnings report analysis** 15 steps · calls a model · Google Docs, Google Drive](https://millionrounds.com/workflow/ai-powered-rag-workflow-for-stock-earnings-report-analysis)
- [**Analyze Facebook comment sentiment with OpenAI and Slack** 15 steps · calls a model · Google Sheets, Outlook](https://millionrounds.com/workflow/analyze-facebook-comment-sentiment-with-openai-and-slack)
- [**Analyze YouTube comments sentiment & keywords with Gemini** 15 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/analyze-youtube-comments-sentiment-and-keywords-with-gemini)
- [**Analyze brand competitors with Decodo and Gemini** 15 steps · calls a model · Google Sheets, Telegram](https://millionrounds.com/workflow/analyze-brand-competitors-with-decodo-and-gemini)