Crawl websites & answer questions with OpenAI: n8n workflow

Crawl websites & answer questions with OpenAI

Started by someone opening a chat with it, and works across Google Sheets. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 33 steps, 2 branches, 1 loop or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

The flow

Starts it 1Model 10Logic 13Service 9

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

1OpenAI Chat ModelLm Chat Open AiModel
2Simple MemoryMemory Buffer WindowModel
3Get row(s) in sheet in Google SheetsGoogle Sheets ToolService
4OpenAI Chat Model1Lm Chat Open AiModel
5Chat webChat triggerStarts it
6Structured Output ParserOutput Parser StructuredModel
7Append row in sheet in Google SheetsGoogle Sheets ToolService
8HTTP Request2Http Request ToolService
9AI AgentAgentModel
10AI Agent1AgentModel
11Get data schemaGoogle SheetsService
12Message a model1Open AiModel
13Respond to Chat1ChatModel
14If1IfLogic
15IfIfLogic
16Loop Over ItemsSplit In BatchesLogic
17OPTIONSSetLogic
18Respond to ChatChatModel
19CompleteGoogle SheetsService
20Req URLHttp RequestService
21UA Rotativo1CodeLogic
22HTML to MarkdownMarkdownLogic
23Req robotsHttp RequestService
24extract sitemap urlCodeLogic
25Req ErrorStop And ErrorLogic
26Maping SitemapHttp RequestService
27XML1XmlLogic
28Sitemap ErrorStop And ErrorLogic
29Message a modelOpen AiModel
30Maping SitemapsHttp RequestService
31XMLXmlLogic
32MergeCodeLogic
33Split URLsSplit OutLogic

How it's built

Starts on: Someone opening a chat with it
Steps: 33, with 2 branches, 1 loop or waits
Size: Large: read it before trusting it with anything live
Connects to: Google Sheets
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 Google Sheets account, and a key for OpenAI. 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 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 33 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 33 steps before you point it at anything that matters.