Templates / Crawl documentation sites and build an AI knowledge base with Olostep

Crawl documentation sites and build an AI knowledge base with Olostep

Unknown

by Yasser Sami ✓ · 194 views · created 2026-02-16 · Document Extraction, Multimodal AI

Unknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.

What this workflow does

This AI workflow has 26 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Google Drive, Google Gemini Chat Model, Google Docs and Olostep (community).

How it runs

Trigger: Manually, when you click “Execute workflow”.

Create a map (Olostep Scrape): work with map
Service Name (Edit Fields (Set)): sets 1 field: Service
Split Out: splits a list into separate items
Create Parent Folder (Google Drive): work with folder
Merge: merges the data from its input branches
Edit Fields (Edit Fields (Set)): sets 2 fields: parent_id, counter
Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
counter (Edit Fields (Set)): sets 3 fields: counter, url, parent_id
If: checks a condition and branches into true / false
Search files and folders (Google Drive): work with file folder

…plus 12 more steps. See the full node list below.

Services it uses

Google Drive Google Gemini Chat Model Google DocsOlostep (community)

Scraping pages by hand? Firecrawl is a simpler option (10% off for new users).

Before you upgrade to n8n 3.0

We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).

Check that n8n-nodes-olostep is verified or supports 3.0 (used in Create a map, Scrape a URL).

Nodes used (14)

Manual Triggern8n-nodes-base.manualTrigger
Split Outn8n-nodes-base.splitOut
Edit Fields (Set)n8n-nodes-base.set
Google Driven8n-nodes-base.googleDrive
Mergen8n-nodes-base.merge
Olostep Scrapen8n-nodes-olostep.olostepScrape
Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
Ifn8n-nodes-base.if
No Operation, do nothingn8n-nodes-base.noOp
Information Extractor@n8n/n8n-nodes-langchain.informationExtractor
Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
AI Agent@n8n/n8n-nodes-langchain.agent
Google Docsn8n-nodes-base.googleDocs
Waitn8n-nodes-base.wait

From the author

AI Documentation Crawler & Knowledge Base Builder This n8n template automatically crawls technical documentation websites, scrapes their content, and converts it into clean, structured, developer-friendly documentation. Each page is organized into folders and…
Excerpt from Yasser Sami's description on n8n.io.

View the original on n8n.io → Check your own copy

Crawl documentation sites and build an AI knowledge base with Olostep

What this workflow does

How it runs

Services it uses

Before you upgrade to n8n 3.0

Nodes used (14)

From the author

Get the weekly “what broke” email