Skip to main content

Crawl documentation sites and build an AI knowledge base with Olostep

Workflow preview

Workflow preview
100%
Crawl documentation sites and build an AI knowledge base with Olostep preview
Open on n8n.io

1. Workflow Overview

AI Documentation Crawler & Knowledge Base Builder This n8n template automatically crawls technical documentation websites, scrapes their content, and converts it into clean, structured, developer f...

Best for

  • Document Extraction automation workflows
  • Multimodal AI automation workflows
  • advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.manualtrigger, n8n-nodes-base.splitout, n8n-nodes-base.set, n8n-nodes-base.googledrive, n8n-nodes-base.merge, n8n-nodes-olostep.olostepscrape, n8n-nodes-base.splitinbatches, n8n-nodes-base.if

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Yasser Sami.

Original n8n.io source

1.1 Workflow description

Title
Crawl documentation sites and build an AI knowledge base with Olostep
Workflow name
Crawl documentation sites and build an AI knowledge base with Olostep

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 saved as Google Docs, making it easy to build or maintain an internal knowledge base.

Who’s it for

  • Developer teams maintaining internal or external documentation
  • SaaS companies onboarding users or support teams
  • AI builders creating documentation-based knowledge bases
  • Anyone who wants to turn raw docs into structured, readable references

How it works / What it does

  1. Manual Trigger
  • The workflow starts manually whenever you want to crawl or refresh documentation.
  1. Documentation Discovery (Crawler)
  • The workflow crawls a root documentation URL and generates a sitemap of all discoverable documentation pages.
  1. URL Processing
  • The sitemap is split into individual URLs.
  • The workflow dynamically analyzes URL depth to recreate the documentation hierarchy.
  1. Folder Structure Creation
  • A parent folder is created in Google Drive for the service.
  • Subfolders are automatically generated to mirror the documentation structure (based on URL paths).
  1. Content Scraping
  • Each documentation page is scraped using the Olostep API.
  • Clean markdown content is extracted from the page.
  1. Information Extraction
  • AI extracts structured technical details such as:
  • API summaries
  • cURL examples
  • Authentication methods
  • Key notes and pitfalls
  1. AI Documentation Generation
  • An AI agent transforms the scraped content into a polished, human-readable API reference or guide.
  1. Document Creation
  • A Google Doc is created for each documentation page.
  • The generated content is inserted into the document and saved in the correct folder.
  1. Rate Control
  • A wait step prevents API throttling during large documentation crawls.

The result is a fully structured documentation library generated automatically from live documentation websites.

How to set up

  1. Import the template into your n8n workspace.
  2. Set the root documentation URL you want to crawl.
  3. Connect your Google Drive and Google Docs accounts.
  4. Add your Olostep API key and AI model credentials.
  5. Execute the workflow to generate your documentation library.

Requirements

  • n8n account (cloud or self-hosted)
  • Olostep API key
  • Google Drive & Google Docs access
  • AI model provider (OpenAI or Gemini)

How to customize the workflow

  • Limit the number of pages crawled per run.
  • Adjust AI prompts to match your documentation style.
  • Store results in Notion, Confluence, or Markdown files instead of Google Docs.
  • Add vector storage (Pinecone, Supabase) to turn docs into an AI knowledge base.
  • Schedule automatic re-crawls to keep documentation up to date.

👉 This template turns complex technical documentation into an organized, searchable knowledge base — automatically.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - When clicking ‘Execute workflow’

Type / Role
n8n-nodes-base.manualTrigger - manualTrigger
Config choices
Version 1

Block 2 - Split Out1

Type / Role
n8n-nodes-base.splitOut - splitOut
Config choices
Version 1

Block 3 - Service Name

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 4 - Create Parent Folder

Type / Role
n8n-nodes-base.googleDrive - googleDrive
Config choices
Version 3

Block 5 - Merge

Type / Role
n8n-nodes-base.merge - merge
Config choices
Version 3.2

Block 6 - Create a map

Type / Role
n8n-nodes-olostep.olostepScrape - olostepScrape
Config choices
Version 1

Block 7 - Edit Fields

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 8 - Loop Over Items

Type / Role
n8n-nodes-base.splitInBatches - splitInBatches
Config choices
Version 3

Block 9 - Search files and folders

Type / Role
n8n-nodes-base.googleDrive - googleDrive
Config choices
Version 3

Block 10 - If

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.3

Block 11 - Create folder

Type / Role
n8n-nodes-base.googleDrive - googleDrive
Config choices
Version 3

Block 12 - counter

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 13 - counter++

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 14 - If1

Type / Role
n8n-nodes-base.if - if
Config choices
Version 2.3

Block 15 - counter++1

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 16 - Scrape a URL

Type / Role
n8n-nodes-olostep.olostepScrape - olostepScrape
Config choices
Version 1

Block 17 - set data

Type / Role
n8n-nodes-base.set - set
Config choices
Version 3.4

Block 18 - No Operation, do nothing

Type / Role
n8n-nodes-base.noOp - noOp
Config choices
Version 1

Block 19 - Information Extractor

Type / Role
@n8n/n8n-nodes-langchain.informationExtractor - informationExtractor
Config choices
Version 1.2

Block 20 - Google Gemini Chat Model2

Type / Role
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices
Version 1

Block 21 - AI Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 3.1

Block 22 - Merge1

Type / Role
n8n-nodes-base.merge - merge
Config choices
Version 3.2

Block 23 - Google Gemini Chat Model

Type / Role
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices
Version 1

Block 24 - Create a document

Type / Role
n8n-nodes-base.googleDocs - googleDocs
Config choices
Version 2

Showing the first 24 of 38 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow Crawl documentation sites and build an AI knowledge base with Olostep
Complexity advanced
Nodes 38
Categories Document Extraction, Multimodal AI
Author Yasser Sami
Published 16 Feb 2026

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/13436/13436.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Crawl documentation sites and build an AI knowledge base with Olostep do?

AI Documentation Crawler & Knowledge Base Builder This n8n template automatically crawls technical documentation websites, scrapes their content, and converts it into clean, structured, developer f...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Document Extraction, Multimodal AI use case.