Go to example tasks

Docs site to OKF bundle grouped by type

Crawl a documentation site into an Open Knowledge Format (OKF) bundle where every page is filed by what it is: guides, tutorials, API references, FAQs and concepts each get their own folder with an index.md. Each concept has an AI summary, key facts, tags and source provenance. This example uses the Apify platform docs; swap in your own docs URL.

Try for free
LLM Wiki & OKF Bundle Generator: Website to Knowledge Base
LLM Wiki & OKF Bundle Generator: Website to Knowledge Basescrape-lads/llm-wiki-okf-generator
Concept
Type
Title
Description
+3 fields
Text
Number
Boolean
List
Object

Input

Start URLs
url:https://docs.apify.com/platform/actors
AI summaries and classification:true
Folder layout:type
Max pages:25

Output fields

Concept
Type
Title
Description
Tags
Source
AI

How it works

Sign up on Apify or log in

The LLM Wiki & OKF Bundle Generator: Website to Knowledge Base Actor is ready to run with the inputs already set for "Docs site to OKF bundle grouped by type". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Docs site to OKF bundle grouped by type" task

The LLM Wiki & OKF Bundle Generator: Website to Knowledge Base Actor will start running based on the input automatically. You can also change all the input fields, like start urls, AI summaries and classification, and more, to match your specific use case.

Receive the "Docs site to OKF bundle grouped by type" output

Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as concept, type, title, and more.

Integrate into your workflow

The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "Docs site to OKF bundle grouped by type" task via API.

Image

Integrate "Docs site to OKF bundle grouped by type" into your workflow

Connect "Docs site to OKF bundle grouped by type" with 100+ integrations, or run it via API or MCP.

Webhook

Webhook

n8n

n8n

Make

Make

Zapier

Zapier

Airbyte

Airbyte

Keboola

Keboola

IFTTT

IFTTT

Hubspot

Hubspot

GDrive

GDrive

Gmail

Gmail

Apify MCP

Apify MCP

GitHub

GitHub

Slack

Slack

LangChain

LangChain

LlamaIndex

LlamaIndex

Flowise

Flowise

Pinecone

Pinecone

OpenAI

OpenAI

Mastra

Mastra

Clay

Clay