Build a chatbot knowledge base from a website

Created by

mohamed senator

Actor

AI-Ready Webpage Extractor

Crawl a website by following its links and turn every page into RAG-ready chunks with heading paths and token estimates, ready to load into a vector database behind a support or docs chatbot. This example crawls part of the Crawlee docs; set your own start URL and path filter to index any public site.

Try for free

AI-Ready Webpage Extractors3nafps/ai-ready-webpage-extractor

URL

Title

Chunks

Input

URLs(required):https://crawlee.dev/js/docs/quick-start

Crawl mode:sameDomain

Only crawl URLs containing:/js/docs/

Maximum pages:25

Split content into RAG chunks:true

Chunk size (tokens):800

Output fields

URL

Title

Chunks

How it works

Sign up on Apify or log in

The AI-Ready Webpage Extractor Actor is ready to run with the inputs already set for "Build a chatbot knowledge base from a website". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Build a chatbot knowledge base from a website" task

The AI-Ready Webpage Extractor Actor will start running based on the input automatically. You can also change all the input fields, like URLs, crawl mode, and more, to match your specific use case.

Receive the "Build a chatbot knowledge base from a website" 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 URL, title, and chunks.

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 "Build a chatbot knowledge base from a website" task via API.