Website to RAG chunks for a vector database

Created by

Scrape Lads

Actor

Web Crawler: Website to Markdown for LLM & RAG

Crawl a website and split every page into overlapping, heading-aware text chunks ready for a vector database such as Pinecone, Qdrant or pgvector. Works with LangChain and LlamaIndex pipelines.

Try for free

Web Crawler: Website to Markdown for LLM & RAGscrape-lads/website-content-crawler-rag

URL

Title

Chunks

Input

Start URLs(required)

url:https://crawlee.dev/js/docs/introduction

Max pages:30

Max crawl depth:5

Crawl scope:path

Include URLs (globs)

Exclude URLs (globs)

Crawler type:auto

Output formats:markdown+1

Remove boilerplate:true

Chunk size (characters):1000

Chunk overlap (characters):150

Discover pages from sitemaps:false

Respect robots.txt:true

Max concurrency:10

Output fields

URL

Title

Chunks

How it works

Sign up on Apify or log in

The Web Crawler: Website to Markdown for LLM & RAG Actor is ready to run with the inputs already set for "Website to RAG chunks for a vector database". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "Website to RAG chunks for a vector database" task

The Web Crawler: Website to Markdown for LLM & RAG Actor will start running based on the input automatically. You can also change all the input fields, like start urls, max pages, and more, to match your specific use case.

Receive the "Website to RAG chunks for a vector database" 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 "Website to RAG chunks for a vector database" task via API.