LangChain Documentation Scraper (Markdown + RAG Chunks)

Created by

LERNOWA AI LABS PRIVATE LIMITED

Actor

RAG Documentation Scraper — LLM-Ready Chunker

Scrape LangChain documentation pages into clean Markdown and vector-ready JSON chunks for RAG pipelines and LLM training.

Try for free

RAG Documentation Scraper — LLM-Ready Chunkerlernowa_ai_labs/rag-docs-scraper

Content

Metadata

Input

Start URLs(required)

url:https://python.langchain.com/docs/introduction/

URL Path Patterns:/docs/**

Max Crawl Depth:3

Max Pages Per Run:500

Chunking Strategy:heading_boundary

Chunk Size (tokens):512

Chunk Overlap (tokens):50

Output Format:markdown

Chunk Size (tokens) — Quick Override:500

Extra CSS Selectors to Exclude

Deduplicate Chunks:true

PDF Handling:skip

AWS Region:us-east-1

Enable Incremental (Delta) Crawling:false

DynamoDB Table Name:rag-docs-scraper-delta

Use Apify Proxy:false

Max Concurrency:5

Navigation Timeout (s):30

Output fields

Content

Metadata

How it works

Sign up on Apify or log in

The RAG Documentation Scraper — LLM-Ready Chunker Actor is ready to run with the inputs already set for "LangChain Documentation Scraper (Markdown + RAG Chunks)". Sign up or log in and you'll land in Apify Console with a copy of this exact task.

Start the "LangChain Documentation Scraper (Markdown + RAG Chunks)" task

The RAG Documentation Scraper — LLM-Ready Chunker Actor will start running based on the input automatically. You can also change all the input fields, like start urls, URL Path Patterns, and more, to match your specific use case.

Receive the "LangChain Documentation Scraper (Markdown + RAG Chunks)" 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 content and metadata.