Back to feed
Dev.to
Dev.to
6/25/2026
How to Build a RAG Knowledge Base from Documentation Sites Using Apify

How to Build a RAG Knowledge Base from Documentation Sites Using Apify

Original: How to Build a RAG Knowledge Base from Any Documentation Site in 5 Minutes

Short summary

Apify's RAG Docs Extractor automates scraping and chunking documentation sites with pre-computed token counts. Includes working LangChain + ChromaDB integration code and alternative single-page markdown tool.

  • •Automates cleaning and chunking of documentation websites for RAG pipelines with noise removal
  • •Provides working Python code using LangChain, ChromaDB, and OpenAI embeddings
  • •Includes token counting via cl100k_base encoding; pay-per-result pricing

Generated with AI, which can make mistakes.

#ai-tools#ai-agents
Read full article at Dev.to

Is this a good recommendation for you?

Explore more

How to Build a RAG System with Your Own Documents in 7 Simple Steps
Dev.to
Reduce LLM Token Waste in RAG with Markdown
Dev.to
I Built RAG From Scratch in Python to Understand It. Here's What I Learned.
Dev.to
Build a RAG application with Runware and LangChain
Dev.to