dead8309/ai-rag-crawler
AI pipeline built with the honc and workers-ai. vector embeddings, web scraping and processing with Cloudflare Workflows (beta)
This tool helps technical writers, support teams, or product managers automatically turn website documentation into an interactive Q&A resource. You provide the base URL of a documentation site, and it scrapes all content, processes it, and lets users ask questions to get instant, context-aware answers. It's designed for anyone managing or needing quick access to information from extensive online documentation.
No commits in the last 6 months.
Use this if you need an automated way to ingest a complete documentation website and allow users to semantically search and get AI-generated answers to their questions without manual setup.
Not ideal if your documentation isn't publicly accessible on a website or if you need to process unstructured text documents like PDFs and Word files.
Stars
32
Forks
1
Language
TypeScript
License
—
Category
Last pushed
Apr 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/perception/dead8309/ai-rag-crawler"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scrapy/scrapy
Scrapy, a fast high-level web crawling & scraping framework for Python.
Altimis/Scweet
A simple and unlimited twitter scraper : scrape tweets, likes, retweets, following, followers,...
lexiforest/curl_cffi
Python binding for curl-impersonate fork via cffi. A http client that can impersonate browser...
plabayo/rama
modular service framework to move and transform network packets
scrapinghub/spidermon
Scrapy Extension for monitoring spiders execution.