janNet - Hybrid Search Engine with MaxSim re-ranking
Posted by: altug
Hello, I made this open source web crawler called janNet that can be configured to index and save webpage contents in your own database. Features include a hybrid search mechanism that combines semantic and lexical scores to be later re-ranked using the MaxSim algorithm. It took me 5-6 months to make it since its my first information retrieval system. I thought this could be found useful here since some of us hoard web page content. Here is the repo: https://github.com/altugjakal/janNet If you have any questions just reach me here I'm happy to help. Happy crawling!
Source: https://github.com/altugj...
Score: 3
Category: IR
Added: 2026-03-08 23:46:01
No sources found yet.