Sahaj.blogs

Day page

11 Oct 2026

Projects

Built this: NLP Document Search Engine

A Gradio app for classical document search: NLTK preprocessing, a TF-IDF vector space model with cosine ranking, term-level explanations and a lexical-matching comparison mode.

  • Results are explainable down to the term: the app shows which words contributed how much to each document's score.
  • A comparison mode puts TF-IDF cosine ranking next to plain keyword matching.

Read the post →