# Semantic Search Mini-Index

**Track:** 3D, Shaders & AI Intuition — Creative Coding — the existing 50
**Framework / surface:** p5.js
**Level:** Advanced
**Prerequisites:** Embeddings & Vector Similarity, Merge Sort & Divide-and-Conquer

**In one line:** Search by meaning, not keywords — rank by closeness.

## Theory, aesthetics & inspiration

Semantic search retrieves by meaning rather than by matching characters. Each document and each query is converted to an embedding vector, and results are ranked by closeness — typically cosine similarity — so a search for "ocean" can surface "sea" without sharing a single letter. The approach generalizes across media once text and images occupy one space, as in Radford and colleagues' CLIP (OpenAI, 2021). Built atop the distributional tradition of word2vec, a small index becomes a map in which proximity is relevance. The aesthetic is one of associative recall over literal lookup: a system that gropes toward what is meant, tolerant of paraphrase, indifferent to mere spelling.