Abstract
This project is an AI fashion matching recommendation system based on the Retrieval-Augmented Generation (RAG) architecture. It aims to provide personalized fashion item recommendations based on users’ input, including gender, current season, skin tone type (based on the four-season color theory), and body measurements (used to infer general size suggestions from height and weight). Additionally, it leverages large language models (LLMs) to generate natural-sounding recommendation rationales;
Detailed Design





