top of page


Flavor Finder

Zhihan Li, Xue Xiao, Daniel Colon Amill, Andres Martinez, William Porteous, Michael Shteyn


The goal of this project is to create a recommendation system that gives advice about the degree of culinary diversity among local restaurants in a queried neighborhood, based on a public Yelp dataset. The project will involve the use of an LLM both to extract features from restaurant reviews and to generate advice, as well retrieval augmented generation (RAG) to provide geographically specific information. Still a little fresh on these topics so the details may evolve but open to anyone with interest in or experience with LLMs, RAG or recommendation systems.

Yelp data: (yelp)
google local:

Screen Shot 2022-06-03 at 11.31.35 AM.png
github URL
bottom of page