My Portfolio

Welcome to my portfolio.

Luna: A Langchain Powered Personal Assistant

A deeper technical explanation along with the code can be found here on my GitHub https://github.com/jbrinkw

Project Summary:

This is my WIP personal assistant project that I use everyday. I finished my original goal of making a personal chef agent that tracks inventory and suggest/plan meals that I'll like.

Future Plans:

Currently I'm thinking my next phase will be developing a personal trainer that can work in conjunction with the personal chef agent to help me meet my physical health goals. I also plan to promote this as an open-source project so others can benefit from it as I have and potentially contribute to its development.

Features:

LLM-driven AI assistant built with LangChain, FastAPI, and Docker
Tracks food inventory & taste preferences, suggesting meals based on available ingredients
Generates multi-day meal plans and automates Walmart delivery orders
Backend hosted on AWS EC2 (Docker), SQL database on Azure
Frontend deployed on Hugging Face Spaces (Streamlit UI)
Uses open-source LLMs (DeepSeek R1, Llama 3) for async processing on personal hardware to cut API costs

LLM Powered Floorplan Generator

A deeper technical explanation along with the code can be found here on my GitHub https://github.com/jbrinkw

Project Motivation:

This project was an attempt at setting the foundation for infinite text driven generation of virtual world. In 2021 when I first had the idea for this I was trying to figure out what the barrier was to full stack text driven generation of video games. A lot of the fundamental forms of AI were already in place. GPT 3 had recently come out and it was good enough to outline the premise of a basic game and recursively generate game mechanics and storyline. Text to image was doing very well and text to 3D had just recently become useable. The only fundamental piece that was missing as a text driven model with enough spatial understanding to dynamically generate the layout of a game world. This project was my attempt at creating that model by augmenting existing LLMs with heavy prompt engineering and automated error correction.

Results:

You can see an example of the the before and after to the left. As you can see in the before pictures the room placements are essentially random. The after is significantly more coherent. To get that result I hardcoded the reasoning chain of the model thinking about how to generate the coordinates of the room. By breaking up the though process into about 7 different logical steps. For about half of the step I implanted error checking via another LLM or a script that checked if the new values lined up with the values the LLM planned originally.