Python

A demonstration of the implementation of role-based access control (RBAC) in a LLM vector database. The application manages access to the nodes of the vector database by attaching an allowlist of roles to the metadata of each node. This enables nodes to have an unlimited number of allowed roles. If the application were extended to use "real" data sources, those roles could be sourced from the data source API, such as the Google Drive API.

This project involves training a neural network to predict the outcome of dice rolls. Two loss functions are explored for the prediction task: one-hot categorical crossentropy and a custom distribution-based loss. The neural network is designed using TensorFlow and Keras.

RaspiWiFi is a program to headlessly configure a Raspberry Pi's WiFi connection using using any other WiFi-enabled device, much like the way a Chromecast or or smart speaker.