In this project, I built a basic Retrieval Augmented Generator (RAG) system, which you can ask various questions about either The Wizard of Oz or Alice in Wonderland.
I used this project to get more comfortable working with APIs, local models, embeddings and environments.
rag_project.ipynb is the main file, but in separate notebooks I also did an investigation of how embeddings work and some exploration of the possible features you can access through the OpenAI API, which inspired my text-to-speech project (also on my GitHub).