The project is a jupyter notebook of the method I used to distill an entire physiology book into it's key points of knowledge. The book I chose is "The Muscle and Strength Training Pyramid v2.0" by Eric Helms. This work is part of an ongoing exploration I'm doing into the ability of LLMs (Large Language Models) to effectively distill knowledge.
The project uses langchain as the main framework and uploads the knowledge as vectors into the pinecone DB.