This Network-graph based literature review tool uses the open-source version of Neo4j with Jupyter Notebooks written in Python to import academic literature metadata from a variety of sources including OpenAlex, arXiv, Sematic Scholar and Web of Science. Also incorporated are OpenAI vector embeddings using Neo4j's Vector Search Index capabilities.

An introduction to vector embeddings, the fundamental concept widely used in machine learning. The Jupyter Notebook was prepared as part of internal presentation for work mates.

An LLM-powered augmented generation suite leveraging LangChain, Ollama, and vector databases to enhance response quality through caching, contextual memory, and retrieval-based methods. This collection of Jupyter notebooks showcases modular techniques for building intelligent, memory-efficient generative systems with real-time semantic awareness.