Building knowledge graphs from unstructured text is an issue of great interest that receives little research. In my most recent blog article, I describe how I built a knowledge network in Neo4j using the LangChain framework and OpenAI functions. Along with learning all the subtleties of employing LLMs to build a knowledge graph, you will also learn the necessary procedures to develop a production information extraction pipeline.
I would like to thank Tomaz Bratanic for preparing this article. You can find the original blog post here. In this article, I worked directly on a book. Those who want to work on Wikipedia can use the code on Tomaz's blog.