KGQA_HLM

Why we included this project

Anyone wanting to see how a knowledge-graph question-answering system is actually wired together will find a clear, working example here. The project takes the characters of Dream of the Red Chamber, scrapes their profile data, turns it into triples, loads those into a Neo4j graph, and lets you ask relationship questions in natural language, with LTP handling segmentation, part-of-speech tagging, and named entity recognition. The code is neatly split into a Flask entry point, separate modules for building and querying the graph, and a QA layer, so it is easy to trace each step and adapt it to another domain. Treat it as a solid teaching reference or a starting point for a small KGQA demo rather than production software; for that purpose it is refreshingly complete.