We present a repository decomposition system that converts large software repositories into a vectorized knowledge graph which mirrors project architectural and semantic structure, capturing semantic relationships and allowing a significant level of automatization of further repository development. The graph encodes syntactic relations such as containment, implementation, references, calls, and inheritance, and augments nodes with LLM-derived summaries and vector embeddings. A hybrid retrieval pipeline combines semantic retrieval with graph-aware expansion, and an LLM-based assistant formulates constrained, read-only graph requests and produces human-oriented explanations.
@article{arxiv.2510.08876,
title = {Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval},
author = {Kostiantyn Bevziuk and Andrii Fatula and Svetozar Lashin Yaroslav Opanasenko and Anna Tukhtarova and Ashok Jallepalli Pradeepkumar Sharma and Hritvik Shrivastava},
journal= {arXiv preprint arXiv:2510.08876},
year = {2025}
}