Extracting Knowledge Graphs from User Stories using LangChain

TL;DR

This paper presents a novel automated method for generating knowledge graphs from user stories using Large Language Models and the LangChain framework, improving software development by better understanding user requirements.

Contribution

It introduces a new methodology leveraging LLMs and LangChain to automate knowledge graph extraction from user stories, enhancing requirement analysis.

Findings

Automated knowledge graph extraction achieved with high accuracy.

Improved visualization of user requirements and domain concepts.

Enhanced alignment between software functionalities and user expectations.

Abstract

This thesis introduces a novel methodology for the automated generation of knowledge graphs from user stories by leveraging the advanced capabilities of Large Language Models. Utilizing the LangChain framework as a basis, the User Story Graph Transformer module was developed to extract nodes and relationships from user stories using an LLM to construct accurate knowledge graphs.This innovative technique was implemented in a script to fully automate the knowledge graph extraction process. Additionally, the evaluation was automated through a dedicated evaluation script, utilizing an annotated dataset for assessment. By enhancing the visualization and understanding of user requirements and domain concepts, this method fosters better alignment between software functionalities and user expectations, ultimately contributing to more effective and user-centric software development processes.