LLM models for learning and retrieving software knowledge

The primary objective of this project is to enhance Large Language Models (LLMs) by incorporating software knowledge documentation. Our approach involves utilizing existing LLMs and refining them using data extracted from software repositories. This fine-tuning process aims to enable the models to provide answers to queries related to software development tasks. Examples of such queries include determining the appropriate design pattern for a specific scenario, identifying relevant quality attributes for a particular design choice, and recognizing the optimal timing for implementing a refactoring action in a software project. Furthermore, the refined LLMs will prove valuable in assisting with writing documentation throughout the software development journey.