Next-gen generative search engine for code base
Abstract
This report presents the design, implementation and evaluation of CodeOrient, an autonomous Artificial Intelligence (AI) search tool, designed to accelerate developer onboarding. This application leverages Natural Language Processing (NLP), code graph visualisation and vector-based retrieval to help new developers understand unfamiliar codebases and reduce the time to first commit. CodeOrient integrates semantic code search using embedding models, structural analysis through dependency graphs and generative user interfaces (UI) to provide context-aware feature cards. Through the use of Retrieval-Augmented Generation (RAG) with source grounding, the application eliminates hallucination, commonly seen in AI code assistants. Preliminary testing suggests that by externalising the mental model of a codebase through a unified graph-and-card interface, the system significantly reduces the cognitive load associated with onboarding and system discovery in large-scale repositories.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.