Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{172635,
        author = {Kedar S. Pawar and Abhishek S. Bhosale and Aditya G. Mahajan and Abhishek V. Ulagadde and Prof. Madhuri Mane},
        title = {AI Based Code Documentation Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {9},
        pages = {411-414},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172635},
        abstract = {Automated documentation generation has become increasingly important in large-scale software development due to the growing complexity and size of modern codebases. Traditional documentation methods are labor-intensive, prone to inaccuracies, and often struggle to keep up with rapid development cycles. The integration of large language models (LLMs), such as GPT-4 and Codex, has introduced significant improvements in automated documentation, but challenges remain, particularly in handling large files and complex module dependencies. This survey paper reviews the current state of research on intelligent code chunking, dependency resolution, and multilanguage support in documentation generation tools. It also proposes a novel system that combines these techniques to generate context-aware documentation for large, multi-language codebases, ensuring accurate and comprehensive documentation generation. The survey examines the technological advancements, challenges, and potential applications of this approach in software engineering.},
        keywords = {LLM, Automation, Modern codebases, GPT 4,Context-aware documentation, Multi-language support, Intelli gent Code Chunking},
        month = {February},
        }