Building Code Explainer Using LLM

Authors

Dipali Kalamdhad, Harsha Bambal, Shital Bansod, Neha Khawse, Gauri Khode, Prof. Kanchan Raipure

Abstract

The Code Explainer project seeks to develop an AI system for translating complex code snippets into human-readable explanations. This project addresses the demand for simplified code comprehension tools, targeting developers, students, and non-technical stakeholders. The Code Explainer platform utilizes Natural Language Processing (NLP) and Language Model (LLM) to enhance explanation quality and deliver a seamless user experience through a user-friendly interface. The Code Explainer project's emphasis on functionality and user-centric design concepts is essential to its success. The UI of the platform is designed to be both simple and intuitive, making it easy for users to submit code samples and obtain detailed explanations with no effort. In addition to its core functionality, the Code Explainer platform incorporates advanced features such as the Save Option. This feature empowers users to save the generated explanations for future reference, allowing for convenient review or sharing. Furthermore, the Saved Explanations Page Module provides users with a dedicated space to manage their saved explanations, enabling them to view, edit, or delete entries as needed. The platform also boasts a powerful Search Functionality, enriching the user experience by providing a robust tool to discover saved explanations. Users can enter search queries based on specific keywords or code snippets into the search bar, and the system intelligently analyzes the input to retrieve relevant explanations from the platform's database.

Keywords

Code Explainer, Code Explanation Generator, LLM, Html, CSS, ReactJs, NodeJs, Firebase.

Building Code Explainer Using LLM. Dipali Kalamdhad, Harsha Bambal, Shital Bansod, Neha Khawse, Gauri Khode, Prof. Kanchan Raipure. 2024. IJIRCT, Volume 10, Issue 2. Pages 1-7. https://www.ijirct.org/viewPaper.php?paperId=2403061