This project was inspired by the difficulty beginners face when trying to understand existing source code. Reading unfamiliar code can be overwhelming, especially when there is little documentation. Through this project, I learned how to integrate large language models into a simple application workflow and how AI can be used to explain technical concepts in a human-friendly way. The project was built using a lightweight backend that sends source code as input to an AI model, which then analyzes the code and generates clear, step-by-step explanations in English. One of the main challenges was selecting a reliable model and handling API limitations such as rate limits and quotas. Overcoming these challenges helped me better understand how real-world AI APIs behave and how to design around their constraints.
Built With
- google-generative-ai-(gemini/gemma-models)
- jupyter
- python
- rest-api
Log in or sign up for Devpost to join the conversation.