The evaluation engine compares OCR output against ground-truth labels to measure model performance. It uses a SequenceMatcher-based similarity algorithm to calculate accuracy and categorizes results ...

In this tutorial, we show how we treat prompts as first-class, versioned artifacts and apply rigorous regression testing to large language model behavior using MLflow. We design an evaluation pipeline ...

This project is an AI-Based Mock Interview Practice System developed as part of the MCA coursework. It aims to help students practice Technical and HR interview questions in a simulated environment.