Image by Author In this tutorial, we will explore Retrieval-Augmented Generation (RAG) and the LlamaIndex AI framework. We will learn how to use LlamaIndex to build a RAG-based application for Q&A over the private documents and enhance the application by incorporating a memory buffer. This will enable the LLM to generate the response using the context from both the document and previous interactions. What is RAG in LLMs? Retrieval-Augmented Generation (RAG) is an advanced methodology designed to enhance the performance […]

Many beginners will initially rely on the train-test method to evaluate their models. This method is straightforward and seems to give a clear indication of how well a model performs on unseen data. However, this approach can often lead to an incomplete understanding of a model’s capabilities. In this blog, we’ll discuss why it’s important to go beyond the basic train-test split and how cross-validation can offer a more thorough evaluation of model performance. Join us as we guide you […]

Statistics and Machine Learning both aim to extract insights from data, though their approaches differ significantly. Traditional statistics primarily concerns itself with inference, using the entire dataset to test hypotheses and estimate probabilities about a larger population. In contrast, machine learning emphasizes prediction and decision-making, typically employing a train-test split methodology where models learn from a portion of the data (the training set) and validate their predictions on unseen data (the testing set). In this post, we will demonstrate how […]