Do you find it difficult to keep up with the latest ML research? Are you overwhelmed with the massive amount of papers about LLMs, vector databases, or RAGs? In this post, I will show how to build an AI assistant that mines this large amount of information easily. You’ll ask it your questions in…

By now we may have moved on from “Happy new year!” territory, but January’s jolt of energy and activity is still very much with us. We see it in the posts that have drawn the most readers and generated the liveliest conversations in recent weeks: they tend to focus on teaching oneself new skills, seeking…

An illustrated and intuitive guide to Neural Networks If you have read my previous articles, you’ll know what’s coming next. In this part of the internet, we take complex-sounding concepts and make them fun and nbd by illustrating them. And if you haven’t read my previous articles, I highly recommend you start with my series…

GENERATIVE AI Learnings from fine tuning a large language model on a single consumer GPU Image by Author (Midjourney).When we think about Large Language Models or any other generative models, the first hardware that comes to mind is GPU. Without GPUs, many advancements in Generative AI, machine learning, deep learning, and data science would’ve been…

Towards a lingua franca for knowledge graph question answering systems Machine Translation (MT) can enhance existing Question Answering (QA) systems, which have limited language capabilities, by enabling them to support multiple languages. However, there is one major drawback of MT — often, it fails at translating named entities that are not translatable word-by-word. For example,…

Exploring mental well-being insights with zero-shot classification Artwork by Vivian Peng — reposted with permissionSentiment analysis is a powerful tool in natural language processing (NLP) for exploring public opinions and emotions in text. In the context of mental health, it can provide compelling insights into the holistic wellness of individuals. As a summer data science…

A deep dive on a powerful and popular algorithm Photo by FlyD on UnsplashFrom drug discovery to species classification, credit scoring to cybersecurity and more, the random forest is a popular and powerful algorithm for modeling our complex world. Its versatility and predictive prowess would seem to require cutting-edge complexity, but if we dig into…

The rise of the MoEs Image by the author — Generated with DALL-ESince the release of Mixtral-8x7B by Mistral AI, there has been a renewed interest in the mixture of expert (MoE) models. This architecture exploits expert sub-networks among which only some of them are selected and activated by a router network during inference. MoEs…

Exploring robust RAG development with LlamaPacks, Lighthouz AI, and Llama Guard Image generated by DALL-E 3 by the authorSince the launch in late November 2023, LlamaPacks has curated over 50 packs to help jump-start your RAG pipeline development. Among these, many advanced retrieval packs emerged. In this article, let’s dive into seven advanced retrieval packs;…

Methods for creating fine-tuning datasets for text-to-Cypher generation. Created with ChatGPT-DALLECypher is Neo4j’s graph query language. It was inspired and bears similarities with SQL, enabling data retrieval from knowledge graphs. Given the rise of generative AI and the widespread availability of large language models (LLMs), it is natural to ask which LLMs are capable of…