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…

Machine learning revolves around algorithms, which are essentially a series of mathematical operations. These algorithms can be implemented through various methods and in numerous programming languages, yet their underlying mathematical principles are the same. A frequent argument is that you don’t need to know maths for machine learning because most modern-day libraries and packages abstract…

Optimize the Embedding Space for Improving RAG Image by author. AI generated.Embeddings are vector representations that capture the semantic meaning of words or sentences. Besides having quality data, choosing a good embedding model is the most important and underrated step for optimizing your RAG application. Multilingual models are especially challenging as most are pre-trained on…

Diving deeply into the working structure of the first version of gigantic GPT-models 2017 was a historical year in machine learning. Researchers from the Google Brain team introduced Transformer which rapidly outperformed most of the existing approaches in deep learning. The famous attention mechanism became the key component in the future models derived from…

The way you retrieve variables from Airflow can impact the performance of your DAGs Photo by Daniele Franchi on UnsplashWhat happens if multiple data pipelines need to interact with the same API endpoint? Would you really have to declare this endpoint in every pipeline? In case this endpoint changes in the near future, you will…