• embeddings
• large language models
• natural language processing
• retrieval
• text generation

In contemporary society, Natural Language Processing (NLP) and Large Language Models (LLMs) have become integral components of numerous applications and industries, profoundly impacting various aspects of daily life. The fusion of advanced algorithms, vast datasets, and scalable computing infrastructure has propelled NLP and LLMs to the forefront of technological innovation. These transformative technologies are becoming indispensable in different sectors ranging from communication and commerce to healthcare and entertainment. The thesis explores the evolution of LLMs, tracing their development from early language models to contemporary transformer-based architectures, for text generation. It presents a case study on the use of generative Large Language Models for the automatic creation of documentation starting from code, and for the automatic recovery of documents using word/document embeddings techniques. The case study was addressed and developed within a corporate reality.