Visualising AI Embeddings in APEX
" To deal with hyper-planes in a 14-dimensional space, visualize a 3-D space and say 'fourteen' to yourself very loudly. Everyone does it." - Geoffrey Hinton , 2018 Turing Award winner. Within the wonderful world of Generative AI , one concept that is all the rage is RAG, or Retrieval Augmented Generation , which is an AI framework that combines the strengths of traditional information retrieval systems (such as databases) with the capabilities of generative large language models (LLM s) . RAG's goal is to improve the accuracy, relevance, and timeliness of information generation - such as documents, text and images - by optimizing LLM output. When creating a RAG system, it’s essential to store information in a format that a LLM can retrieve. This is where data is converted into embeddings through a pro...