Žiga Vaupot's Blog

Using SELECT AI with RAG In my two previous blog posts, Talking to Oracle Database in plain English and Talking to Oracle Database, this time in plain Slovenian , I explored Select AI within the Oracle 23ai database. In those posts, I tested how the Oracle 23ai feature called Select AI enables SQL access to generative AI by using Large Language Models (LLMs) to generate SQL queries that are then executed in the database. In this post, I will focus on using Select AI for Retrieval-Augmented Generation (RAG), a powerful approach that enhances natural language prompts by retrieving relevant documents from a vector store maintained within Oracle 23ai . This augmentation helps reduce hallucinations and provides more accurate, evidence-backed answers. What is Select AI with RAG? Select AI with RAG combines the power of generative AI with vector search capabilities. It uses Oracle 23ai AI Vector Search to perform similarity searches based on vector embeddings, retrieving releva...

HROUG  hosted its 2024 's conference between16th and 19th October, as usual, in Rovinj, Croatia. This year, I was invited to present the two of my presentations: Extending Oracle Analytics Machine Learning Capabilities with OCI Services and Talking to Oracle Database in plain English … i Hrvatski! Talking to Oracle Database in plain English … i Hrvatski! My first session was about one of the coolest additions to Oracle Database 23ai, SELECT AI . SELECT AI allows users to ask the database (questions in natural language. By enabling connections with generative Large-Language Models such as ChatGPT, OpenAI Azure, Cohere and others, users can simply ask the question and can expect results, based on data stored in the database, returned narrated or simply by datasets which can be visualised and nicely presented. In this presentation, I am describing and demonstrating how to setup Oracle Database to use LLMs and  explore how well Oracle Database speaks and understand English. And si...