Žiga Vaupot's Blog

In the beginning of December, I attended UKOUG Annual Conference DISCOVER 2024 in Birmingham. I was presenting there and I am said (or perhaps not) to share this information, but this was my last time I was presenting under Version 1 / Qubix umbrella. Our paths are finally splitting at the end of this year and I will share more in my future posts. Back to my presentation in Birmingham.   Depending on the existing / future architecture OCI users have various option to choose from. The question is which ML approach is the most suitable for a specific user? And among these, some could be quite interesting. For example, which solution could be the best fit if customer still prefers to stay on-premise or what if data is fluent. So, what options have we got in OCI? In my presentation titled  3 Case Studies: Machine Learning in OCI , I am trying to answer some of the questions mentioned about and I am discussing development and deployment options that we have in Oracle Clou...

In my two previous blog posts Talking to Oracle Database in plain English and Talking to Oracle Database, this time in plain Slovenian I have been playing with Select AI in Oracle 23ai database. In these two blog posts I tested how Oracle 23ai feature called Select AI provides SQL access to generative AI using Large Language Models to generate SQL query which is then executed in database. In this blog post I am testing an option to use Select AI for Retrieval-Augmented Generation (RAG). Select AI with RAG augments natural language prompt by retrieving data (documents) from vector store (stored in Oracle 23ai ). With this additional content, hallucinations can be reduced and much more accurate answers could be retrieved. Setting it up Select AI is using Oracle 23ai AI Vector Search for similarity search using vector embeddings. To set the environment for Select AI with RAG two main tasks needs to be performed: set up vector store in Object Storage and create vector...

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...

I will assume that I have already created a semantic model which has been deployed in my OAC environment. My intention is to share this semantic model with other developers who are working on this same model in the same time. In OBIEE this was only possible by setting up Multi-User Development Environment (MUDE). My experience with MUDE is that it wasn't perfect, often, if not careful, it was leading to problems with locking, merging, deployments. With Oracle Analytics and in particular with Semantic Modeler introduction, this has changed. When working with Semantic Modeler, Oracle Analytics gives developers two options how to setup (much stronger) collaborative environment by: giving permissions to make updates to the model to other users - Semantic Modeler is, in a way, by default multi-user development environment, and using Git , which provides proper multi-user development environment. In this case, access rights are given through Git directly. Integrating Semantic ...