UTOUG Training Days 2025: Full Schedule

9:30am MDT

Learn Generative AI and LLMs with OCI Generative AI Services

Monday March 24, 2025 9:30am - 10:15am MDT

This session introduces Generative AI and Large Language Models (LLMs) to Oracle technology professionals. It covers the technical aspects of LLMs, including LLM basics, architecture, fine-tuning techniques, prompt engineering, and the fundamentals of code models. Using examples, we'll also explore OCI's Generative AI services, such as pretrained generative models, model inference, and dedicated AI clusters.

Key topics like Retrieval-Augmented Generation (RAG), vector databases, semantic search, and the LangChain framework (including prompts, models, memory, and chains) will also be discussed. Additionally, this session serves as an introduction to the Oracle Cloud Infrastructure OCI 2023 Generative AI Professional certification.

Audience members will learn:

- An introduction to Generative AI and LLMs, including LLM basics, architecture, fine-tuning techniques, prompt engineering, and code model fundamentals
- OCI Generative AI services, such as pretrained generative models, model inference, and dedicated AI clusters
- Key topics like RAG, vector databases, semantic search, and the LangChain framework
- How to prepare for the Oracle Cloud Infrastructure OCI 2023 Generative AI Professional certification exam.

Speakers

Kai Yu

Principal Consultant, Independent

Kai Yu is an independent principal consultant with over 30 years of experience in the tech industry, specializing in Oracle Database, Oracle Applications, Cloud, and AI and machine learning. He previously served as a Distinguished Engineer at Dell Technologies, leading Oracle Database... Read More →

Monday March 24, 2025 9:30am - 10:15am MDT
Room 224

Data (not database), Infrastructure (including database)

11:30am MDT

Leveraging the Vector Database & AI Panel

Monday March 24, 2025 11:30am - 12:15pm MDT

Room 224

The Oracle AI Panel will answer your questions and discuss how AI will shape our future. We’ll cover practical uses of vector search and the vector database, along with their business impacts. Hosted by Rich, Oracle experts will share their insights on AI's possibilities, benefits, and challenges.

Speakers

Rich Niemiec

Chief Innovation Officer, Viscosity North America

Rich Niemiec is the current chief innovation officer of Viscosity North America. A world-renowned IT and data expert, he co-founded and served as CEO of TUSC, a Chicago-based systems integrator of business solutions founded in 1988. Rich is inducted into both the Chicago and E&Y National... Read More →

Monday March 24, 2025 11:30am - 12:15pm MDT
Room 224

Data (not database), Development

2:15pm MDT

Beyond Simple RAG: Combining Advanced Techniques for Superior Results

Monday March 24, 2025 2:15pm - 3:00pm MDT

Room 224

RAG, or Retrieval-Augmented Generation, is often seen as a way to enhance language models with extra information. But there's far more potential here than simply adding data. This presentation will guide you in transforming a basic RAG setup into something exceptional.

We'll start by exploring the value of RAG, its limitations, and why just attaching information won't cut it. From there, I'll demonstrate advanced techniques that each add value but, when combined, create a truly powerful RAG app. Through live demonstrations in a working application, you'll see these methods in action. Join us to discover the strategies that will take your RAG app from OK to outstanding.

Speakers

Craig Shallahamer

Applied AI Scientist, OraPub / Viscosity North America

Having worked with Oracle technology since 1989, Craig Shallahamer is a leader in the fields of machine learning, artificial intelligence and Oracle database performance tuning.Craig has extensive experience in constructing and teaching predictive modeling methods, notably developing... Read More →

Monday March 24, 2025 2:15pm - 3:00pm MDT
Room 224

Data (not database), Development

9:15am MDT

Introduction to GraphRAG: Enhance Generative AI Results with Graphs on Oracle Database 23ai

Tuesday March 25, 2025 9:15am - 10:00am MDT

Room 224

Knowledge graphs store complex information by capturing relationships between data entities. Data represented in a graph provides additional insights, derived from how it connects to other entities. Instead of viewing data as standalone points, a graph data model sees it as a set of connected entities. This connection enables new, deeper insights. Capturing this data provides richer context for generative AI. Retrieval Augmented Generation (RAG) can be enhanced with graph-RAG. Join us to explore graphs, graph-RAG, and the power of combining graphs and generative AI. We'll demonstrate how easy it is to implement this using Graph and Vector technologies in Oracle Database.

Speakers

Rahul Tasker

Senior Product Manager, Oracle

Rahul is a senior product manager for Oracle Spatial and Graph. He defines product strategy and vision to drive revenue, growth, and market adoption, while also identifying technology products and features that meet customer needs.

Tuesday March 25, 2025 9:15am - 10:00am MDT
Room 224

Data (not database), Development

10:15am MDT

Why Medallion Architecture Is the Best for Data Warehouses/Lakehouses

Tuesday March 25, 2025 10:15am - 11:00am MDT

Room 224

We chose a medallion architecture with bronze, silver, and gold layers for our data lakehouse design, and it has supported every use case we’ve needed perfectly. In this session, we’ll explain what medallion architecture is, how we implemented it, and how it has solved complex problems across various use cases.

Speakers

Michelle Hardwick

Chief Data Officer, University of California, Riverside

Michelle Hardwick is the current UTOUG president. She has presented at many Oracle and other tech events, including Oracle OpenWorld, Collaborate, and the Oracle OTN Latin America Tour.

Tuesday March 25, 2025 10:15am - 11:00am MDT
Room 224

Data (not database), Infrastructure (including database)

11:15am MDT

The Best Data Modeling Tools

Tuesday March 25, 2025 11:15am - 12:00pm MDT

Room 224

I recently evaluated sixteen of the leading data modeling tools and will share my findings, including the top scorers, their costs and licensing models, pros and cons, and any deal-breakers. I’ll also walk you through the 65 criteria and scoring methodology I used. We’ll take a closer look at the tool that claimed first place. I first came across this tool in 2019 when it ranked second in a similar evaluation I conducted of twelve modeling tools. Since then, it has only gotten better, saving my employers substantial amounts of money.

Speakers

Bill Coulam

Founder, dbSherpa.com & dataSherpa.blog

Bill has been designing and building large volume, custom Oracle systems since 1995 and writing and speaking at Oracle user groups since 2001. Bill serves on the board of UTOUG.

Tuesday March 25, 2025 11:15am - 12:00pm MDT
Room 224

Data (not database), Development

1:30pm MDT

Building a Generative AI RAG Application with Vector Search in Oracle Database 23ai

Tuesday March 25, 2025 1:30pm - 2:15pm MDT

Room 224

A key AI feature introduced in Oracle Database 23ai is vector search. A vector is an array of numbers representing the semantic content of data, rather than words or image pixels. Vectors enable similarity searches based on semantic content.

In this session, we'll explore the AI vector search features in Oracle 23ai, including generating, storing, indexing, and searching vectors, as well as integrating vector search with mission-critical enterprise capabilities.

Through sample code, we'll cover vector embedding generation methods for unstructured data, including using external embedding services and Oracle's native PL/SQL procedure, VECTOR_EMBEDDING(), to import ONNX embedding models.

We'll also discuss how to perform vector similarity searches and address challenges associated with managing high-dimensional data efficiently, ensuring query performance and accuracy, and creating new vector indexes for faster, more accurate similarity searches.

Finally, we'll explore how vector search enhances Generative AI and Large Language Models (LLMs), addressing the hallucination issue by augmenting prompts with private database content. Using examples, we will demonstrate building a Retrieval-Augmented Generation (RAG) application, incorporating tracking, embedding with the LangChain framework, and LLMs.

Speakers

Kai Yu

Principal Consultant, Independent

Tuesday March 25, 2025 1:30pm - 2:15pm MDT
Room 224

Data (not database), Development

2:30pm MDT

Generating OAC Semantic Model Using LLMs

Tuesday March 25, 2025 2:30pm - 3:15pm MDT

Room 224

Large language models (LLMs) are powerful tools for gathering data across various fields, ushering in a new era of AI-driven code generation. LLMs can generate structured data formats such as XML and SQL. By training on extensive datasets of XML documents, these models learn to understand both the syntax and semantics of XML, enabling them to produce well-formed XML documents, complete existing structures, and transform XML data into other formats.

We aim to test the hypothesis that LLMs can generate an OAC Semantic Model. The creation of a Semantic Model is time-consuming and stands to benefit significantly from improvement. We are currently investigating this approach and are eager to determine its efficacy.

Our idea is to train the LLM using XML generation techniques for the OAC Semantic Model, based on ADW Schema metadata, including table definitions, foreign keys, view definitions, table statistics, table documentation, and data catalogs. We plan to begin training with simple examples of the Semantic Model and gradually increase the complexity.

To test our hypothesis, we will use several LLMs, including GPT, Gemini, LLaMA, and Perplexity. We will evaluate multiple test cases for each model, comparing the results to see if they can effectively generate the models and whether these models can be successfully uploaded into OAC.

Speakers

Konstantin Zhernevskiy

Senior DWH Architect, Data Intensity

Konstantin is a senior DWH architect at Data Intensity with over 20 years of experience in the Oracle technology stack. For the past 10 years, he has focused on delivering data marts, data warehouses, and analytical reporting applications. His expertise includes AI, machine learning... Read More →

Tuesday March 25, 2025 2:30pm - 3:15pm MDT
Room 224

Data (not database)

UTOUG Training Days 2025

From $50.00