Leveraging Retrieval-Augmented Generation (RAG) for Contextual Generative AI Solutions

This session explores contextual Generative AI solutions by leveraging retrieval-augmented generation (RAG) methodology. Attendees will gain an understanding of RAG architecture and the pivotal role of contextual information.
The session will cover the RAG framework and the implications of contextual cues in enhancing generative AI outcomes. Through practical demonstrations in Azure Databricks, participants will dive into the nuances of data preparation for generative AI applications, seamlessly integrating this preparatory phase with implementing an RAG architecture. In addition, the session dives into advanced concepts surrounding vectors and vector databases, improving their relevance in augmenting generative AI capabilities.

In essence, this session provides attendees with the knowledge and tools necessary to navigate contextual generative AI, empowering them to leverage the transformative potential of RAG methodology in diverse applications.

Is Data Mesh right for your Organization?

This session explores the concept of Data Mesh and its potential applicability to your organization. Based on theoretical insights and real-world case studies, attendees will gain a deep understanding of the principles behind Data Mesh and its implications for data management, scalability, and agility. In addition, we will discuss key considerations when determining whether Data Mesh aligns with your organization's goals, culture, and technical capabilities.
Walking away from this session, attendees will have a better understanding of:
- What is Data Mesh
- Pros and Cons of Data Mesh
- Walkthrough of successful implementation of Data Mesh

End to End MLOps using Azure Machine Learning

The first segment of this beginner-level session will provide an introduction to MLOps and an overview of the machine learning lifecycle, spanning data preparation, model training, deployment, and maintenance.
The subsequent part will shift the focus to hands-on MLOps practices, harnessing the capabilities of Azure ML for seamless integration into your machine learning projects.
Participants will explore various MLOps techniques, including data versioning, experiments, and model tracking, which are essential for ensuring reproducibility and scalability. Moreover, we will explore operationalizing models using Azure ML, empowering attendees to efficiently manage and scale model deployments across your organization.
This session is suitable for anyone interested in MLOps or who wants to learn more about Azure ML's capabilities.

Data Governance and Management with Databricks Unity Catalog

Adopting Unity Catalog has been crucial to meet compliance and auditing requirements in the Lakehouse. In this session, we'll discover the intricacies of Unity Catalog's integration with the Databricks Platform, providing you with the insights and tools necessary to harness the full potential of your data assets. Gain invaluable knowledge on accessing Unity Catalog through Clusters and SQL Warehouses, enabling seamless data management across your organization. And finally, we will share how to integrate Unity Catalog external Delta tables to OneLake using shortcuts.

Discover best practices for creating and governing data assets within Unity Catalog, empowering your team to unlock actionable insights and drive informed decision-making.

Data Engineering with Databricks on Google Cloud

Databricks, based on Apache Spark, is a fast, easy-to-use, and scalable data platform.
With Databricks on Google Cloud, you can build open, flexible data lakes integrated with BigQuery and Looker.
In this session, you will learn about Spark and Databricks, what problems it solves, and how Databricks work on Google Cloud.
This isn't another theoretical presentation; this session will include hands-on demonstrations of loading, transforming, and visually presenting data with Databricks.

Seminar for College Students

This two hour seminar is composed of four sessions of approximately 30 minutes each. You'll get to hear about the many different job titles and technologies in the area of data, getting ready for your first interview, how to participate in your profession now, and lots of Q&A. No preparation needed, join us and you'll get to hear professionals working in IT share ideas and answer questions very relevant to those trying to focus their education and getting ready for their first job in IT! See your professor about extra credit for attending. Note that this seminar is held concurrently with SQLSaturday, you're welcome to attend those sessions after the seminar completes.

Getting Started with Azure Databricks: Data Engineering

Azure Databricks, based on Apache Spark, is a fast, easy-to-use, and scalable data platform.
In this session, you will learn what is Apache Spark and Azure Databricks, what problems Azure Databricks solve, and how Azure Databricks work.
This session will include hands-on demonstrations of loading, transforming, and presenting data with Azure Databricks.

Building a Data-Driven Organization

What do you need to become a data-driven organization? More important than having big data or a team of 'unicorn' data scientists, it requires an effective, deeply-ingrained data culture, tools, and abilities to support users to act on data. The role of the Business Data Analyst is critical in all 4 types of analytics methods: descriptive, diagnostic, predictive, and prescriptive.
This session will review different analytics maturity levels, data architectures, and types of analysis delivering insights. We will discuss and understand how Business Data Analysts can spur a data-driven culture while leveraging insights to influence business decision-making.

Building Data Lake on Azure

Your organization is building a Data Lake on Azure and you are on the team implementing it... How do you organize the information in the Data Lake? What are the security best practices to protect your data? What paths companies take to build an effective solution? In this session, you will learn about design and architecture patterns in building Data Lakes on the Azure cloud. We will discover ways to design zones or layers to provide different groups access to the data, which was curated at different levels. You will leave this session with a clear understanding of how to implement and bring together the best of your data warehouse and data lake into one unified platform.

How to get started with MLOps in Azure Databricks

The first portion of this entry-level session will introduce you to the machine learning life cycle, including data preparation, model training, selection, and deployment. The second portion of this session will cover how to use Azure Databricks for your Machine Learning project. We will try different algorithms, parameters, and track this information to reproduce our work. We will learn how to operationalize your model with Databricks Machine Learning, and gain a deeper understanding of how to scale deployments of models across your company.