Jackie Gleason
THE Jackie Gleason
Columbus, Ohio, United States
Actions
Jackie Gleason is an experienced principal engineer for a property management startup named PurePM. Mr. Gleason has almost 20 years of experience in the Columbus area including Chase, NetJets, PUCO, OCLC and the Columbus Foundation. Jackie has presented previously at CodeMash, M3, and other local user groups on topics such as Java, Javascript, mobile development, testing and more. In addition to development Jackie enjoys 3D printing, billiards, and traveling. For more information or to reach out go to https://jackiergleason.com.
Area of Expertise
Vector Databases and Embeddings Demystified
Ever wonder how Netflix knows you'll love that obscure documentary about penguins, or how Google Photos finds every picture of your dog even though you never tagged them? The secret sauce is vector embeddings and similarity search – technologies that convert complex data (text, images, audio) into high-dimensional numerical representations that capture semantic meaning. While traditional databases excel at exact matches ("find user ID 12345"), vector databases revolutionize "find similar" queries by measuring relationships between these numerical vectors using techniques like cosine similarity. This session demystifies the math and technology behind the AI-powered search and recommendation systems you use every day.
You'll discover how companies transform words into vectors where "king" - "man" + "woman" actually equals "queen" in mathematical space, explore the architecture behind popular vector databases like Pinecone and see live demonstrations of building semantic search systems. We'll cover real-world applications from RAG-powered chatbots to fraud detection, show you how to implement document similarity search in 20 lines of Python, and discuss the practical considerations of scaling vector systems to billions of embeddings. Whether you're building recommendation engines, semantic search, or AI-powered applications, this session provides the foundational knowledge to leverage vector databases effectively in your projects.
Using IoT for good
In this presentation we'll explore how technology can transform everyday life, particularly for those with disabilities or special needs. We’ll begin by breaking down the basics of home automation, showing how even simple wired and wireless sensors and switches can significantly enhance quality of life.
Next, we’ll delve into tools like Home Assistant and HiveMQ, which simplify and organize these devices into manageable topics and automations, making home automation more intuitive and accessible.
Finally, we'll explore how AI and Machine Learning can take these systems to the next level. By integrating additional state information and using advanced techniques like Retrieval-Augmented Generation (RAG) and agent platforms, we can improve decision-making and uncover unexpected efficiencies.
To bring this all to life, I'll share real-world experiences, including how this technology has improved the quality of life for my friends and family, demonstrating its profound impact on accessibility and independence.
OAuth2 using PKCE
OAuth is an important RFC that handles delegated authorization. PKCE (or Proof Key for Code Exchange) is an OAuth 2.0 flow, that can be managed in a frontend application, allowing the user to handle storing tokens in the browser. This eliminates the need to rely on a server-side session making the authorization stateless. PKCE also removes the need for complex session caching, and provides the end user with control over their tokens. To understand PKCE this presentation will look at the history of OAuth, how PKCE fits into current applications, and run through an example. The talk will focus on how this can be done across the major frameworks such as Vue, Angular, and React. With these tools anyone will be able to implement a stateless, secure, and standard way to handle authorization and authentication.
MQTT + Ollama = Building Home Automation That Actually Works (And Doesn't Spy on You)
Tired of smart home devices that need the internet to turn on a light bulb? Fed up with voice assistants that mishear "dim the bedroom" as "order three tons of cat food"? This session explores how to create a truly intelligent home automation system using Ollama for local AI processing and MQTT for reliable device communication. We'll examine how a custom MCP (Model Context Protocol) server translates natural language commands into MQTT messages, letting you control Z-Wave devices, smart switches, and sensors through conversational AI that runs entirely on your local network. Unlike corporate voice assistants that maintain corporate politeness, your local AI can have personality – imagine an assistant that responds to "turn off all the lights" with "Finally going to bed at a reasonable hour? Impressive." or sarcastically comments when you ask it to turn the heat up for the third time today.
We'll explore how this architecture bridges AI understanding and IoT device control, turning "make the living room cozy for movie night" into precise MQTT commands thatcoordinate multiple devices. The session covers integration patterns with popular platforms like Home Assistant and Z-Wave JS, examines Home Assistant's remarkable progress through their Year of Voice initiative (including their recent achievements in local voice processing), and demonstrates how structured prompting creates reliable device control while maintaining the personality you actually want in your home. No cloud dependencies, no monthly subscriptions, and definitely no corporate eavesdropping on your late-night snack requests – just a working example of how local AI can make your smart home both intelligent and entertaining.
Making AI Cross-Cloud Using LiteLLM
We've all been there: you need your app to switch from Claude to ChatGPT, but they're on separate clouds. This means configuring cross-cloud permissions, managing different API formats, and wrestling with vendor-specific authentication - but what if you could just proxy those prompts to the appropriate cloud and avoid all the additional setup headaches? Welcome to LiteLLM, your new best friend in the multi-model world.
LiteLLM acts as a universal translator for over 100 LLM providers (OpenAI, Claude, Bedrock, Azure, Cohere, Hugging Face, and more), converting everything to a unified OpenAI API format so your code doesn't have to know whether it's talking to GPT-4 or Llama running locally on your laptop. Notice your AI spend creeping up and want to understand what's burning through your budget? LiteLLM provides detailed cost tracking, spending limits per user or project, and can even load balance across multiple models to optimize for cost and performance. It handles the nitty-gritty of rate limiting, failover logic, and streaming responses while providing enterprise-grade logging and monitoring.
This session will cover what LiteLLM is, how it simplifies multi-cloud AI architecture, and practical setup strategies including cost management, load balancing, and security considerations. In our brave new world of model diversity, technology like LiteLLM isn't just convenient - it's crucial for maintaining sanity while building production AI applications. Get ready to take your LLM consumption game to the next level without losing your mind (or your budget) in the process.
Home Assistant 101
Home automation is transforming our lives, with smart switches, cameras, and wireless devices making our homes more comfortable and efficient. However, with so many different brands and proprietary ecosystems, managing these devices can feel like navigating a complex patchwork. That’s where Home Assistant comes in—a powerful framework to bring all your devices under one roof.
In this 2-hour session, we'll guide you through installing Home Assistant, both locally and on container-based platforms. You'll learn how to configure it for various interfaces, including Z-Wave, Wi-Fi, and Zigbee. We’ll then explore how to automate everyday tasks, making your smart home even smarter. Finally, we’ll cover integration with voice assistants like Amazon Alexa and Google Assistant, giving you hands-free control over your devices.
By the end of this presentation, you'll have the knowledge to become a home automation pro, ready to enhance your comfort and convenience.
Building Enterprise AI Agents with Spring AI and MCP
In this intensive 4-hour precompiler, you'll learn how to build enterprise-grade AI agent systems using Spring AI's complete ecosystem. We'll construct a robust application that can run locally for development and scale to cloud environments for production. You'll create a production-ready chatbot using Spring Boot, add a custom-built Spring MCP server, implement Spring AI's effective agent patterns, and integrate RAG capabilities with a variety of vector databases. Using AI models through both local Ollama and cloud providers like AWS Bedrock, you'll develop highly available and intelligent agents with structured outputs, comprehensive analytics, and enterprise monitoring.
This precompiler is perfect for Java developers and enterprise architects ready to add AI capabilities to existing Spring applications. You'll leave with a complete working system: enterprise MCP server, Spring AI agent workflows, RAG integration, production analytics with Spring Boot Actuator, and Apache Airflow orchestration patterns. Learn deployment strategies that give you flexibility for any scenario - from local development to enterprise cloud deployments.
Jackie Gleason
THE Jackie Gleason
Columbus, Ohio, United States
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top