Large Language Models (LLMs) - Building applications with an open source approach by Don Shin

How to build secure, scalable, and local AI applications with open source tools
Don’s presentation provides valuable insights for developers looking to build AI applications. By leveraging open source tools and local setups, developers can create powerful, cost-effective AI solutions while maintaining control over data privacy. His client experience highlights the importance of addressing concerns and offering flexible, secure AI options. Using an open source approach offers developers more opportunities for innovation and flexibility in building AI-powered tools.
###
Save the date:
All Things Open 2025 is happening October 12-14, 2025 -- Raleigh, NC | 2025.allthings...
All Things Open AI is happening March 17-18, 2025 -- Durham, NC | allthingsopen.ai/
###
Presentation title: Large Language Models (LLMs) - Building applications with an open source approach by Don Shin
Session: Large Language Models (LLMs) - Building Applications with an Open Source Approach
Large Language Models (LLMs) can power more than just chatbots- this generative AI technology can also summarize large amounts of text and multi-modal data for quick consumption, sort/categorize/triage information based on semantic meaning, and bridge the gap between humans and computers by providing structure to unstructured data. However the need for data confidentiality, privacy, and security poses obstacles for many organizations wishing to utilize 3rd party LLM services such as ChatGPT. Thankfully, an open source approach to building LLM applications is not only feasible but preferable for organizations with such concerns.
Attendees of this talk will learn about:
Why maintaining end-to-end control of the prompt chain matters for security and reliability
The open source LLM models, vector databases, and frameworks that are available for rapid LLM application development
A live demonstration of how such frameworks can be used to build useful LLM applications
The runtime/deployment options for powering a LLM-powered application for their organization’s use
###
About We Love Open Source
We Love Open Source is an open source community educational hub that includes blogs, interviews, presentations, podcasts, how-to's, and more, from the All Things Open community members:
Start reading: allthingsopen....
How to contribute: allthingsopen....
About All Things Open
All Things Open is a universe of open source events and platforms designed to educate and connect technologists around the world. It includes the All Things Open conference, the largest open source / tech / web event on the U.S. East Coast, meetups in the Research Triangle Park (RTP) of NC, South Carolina, and New York City, and a TH-cam channel with more than 1,000 free recordings. See everything we do at allthingsopen.org.
Join our meetups:
Research Triangle Park, NC meetup: www.meetup.com...
South Carolina meetup: www.meetup.com...
New York City meetup: www.meetup.com...
Follow All Things Open:
TH-cam: / allthingsopen
LinkedIn: / all-things-open
Instagram: / allthingsopen
Facebook: / allthingsopen
X: x.com/AllThing...