Synthetic Data for Enterprise
Using LLMs the right way is hard. Selecting use cases is hard. Pairing tools and emerging techniques to the right use cases is hard. However, there is one task for which LLMs have an unusually high probability of being useful: Synthetic Data Generation (SDG).
SDG can enhance many aspects of building production LLM applications, from training, fine-tuning, and alignment to evaluation and assessment.
In this event, we’ll cover the specific ways that SDG is used in the market to accelerate LLM application development. From RAG Assessment to NVIDIA’s Nemotron, to scaling personas, this is an active area of research and development. We will also dig into the mechanics of how SDG can be used for both fine-tuning and eval.
We will do a deep dive into the concepts and code of how to use LangSmith to quickly test production LLM applications. After scoping the financial problems we want to solve, choosing one, and building an LLM prototype, we’ll generate the right synthetic data to test the performance of the prototype. We will discuss each step of the SDG data synthesis process and the best-practice options that generally used across the landscape. Based on the initial evaluation, we’ll investigate ways to improve the performance of our system for our application.
We’ll wrap up with a discussion about the ways that LangSmith is being used today by real financial services companies, and what the recommended best practices are for various applications.
As always, we’ll provide a detailed code walkthrough
📚 You’ll learn:
How to use Synthetic Data Generation for evaluation and assessment of LLM applications
How LangSmith can be used to accelerate moving from LLMs into production
What leading financial services firms are using synthetic data generation for
🤓 Who should attend the event:
Aspiring AI Engineers who to do robust evaluation with the latest open-source tools
AI Engineering leaders who want to accelerate LLM app deployment to production
Speaker:
Dr. Greg” Loughnane is the Co-Founder & CEO of AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. Since 2021 he has built and led industry-leading Machine Learning education programs. Previously, he worked as an AI product manager, a university professor teaching AI, an AI consultant and startup advisor, and an ML researcher. He loves trail running and is based in Dayton, Ohio.
Chris “The Wiz” Alexiuk is the Co-Founder & CTO at AI Makerspace, where he is an instructor for their AI Engineering Bootcamp. During the day, he is also a Developer Advocate at NVIDIA. Previously, he was a Founding Machine Learning Engineer, Data Scientist, and ML curriculum developer and instructor. He’s a YouTube content creator YouTube who’s motto is “Build, build, build!” He loves Dungeons & Dragons and is based in Toronto, Canada.
Follow AI Makerspace on LinkedIn and YouTube to stay updated about workshops, new courses, and corporate training opportunities.