DSPy: Advanced RAG?
Following our Part I on DSPy: Advanced Prompt Engineering? we’re following up with Part II: DSPy: Advanced RAG?
Last time, we learned to leverage DSPy as a wrapper that we could use to automate prompt engineering. We learned to tweak the input to get a better output.
In this event, we’ll learn to leverage DSPy to move past prompt engineering and automating prompting. We’ll see what DSPy can do with Retrieval Augmented Generation, or RAG!
According to DSPy’s author, Omar Khattab, the project “unifies prompting, fine-tuning, reasoning, and retrieval augmentation.” We can use DSPy to “express ‘any’ pipeline as clean, Pythonic control flow.”
In this event, we’ll cover a simple example that leverages DSPy to enhance a basic LangChain RAG application with OpenAI. Through this lens, we’ll try to see the unification of the patterns of GenAI and how pipelines of various types can be expressed in the new paradigm; one where “LLMs and their prompts fade into the background as optimizable pieces of a larger system that can learn from data.”
In short, we’ll leverage Declarative Self-improving Language Programs, pythonically, for RAG.
We’ll learn how this works, from concepts to code, and answer your questions along the way!
📚 You’ll learn:
The core concepts that extend DSPy for prompt engineering into DSPy for RAG
How DSPy can be used to augment your RAG applications
Where you should think about fitting DSPy into your workflow
🤓 Who should attend the event:
Aspiring AI Engineers who want to understand the latest prompting (ahem, programming) methods
AI Engineering leaders interested in avoiding manual trial-and-error RAG app optimization
Speakers:
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.