Production-Ready Optimization Strategies for RAG
Once AI Engineers can build a simple prototype and there is some interest in making it faster, more reliable, more secure, and better able to scale to many users, the real work of building a production LLM application begins!
In this event, we’ll explore some production-ready optimization strategies including:
Async: Asynchronous requests is a powerful pattern for handling multiple tasks concurrently
Caching: cache is king! We need to avoid running the same prompts through our LLM chat model and running the same data through our embedding model!
Sessions: the life cycle of a user chat session is important to track at scale
We will explore each of these introductory aspects of production-readiness in detail in the context of a simple Chainlit RAG application built with LangChain!
Further, we’ll touch on a few other slightly more advanced important aspects of dealing with more complex RAG applications, including:
Methods: Calling chains, functions, tools, APIs
Parallelization: How should we think about parallelized vs. serialized chains
Database Scaling: What do we need to know about scaling our vector DBs?
We hope that this event will serve as a useful introduction to making your RAG application production-ready!
As always, all content, from concepts to code, will be shared and your questions will be answered live!
📚 You’ll learn:
Key introductory aspects of production-readiness for RAG applications
How to set up asynchronous requests, caching, and sessions in your Chainlit application!
🤓 Who should attend the event:
Aspiring AI Engineers who want to build production LLM applications
AI Engineering leaders who want to learn to deploy RAG in production
A message from the Chainlit team: If you like building LLM and RAG applications with Chainlit, check out Literal AI, the platform for evaluating and improving your RAG application's performance. Both Chainlit and Literal have been created by the same team!
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.