RAG: The 2025 Best-Practice Stack, Part II: Enterprise Production
Part II: Enterprise Production
Building on our first event, **RAG: The 2025 Best-Practice Stack, we are back with Part II where we will focus on the real issues that prevent successful production deployments!**
Once you have a simple on-prem prototype that you can show stakeholders on a laptop, how do you go about getting into production so that you can scale it?
In this event, we’ll break down the phases of moving from prototype to production in enterprise, including:
Phase I: On-Prem Demo (POC/MVP) with Executive/VP/Director buy-In
Phase II: Refined On-Prem Demo with Engineering buy-In
Phase III: Data Preparation & Quality Validation with buy-in from architects, data practitioners, and security
Phase IV: Beta Testing with customer/stakeholder buy-in
Phase V: Scaling a User-Friendly Product with product/design buy-in
As we saw during Part I of the series, we can pick up open-source Commercial-Off-The-Shelf (COTS) tools to build your first RAG application today with a Best-Practice RAG Application Stack, including:
We’ll explore:
🎺 Our pick for the best orchestration framework: LangChain’s LangGraph
↗️ Our pick for the best vector database: QDrant
📊 Our pick for the best way to enhance retrieval out of the box: Cohere’s Rerank
📐 Our pick for the best evaluation framework: RAGAS
So the question is, then, what happens when we need to know move from Phase I into the organization and into a Cloud Service Provider (CSP)?
Depending on your current CSP, your solution might have to look different today.
However, if you have all of the choices, it seems there is a lowest-friction pathway to deploying your LangGraph RAG applications in the cloud at scale.
Our pick for best Cloud Service Provider Integration: LangChain on Azure Databricks
We will discuss the benefits of using this approach with LangGraph applications, as well as mention some other leading partnerships worth noting in the industry that prioritize speed to production (e.g., CrewAI on AWS).
We’ll also discuss some of the remaining best practices we didn’t cover in part I to highlight some of the production-grade tooling, including:
🐕 Leading Advanced retrieval techniques
🔤 Dealing with structured vs. unstructured data
🔖 The importance of metadata
We believe this is the correct stack to maximize performance and efficiency today.
Stay tuned, as the industry moves quickly!
Of course, we’ll continue to build, ship, and share the RAG-In-Practice-2025 application that we started in Part I!
Join us live to dig into the details and get your questions answered, from concepts to code!
📚 You’ll learn:
How to ship your LangGraph RAG prototype to production according in 2025 best practices
Why there is a right answer to the “best” components for shipping RAG to prod right now
How to think about enhancing the RAG applications you ship to production through evaluation and enhancements
🤓 Who should attend the event:
Aspiring AI Engineers who want to build, ship, and share production-grade LLM applications
AI Engineering leaders who want to build the best possible RAG applications, fast
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.