On-Prem Agents with LangGraph Platform
When building powerful agent applications in enterprise businesses, it is often important to maintain privacy and security.
For applications built in the cloud, managed services charge a premium for privacy and security.
To ensure even privacy from Cloud Service Providers (CSP), you must build applications to run on your hardware.
This is on-prem.
More and more AI engineering leaders are considering on-prem solutions, especially in highly-regulated businesses. That’s because it’s easier to prototype applications on-prem than most people think!
There are many reasons to give a small team of high-performance coders access to a small cluster of local GPUs and let them build, ship, and share various prototypes in your roadmap that you can test with internal stakeholders.
During our last foray into on-prem RAG, we covered the basics of being on-prem and what an on-prem setup looks like if you’re using the llamaindex ecosystem today.
In this event, we’ll go deeper on important aspects building capability on your local premises, and we’ll investigate how to do it with the LangChain ecosystem.
We’ll build, ship, and share an agent application with LangGraph Platform and deploy it to an API directly using LangGraph Server, all on-prem! We’ll use ollama for local model hosting.
As always, all content, from concepts to code, will be shared and your questions will be answered live!
📚 You’ll learn:
How to choose the right hardware and software components for prototyping agent applications on-prem
How to build on-prem with LangChain, and what to watch out for when scaling
🤓 Who should attend the event:
Aspiring AI Engineers who want to build at the open-source edge with LangChain
AI Engineering leaders who want to build production LLM applications on premises.
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.