On-Prem Agentic RAG: Report Generation
As LLMs have become more mainstream, enterprises have begun adopting the practice of building, shipping, and sharing production LLM applications.
One question we get from enterprise leaders is how they can get things done “on their system” or on their local “premises.”
In other words, they have compute resources (not in the cloud - but GPUs sitting in their shop) that they want to use to serve LLMs for their AI research and product development.
Is “On-Prem RAG” something that’s actually possible today?
Yes! And it’s much easier than you think!
The leading orchestration tools in the LLM space, including LlamaIndex, have curated a stack of tools that can streamline building out “On-Prem” solutions, even agentic applications.
In this event, we’ll break down how to leverage LlamaIndex tooling, including Workflows and llama-deploy, along with ollama, to prototype and serve your complex agentic RAG application!
The use case we’ll cover is Report Generation, in which you can use open-source LLMs to answer and fill out a series of blanks in a form (or questions in a questionnaire). First, each part is answered individually, and then the answers can be combined into a summary report that includes the filled-out form.
Join us live to build, ship, and share an epic one - a real agentic RAG use case that your enterprise might use on-prem soon!
As always, all content, from concepts to code, will be shared and your questions will be answered live!
📚 You’ll learn:
How an “on-prem” complex LLM app stack differs from one used in the cloud
The core concepts and code behind LlamaIndex Workflows, Llama-Deploy, and ollama
How to a state-of-the-art agentic RAG application with open-source models
What the “on-prem” stack options are for building, shipping, and sharing with LLMs today
🤓 Who should attend the event:
Aspiring AI Engineers who want to build at the open-source edge with LlamaIndex
AI Engineering leaders who want to build production LLM application 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.