Data Agents with LlamaIndex
Agents continue to gather steam in 2024! The patterns of agentic reasoning can be applied throughout your LLM applications. When architecting your applications to solve specific problems, deciding how to combine agentic reasoning with function calling, RAG, and fine-tuning is a task that falls to the AI Engineer or AI Engineering Leader.
How systems are built on the back end, specifically how tradeoffs are made between performance and cost-efficiency, impacts bottom-line business value.
Further, to understand the landscape of possible options, you’ve got to have a firm grasp on the fundamentals of the architecture of the framework you’re using.
In LlamaIndex v0.10, the infrastructure for agents is centered around the idea of a Data Agent, or what they call an “LLM-powered knowledge worker.” While the query engines at the heart of LlamaIndex can read from vector databases, data agents can dynamically deal with data from vector databases and a host of external tools.
In this event, we deep dive into how LlamaIndex does agents, and how agents interact with the core constructs of nodes and query engines. We build a complex RAG capable of answering questions by reasoning through quantitative (structured) and qualitative (unstructured) information.
First, we’ll construct RAG pipelines. A semantic pipeline is used for textual information, and NL2SQL tooling is used to query tabular data. Finally, a metadata filtering technique powered by OpenAI’s functional endpoint is used to select and query the right index at the right time.
As always, all content, from concepts to code, will be shared and your questions will be answered live!
📚 You’ll learn:
How to build RAG applications with reasoning loops in LlamaIndex
To construct and query vector databases containing structured and unstructured data
To leverage metadata filtering and add agentic reasoning behavior to your LLM applications
🤓 Who should attend the event:
LLM practitioners who want to understand how to build agentic RAG applications
Aspiring AI Engineers who want to build at the open-source edge with LlamaIndex
AI Engineering leaders who want to learn the most popular open-source agent frameworks
Speaker
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. 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.