RAG in 2024: Advancing to Agents


Retrieval-augmented generation is an essential tool for building modern information-retrieval systems, but it isn't enough. In this talk, we make the case that while RAG is necessary, it's not sufficient: you need to add agentic strategies to your system. We discuss the basic components of an agentic system including routing (selecting between sources), memory (providing context between queries), planning (what should we do?), reflection (did we correctly do what we intended?) and tool use. We also discuss agentic reasoning strategies including sequential (chain of thought), DAG-based, and tree based (tree of thought). Finally we dip briefly into further extensions to agents including observability, controllability and customizability.

Session Outline:

Attendees will learn how to use LlamaIndex to build a RAG pipeline, create agents with arbitrary tool sets and add routing, memory, planning and reflection to them, including chain of thought, DAG-based and tree of thought based reasoning.

Background Knowledge:

Basic working knowledge of python is helpful.


Laurie Voss is VP of Developer Relations at LlamaIndex, the framework for connecting your data to LLMs. He has been a developer for 27 years and was co-founder of npm, Inc.. He believes passionately in making the web bigger, better, and more accessible for everyone.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google