RAG in 2024: Advancing to Agents
I'm Laurie, VP of Developer Relations at Llama Index. If you've spent time with LlamaIndex, you already know about the importance of retrieval-augmented generation or RAG. In this video, I make the case that while RAG is necessary, it's not enough for sophisticated knowledge retrieval. You need to build an agent. In this video we cover:
Basic RAG
Agentic components, including
Routing
Memory
Planning
Tool use
Agentic reasoning, including
Sequential (like Chain of Thought)
DAG-based
Tree-based (like Tree of thought)
And we briefly cover further extensions including
Observability
Controllability
Customizability
You can find links to all the resources covered in this video at https://bit.ly/li-agent-resources