Jerry is the co-founder/CEO of LlamaIndex, the data framework for building LLM applications. Before this, he has spent his career at the intersection of ML, research, and startups. He led the ML monitoring team at Robust Intelligence, did self-driving AI research at Uber ATG and worked on recommendation systems at Quora.
RAG is a key concept for getting LLMs to understand your private sources of data. But the current RAG stack is quite naive, consisting of vector-based retrieval and a one-shot call to the LLM for synthesis. LLMs are developing intelligent reasoning capabilities; how can we apply these capabilities on top of your documents for much more advanced question-answering? This talk will cover some initial directions towards that.