LLMs + Smarter Search: The Future of RAG [Register on Luma]
This talk explores flexible retrieval approaches that let you optimize for accuracy, cost, and latency based on your specific use case.
Let us know what you are building and we will let you know if you qualify for free Dedicated Developer hours!
Agenda 17:30-17:45: Walk in with drinks
17:45- 18:30: Talks
Some insights on LLMs, by Lukasz Kaiser (“Attention is All you Need” co-author, co-inventor of Transformers)
Taming Unstructured Data: Which Indexing Strategy Wins? by Jan Chorowski (CTO, Pathway)
We are welcoming Flash Talks of 3-5 minutes, reach out to hello@pathway.com
18:30-20:00: Networking + drinks and bites (🍕 /🍺)
TalksTalk 1: Deep Learning Past and Future: What Comes After GPT? by Lukasz Kaiser (“Attention is All you Need” co-author, Member of Technical Staff, OpenAI)
Talk 2: Taming Unstructured Data: Which Indexing Strategy Wins? by Jan Chorowski (CTO, Pathway)
Challenge: Building LLM-powered systems that accurately answer questions over vast, ever-changing unstructured data sets is a challenge. Traditional one-size-fits-all vector indexing struggles to keep up.
Solution: This talk explores flexible retrieval approaches that let you optimize for accuracy, cost, and latency based on your specific use case. Discover the strengths and trade-offs of various indexing strategies, including your favorite vector indexing engines like FAISS, full-text search, LLM-augmented retrieval, and knowledge graphs. You will learn how to mix-and-match these strategically. We'll showcase several real-world examples of "needle in the haystack" tasks when querying legal documents.
This talk is for you if:
- You're struggling to extract meaningful insights from unstructured data.
- You're curious about the latest advancements in RAG technology.
- You want to unlock the full potential of your large language models (LLMs).
Speaker BiosLukasz Kaiser
Lukasz is a deep learning researcher at OpenAI and was
previously part of the Google Brain team. He recently worked
on GPT4 and Codex models. Earlier he co-invented Transformers
and other neural sequence models and co-authored the TensorFlow
system. Before working on machine learning, Lukasz was a tenured
researcher at University Paris Diderot and worked on logic and
automata theory. He received his PhD from RWTH Aachen
University in 2008 and his MSc from the University of Wroclaw, Poland.
Jan Chorowski
Jan is the CTO at Pathway. Jan is a reference figure in AI and NLP who worked at Microsoft Research, Google Brain, and the MILA AI Institute. He co-authored papers with Yoshua Bengio and Geoff Hinton, two of the three Godfathers of AI. Jan is highly recognized for his research in machine learning with over 10,000 citations on Google Scholar. He has a deep love for good engineering, holds a PhD in Neural Networks, and has a background in Electrical Engineering.
Team
Events