Unstructured Data in LLMs - South Bay Edition

This is an in-person event! Registration is required in order to get in.

Topic: Connecting your unstructured data with Generative AI

What we’ll do:
Have some food and refreshments. Hear three exciting talks about unstructured data and generative AI.
5:30 - 6:00 - Welcome/Networking/Registration
6:05 - 6:30 - Yi Ding
6:35 - 7:00 - Kunal Sonalkar, Data Scientist, Nordstrom
7:05 - 7:30 - Hakan Tekgul, Solutions Architect, Arize
7:45 - 8:30 - Networking

Tech Talk 1: Small to Slide: RAG using MultiModal LLMs.
Speaker: Yi Ding
Abstract: With the advent of LLMs understanding multimodal inputs, document understanding has a new tool in the arsenal. Elliot Kang and I built an example using Milvus and a real slide deck to show how you can use retrieval in combination with multimodal input to get better results from your existing powerpoint slides.

Tech talk 2: Transformers4rec: Harnessing NLP Advancements for Cutting-Edge Recommender Systems
Speaker: Kunal Sonalkar, Data Scientist, Nordstrom
Abstract: Transformers4rec is a powerful open-source library by NVIDIA that bridges the gap between natural language processing (NLP) and recommender systems. We will review how it leverages state-of-the-art Transformer architectures from NLP to enhance sequential and session-based recommendation tasks.

Tech Talk 3: Evaluating RAG pipelines built on unstructured data
Speaker: Hakan Tekgul, Solutions Architect, Arize
Abstract: This talk will cover different techniques for evaluating a RAG pipeline built on unstructured data. Standing up a basic RAG pipeline is becoming easier every day, however identifying weak points in your application or dataset remains a challenge. We'll review how you can use traditional assertion-based evaluation techniques, LLM-as-a-Judge approaches, and embedding visualization tools to improve your pipeline using Arize Phoenix.

Who Should attend:
Anyone interested in talking and learning about Unstructured Data and Generative AI Apps.

When:
September 17, 2024
5:30PM

Where:
This is an in-person event. Registration is required to get into the event. Registration in advance will close 2 days before the event.
This event is co-sponsored by Zilliz (maintainers of Milvus), SAP, and Arize