Unstructured Data Meetup SF
This is an in-person event! Registration is required to get in. Github will email you a form the day before the event, which you will need to complete for your access pass. Registration will close 2 days before the event.
Topic: Connecting your unstructured data with Generative LLMs
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 - Hakan Tekgul, Evaluating RAG pipelines built on unstructured data
6:35 - 7:00 - James Luan, Dense Embeddings != Complete Search - a sneak peak of Milvus 2.5
7:05 - 7:30 - Max Mathys, Gandalf: Insights from the World's Largest Red Team
7:35 - 7:45 - Community demo
7:45 - 8:30 - Networking
Tech Talk 1: 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.
Tech Talk 2: Dense Embeddings != Complete Search - a sneak peak of Milvus 2.5
Speaker: James Luan, VP of Engineering, Zilliz
Abstract: Dense embeddings miss exact matches. Keyword search misses semantic meaning. Running two separate systems is a maintenance nightmare. We'll show how Milvus 2.5's hybrid search tackles this with a unified solution, preview its sparse-based BM25 implementation, and share performance numbers against current Elasticsearch-based architectures.
Key Points:
Where dense embeddings fall short and how a unified system architectures address the search needs
Sneak Peak of Milvus 2.5 - Quick look at our BM25 implementation and sparse vector optimizations
Benchmark results comparing hybrid search latency and throughput vs ElasticSsearch
What's Next - Brief overview of upcoming features in our technical roadmap
Tech Talk 3: Gandalf: Insights from the World's Largest Red Team
Speaker: Max Mathys, ML Engineer, Lakera AI
Abstract: Gandalf is a challenge where people can attack LLMs with prompt attack techniques. It has been played by 7M+ players and recorded 10M+ successful attacks against LLMs. This talk analyses different types of attacks that actual players came up with and how you should defend against these attacks.
Who Should attend:
Anyone interested in talking and learning about Unstructured Data and Generative AI Apps.
When:
Nov 19, 2024
5:30PM
Where:
This is an in-person event! Registration is required to get in. Registration will close 2 days before the event. Co-sponsored by Zilliz (maintainers of Milvus) and Arize.