Unstructured Data Meetup - Berlin
Topic: Connecting your unstructured data with LLMs
We are meeting for another happy hour/discussion group about Unstructured Data and its future in machine learning and LLM apps!
What we’ll do:
Have some snacks and refreshments. Have a couple of talks and then unstructured networking.
Schedule
6:00-6:55 - Open Doors, food and open networking
7:00-7:30 - TBD - Stephen Batifol, Zilliz
7:30-8:00 - LLM Agent Observability: Lessons Learned from Real-World Applications - Dat Ngo, Arize
8:00-8:05 - Small Break
8:05-8:30 - Structuring Unstructured Text using generative AI: The key to information extraction - Oren Matar, Anaplan
9:00-10:00 - Networking
Who Should attend:
Anyone interested in talking and learning about Unstructured Data and LLM Apps.
When:
Nov 14nd, 2024
6:00PM
42 Berlin
Tech Talk 1: TBD
Speaker: Stephen Batifol, Developer Advocate, Zilliz
Abstract: TDB
Tech Talk 2: LLM Agent Observability: Lessons Learned from Real-World Applications
Speaker: Dat Ngo, Developer Advocate, Arize
Abstract: If you’re tired of the endless hype around Large Language Models (LLMs) and want to learn real, practical lessons, this talk is for you. We’ll cut through the noise and focus on actionable insights from real-world experiences with LLMs in production. Discover what observability truly means in the context of LLMs, as I share key lessons learned from customers who have successfully scaled their LLM applications. We’ll dive into best practices that can guide your team on its LLM journey, highlighting what works and what to avoid. Whether you’re just starting with LLMs or looking to optimize, expect actionable takeaways from some of the top LLM teams in the world that will help you succeed in the evolving AI landscape.
Tech Talk 3: Graph Storage: 10x faster & 100x cheaper
Speaker: Oren Matar, AI Researcher, Anaplan
Abstract: In the world of Natural Language Processing (NLP), we often need to extract some of the information from natural language into a structured format: for example, converting a natural query to SQL. Generative AI is a great tool for this task, however, transformer-based translation models, such as GPT, sometimes struggle to adhere to the desired format, and to support the variety of expression of a natural language. In this session we will delve into the intricacies of using transformer-based models to extract information from natural language to a predefined structure. We'll explore effective best practices, including Constrained Generative AI, a technique that can eliminate syntactic errors. Additionally, we will explore the pre-processing, data generation and augmentation methods that helped us achieve near-perfect accuracy in extracting dates and times from textual data. By the end of the session, you will gain insights into harnessing generative AI language models for structured output, opening doors to more accurate and efficient NLP applications.
Check out Zilliz blog, join our Discord and Milvus Github
📸Important note: Please be advised that this event will be recorded and photographed. If you prefer not to be included in any recordings or photographs, please do not hesitate to let us know during the event. Your comfort and privacy are important to us.