talk-data.com

This 21th Eindhoven Data Community meetup will feature two sessions focused on leveraging AI technologies for performance evaluation and operational efficiency. The first session will discuss the challenges of evaluating Large Language Models (LLMs) at scale, highlighting the use of LLM-as-a-Judge systems and the implementation of a scalable evaluation framework using Vertex AI and Gemini on Google Cloud. The second session will introduce Menu AI at Just Eat Takeaway, a solution designed to automate the transcription of restaurant menus, significantly reducing the time and effort required for this task. You will learn about the cloud architecture and multimodal models used for parsing menu images and extracting structured data. Overall, the event will showcase innovative strategies for enhancing AI application evaluations and improving operational processes.

Location: Skybar, Microlab Eindhoven, Kastanjelaan 400, Eindhoven.

Evaluating LLM applications at scale As LLM deployments grow, evaluating their performance effectively and efficiently becomes of critical performance. Standard metrics struggle with the heterogeneity of LLM outputs, and manual expert review doesn't scale. LLM-as-a-Judge systems promise automation but require careful implementation to handle specific jargon and ensure alignment with human standards.This session dives into practical solutions for these evaluation challenges, grounded in a large-scale project evaluating a customer-facing chatbot handling over one million conversations per year. We will explore strategies for overcoming both conceptual hurdles (like judge alignment and context awareness) and technical bottlenecks (including cost optimization, data throughput, and robust API interaction). Learn how we leveraged the power of Vertex AI and Gemini on Google Cloud to implement a scalable, reliable, and insightful LLM evaluation framework.

Decoding Culinary Complexity: Transforming Menu Transcription Menu AI at Just Eat Takeaway Step into the shoes of a team faced with the herculean task of transcribing restaurant menus by hand. Each menu, a labyrinth of culinary offerings, can take an excruciating 2-4 hours to decode, demanding unwavering attention to detail amidst a jungle of artistic fonts and intricate designs. Now multiply that by 1700, the number of menus that land on the desks of JET every month only in UK. This is the very pain point that Menu AI promises to alleviate, setting the scene for a transformative solution we're eager to share with you. Join us for an insightful session on how JET integrates restaurant menus into its platform. Our talk will delve into the intricacies of Menu AI, from cloud architecture to the parsing of pictures of restaurant menus and how it and augments the productivity of humans in the loop. We will also get under the hood on how to leverage the power of multimodal models and their vision capabilities on parsing photos, describing menus in structured data, and the importance of mapping relationships among menu items. Moreover, we'll share insights into the significant cost savings realized by the project in Customer Services Operation costs.

Program

• 17:00 – 18:00 Food
• 18:00 – 18:10 Welcome
• 18:10 – 19:00 Sander van Donkelaar: Evaluating LLM applications at scale
• 19:00 – 19:15 Break
• 19:15 – 20:00 Caio Benatti Moretti: Decoding Culinary Complexity: Transforming Menu Transcription with
• 20:00 - 21:00 Drinks

Sander van Donkelaar \| AI/ML Engineer at Xebia Data Sander is an AI/ML Engineer skilled in building AI products and platforms. Experienced across diverse industries, Sander has a proven track record of delivering innovative solutions At the core of Sander's expertise is the ability to translate complex business problems into tangible AI-powered solutions, driving efficiency, innovation, and data-driven decision-making for organizations.

Caio Benatti Moretti \| AI consultant at Xebia Data Caio holds a PhD in Computer Science and has been acting as a DS/MLE both in academia and industry since 2014. Currently working as an AI Consultant at Xebia, he created SlackGPT and is particularly keen on neural networks in its many forms and applications. His enthusiasm even led him to make a neural network fit inside a business card. Apart from practical experience, Caio has been giving seminars and trainings on how to empower businesses with LLMs from use cases to technical tooling. He is focused on how LLMs can augment human productivity and hence helping businesses to leverage novel technologies to achieve their goals.

AI Learning Week

Dates: April 28 – May 1, 16:00 - 18:00 CET Speakers: Steven van Duin, Jeroen Overschie, Lysanne van Beek, Caio Benatti Moretti

Join us for Xebia Academy's AI Learning Week, a complimentary four-day webinar series designed to enhance your understanding of both the technical and strategic facets of Artificial Intelligence.

From April 28 to May 1, 2025, at 4 PM CET daily, engage with industry experts through two distinct tracks:

• Base Track: Delve into AI strategies, ethics, and how AI can drive business success.
• Tech Track: Explore practical skills in Prompt Engineering, AI coding, and Generative AI.

Agenda Highlights:

• April 28: AI Strategies for Leaders: Ethics, Governance, and Business Success with Steven van Duin
• April 29: Practical GenAI: Building LLM-powered Applications with Jeroen Overschie
• April 30: Prompt Engineering Made Easy: Quick Tips to Get More out of ChatGPT with Lysanne van Beek
• May 1: PDFs – When a Thousand Words Are Worth More Than a Picture (or Table) with Caio Benatti Moretti

Don't miss this opportunity to learn from seasoned professionals and advance your AI expertise. Secure your spot today!

Please note: Registration is mandatory to attend the event. Secure your spot by registering on the GoDataFest website.

The GoDataFest Lite 2023 Summer Edition is around the corner. This full-day event is an opportunity to learn about the latest trends in data, AI/ML, and cloud technology. We're hosting it on-site in Amsterdam on July 5. The event is FREE to attend - all you need to do is register here. Seating is limited!

Engage with product specialists and experienced practitioners of leading tech. Learn from the experiences of industry-leading enterprises.

🗓️ Wednesday, July 5, 2023 📌 Xebia Data Office - Amsterdam, Wibautstraat 202, 1091 GS

Schedule: 9.30 - Open doors

10:00 AM-12:25 AM: Kedro Breakfast Jordi Smit and Caio Benatti Moretti would like to invite you to a Kedro Breakfast session. Here, you'll learn how to manage data pipelines locally and on the cloud, all with the same code. They'll provide guidance on segregating IO artifacts from your code to create a more stable setup, as well as how to review the current status of each pipeline node for efficient debugging and testing.

12.30-13.30: Lunch

13:30-14:10: Scaling Real-Time Streaming Analytics with Apache Flink: Unlocking Business Value and Future-Proofing Enterprises Krzysztof Zarzycki will explore the transformative capabilities of Real-Time Streaming Analytics and the crucial role Apache Flink plays in powering such processes.

14:10-14:55: The multidisciplinary art of creating great KPIs In this workshop, Juan Manuel Perafan will break down all the knowledge required to create robust KPIs. From how it ties to your business goals, perverse incentives, to its technical implementation. Everybody is welcome! No coding required.

15:00-15:40: Data Modelling for Dummies in DBT Lasse Benninga will provide a fundamental understanding of data modeling for analytics, using dbt as an example. By the conclusion, you should have a comprehensive grasp of DBT's function and how analytics engineers worldwide use it to structure their data.

16:00-16:40: Our journey from 0 to MLOps Platform in Snowflake Marcin Zabłocki will show you how we’ve built a usable MLOps platform on Snowflake by combining the powers of Snowpark, MLflow & Kedro to make ML part of the data platform.

16.45-17:20: How to trade repeatability of bad habits for reusability of best practices. A few facts about open-source QuickStart ML Blueprints Piotr Chaberski will dive deep into QuickStart ML Blueprints - an open-source collection of examples for efficient prototyping of production-ready ML solutions that is the concrete embodiment of best development practices ready to apply to new challenges.

17.25-18.05: The Role of Machine Learning System Design in Ensuring MLOps Success During this talk, Roy van Santen will discuss why Machine Learning System Design is important, what it entails, and provide you with a framework on how to approach making a design. Machine Learning System Design takes a holistic view on ML applications.

18.15-19.00: Journey into Gen AI Rens Dimmendaal will address the challenges encountered with ChatGPT and how we tackled them by creating an internal tool, SlackGPT.

19.00 - Pizza & networking

Register now! Seats are limited.

We look forward to seeing you there!