Prompting Large Language Models (LLMs) with instructions performs impressively in many AI tasks such as intent detection and question answering over document sources. As Generative AI becomes widely adopted, small and medium-sized enterprises (SMEs) are increasingly turning to third-party services that allow them to prompt LLMs via a standard API to solve such AI tasks in business settings.
Prompting Large Language Models (LLMs) with instructions performs impressively in many AI tasks such as intent detection and question answering over document sources. As Generative AI becomes widely adopted, small and medium-sized enterprises (SMEs) are increasingly turning to third-party services that allow them to prompt LLMs via a standard API to solve such AI tasks in business settings.
2024AI
ΑΙ
Cache me if you can: Efficient use of Large Language Models through Smart Caching
Sat 23 Nov 2024 • 13:10 (CET)
Auditorium
Prompting Large Language Models (LLMs) with instructions performs impressively in many AI tasks such as intent detection and question answering over document sources. As Generative AI becomes widely adopted, small and medium-sized enterprises (SMEs) are increasingly turning to third-party services that allow them to prompt LLMs via a standard API to solve such AI tasks in business settings.
Testing is essential to ensure that your software application performs as expected. No doubt about it. But even if your application runs smoothly in a testing environment, unexpected incidents can occur in production, such as a crashed database or a lost connection to a third-party service. To ensure your application can handle such incidents and minimize their impact, you need to incorporate chaos testing into your delivery process. In this workshop, we will start with a brief introduction to k6 for backend performance testing and we’ll explore how to implement chaos testing using k6 for two backend services, to help you ensure the resilience of your application.
Redis is an in-memory database popular for many use cases, such as content caching, session stores, real-time analytics, message broker and data stream needs. Since version 5.0 of Redis a new data structure, Redis Streams, dedicated to managing streams has been introduced. Using Redis Streams, anyone can do a lot more than what was possible with Pub/Sub, Lists or Sorted Sets in the data stream domain. In this all-hands session, we’ll walk you through the basics of how to use Redis Streams, how consumer groups work, and finally show a working application using Go that uses Redis Streams.
Join us for an exciting firechat with experts from product management, test engineering, DevOps, and software development. We’ll take you through the journey of turning an idea into a fully finished product ready for the market.
Hear firsthand from our panelists about the teamwork needed to create innovative products. They’ll share insights about the ups and downs, breakthroughs, and challenges they’ve faced. Learn the secrets of successful product launches, including careful planning, prioritizing tasks, and effective teamwork.
Find out how testing and quality checks ensure product excellence, and see how continuous integration and DevOps practices make the process smoother. Understand why user feedback is important for improving products, and get tips on the latest tools and methods that boost efficiency and innovation.
Whether you’re experienced or just starting out, you’ll gain valuable insights into every step of bringing a product to life, from the first idea to the final launch.
Join us for an interactive workshop where Matina & Lilian having worked as Tech / AI Leaders at Meta, IBM, Vodafone, Startups share valuable insights into the opportunities available in AI and data science. Gain practical knowledge and industry perspectives to guide your career journey in this rapidly evolving field
In this 50-minute workshop participants will delve into the intricacies of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). The session will explore how these advanced AI technologies are transforming various industries by enhancing natural language understanding and generation. Attendees will gain insights into the fundamental differences between LLMs and RAG, their respective strengths, and the unique challenges they present when applied to real-world scenarios.
The workshop will also highlight practical applications and case studies, showcasing how businesses and researchers are leveraging LLMs and RAG to solve complex problems. Participants will have the opportunity to engage in interactive discussions, addressing common obstacles such as data privacy, model interpretability, and scalability. By the end of the session, attendees will be equipped with a deeper understanding of how to harness the potential of these cutting-edge technologies to drive innovation and efficiency in their own projects.
