Open Source Summit Europe 2024

Part art, part science, prompt engineering is the process of crafting input text to fine-tune a given large language model for best effect. Foundation models have billions of parameters and are trained on terabytes of data to perform a variety of tasks, including text-, code-, or image generation, classification, conversation, and more. A subset known as large language models are used for text- and code-related tasks. When it comes to prompting these models, there isn't just one right answer. There are multiple ways to prompt them for a successful result. In this workshop, you will learn the basics of prompt engineering, from monitoring your token usage to balancing intelligence and security. You will be guided through a range of exercises where you will be able to utilize the different techniques, dials, and levers illustrated in order to get the output you desire from the model. Participants of this workshop will be equipped with a comprehensive understanding of prompt engineering along with the practical skills required to achieve the best results with open source large language models.

AI is "the" hot new thing. But what's AI got to do with databases? As it turns out, quite a lot. The right database can help your application, business, or customer get more out of AI, faster. What's more, the right database can even make the AI models themselves work better. This workshop will show you how all of this works through a hands-on experience with an "AI-native" database. AI-native databases are designed to empower builders and developers to build AI-powered tools. You will see how they enable better search, integrate with generative AI models, and improve generative models' capabilities. You will be getting hands-on experience with the key pieces of technology, like vector indexes, vector and hybrid search, retrieval augmented generation, and multi-tenancy. Even better, this will use an open-source stack for everything from embeddings, to a vector database and a language model. So join us to learn how to give your app AI superpowers.

In the cloud native era systems are getting ever more dynamic and complex. With containers and microservices architecture, monitoring and troubleshooting systems is more challenging than ever before. The open source community has risen up to the challenge and has delivered solutions that fit modern environments. Established open source projects such as Prometheus and the ELK Stack have gathered massive adoption, while new projects keep emerging and uncovering yet untapped possibilities such as continuous profiling and eBPF. Alongside tools, open standards, such as OpenMetrics and OpenTelemetry, are emerging to converge the industry and prevent vendor lock-in. Goodness, it’s hard to keep track of all that goodness. In this talk Horovits will talk about the recommended open source tools and standards for observability (looking also beyond logs, metrics and traces), and how to combine them to help you achieve effective observability in your environment.