AI and Elasticsearch: Entering a New Era with Elastic
Log
20.02.2024 08:50 - We have opened registrations
Info
* Conference price is without VAT
Get your Wild Cards for the 75th and 149th seats and enjoy the conference for free (positions count according to registrations received).
Refreshments - if you need to provide gluten-free refreshments, please indicate this in the "Notes" section of the registration form. We will be happy to provide food on your behalf.
The programe and venue of the conference are subject to change.
Program
AI in Elastic’s landscape: the overview
Artificial intelligence is increasingly present in the tools we use and create. Obviously, it's more than just a chat agent with general knowledge. And instead of building your own tools from scratch (for your teams or customers) or adding more dependencies, you can leverage what's already available at your fingertips.
In this section, we'll look at how you can easily benefit from Elastic's AI work: not only in search, but also in web observability and reliability. The biggest effort should be to upgrade to the latest version.
Piotr Przybyl
Notorious engineer at work and after hours, tracing meanders of the art of software engineering. Remote Software Gardener, mostly working in web-oriented Java gardens. Java Champion. Testcontainers Champion. Oracle ACE. Programming usually in Java (since 1.3), Scala and Go, but in other languages too. Fan of agility, seen mostly as choosing the right tools and approaches after asking the right questions. Developer, trainer and conference speaker. In his talks, Piotr covers not only hardcore Java but also software architecture, computer security, and soft-skills.
Semantic Search with Elasticsearch
With increasingly powerful hardware and capable models, vector text representation and semantic search are becoming increasingly attractive options for information retrieval use cases. In this talk, we will use Elasticsearch as a tool for implementing semantic search using data from the Czech Wikipedia. The talk will provide a high-level overview of the basic concepts of semantic search, as well as a code-based demonstration of the entire workflow with several potential performance optimizations.
- Difference between semantic and lexical search
- Basic concepts of embeddings and vector similarity
- Pre-trained models, multi-linguality
- Pre-processing and splitting the data
- Efficient generation of embeddings
- Efficient indexing of embeddings
- Efficient inference
- Nearest neighbour search in Elasticsearch
- Search quality evaluation with the Rank Eval API
Karel Minařík
Karel Minařík is a software developer with a focus on system architectures, web APIs, interactive applications, and data visualization.
For almost a decade, he worked at Elastic, writing Ruby and Go code for libraries and internal applications. Until last year, he helped with the digital transformation in the Czech Republic as part of the Česko Digital team. Currently, his focus is on semantic search and language-oriented machine learning.
RAG with Elasticsearch
The presentation will focus on the principles of RAG (Retrieval-Augmented Generation) search and its implementation using Elasticsearch. We will explore what RAG search brings to the world of information retrieval and how it increases the quality and relevance of answers. We will also dive into the practical use of Elasticsearch for RAG applications, including basic setup and configuration for effective search. We will explore current tools and frameworks that enable easy and efficient RAG application development and demonstrate how they can be used to develop advanced internal data search and response systems. The goal of the presentation is to provide a comprehensive view of the possibilities of using RAG in search.
- Introduction to RAG (Retrieval-Augmented Generation) search and its benefits
- The role of Elasticsearch in RAG applications
- Setup and configuration of Elasticsearch
- Tools and frameworks for building RAG applications
- Examples of RAG usage in search systems
Petr Novotný
Petr has been working with ElasticSearch on a daily basis for the last 10 years and during this time he has deployed Elastic at Mall.cz and several other IT companies. His expertise ranges from solution architecture through custom development (JavaScript, PHP), ElasticSearch, Oracle, PL/SQL to agile methodologies and SCRUM.
From RAGs to riches – Building viable commercial products with Generative AI
As the prevalence of Generative AI has witnessed a substantial surge in the past year, an increasing number of enterprises are integrating Generative AI solutions into their daily operations. A September 2023 Gartner survey of 1,500 executives found that 45% of organizations are actively piloting multiple generative AI solutions.
While large language models are at the heart of most of these applications, a successful solution covers much more than just a vector search-based model wrapped in an API.
The goal of this talk is to take the technical concepts presented at this conference and transform them step-by-step into a commercially viable product – including identifying the right problem to solve, managing integration with current systems, and addressing the dreaded security and compliance requirements.
Outline
- Business case: a problem worth solving
- The specifics of Proof-of-Concepts
- User Interface: we need to talk to each other
- Infrastructure: running our application
- Integrations: living inside the company’s ecosystem
- Monitoring and Analytics: knowing what’s going on
- Security & Compliance: the less favored part of applications
Andrej Svitek
Andrej is the an AI architect and principal Python lead developer with ten years of experience in the automotive industry, banking and e-commerce, specializing in strategic design and implementing big data and AI-driven solutions in cloud environments. In the era of generative AI, most of Andrej's projects use the semantic search capabilities of Elasticsearch as the backbone of the underlying Large Language Models in applications. As an added bonus
Panel discussion
Registrační formulář
Proč se přijít podívat?
Storno podmínky
Registration for the conference is binding and cancellation is possible "free of charge" only in writing by e-mail no later than 14 calendar days before the conference.
If the participant cancels the conference registration less than 14 calendar days before the conference, the organizer reserves the right to pay a cancellation fee of the full value of the ticket to the participant.
Thank you for your understanding
Jak se k nám dostanete
The Institute of Clinical and Experimental Medicine (IKEM) is located at Vídeňská 1958/9, 140 21 Prague 4. The Congress Centre is located on the 5th floor of the main building.
The fastest way from the centre of Prague: by metro to Budějovická station (line C). Then take bus No. 193 to the IKEM stop (announced on the bus as "Institute of Clinical and Experimental Medicine").
By car
Parking is available on two floors of the garage building at the Hotel Residence EMMY in the surrounding area. You can also use the parking lot for visitors and patients of IKEM, which is about 100 m from the main entrance to the IKEM building (capacity 200 spaces).
By bus
Bus lines 193, 138, 203 stopping at the IKEM bus stop.
Regional lines: 332, 335, 337, 339, 362
By tram
This popular connection is not available.