We are delighted to announce the 27th London Information Retrieval Meetup & AI, a free evening event aimed at enthusiasts and professionals curious to explore and discuss the latest trends in the field.
in LONDON
Location: Gladwin Tower, nine elms point sw8 2fs London [see on google maps]
Date: 23rd June 2026 | open doors from 6:15 PM (BST)
ONLINE
Zoom: The access link will be sent the day before the event. Please make sure to register in order to receive it.
Date: 23rd June 2026 | open doors from 6:30 PM (BST)
LONDON INFORMATION RETRIEVAL & AI MEETUP
PROGRAM
The event will be structured around 2 technical talks, each followed by a Q&A session. The event will end with a networking session.
> Open doors from
6:15 PM BST (in-presence)
6:30 PM BST (online)
> 6:30-6:45 PM Welcome from Alessandro Benedetti (Director @ Sease)
6:45-7:30 PM FIRST TALK
“Binary Quantization 101” – Carly Richmond, Principal Developer Advocate @ Elastic> 7:30-8:15 PM SECOND TALK
> Networking session + buffet
talk
Binary Quantization 101
Managing storage and performance of vector search can be a minefield. Let’s dive into the world of binary quantization. I’ll explain how it works, how it compares to other quantization techniques, and how BBQ, or Better Binary Quantization, can be leveraged in Elastisearch.
The speaker
Carly Richmond
PRINCIPAL DEVELOPER ADVOCATE @ ELASTIC
Carly is a principal developer advocate at Elastic. Before joining Elastic in 2022, she spent over 10 years working as a software engineer, scrum master, and engineering leader at a large investment bank. She is a UI engineer who occasionally dabbles in writing backend services, a speaker, and a regular blogger on both her personal blog and the Elastic blog.
She enjoys cooking, photography, drinking tea, and chasing after her young son in her spare time.
second talk
From RAG to Agents: Building AI Applications on OpenSearch
Generative AI is evolving from chatbots to autonomous agents that reason, plan, and act. OpenSearch has become a key component in these architectures, providing semantic search, vector databases, hybrid retrieval, and observability for AI workloads. Join us for a practical look at how to build production-ready AI and agentic systems using OpenSearch, with examples, architectural patterns, and lessons learned from the field.
In this session, we’ll explore how OpenSearch serves as the foundation for modern AI applications by combining vector search, hybrid retrieval, semantic ranking, metadata filtering, and operational visibility into a single platform.
After a brief introduction to the evolution from traditional keyword search to Retrieval-Augmented Generation (RAG), traditional keyword search to RAG architectures, we’ll then move beyond RAG into agentic architectures, discussing how agents use OpenSearch as long-term memory, knowledge retrieval, context management, and planning infrastructure.
Through real-world examples and reference architectures, you’ll learn:
– Why a simple RAG is not enough anymore– How vector search, BM25, and hybrid retrieval work together in production AI systems– How to combine all this into a search that understands intentt– Designing scalable RAG pipelines with OpenSearch– What it means to create an agentic RAG– Agent memory patterns and using OpenSearch as memory and knowledge infrastructure for AI agents– Production concerns running OpenSearch at scale for Agentic workloads (cost, performance, etc)
The speaker
Itamar syn-hershko
CTO & Founder @ BigData Boutique
Itamar is a BigData and search technologies expert, and BigData Boutique’s CTO. Equipped with many years of experience building and optimizing data platforms for organizations in various scales, Itamar’s current job is to keep BigData Boutique’s team engaged with the latest technologies and working with customers to optimize their journey in the world of BigData.
