OpenSearch Project München Third meetup

Hi Everyone,
mark your calendars for the third OpenSearch Project München meetup
Agenda

6.30 pm Start (Drinks and snacks will be provided)

6.45 pm Aswath Srinivasan (AWS)

# OpenSearch as Vector Database

K-Nearest Neighbors (KNN) search has been available with Apache Lucene since 2019, however the adoption rate picked up only since the raise of LLMs. OpenSearch leverages the Lucene engine for KNN. OpenSearch also supports FAISS and NMSLIB for Approximate-Nearest Neighbors (ANN) Search to handle large amount of vectors.
In this talk, we will explore the different options that OpenSearch provides
for implementing Semantic Search and RAG solutions. We will look into different methods such as HNSW, IVF. We will also dive into the sizing aspects and different quantization techniques to reduce cost when implementing KNN Search.
We will also touch on Hybrid Search, a way to combine the classic lexical search and the KNN search so you get the best of both worlds.

7.30 pm Break (Drinks and Snacks)

7.50 pm Daniel Wrigley
(Search Relevance Consultant, OpenSource Connections)

# Measuring Search Relevance with User Behavior Data in OpenSearch
Ensuring high-quality search results is a complex and ongoing challenge for search engineers. As data, ranking algorithms, and search platforms evolve, measuring relevance effectively becomes even more critical—yet also increasingly difficult. Traditional evaluation methods often require significant resources, making it particularly challenging for small organizations or teams without dedicated search expertise.

In this talk, we will explore how user behavior data can be leveraged to measure search relevance within OpenSearch. We'll discuss key challenges, such as position bias (users preferring higher-ranked results) and data sparsity, and how these factors impact implicit judgments. We will show how User Behavior Insights (UBI) can be leveraged as a tool for collecting and analyzing behavioral signals, and how the search quality evaluation app can transform these raw interaction signals into meaningful search relevance metrics.

The session will include a live demo showcasing how to collect user behavior data with UBI, derive implicit judgments, and use these insights to quantify search quality over time. Attendees will leave with practical strategies to improve search relevance measurement, even in resource-constrained environments.

8.30 pm Networking

9.00 pm Close.