Personalize Search Results with OpenSearch Agentic Memory
Improving search relevance typically requires complex personalization pipelines — recommendation engines, feature stores, ML models. This session shows a simpler path: multiple lightweight agents that collaborate through OpenSearch’s agentic memory to understand and enrich queries in real time. Same query, different results for different users.
Tensor arithmetics in search and ranking for Ecommerce.
Small, domain-specific vision models can dramatically enhance the buyer search experience by delivering more relevant visual understanding. But the real opportunity comes from controllable image embeddings: by fusing base search embeddings with additional control vectors, representing features such as color, shape, and style,
Relevance Feedback Inside the Search Engine
How does searching for new information often look? Loops: query, review results for relevance, rewrite the query, repeat… Until success, or until the user churns / the token budget burns.
This talk introduces a new instrument for search pipeline builders: propagating query-results relevance right inside the search algorithm of a search engine.
Scientific Data Under Threat in Today’s America
A brief look at how scientific data came under political pressure during the presidency of Donald Trump, and how scientists and data repositories in Europe worked to protect public access to evidence-based research, ensuring access for data science in a well-structured way.
Writes, 3 ways: Postgres, Apache Kafka® and Apache Iceberg™
Learning new things is hard, but a useful way to think about new things is by comparing them to things you already know. In this talk, we’ll compare writes between 3 different popular data services: Postgres, Apache Kafka and Apache Iceberg. In doing so, we’ll learn a bit about the evolution of how we’ve thought of data storage as developers.
From OLTP to OLAP: Is PostgreSQL Eating Analytics Too?
Can PostgreSQL become a serious analytics engine? With emerging columnar extensions, PostgreSQL is pushing beyond OLTP into OLAP territory. This talk explores the current columnar landscape, architectural trade-offs, and how far PostgreSQL can go compared to analytical engines like ClickHouse.
Ultraviolet: Turn Hidden Document Data into an AI Advantage
Every PDF hides a world of structure, metadata and embedded signals that can silently influence AI based processing. With ultraviolets, we reveal how those can be exploited for malicious purposes and even become powerful tools for smarter applications. Designing for both humans and machines become a vital aspect of AI experience design.
From Legacy Search to Vespa: What a Real PoC Taught Us
For years, Germany’s largest classifieds website relied on a search-first relevance approach because structured data was sparse. This talk shares how we introduced Vespa in the Motors category, enriched signals with embeddings and extracted attributes, and migrated step by step; what worked, what failed, and which lessons only a real PoC reveals.
Circular Dependency Fixes when Bootstrapping a Golden Set
For a golden set, you need queries. Even if you have them, you can’t judge all docs for each query. Only the top N. How do we rank the top N? See the circular dependency? We’ll talk about ways to untangle it: lexical search, significant terms, training an embedder from scratch, etc. By iteratively refining data and queries, we’ll get there.
Low-Resource Languages as Stress Tests for NLP Data
Low-resource languages expose weaknesses in NLP systems that are often hidden by benchmark data. Drawing on experience annotating fieldwork data, this talk shows how ambiguity and annotation decisions reveal fundamental data quality issues relevant to real-world NLP pipelines.