It’s not technology that’s holding back AI … What’s missing? Search skills. You’re missing the ‘search’ part of the ‘AI team’. The search skills gap is a hidden, under-resourced bottleneck leading to project delays and poor execution.
2025 was a turning point for the Learning to Rank (LTR) plugin. After several years as a community-driven add-on that sat slightly outside the core OpenSearch ecosystem, LTR officially…
This year’s SIGIR conference featured the “LiveRAG Challenge”. In this competition participants received 500 questions synthesized from a given corpus (FineWeb10BT) and had 2 hours time to generate answers…
A proof of concept in Chorus OpenSearch Edition TL;DR: Team draft interleaving provides a path to faster A/B testing. Our proof of concept implementation within the Chorus Ecommerce search…
Quepid has provided an implementation of nDCG for quite some time now and has added an implementation of ERR in version 8.0. As both of these metrics use multi-valued…
Vector similarity search (or “dense retrieval” when text embeddings are involved) has gained widespread popularity over the last few years. It has become a fundamental component in various applications,…
I’ve had some interesting conversations over the last few months around the three big hitters of open source search: Solr, OpenSearch and Elasticsearch. Solr is the old dog in…
The Next Generation of Search at OpenSource Connections In 2016 Manning published Relevant Search, co-written by Doug Turnbull and John Berryman. Unlike most books on the subject of ‘search’…
Sometimes a query should produce zero search results – but how do we score this correctly in Quepid, the search relevance workbench?
Are your users searching for particular brands? Can we use LLMs for brand detection and use this to improve search & drive business?
Eric Pugh and Heather Halter discuss how we can improve OpenSearch documentation after a Lightning Talk at OpenSearchCon EU
Here’s what people at two recent conferences thought about UBI, an open source solution for tracking user behavior we’re working on with the OpenSearch team
