What do nDCG and ERR model in Quepid?
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 Search: Navigating Recall and Performance
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,…
Dogfights in Open Source Search: Solr, OpenSearch and Elasticsearch
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…
Lead Author of “AI-Powered Search” Trey Grainger joins OSC team
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’…
When Zero Search Results is the right answer (& how to measure this in Quepid)
Sometimes a query should produce zero search results – but how do we score this correctly in Quepid, the search relevance workbench?
More Query Understanding: Brand Detection with LLMs
Are your users searching for particular brands? Can we use LLMs for brand detection and use this to improve search & drive business?
So you want better OpenSearch documentation?
Eric Pugh and Heather Halter discuss how we can improve OpenSearch documentation after a Lightning Talk at OpenSearchCon EU
What we learned about tracking user behavior at Haystack & OpenSearchCon
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
Haystack US 2024 – a review by the winners of the Hughes Scholarship
A review of Haystack US 2024, the search relevance conference, by the three winners of the Hughes Scholarship.
How to get the best from a search conference (updated)
Search conference veteran Charlie Hull lists the different kinds of search conference and how you can get the most from them
Announcing the Hughes Scholarship for Haystack US 2024
Announcing the Hughes Scholarship to assist those at an early stage of their search & AI careers to attend Haystack conferences.
What do you actually mean? Query Understanding with LLMs
Query Understanding helps you find out what users actually mean when they search – and LLMs can be used to detect this user intent, relax and even replace queries for better recall