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
New Quepid Features
New Quepid features include improved user interfaces, APIs and the ability to work with any search backend, plus new metrics including Jaccard similarity
A reality check for LLMs: access control and other lessons from enterprise search
How do you manage access control & data quality when building AI-powered enterprise search? A reality check
Until Decompounding Do Us Part – Solving compound noun challenges with Querqy & LLMs
The challenges with compound nouns in search, how to successfully tackle them with decompounding using Query Rewriting and the role of LLMs.
CI/CD……CE! Continuous Experimentation for Search Improvement
Continuous experimentation as part of your CI/CD pipeline can drive continuous improvement of search quality