Own your search
Smart search is core to your value: don't outsource it.
We help your org innovate in search and relevance. Whether it's Solr or Elasticsearch - let us empower your team!
We wrote the book
Good search understands a user's intent, not just what they type.
We wrote Relevant Search to help teams build smarter Elasticsearch and Solr applications.
One of the best and most engaging technical books I've ever read. — Trey Grainger, Lucidworks
Will help you solve real-world search relevance problems for Lucene-based search engines — Dimitrios Kouizes-Loukas, Bloomberg
Pioneers in machine learning
We built Elasticsearch Learning to Rank, which powers search at Yelp, Wikipedia, Snag, and others.
Since deploying learning to rank, weāve seen a net 32% increase in conversion metrics across our historically lowest performing use-cases. — Jason Kowalewski, Sr Director of Engineering at Snag
Learning to rank canāt stay hidden away in obscure academic journals or multi-million dollar products. Weāre making this stuff accessible to all search teams: opening up the black box for everyone to useā. — Doug Turnbull - OpenSource Connections CTO
We have the tools
We built Quepid, a search testing platform that takes the guesswork out of search relevancy.
Do NOT attempt a search project without it. — John Bickerstaff
Just want to understand why results are showing up in your search?
We support the community
We run Haystack, the Search Relevance conference. We sponsor MICES, the E-Commerce Search conference.
We host a Slack Channel where practitioners support each other and share solutions.
We empower some of the world's best search teams at:
Our publications
Relevant Search »
Learn the secrets of building intuitive, targeted search.
Elasticsearch course »
Dive into Elasticsearch and AngularJS in this video course.
Solr Enterprise Server »
We cowrote the first book on Solr. Now in its third edition.
The blog and other happenings
Understanding BERT and Search Relevance
Max irwin on November 5, 2019
There is a growing topic in search these days. The hype of BERT is all around us, and while it is an amazing breakthrough in contextual representation of unstructured text, newcomers to NLP are left scratching their heads wondering how and why it is changing the field. Many of the examples are tailored for tasks such as text classification, language understanding, multiple choice, and question answering. So what about just plain-old findin' stuff? This article gives an overview into the opportunities and challenges when applying advanced transformer models such as BERT to search.
It's okay to run Tika (and Tesseract!) inside of Solr ;-) If and Only If....
Eric pugh on October 24, 2019
Don't be afraid of running Tesseract and Tika in your Solr cluster if...
What happens at a Lucene/Solr Hackday
Charlie hull on September 23, 2019
How we hosted and ran a Lucene Hackday in Washington DC the week of the Activate conference, and what attendees considered and achieved during the day
Come see Eric at Elasticsearch 'Think Like a Relevance Engineer' Training at Relevance Cornucopiaš¦!
November 12th-13th, 2019 | Charlottesville, VA
Learn to improve search quality from the best experts in the field. From TFIDF, to Semantic Search, to Learning to Rank with Elasticsearch!
Talk directly with Eric Pugh, our founder & CEO
(434) 466-1467 | [email protected]
The latest in search news, delivered to straight to your inbox.