Articles by Benjamin Trent

Principal Software Engineer

Ben is a software engineer working on the intersection of machine learning and search. He is an Apache Lucene committer and wants to make search better for everyone.


Adding passage vector search to Lucene

Discover how we added passage vectors to Apache Lucene, the benefits of doing so, and how existing Lucene structures were used to create an efficient retrieval experience.


Save space with byte-sized vectors

Elasticsearch is introducing a new type of vector that has 8-bit integer dimensions. This is 4x smaller than the current vector with 32-bit float dimensions, which can result in substantial space savings.


Getting the Most Out of Transformers in Elastic

In this blog, we will briefly talk about how we fine-tuned a transformer model meant for a masked language modeling (MLM) task, to make it suitable for a classification task.


Aggregate data faster with new the random_sampler aggregation

Aggregate billions of documents in milliseconds instead of minutes with Elastic. Learn more about how the new random_sampler aggregation gives you statistically robust results at a lower cost.


Categorize your logs with Elasticsearch categorize_text aggregation

Categorize_text expands the toolset for exploring your logs. It automatically clusters logs, taking advantage of all the flexibility and power of the extensive Elasticsearch aggregation framework, now in 7.16.


Using Elastic supervised machine learning for binary classification

The release of supervised machine learning in Elastic Stack 7.6 closes the loop for an end-to-end machine learning pipeline. Learn how to get started with it in this example using binary classification.