Thomas Veasey
Author

Thomas Veasey


Articles

Aggregate data faster with new the random_sampler aggregation
Generative AI

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.

Benjamin Trent

Thomas Veasey

Improving information retrieval in the Elastic Stack: Improved inference performance with ELSER v2
ML Research

Improving information retrieval in the Elastic Stack: Improved inference performance with ELSER v2

Learn about the improvements we've made to the inference performance of ELSER v2, achieving a 60% to 120% speed increase over ELSER v1.

Thomas Veasey

Quentin Herreros

Valeriy Khakhutskyy

Improving information retrieval in the Elastic Stack: Optimizing retrieval with ELSER v2
ML Research

Improving information retrieval in the Elastic Stack: Optimizing retrieval with ELSER v2

Learn how we are reducing the retrieval costs of the Learned Sparse EncodeR (ELSER) v2.

Thomas Veasey

Quentin Herreros

Valeriy Khakhutskyy

RAG evaluation metrics: A journey through metrics
ML Research

RAG evaluation metrics: A journey through metrics

Explore RAG evaluation metrics like BLEU score, ROUGE score, PPL, BARTScore, and more. Discover how Elastic is evaluating RAG with UniEval.

Quentin Herreros

Thomas Veasey

Thanos Papaoikonomou

Evaluating scalar quantization in Elasticsearch
ML Research

Evaluating scalar quantization in Elasticsearch

Learn how scalar quantization can be used to reduce the memory footprint of vector embeddings in Elasticsearch through an experiment.

Thanos Papaoikonomou

Thomas Veasey

Evaluating search relevance part 1 - The BEIR benchmark
ML Research

Evaluating search relevance part 1 - The BEIR benchmark

Learn to evaluate your search system in the context of better understanding the BEIR benchmark, with tips & techniques to improve your search evaluation processes.

Thanos Papaoikonomou

Thomas Veasey

Evaluating search relevance part 2 - Phi-3 as relevance judge
ML Research

Evaluating search relevance part 2 - Phi-3 as relevance judge

Using the Phi-3 language model as a relevance judge, with tips & techniques to improve the agreement with human-generated annotation

Thanos Papaoikonomou

Thomas Veasey

Improving information retrieval in the Elastic Stack: Benchmarking passage retrieval
Generative AI

Improving information retrieval in the Elastic Stack: Benchmarking passage retrieval

In this blog post, we'll examine benchmark solutions to compare retrieval methods. We use a collection of data sets to benchmark BM25 against two dense models and illustrate the potential gain using fine-tuning strategies with one of those models.

Grégoire Corbière

Quentin Herreros

Thomas Veasey

Improving information retrieval in the Elastic Stack: Hybrid retrieval
Generative AI

Improving information retrieval in the Elastic Stack: Hybrid retrieval

In this blog we introduce hybrid retrieval and explore two concrete implementations in Elasticsearch. We explore improving Elastic Learned Sparse Encoder’s performance by combining it with BM25 using Reciprocal Rank Fusion and Weighted Sum of Scores.

Quentin Herreros

Thomas Veasey

Improving information retrieval in the Elastic Stack: Steps to improve search relevance
Generative AI

Improving information retrieval in the Elastic Stack: Steps to improve search relevance

In this first blog post, we will list and explain the differences between the primary building blocks available in the Elastic Stack to do information retrieval.

Grégoire Corbière

Quentin Herreros

Thomas Veasey

Scalar quantization optimized for vector databases
ML Research

Scalar quantization optimized for vector databases

Optimizing scalar quantization for the vector database use case allows us to achieve significantly better performance for the same retrieval quality at high compression ratios.

Thomas Veasey

Benjamin Trent

Understanding Int4 scalar quantization in Lucene
LuceneML Research

Understanding Int4 scalar quantization in Lucene

This blog explains how int4 quantization works in Lucene, how it lines up, and the benefits of using int4 quantization.

Benjamin Trent

Thomas Veasey

Improving information retrieval in the Elastic Stack: Introducing Elastic Learned Sparse Encoder, our new retrieval model
ML Research

Improving information retrieval in the Elastic Stack: Introducing Elastic Learned Sparse Encoder, our new retrieval model

Learn about the Elastic Learned Sparse Encoder (ELSER), its retrieval performance, architecture, and training process.

Thomas Veasey

Quentin Herreros

Speeding Up Multi-graph Vector Search
Lucene

Speeding Up Multi-graph Vector Search

Explore multi-graph vector search in Lucene and discover how sharing information between segment searches enhances search speed.

Mayya Sharipova

Thomas Veasey