Improving information retrieval in the Elastic Stack

This series explores steps to improve search relevance, benchmarking passage retrieval, ELSER, and hybrid retrieval.

Teil 1

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

13. Juli 2023

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.

Teil 2

Improving information retrieval in the Elastic Stack: Benchmarking passage retrieval

13. Juli 2023

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.

Teil 3

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

21. Juni 2023

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.

Teil 4

Improving information retrieval in the Elastic Stack: Hybrid retrieval

20. Juli 2023

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.

Sind Sie bereit, hochmoderne Sucherlebnisse zu schaffen?

Eine ausreichend fortgeschrittene Suche kann nicht durch die Bemühungen einer einzelnen Person erreicht werden. Elasticsearch wird von Datenwissenschaftlern, ML-Ops-Experten, Ingenieuren und vielen anderen unterstützt, die genauso leidenschaftlich an der Suche interessiert sind wie Sie. Lasst uns in Kontakt treten und zusammenarbeiten, um das magische Sucherlebnis zu schaffen, das Ihnen die gewünschten Ergebnisse liefert.

Probieren Sie es selbst aus