Looking back at Elastic's vector search innovations in Elasticsearch and Lucene

Elasticsearch 7.x

Elasticsearch 8.0

Elasticsearch 8.2

Elasticsearch 8.3

Elasticsearch 8.4

Elasticsearch 8.5

Elasticsearch 8.6

Elasticsearch 8.7

Elasticsearch 8.8

Elasticsearch 8.9

Elasticsearch 8.10

Elasticsearch 8.11

Elasticsearch 8.12

Elasticsearch 8.13

Elasticsearch 8.14

Elasticsearch 8.15

... and beyond!

Vector search improvements in Elasticsearch and Lucene

Looking back: A timeline of vector search innovations

Introducing the general availability of query rules

Introduction

How do query rules work?

New query rule features

What does this look like?

These are simple examples, what about some more complex examples?

Troubleshooting query rules

What's next?

Elasticsearch query rules are now generally available

Discover how Learning To Rank (LTR) can help you to improve your search ranking and how to implement it in Elasticsearch.

Understanding relevance features and how to build a  scoring function

Scoring in the Elasticsearch Query DSL

Hello Learning To Rank (LTR)!

Getting started with LTR in Elasticsearch

Train and deploy an LTR model to Elasticsearch

Use your LTR model as a rescorer in Elasticsearch

Try LTR yourself!?

LTR uses a trained machine learning (ML) model to build a ranking function for your search engine. Typically, the model is used as a second stage re-ranker, to improve the relevance of search results returned by a simpler, first stage retrieval algorithm.

What is Learning To Rank (LTR)?

Elasticsearch Learning to Rank (LTR): Improving search ranking

Introducing Learning To Rank (LTR) in Elasticsearch

Explore strategies for using semantic reranking to boost the relevance of top search results, including semantic reranking with retrievers.

What is semantic reranking?

Why is semantic reranking important?

How do we perform semantic reranking?

The `rerank` inference type

Reranking search results today - through your application

Reranking search results tomorrow - with retrievers

Conclusion

Semantic reranking is a method that allows us to utilize the speed and efficiency of fast retrieval methods while layering semantic search on top of it. It also lets us immediately add semantic search capabilities to existing Elasticsearch installations.

What is semantic reranking in Elasticsearch?

Elasticsearch reranking: Semantic reranking with retrievers & more

Semantic reranking in Elasticsearch with retrievers

Learn how to train ranking models that improve search relevance for individual users.

Search Relevance

Personalized search with LTR

Looking back: A timeline of vector search innovations

Elasticsearch query rules are now generally available

Introducing Learning To Rank (LTR) in Elasticsearch

Semantic reranking in Elasticsearch with retrievers