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

Ranking factors

Personalized results

Personalization with LTR

Feature engineering

Example: music preferences

Conclusion

Personalized search with Elasticsearch Learning to Rank

Personalized search with LTR

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

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

Elasticsearch retrievers have gone through a significant revamp and are now generally available for all to use. Learn all about their architecture and use-cases.

Retrievers

Technical drill down

Playing with the (golden) retrievers!

Composability

Aggregations

Collapsing

Pagination

Explain

Retrievers are a new abstraction layer added to the Search API in Elasticsearch that is now generally available. They offer the convenience of configuring multi-stage retrieval pipelines within a single `_search` API call.

What are retrievers in Elasticsearch?

All base queries are accessible through the use of the `standard` retriever. In addition to that, one can use more fine-grained retrievers like `knn`, `rrf`, and `text_similarity_reranker` to either produce a set of results, or combine/rerank the results of another retriever.

Search Relevance

Elasticsearch retrievers are generally available with Elasticsearch 8.16.0!

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