Learn about Elasticsearch retrievers, including Standard, kNN, text_expansion, and RRF. Discover how to use retrievers with examples.

Initial types of Retrievers

How are Retrievers different, and why are they useful?

Retrievers usage examples

Standard - Search All the Text!

kNN - Search all the Dense Vectors!

text_expansion - Search all the Sparse Vectors!

rrf - Combine All the Things!

Current restrictions with Retrievers

Conclusion

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

What are retrievers in Elasticsearch?

Retrievers come with certain restrictions users should be aware of. For example, only the query element is allowed when using compound retrievers. Additionally, sub-retrievers may not use elements restricted from having a compound retriever as part of the retriever tree.

What are the current restrictions of Elasticsearch retrievers?

Elasticsearch retrievers - How to use search retrievers in Elasticsearch

Introducing Retrievers - Search All the Things!

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.

Let's quantize

Some real-world numbers

Save space with byte-sized vectors

Author

Jack Conradson

Articles

Introducing Retrievers - Search All the Things!

Save space with byte-sized vectors