Learn more about exact and approximate kNN search in Elasticsearch, and when to use each one.

What is kNN?

Exact kNN: Search everything

Approximate kNN: A good estimate

Indexing for exact and approximate search

dense_vector field type

Quantization

How do I choose between exact and approximate kNN search?

Data size

Filtering

Future enhancements for kNN

Conclusion

Having less than 10 thousand documents to search could be an indication that exact search should be used. Approximate search scales better in terms of the number of documents, so it should be the preferred choice if you have a big number of documents or expect it to grow significantly.

How to choose between exact and approximate kNN search in Elasticsearch?

Exact kNN calculates the closer results by comparing all the existing document embeddings with the one for the query, ensuring accuracy but requiring more time. In contrast, approximate kNN provides an efficient approximation to kNN.

What is the difference between exact and approximate kNN search?

Elasticsearch kNN: How to choose between exact and approximate kNN search

How to choose between exact and approximate kNN search in Elasticsearch

Learn how to use the new semantic_text field type and semantic query for simplifying semantic search in Elasticsearch.

semantic_text - You know, for semantic search!

How to perform semantic search

Choosing an inference model

Creating your index mapping

Setting up indexing

Automatically handling long text passages

Querying your data

Under the hood: How `semantic_text` works

Customizing `semantic_text`

Query customization

Data type customization

What's next with `semantic_text`?

Try it out!

Semantic search is a sophisticated technique designed to enhance the relevance of search results by utilizing machine learning models. Unlike traditional keyword-based search, semantic search focuses on understanding the meaning of words and the context in which they are used.

What is semantic search?

semantic_text is a field type that simplifies semantic search by making default decisions about indexing and querying your data.

What is semantic_text in semantic search?

Elasticsearch semantic_text mapping: Simplifying semantic search

Elasticsearch new semantic_text mapping: Simplifying semantic search

Previously, updating synonyms required the use of synonym files that needed to be updated on every node in your Elasticsearch clusters. Now you can use the synonyms API to update synonyms in a single request!

Previous synonym updating process<a id="previous-synonym-updating-process"></a>

Why add a synonyms API?<a id="why-add-a-synonyms-api"></a>

Enter the synonyms API<a id="enter-the-synonyms-api"></a>

Define synonyms sets<a id="define-synonyms-sets"></a>

Configuring the synonyms set<a id="configuring-the-synonyms-set"></a>

Updating a synonyms set<a id="updating-a-synonyms-set"></a>

Try it out!<a id="try-it-out"></a>

Update your synonyms in Elasticsearch: Introducing the synonyms API

Author

Carlos Delgado

Articles

How to choose between exact and approximate kNN search in Elasticsearch

Elasticsearch new semantic_text mapping: Simplifying semantic search

Update your synonyms in Elasticsearch: Introducing the synonyms API