Explore the machine learning (ML) models supported in Elastic, the Eland library for loading models and how to apply transformers & NLP in Elastic.

Elastic supports the machine learning models you need

Eland lets you load ML models into Elastic

Which models Elastic support?

How to apply transformers and NLP in Elastic, with ease!

Check these resources for more details

Elastic supports a variety of transformer models, as well as the most popular supervised learning libraries: NLP and embedding models, supervised learning, and generative AI.

Which machine learning models does Elastic support?

Elastic machine learning: Accessing & using ML models with Elastic

Accessing machine learning models in Elastic

Here's how multilingual vector search works and how to use Elasticsearch with the multilingual E5 embedding model, including examples.

Why multilingual embeddings?

Let's consider a few examples

Example 1

Example 2

Example 3a

Example 3b

Multilingual E5 embedding model

Elasticsearch for multilingual vector search with E5

Setup

Indexing

Search

Conclusion

Multilingual embeddings models are models that can embed multiple languages into the same 'embedding space', enabling cross-lingual search capabilities. These models are capable of working with pairs of text in any of the languages they were trained in.

What are multilingual embedding models?

The E5 embedding model, or Embeddings from Bidirectional Encoder Representations was introduced by Microsoft. It has state-of-the-art performance in zero-shot and multilingual settings.

What is the E5 embedding model?

Multilingual vector search: Elasticsearch with E5 embedding model

Multilingual vector search with the E5 embedding model

Author

Josh Devins

Articles

Accessing machine learning models in Elastic

Multilingual vector search with the E5 embedding model