Finally, Elastic entered the VectorOps landscape with its new ESRE offer

After years of nothingness, and a first timid ANN search, here comes the great announcement everyone was expecting.

Thanks to ESRE, short for “Elasticsearch Relevance Engine”, the first real full-fledge offer around LLMs.

Note that Elasticsearch already provided a vector search. But without dedicated embedding management, this just deported the work to good old Python code.

Now, what looks great about ESRE?

1. Import and configure Hugging Face transformers inside Kibana
It can be done from a local docker instance, or from a Colab

2. Build embeddings from the ingestion API

3. Search with ANN on embeddings

4. Hybrid ranking with RFF

5. APIs to manage all those steps

You will need the Elastic Platinum plan to be able to activate ML nodes.

Question: WPSOLR already integrates Elasticsearch APIs for sparse search. But will it also do it for the ESRE suite? Stay tuned!

ESRE documentation

WPSOLR + Elasticsearch: https://wpsolr.com

#wpsolr #elasticsearch #vectorsearch