How to calculate aggregations in Elasticsearch as percentages?
This blog post shows you how to calculate aggregations in Elasticsearch as percentages through the use of Bucket Script Aggregation
Ilaria Petreti
August 5, 2024
OpenSearch Neural Sparse Search Tutorial
This blog post will focus on exploring Neural Sparse Search, an alternative approach to neural text search.
Ilaria Petreti
July 16, 2024
Image Retrieval Using ViT + Generative Pre-trained Transformer (GPT)
Implementation of image retrieval through a textual query using a Vision Transformer and a GPT for image captioning.
SQUID
April 18, 2024
Elasticsearch Relevance Engine: Combining AI With Elastic’s Text Search
The goal of this blog post is to highlight new vector search capabilities introduced in version 8.8.0, especially ESRE
Ilaria Petreti
July 26, 2023
How to Choose the Right Large Language Model for Your Domain – Open Source Edition
Note on “Open Source” claims This blog post was originally written before the publication of the Open Source AI Definition, which provides a much-needed clarification
Alessandro Benedetti
June 9, 2023
Elasticsearch Neural Search Improvements in 8.6 and 8.7
This blog post showcases the vector search improvements that have been introduced in the latest versions of Elasticsearch (8.6 and 8.7)
Ilaria Petreti
May 16, 2023
Vespa Neural Search Tutorial
An end-to-end tutorial to implement Neural Search in Vespa. From documents and model preparation, to embeddings creation and k-NN queries.
Anna Ruggero
February 6, 2023
Categorical Features in Apache Solr Learning to Rank
In this blog post we present the available learning to rank Apache Solr features with a focus on categorical features and how to manage them.
Anna Ruggero
October 6, 2022
How the Feature Vector Cache Is Used in Apache Solr
How the FeatureLogger works? When the Feature Vector Cache is used in Solr? Is the cache speeding up the rerank process?
Anna Ruggero
February 14, 2022
Tackling Vocabulary Mismatch with Document Expansion
Let’s attenuate vocabulary mismatch by leveraging document expansion using two modern transformer-based approaches.
Antonio Mallia
January 31, 2022
We are Sease, an Information Retrieval Company based in London, focused on providing R&D project guidance and implementation, Search consulting services, Training, and Search solutions using open source software like Apache Lucene/Solr, Elasticsearch, OpenSearch and Vespa.
