Scalar Quantization of Dense Vectors in Apache Solr
This blog post explores scalar vector quantization and the recent Solr contribution which adds support for this technique.
Ilaria Petreti
January 2, 2026
Faster Vector Search: Early Termination Strategy Now in Apache Solr
In this blog we explores an early termination strategy designed to make approximate k-NN search faster in Apache Solr.
Ilaria Petreti
December 2, 2025
OpenSearch and Large Language Models
In this blog post, we provide a comprehensive overview of the features based on large language models (LLM) currently supported by OpenSearch.
Ilaria Petreti
November 24, 2025
ColBERT in Practice: Bridging Research and Industry
In this blog post, we examine the ColBERT paper, which adapts deep learning models, in particular, BERT, for efficient retrieval.
Nazerke Seidan
November 10, 2025
GLiNER as an Alternative to LLMs for Query Parsing – Evaluation
This blog post explores GLiNER as a viable alternative to large language models (LLMs) for query parsing tasks.
Ilaria Petreti
October 27, 2025
GLiNER as an Alternative to LLMs for Query Parsing – Introduction
This blog post explores how GLiNER works, highlighting its underlying architecture and how it differs from traditional NER models.
Ilaria Petreti
October 13, 2025
AI-Powered Search Results Navigation with LLMs & JSON Schema
It explores an AI-powered Filter Assistant to improve User eXperience in navigating search results efficiently and effectively.
Ilaria Petreti
August 20, 2025
Evaluating Solr Vector Search with Quepid
This blog post explore a practical way to evaluate the performance of vector search results in Apache Solr.
Ilaria Petreti
October 2, 2024
Challenges in Mathematical Formulae Retrieval
How do you retrieve mathematical formulae? What are the main problems and challenges in mathematical formulae retrieval?
Simone Bortolin, Alessandra Pastore, Gil Czaczkes
September 4, 2024
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
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.
