Main blog
Welcome to our Main Blog, the cornerstone of our exploration into information retrieval. This dedicated space serves as a comprehensive repository where we delve into our research, findings, and various topics predominantly centered around information retrieval.
Nested Vectors Search in Apache Lucene
When using Lucene’s parent-child block-join mode, you are dealing with a “one-to-many relationship”. You have a single document (parent) owning multiple vector embeddings (children).To search
Benchmarking JSON Facet Methods in Apache Solr
This blogpost explores the performance impact of DocValues vs. Inverted Index for Apache Solr facets done through JSON facet API.
Apache Solr 10 – What Is New for Vector Search and LTR
This blog summarises the main new features introduced in Apache Solr 10.0.0, focusing on Vector Search and Learning to Rank (LTR).
Apache Solr New Learning To Rank Cache
A comparison between Solr’s current LTR cache and a new implementation that works not only for logging features, but also for reranking.
New in Apache Solr 10: Improved Filtering In Vector Search with ACORN
Hi readers, In this blog post, we are excited to share some important news with you:Sease has contributed a new feature to Apache Solr by
Hybrid Search Using a Custom Algorithm in Apache Solr
This blog post explores the Combined Query Feature using a custom algorithm in Apache Solr with a hands-on approach.
Hybrid Search with Reciprocal Rank Fusion in Apache Solr
We explore the Combined Query Feature using Reciprocal Rank Fusion in Apache Solr with a hands-on approach.
Lexically accelerated vector search: SeededKnnVectorQuery Support in Apache Solr 10
In this blog we explores our recent contribution to Apache Solr that introduces support for SeededKnnVectorQuery.
Searching Children, Finding Parents: Nested KNN Vector Search in Solr
New feature coming to Solr v10.x: KNN search on nested vectors via Block Join. KNN Block Join query enables searching across specific child paragraphs and surfacing the most relevant parent documents in a single request.
Binary Quantization of Dense Vectors in Apache Solr
This blog post explores binary vector quantization and the recent Solr contribution which adds support for this technique.
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.
Retrieval and Responsibility: The Ethics of Augmented Knowledge
As companies rush to embed generative AI into search, support, and decision-making, the real competitive edge won’t come from scale alone, but from how responsibly
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.
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.
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.
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.
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.
Enterprise AI Products for Search: Limits and Risks
Imagine stumbling upon a shiny platform that claims to offer “done-for-you” searches with AI-powered relevance and conversational chat, all rolled into one, perfectly working out
OpenSearch Semantic Sentence Highlighting Explained
Explore Semantic Highlighting feature in OpenSearch v3.0, how it works, and how it compares to the Sease Solr Neural Highlighting plugin.
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.
Semantic Search (Text to Vector) with Apache Solr
Learn all the secrets of the new semantic search in Apache Solr 9.8 that uses LLMs to vectorise text and support natural language queries.
Search Limitations and Workarounds in OpenSearch
This blog post focuses on limitations in OpenSearch v2.17 during the implementation of search features and proposes practical workarounds.
Why Solr More Like This Ignores Your copyField – How to Deal With It
This blog post explains a workaround implemented in Solr’s CloudMLTQParser to handle fields populated via copyField.
Best Large Language Models You Can Use in 2025 (Full Guide)
Curious about which large language models are dominating 2025? This comprehensive guide breaks down the top options—open-source, hybrid, and commercial, helping you choose the right AI tool for your needs.
Evaluating Solr Vector Search with Quepid
This blog post explore a practical way to evaluate the performance of vector search results in Apache Solr.
Challenges in Mathematical Formulae Retrieval
How do you retrieve mathematical formulae? What are the main problems and challenges in mathematical formulae retrieval?
From Natural Language to Structured Solr Queries using LLMs
It explores translating natural language queries into structured Solr queries using LLM and metadata to improve search and user experience.