56% faster, up to 50% better retrieval performance: What's inside Jina's new 600 million parameter listwise reranker
Jina Reranker 3.5 beats v3 by 50%+ on case law, closes the gap with models 7x its size on legal, medical, and financial benchmarks, and beats them outright on structured data. It's a drop-in replacement for v3, with no API changes.
July 20, 2026
AI shopping agents: Why context comes before the query
AI shopping agents that guess at your vocabulary make expensive mistakes. Pre-computed catalog context stops the guessing before the first tool call.
July 16, 2026
A picture is worth 1.5x the words: What we learned benchmarking product search embeddings
We benchmarked two embedding models on 5,000 real products and found that combining image and text beats either alone by up to 50%. Here's the data and the model that won.
How to build search analytics on Elastic using OpenTelemetry, no extra pipeline required
How to instrument your search application to use modern Open Telemetry standard to drive insights in to your search and users.
March 31, 2026
From judgment lists to trained Learning to Rank (LTR) models
Learn how to transform judgment lists into training data for Learning To Rank (LTR), design effective features, and interpret what your model learned.
March 5, 2026
Does MCP make search obsolete? Not even close
Explore why search engines and indexed search remain the foundation for scalable, accurate, enterprise-grade AI, even in the age of MCP, federated search, and large context windows.
February 20, 2026
Ensuring semantic precision with minimum score
Improve semantic precision by employing minimum score thresholds. The article includes concrete examples for semantic and hybrid search.
February 17, 2026
An open‑source Hebrew analyzer for Elasticsearch lemmatization
An open-source Elasticsearch 9.x analyzer plugin that improves Hebrew search by lemmatizing tokens in the analysis chain for better recall across Hebrew morphology.
January 30, 2026
Query rewriting strategies for LLMs and search engines to improve results
Exploring query rewriting strategies and explaining how to use the LLM's output to boost the original query's results and maximize search relevance and recall.