Agentic RAG, Apache Solr Quantization, Instructed Retriever, Solr Nested KNN and so much more!
We farmed the retrieval zones all month, and the drops were decent: agents, vector search, Solr tricks, and real-world takeaways 👾. Subscribe for the next run!
📰 News
“OpenSearch 3.4 is ready for download with a host of new and updated features for a range of use cases, plus enhancements to drive better performance for common workloads.”
➡️ Read more
Instructed Retriever: Unlocking System-Level Reasoning in Search Agents “In this blog, we present the Instructed Retriever – a novel retrieval architecture that addresses the limitations of RAG, and reimagines search for the agentic era.”
➡️ Read more
“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 they handle knowledge.”
➡️ Read more
📰 Blog Posts
Scalar Quantization and Binary Quantization of Dense Vectors in Apache Solr
“In these blog posts, we would like to introduce the concepts of vector quantization, with a particular focus on scalar and binary vector quantization, explaining what they are and why they are important.”
“In this post, I’ll show you how to build a basic Agentic RAG system in about 10 minutes — a travel agent that searches 2,000 London Airbnb listings using natural language.”
➡️ Read more
Recommended by LinkedIn
“Learn how to use LangGraph.js with Elasticsearch to build an AI-powered financial search workflow that turns natural language queries into dynamic, conditional filters for investment and market analysis.”
➡️ Read more
“We are excited to introduce a new feature coming to Solr 10.1: KNN search on nested vectors via Block Join contributed by Sease, Alessandro Benedetti (merged PR). In this post, we will cover: 1) Challenge: Current KNN Search in Solr 2) KNN Block Join Query 3) Nested KNN Search Example”
➡️ Read more
🏆 Must-Read Research and Papers:
🗓️ Next events:
In case you missed our talks:
If you know of any AI & Information Retrieval events that are not listed, do give us a heads-up so we can add them!
About us
Sease is an Information Retrieval Company based in London, focused on building Search solutions and AI integrations with cutting-edge Machine Learning, such as Large Language Models (RAG, Vector-Based search) and Learning To Rank.
