All about those chunks, ’bout those chunks, and snippets!
Exploring chunking and snippet extraction for LLMs, highlighting enhancements for identifying the most relevant chunks and snippets to send to models such as rerankers and LLMs.
Hybrid search and multistage retrieval in ES|QL
Explore the multistage retrieval capabilities of ES|QL, using FORK and FUSE commands to integrate hybrid search with semantic reranking and native LLM completions.
Evaluating search query relevance with judgment lists
Explore how to build judgment lists to objectively evaluate search query relevance and improve performance metrics such as recall, for scalable search testing in Elasticsearch.
How to improve e-commerce search relevance with personalized cohort-aware ranking
Improve e-commerce search relevance with explainable, cohort-aware ranking in Elasticsearch. Learn how multiplicative boosting delivers stable, predictable personalization at query time.
Hybrid search without the headache: simplifying hybrid search with retrievers
Explore how to simplify hybrid search in Elasticsearch with a multi-field query format for linear and RRF retrievers, and create queries with no previous knowledge about your Elasticsearch index.
You Know, for Context - Part I: The evolution of hybrid search and context engineering
Explore how hybrid search and context engineering have evolved from lexical foundations to enable the next generation of agentic AI workflows.
The impact of relevance in context engineering for AI agents
Discover how hybrid retrieval, semantic chunking, and agentic search improve LLM performance by managing context relevance efficiently.
Balancing the scales: Making reciprocal rank fusion (RRF) smarter with weights
Exploring weighted reciprocal rank fusion (RRF) in Elasticsearch and how it works through practical examples.
MCP for intelligent search
Building an intelligent search system by integrating Elastic's intelligent query layer with MCP to enhance the generative efficacy of LLMs.
Building intelligent duplicate detection with Elasticsearch and AI
Explore how organizations can leverage Elasticsearch to detect and handle duplicates in loan or insurance applications.
Diversifying search results with Maximum Marginal Relevance
Implementing the Maximum Marginal Relevance (MMR) algorithm with Elasticsearch and Python. This blog includes code examples for vector search reranking.
Semantic text is all that and a bag of (BBQ) chips! With configurable chunking settings and index options
Semantic text search is now customizable, with support for customizable chunking settings and index options to customize vector quantization, making semantic_text more powerful for expert use cases.