Blogs
Insights de desenvolvedores e artigos práticos dos nossos experts para inspirar e fortalecer suas buscas
How to deploy Elasticsearch on Azure AKS Automatic
Learn how to deploy Elasticsearch with Kibana on Azure using AKS Automatic and ECK for a partially managed Elasticsearch setup configuration.
Creating an LLM Agent newsroom with A2A protocol and MCP in Elasticsearch: Part I
Explore the concepts of A2A protocol and MCP within a practical newsroom example where specialized LLM agents collaborate to research, write, edit, and publish news articles.
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.
Configuring recursive chunking for structured documents in Elasticsearch
Learn how to configure recursive chunking in Elasticsearch with chunk size, separator groups, and custom separator lists for optimal structured document indexing.
How to deploy Elasticsearch and Kibana on AWS EKS auto mode with ECK
Learn how to deploy Elasticsearch and Kibana on Kubernetes using AWS EKS Auto Mode and ECK in this easy-to-follow guide.
Introducing Elasticsearch Query Rules UI in Kibana
Learn how to use the Elasticsearch Query Rules UI to add or exclude documents from search queries using customizable rulesets in Kibana, without affecting organic ranking.
Building a knowledge agent with semantic recall using Mastra and Elasticsearch
Learn how to build a knowledge agent with semantic recall using Mastra and Elasticsearch as a vector store for memory and information retrieval.
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.
Multimodal search for mountain peaks with Elasticsearch and SigLIP-2
Learn how to implement text-to-image and image-to-image multimodal search using SigLIP-2 embeddings and Elasticsearch kNN vector search. Project focus: finding Mount Ama Dablam peak photos from an Everest trek.
Improving multilingual embedding model relevancy with hybrid search reranking
Learn how to improve the relevancy of E5 multilingual embedding model search results using Cohere's reranker and hybrid search in Elasticsearch.
How to install and configure Elasticsearch on AWS EC2
Learn how to deploy Elasticsearch and Kibana on an Amazon EC2 instance in this step-by-step guide.
Context engineering using Mistral Chat completions in Elasticsearch
Learn how to utilize context engineering with Mistral Chat completions in Elasticsearch to ground LLM responses in domain-specific knowledge for accurate outputs.