Tag
Elastic describes using an AI agent with a benchmarking harness to automate code optimization in Elasticsearch, leading to verified performance improvements.
This article describes a reference RAG agent implementation using Mastra and Elasticsearch vector store, demonstrated on a corpus of 500 sci-fi movies, with the agent built in approximately 60 lines of TypeScript.
The article describes the architecture of a notification service that uses Kafka for messaging, Redis for rate limiting, Cassandra for tracking, and Elasticsearch for user targeting in bulk notifications.
A user shares their experience of switching from multiple independent systems to Elasticsearch, which can handle logging, search, and monitoring tasks simultaneously, and introduces its distributed features based on Apache Lucene and its application in AI.
Elastic and OpenAI are expanding their collaboration to integrate OpenAI's reasoning capabilities with Elasticsearch's retrieval layer, enabling context-aware AI agents for enterprise data, observability, and security.
Elasticsearch blog post describes building a persistent agent memory layer with three memory types (episodic, semantic, procedural), achieving 0.89 recall on a QA eval with zero tenant leaks using hybrid recall and DLS isolation.
A workshop/tutorial on agentic search techniques for context engineering, teaching how AI agents decide what context to retrieve from files, databases, memory, and the web using langchain and Elasticsearch.
The article argues against overusing vector search, highlighting BM25's effectiveness for exact keyword matching and its role in hybrid search systems.