Experiments in improving Agentic AI tools for Elasticsearch
Learn how we improved AI agent workflows for Elasticsearch through iterative experiments by combining linear retrievers, hybrid search, and semantic_text for scalable RAG optimization.
Hybrid search revisited: introducing the linear retriever in Elasticsearch!
Discover how the linear retriever enhances hybrid search by leveraging weighted scores and MinMax normalization for more precise and consistent rankings, and learn how to use it.
First to hybrid search: with Elasticsearch and Semantic Kernel
Learn how use hybrid search and the Semantic Kernel connector with Elasticsearch to improve retrieval results.
Built with Elastic: Hybrid search for Cypris – the world’s largest innovation database
Discover how Cypris optimized hybrid search in Elasticsearch to handle 500M vectors, cutting query times from 60 seconds down to 5–10 seconds using binary quantization and segment tuning.
Beyond vectors: Intelligent hybrid search with LLM agents in Elasticsearch
Vector search alone does not account for time, space, or intention, limiting its effectiveness. Thankfully, a solution lies in combining Elastic's traditional search features with LLM agents.
Elasticsearch hybrid search
Learn about hybrid search, the types of hybrid search queries Elasticsearch supports, and how to craft them.
When hybrid search truly shines
Demonstrating when hybrid search is better than lexical or semantic search on their own.