How we built a persistent agent memory layer on Elasticsearch with 0.89 recall and zero tenant leaks
Elasticsearch Labs
How we built a persistent agent memory layer on Elasticsearch with 0.89 recall and zero tenant leaks
Discover the architecture behind a persistent, multi-tenant agent memory layer on Elasticsearch: three indices, hybrid retrieval with RRF and a reranker, supersession, decay, and per-user DLS isolation. R@10 0.89 across 168 questions. Full open-source implementation included.
Better text analysis for complex languages with Elasticsearch and neural models
Elasticsearch Labs
Better text analysis for complex languages with Elasticsearch and neural models
Using neural models and the Elasticsearch inference API to improve search in Hebrew, German, Arabic, and other morphologically complex languages.