elasticsearch

Tag

Cards List
#elasticsearch

We built a persistent agent memory layer on Elasticsearch with 0.89 recall

Hacker News Top · 5d ago Cached

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.

0 favorites 0 likes
#elasticsearch

@techwith_ram: Watching this talk about Agentic Search for Context Engineering by @helloiamleonie Watched half of this talk. Really we…

X AI KOLs Timeline · 2026-05-08 Cached

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.

0 favorites 0 likes
#elasticsearch

@DailyDoseOfDS_: Stop using vector search everywhere! A 30-year-old algorithm with zero training, zero embeddings, and zero fine-tuning …

X AI KOLs Timeline · 2026-05-07

The article argues against overusing vector search, highlighting BM25's effectiveness for exact keyword matching and its role in hybrid search systems.

0 favorites 0 likes
← Back to home

Submit Feedback