Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
Articole: 5
-
Turning user intent into validated Elasticsearch queries with guardrails.
-
TL;DR The Problem: Traditional metrics like nDCG assume a human scrolling a ranked list.
-
TL;DR The Surprise: Dense “semantic” retrievers work better on proper names than expected.
-
TL;DR I poked modern embedding models (text-embedding-3-large / -small) with real conversational fluff and watched the cosine similarity to the clean query drop, dropping more in French than in English, and more in the small model than the large.
-
TL;DR The Problem: building RAG evaluation sets (“Golden Sets”) requires ranking relevant documents.