<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>BM25 – M365.FM</title><link>https://www.m365.fm/entity/bm25/</link><description>BM25 (Okapi BM25) is a classic sparse ranking function that scores documents by exact term overlap with a query; it is commonly combined with vector search in hybrid retrieval.</description><language>en</language><item><title>Why Pure Vector Search Fails Enterprise AI (And How to Fix It)</title><link>https://www.m365.fm/community/u/mirko-p/blog/why-pure-vector-search-fails-enterprise-ai-and-how-to-fix-it/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/why-pure-vector-search-fails-enterprise-ai-and-how-to-fix-it/</guid><pubDate>Wed, 26 Aug 2026 13:09:05 -0000</pubDate><category>article</category><description>When you start deploying generative AI across your organization, you quickly realize that standard Retrieval-Augmented Generation (RAG) setups lean heavily on pure …</description></item></channel></rss>