<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Hybrid search – M365.FM</title><link>https://www.m365.fm/entity/hybrid-search/</link><description>Search approach that runs keyword (full-text) and vector queries together and merges the results into one ranked list, for example with Reciprocal Rank Fusion (RRF) in Azure AI Search.</description><language>en</language><item><title>Mastering Azure AI Search: Beyond Traditional Keyword Matching</title><link>https://www.m365.fm/community/u/mirko-p/blog/mastering-azure-ai-search-beyond-traditional-keyword-matching/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/mastering-azure-ai-search-beyond-traditional-keyword-matching/</guid><pubDate>Thu, 27 Aug 2026 06:39:00 -0000</pubDate><category>article</category><description>Welcome to our deep dive into the world of cloud-based discovery and retrieval systems. If you have ever typed a query into a company intranet, e-commerce site, or …</description></item><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><item><title>Solving the Billion-Vector Problem in Azure AI Search</title><link>https://www.m365.fm/community/u/mirko-p/blog/solving-the-billion-vector-problem-in-azure-ai-search/</link><guid>https://www.m365.fm/community/u/mirko-p/blog/solving-the-billion-vector-problem-in-azure-ai-search/</guid><pubDate>Wed, 26 Aug 2026 09:52:17 -0000</pubDate><category>article</category><description>Explore the unique technical challenges of searching massive datasets at scale. This post breaks down how high dimensionality and memory constraints impact enterpri…</description></item><item><title>Azure AI Search – Simply Explained</title><link>https://www.m365.fm/show/episodes/azure-ai-search-simply-explained/</link><guid>https://www.m365.fm/show/episodes/azure-ai-search-simply-explained/</guid><pubDate>Fri, 17 Jul 2026 00:00:00 -0000</pubDate><category>episode</category><description>Azure AI Search is Microsoft's intelligent search and information retrieval service for building modern search experiences and AI-powered applications. It combines traditional keyword search with vector search, semantic ranking, and AI enrichment, making it a…</description></item><item><title>Vector Databases - Simply Explained</title><link>https://www.m365.fm/show/episodes/vector-databases-simply-explained/</link><guid>https://www.m365.fm/show/episodes/vector-databases-simply-explained/</guid><pubDate>Thu, 16 Jul 2026 00:00:00 -0000</pubDate><category>episode</category><description>Vector databases are one of the key technologies powering modern AI applications, yet most people never interact with them directly. Unlike traditional databases that search for exact words or values, vector databases search by meaning, enabling AI to…</description></item><item><title>RAG on Azure — Simply Explained</title><link>https://www.m365.fm/show/episodes/rag-on-azure-simply-explained/</link><guid>https://www.m365.fm/show/episodes/rag-on-azure-simply-explained/</guid><pubDate>Thu, 16 Jul 2026 00:00:00 -0000</pubDate><category>episode</category><description>Retrieval-Augmented Generation (RAG) is one of the most important techniques behind modern AI applications, enabling large language models to answer questions using your own business data instead of relying only on their training knowledge. In this episode of…</description></item><item><title>How to Build Low-Cost AI Agents in Microsoft Cloud</title><link>https://www.m365.fm/show/episodes/how-to-architect-low-cost-ai-agents-in-the-microsoft-cloud/</link><guid>https://www.m365.fm/show/episodes/how-to-architect-low-cost-ai-agents-in-the-microsoft-cloud/</guid><pubDate>Wed, 10 Jun 2026 00:00:00 -0000</pubDate><category>episode</category><description>Learn how to build low-cost AI agents in Microsoft Cloud with Azure OpenAI, Copilot Studio, Power Platform, and practical cost controls.</description></item><item><title>HNSW vs DiskANN for Vector Search in Azure AI Search</title><link>https://www.m365.fm/show/episodes/the-billion-vector-problem-hnsw-vs-diskann-in-azure-ai-search/</link><guid>https://www.m365.fm/show/episodes/the-billion-vector-problem-hnsw-vs-diskann-in-azure-ai-search/</guid><pubDate>Mon, 08 Jun 2026 00:00:00 -0000</pubDate><category>episode</category><description>The explosion of AI-powered applications has created a new challenge: how do you efficiently search through billions of vector embeddings without exploding infrastructure costs? In this episode, we explore the “billion-vector problem” and compare two leading…</description></item><item><title>Scaling Microsoft Copilot to 35 Million Pages: The Epstein Files</title><link>https://www.m365.fm/show/episodes/i-engineered-copilot-for-35-million-pages-the-epstein-files-challenge/</link><guid>https://www.m365.fm/show/episodes/i-engineered-copilot-for-35-million-pages-the-epstein-files-challenge/</guid><pubDate>Sun, 07 Jun 2026 00:00:00 -0000</pubDate><category>episode</category><description>In this episode, Mirko Peters explores one of the most ambitious experiments in enterprise AI: engineering Microsoft Copilot to analyze and reason across more than 35 million pages of highly complex and interconnected information, inspired by the scale and…</description></item><item><title>Improve Microsoft Copilot Accuracy Beyond Vector Search</title><link>https://www.m365.fm/show/episodes/vector-search-is-not-a-strategy-the-new-standard-for-copilot-accuracy/</link><guid>https://www.m365.fm/show/episodes/vector-search-is-not-a-strategy-the-new-standard-for-copilot-accuracy/</guid><pubDate>Fri, 01 May 2026 00:00:00 -0000</pubDate><category>episode</category><description>This episode explains that vector search on its own is not a complete or reliable strategy for building accurate AI systems like Copilot. While many organizations rely on embeddings and vector databases to retrieve information, this approach often leads to…</description></item><item><title>Fix Common Azure AI Foundry Project Failures</title><link>https://www.m365.fm/show/episodes/the-azure-ai-foundry-trap-why-most-fail-fast/</link><guid>https://www.m365.fm/show/episodes/the-azure-ai-foundry-trap-why-most-fail-fast/</guid><pubDate>Mon, 03 Nov 2025 00:00:00 -0000</pubDate><category>episode</category><description>In this episode we walk through what really happens when Azure AI Foundry doesn’t behave the way you expect, especially when the Agent Service or deployments start acting up. Azure AI Foundry is supposed to feel smooth, almost invisible, tying together OpenAI…</description></item></channel></rss>