Concept
Traditional lexical search that matches the exact words of a query against documents, often ranked with the BM25 algorithm; precise for exact terms but blind to meaning.
| Type | Concept |
|---|
2026-06-07 · Video on YouTube
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…
2026-07-17 · Video on YouTube
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…
2026-05-01 · Video on YouTube
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…
2026-07-16 · Video on YouTube
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…
2026-05-29 · Video on YouTube
In this episode of the Microsoft 365-focused podcast from m365.fm, the discussion explores how organizations can implement intelligent knowledge graph architectures to support modern hybrid work environments. The episode examines how Microsoft technologies…
Information is fragmented across millions of documents, relationships, entities and timelines, and hidden connections are hard to find with keyword search. · From the episode: Scaling Microsoft Copilot to 35 Million Pages
Hybrid retrieval combines vector search with keyword search so the system matches both meaning and exact terms. This improves precision and recall, and it is presented in the episode as the new standard for Copilot-style retrieval. · From the episode: Improve Microsoft Copilot Accuracy Beyond…
The episode suggests trying it with a small set of about 100 documents to feel the difference from keyword search right away. · From the episode: Vector Databases - Simply Explained
Context-driven retrieval is AI-based information retrieval that uses context from people, content and activity, moving beyond traditional keyword search. · From the episode: Microsoft Cowork IQ Knowledge Graph Architecture
Short info above, community knowledge below: add practical tips, examples or corrections. New contributions are reviewed first; trusted members publish directly.
Nobody has listed this topic yet. Add it to your profile.
Maintained by Mirko Peters (Microsoft MVP) · Last updated:
EN
Deutsch
Español
Français
Italiano
Português
Nederlands
Polski
Bahasa Indonesia
Русский
Українська
العربية
עברית
日本語
한국어