Concept
Numeric vectors produced by machine learning models that represent the meaning of text, images or other content, so that similar content lies close together and can be compared by distance in vector search.
| Type | Concept |
|---|---|
| Documentation | learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/understand-embeddings |
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…
2026-06-07 · 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…
2026-06-18 · Video on YouTube
Artificial Intelligence is transforming the way organizations manage knowledge, documents, and collaboration. Yet as companies rush to adopt AI assistants and large language models, one question continues to dominate every conversation: how can you benefit…
2026-06-08 · Video on YouTube
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…
2026-05-11 · Video on YouTube
In this episode of the m365.fm podcast, Mirko Peters explores why traditional AI security testing is no longer enough in modern enterprise environments. The discussion focuses on “red teaming” for multi-model AI systems, especially in highly regulated…
2026-07-16 · Video on YouTube
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…
2026-01-21 · Video on YouTube
In this episode of the M365.FM Podcast we dive into Azure AI infrastructure architecture — not as another workload, but as a fundamentally different architectural reality that every CIO, CTO, CISO, and enterprise leader must understand. Most organizations…
2026-06-20 · Video on YouTube
veryone is talking about Private RAG, sovereign AI, regional hosting, and keeping enterprise data inside controlled environments. But in this episode of M365 FM, Mirko Peters explores a critical security gap that many organizations overlook: data sovereignty…
2026-08-10
Copilot can answer a question perfectly today and fumble the same question tomorrow because it searches instead of remembering. This episode explains why RAG-based Copilot stays shallow and how the LLM Wiki pattern adds compiled, maintained knowledge, for IT…
2026-06-06 · Video on YouTube
In this episode of M365.fm, Mirko Peters explores how organizations can build a secure and private Retrieval-Augmented Generation (RAG) platform using SharePoint as the knowledge source and n8n as the orchestration layer. The discussion focuses on moving…
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…
A vector database stores data as embeddings and finds the closest match by meaning rather than exact words. This lets applications search by intent and context. · From the episode: Vector Databases - Simply Explained
Embeddings are vectors created when raw data such as text, images or audio is vectorized. They capture meaning so similar items sit close together. · From the episode: Vector Databases - Simply Explained
The challenge of efficiently searching billions of vector embeddings without runaway infrastructure cost. · From the episode: HNSW vs DiskANN for Vector Search in Azure AI…
DiskANN relies on SSDs rather than RAM, so memory costs fall for large datasets. This addresses the cost problem of searching through very large numbers of vector embeddings. · From the episode: HNSW vs DiskANN for Vector Search in Azure AI…
Documents are split into chunks represented by embeddings, the question is turned into a comparable representation, and the most relevant chunks are given to the language model as context for its answer. · From the episode: Your Copilot Has No Memory — Why RAG Fails and…
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