Hybrid Search in RAG: BM25 + Vectors for Better Retrieval
Learn how to implement Hybrid Search in RAG using C#. Combine BM25 precision with Vector semantics in Azure AI Search for better retrieval.
Microsoft FoundryA collection of 18 posts
Posts exploring Microsoft Foundry, the unified Azure platform for deploying, managing, and scaling production‑ready AI models and applications.
Naive RAG Explained: The Core Pattern
Learn how to build a Naive RAG system using C# and Microsoft Foundry. Ground LLMs in private markdown data for accurate FAQ bots.
Image Verbalization via LLMs: A Simplified Path to Multimodal Search
Learn Image Verbalization via LLM to bridge the gap between pixels and text. Master C# vector search by turning images into searchable descriptions.
Integrated Vectorization in Azure AI Search: How to Automate Embeddings
A complete guide to integrated vectorization in Azure AI Search, showing how to automate embeddings and streamline your vector search pipeline.
Vectorizers in Azure AI Search: 5 Key Insights You Must Know
Learn how Vectorizers in Azure AI Search simplify embedding generation, streamline C# code, and improve vector search workflows.
Vector Search in Azure AI Search: A Practical Guide
Vector Search in Azure AI Search explained with filters, role-based filtering and C# examples for building fast, intelligent vector search features.
Vector Search in Azure Cosmos DB for NoSQL: A Practical Guide
Hands-on guide to Vector Search in Azure Cosmos DB for NoSQL with practical examples in C# using embeddings and vector indexes.
Vector Databases in Azure: Powering AI Apps at Scale
A practical intro to Vector Databases in Azure, how they work, key search algorithms, and how to choose the right Azure service for AI apps.
Introduction to embeddings: Capture the meaning of data
Introduction to embeddings that explains how they capture meaning in high‑dimensional space and semantic search with Microsoft Foundry and C#.