Foundry IQ Masterclass: The Agentic Retrieval Pipeline Explained
Understand how Foundry IQ uses Agentic Retrieval Pipeline to navigate data silos. Learn how to tune Reasoning Effort for speed and accuracy.
Azure AI SearchA collection of 15 posts
Posts exploring Microsoft’s cloud search service powered by artificial intelligence. Learn how AI enhances indexing, semantic ranking, and query understanding to deliver smarter, more relevant search experiences in your applications.
Foundry IQ for Agentic Retrieval: Intro to enterprise RAG
Learn how Foundry IQ uses Knowledge Bases and Knowledge Sources to simplify Agentic Retrieval. Build enterprise-ready RAG in Microsoft Foundry.
Contextual Retrieval for RAG: Additional Context to Boost Accuracy
Master Contextual Retrieval and enriched chunk logic with OpenAI and Azure AI Search. Use Prompt Caching in Microsoft Foundry to optimize RAG costs and speed.
HyDE for RAG in Azure: Improve Retrieval with Hypothetical Embeddings
HyDE for RAG explained: a practical guide to boosting retrieval accuracy with hypothetical answers and advanced search methods (Azure AI Search + Foundry).
Multi-Query Retrieval for RAG: Query Rewrites in Azure AI Search
Learn how Multi-Query Retrieval for RAG uses query rewrites and Azure AI Search to improve accuracy and boost retrieval quality.
Semantic Ranking in Azure AI Search: How Cross-Encoders Improve RAG Retrieval
Semantic Ranking in Azure AI Search explained with cross‑encoders that boost RAG accuracy and improve retrieval relevance.
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.
Vector Quantization in Azure AI Search: Cut RAM by 97%
Vector quantization in Azure AI Search: Scalar Quantization and Binary Quantization with oversampling, rescoring, and MRL for space saving and efficiency.
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.