Improve the “R” in RAG and embrace Agentic RAG in Azure SQL
The RAG (Retrieval Augmented Generation) pattern, which is commonly discussed today, is based on the foundational idea that the retrieval part is done using vector search. This ensures that all the most relevant information available to answer the given question is returned and then fed to an LLM to generate the final answer. While vector […]
The post Improve the “R” in RAG and embrace Agentic RAG in Azure SQL appeared first on Azure SQL Devs’ Corner.
Published on:
Learn moreRelated posts
Power Pages + Azure AD B2C: “The Provided Application Is Not Valid” Error
If you are new to configuring Azure AD B2C as Identity Provider in Power Pages, refer Power Pages : Set up Azure AD B2C After completing the s...
Semantic Reranking with Azure SQL, SQL Server 2025 and Cohere Rerank models
Supporting re‑ranking has been one of the most common requests lately. While not always essential, it can be a valuable addition to a solution...
How Azure Cosmos DB Powers ARM’s Federated Future: Scaling for the Next Billion Requests
The Cloud at Hyperscale: ARM’s Mission and Growth Azure Resource Manager (ARM) is the backbone of Azure’s resource provisioning and management...
Automating Business PDFs Using Azure Document Intelligence and Power Automate
In today’s data-driven enterprises, critical business information often arrives in the form of PDFs—bank statements, invoices, policy document...
Azure Developer CLI (azd) Dec 2025 – Extensions Enhancements, Foundry Rebranding, and Azure Pipelines Improvements
This post announces the December release of the Azure Developer CLI (`azd`). The post Azure Developer CLI (azd) Dec 2025 – Extensions En...
Unlock the power of distributed graph databases with JanusGraph and Azure Apache Cassandra
Connecting the Dots: How Graph Databases Drive Innovation In today’s data-rich world, organizations face challenges that go beyond simple tabl...
Azure Boards integration with GitHub Copilot
A few months ago we introduced the Azure Boards integration with GitHub Copilot in private preview. The goal was simple: allow teams to take a...