August 2025 Recap: Azure Database for PostgreSQL
Hello Azure Community, August was an exciting month for Azure Database for PostgreSQL! We have introduced updates that make your experience smarter and more secure. From simplified Entra ID group login to integrations with LangChain and LangGraph, these updates help with improving access control and seamless integration for your AI agents and applications. Stay tuned as we dive deeper into each of these feature updates. Feature Highlights Enhanced Performance recommendations for Azure Advisor - Generally Available Entra-ID group login using user credentials - Public Preview New Region Buildout: Austria East LangChain and LangGraph connector Active-Active Replication Guide Enhanced Performance recommendations for Azure Advisor - Generally Available Azure Advisor now offers enhanced recommendations to further optimize PostgreSQL server performance, security, and resource management. These key updates are as follows: Index Scan Insights: Detection and recommendations for disabled index and index-only scans to improve query efficiency. Audit Logging Review: Identification of excessive logging via the pgaudit.log parameter, with guidance to reduce overhead. Statistics Monitoring: Alerts on server statistics resets and suggestions to restore accurate performance tracking. Storage Optimization: Analysis of storage usage with recommendations to enable the Storage Autogrow feature for seamless scaling. Connection Management: Evaluation of workloads for short-lived connections and frequent connectivity errors, with recommendations to implement PgBouncer for efficient connection pooling. These enhancements aim to provide deeper operational insights and support proactive performance tuning for PostgreSQL workloads. For more details read the Performance recommendations documentation. Entra-ID group login using user credentials - Public Preview The public preview for Entra-ID group login using user credentials is now available. This feature simplifies user management and improves security within the Azure Database for PostgreSQL. This allows administrators and users to benefit from a more streamlined process like: Changes in Entra-ID group memberships are synchronized on a periodic 30min basis. This scheduled syncing ensures that access controls are kept up to date, simplifying user management and maintaining current permissions. Users can log in with their own credentials, streamlining authentication, and improving auditing and access management for PostgreSQL environments. As organizations continue to adopt cloud-native identity solutions, this update represents a major improvement in operational efficiency and security for PostgreSQL database environments. New Region Buildout: Austria East New region rollout! Azure Database for PostgreSQL flexible server is now available in Austria East, giving customers in and around the region lower latency and data residency options. This continues our mission to bring Azure PostgreSQL closer to where you build and run your apps. For the full list of regions visit: Azure Database for PostgreSQL Regions. LangChain and LangGraph connector We are excited to announce that native LangChain & LangGraph support is now available for Azure Database for PostgreSQL! This integration brings native support for Azure Database for PostgreSQL into LangChain or LangGraph workflows, enabling developers to use Azure PostgreSQL as a secure and high-performance vector store and memory store for their AI agents and applications. Specifically, this package adds support for: Microsoft Entra ID (formerly Azure AD) authentication when connecting to your Azure Database for PostgreSQL instances, and, DiskANN indexing algorithm when indexing your (semantic) vectors. This package makes it easy to connect LangChain to your Azure-hosted PostgreSQL instances whether you're building intelligent agents, semantic search, or retrieval-augmented generation (RAG) systems. Read more at https://aka.ms/azpg-agent-frameworks Active-Active Replication Guide We have published a new blog article that guides you through setting up active-active replication in Azure Database for PostgreSQL using the pglogical extension. This walkthrough covers the fundamentals of active-active replication, key prerequisites for enabling bi-directional replication, and step-by-step demo scripts for the setup. It also compares native and pglogical approaches helping you choose the right strategy for high availability, and multi-region resilience in production environments. Read more about the active-active replication guide on this blog. Azure Postgres Learning Bytes 🎓 Enabling Zone-Redundant High Availability for Azure Database for PostgreSQL Flexible Server Using APIs. High availability (HA) is essential for ensuring business continuity and minimizing downtime in production workloads. With Zone-Redundant HA, Azure Database for PostgreSQL Flexible Server automatically provisions a standby replica in a different availability zone, providing stronger fault tolerance against zone-level failures. This section will guide you on how to enable Zone-Redundant HA using REST APIs. Using REST APIs gives you clear visibility into the exact requests and responses, making it easier to debug issues and validate configurations as you go. You can use any REST API client tool of your choice to perform these operations including Postman, Thunder Client (VS Code extension), curl, etc. to send requests and inspect the results directly. Before enabling Zone-Redundant HA, make sure your server is on the General Purpose or Memory Optimized tier and deployed in a region that supports it. If your server is currently using Same-Zone HA, you must first disable it before switching to Zone-Redundant. Steps to Enable Zone-Redundant HA: Get an ARM Bearer token: Run this in a terminal where Azure CLI is signed in (or use Azure Cloud Shell) az account get-access-token --resource https://management.azure.com --query accessToken -o tsv Paste token in your API client tool Authorization: `Bearer <token>` </token> Inspect the server (GET) using the following URL: https://management.azure.com/subscriptions/{{subscriptionId}}/resourceGroups/{{resourceGroup}}/providers/Microsoft.DBforPostgreSQL/flexibleServers/{{serverName}}?api-version={{apiVersion}} In the JSON response, note: sku.tier → must be 'GeneralPurpose' or 'MemoryOptimized' properties.availabilityZone → '1' or '2' or '3' (depends which availability zone that was specified while creating the primary server, it will be selected by system if the availability zone is not specified) properties.highAvailability.mode → 'Disabled', 'SameZone', or 'ZoneRedundant' properties.highAvailability.state → e.g. 'NotEnabled','CreatingStandby', 'Healthy' If HA is currently SameZone, disable it first (PATCH) using API. Use the same URL in Step 3, in the Body header insert: { "properties": { "highAvailability": { "mode": "Disabled" } } } Enable Zone Redundant HA (PATCH) using API: Use the same URL in Step 3, in the Body header insert: { "properties": { "highAvailability": { "mode": "ZoneRedundant" } } } Monitor until HA is Healthy: Re-run the GET from Step 3 every 30-60 seconds until you see: "highAvailability": { "mode": "ZoneRedundant", "state": "Healthy" } Conclusion That’s all for our August 2025 feature updates! We’re committed to making Azure Database for PostgreSQL better with every release, and your feedback plays a key role in shaping what’s next. 💬 Have ideas, questions, or suggestions? Share them with us: https://aka.ms/pgfeedback 📢 Want to stay informed about the latest features and best practices? Follow us here for the latest announcements, feature releases, and best practices: Azure Database for PostgreSQL Blog More exciting improvements are on the way—stay tuned for what’s coming next!July 2025 Recap: Azure Database for PostgreSQL
Hello Azure Community, July delivered a wave of exciting updates to Azure Database for PostgreSQL! From Fabric mirroring support for private networking to cascading read replicas, these new features are all about scaling smarter, performing faster, and building better. This blog covers what’s new, why it matters, and how to get started. Catch Up on POSETTE 2025 In case you missed POSETTE: An Event for Postgres 2025 or couldn't watch all of the sessions live, here's a playlist with the 11 talks all about Azure Database for PostgreSQL. And, if you'd like to dive even deeper, the Ultimate Guide will help you navigate the full catalog of 42 recorded talks published on YouTube. Feature Highlights Upsert and Script activity in ADF and Azure Synapse – Generally Available Power BI Entra authentication support – Generally Available New Regions: Malaysia West & Chile Central Latest Postgres minor versions: 17.5, 16.9, 15.13, 14.18 and 13.21 Cascading Read Replica – Public Preview Private Endpoint and VNet support for Fabric Mirroring - Public Preview Agentic Web with NLWeb and PostgreSQL PostgreSQL for VS Code extension enhancements Improved Maintenance Workflow for Stopped Instances Upsert and Script activity in ADF and Azure Synapse – Generally Available We’re excited to announce the general availability of Upsert method and Script activity in Azure Data Factory and Azure Synapse Analytics for Azure Database for PostgreSQL. These new capabilities bring greater flexibility and performance to your data pipelines: Upsert Method: Easily merge incoming data into existing PostgreSQL tables without writing complex logic reducing overhead and improving efficiency. Script Activity: Run custom SQL scripts as part of your workflows, enabling advanced transformations, procedural logic, and fine-grained control over data operations. Together, these features streamline ETL and ELT processes, making it easier to build scalable, declarative, and robust data integration solutions using PostgreSQL as either a source or sink. Visit our documentation guide for Upsert Method and script activity to know more. Power BI Entra authentication support – Generally Available You can now use Microsoft Entra ID authentication to connect to Azure Database for PostgreSQL from Power BI Desktop. This update simplifies access management, enhances security, and helps you support your organization’s broader Entra-based authentication strategy. To learn more, please refer to our documentation. New Regions: Malaysia West & Chile Central Azure Database for PostgreSQL has now launched in Malaysia West and Chile Central. This expanded regional presence brings lower latency, enhanced performance, and data residency support, making it easier to build fast, reliable, and compliant applications, right where your users are. This continues to be our mission to bring Azure Database for PostgreSQL closer to where you build and run your apps. For the full list of regions visit: Azure Database for PostgreSQL Regions. Latest Postgres minor versions: 17.5, 16.9, 15.13, 14.18 and 13.21 PostgreSQL latest minor versions 17.5, 16.9, 15.13, 14.18 and 13.21 are now supported by Azure Database for PostgreSQL flexible server. These minor version upgrades are automatically performed as part of the monthly planned maintenance in Azure Database for PostgreSQL. This upgrade automation ensures that your databases are always running on the most secure and optimized versions without requiring manual intervention. This release fixes two security vulnerabilities and over 40 bug fixes and improvements. To learn more, please refer PostgreSQL community announcement for more details about the release. Cascading Read Replica – Public Preview Azure Database for PostgreSQL supports cascading read replica in public preview capacity. This feature allows you to scale read-intensive workloads more effectively by creating replicas not only from the primary database but also from existing read replicas, enabling two-level replication chains. With cascading read replicas, you can: Improve performance for read-heavy applications. Distribute read traffic more efficiently. Support complex deployment topologies. Data replication is asynchronous, and each replica can serve as a source for additional replicas. This setup enhances scalability and flexibility for your PostgreSQL deployments. For more details read the cascading read replicas documentation. Private Endpoint and VNET Support for Fabric Mirroring - Public Preview Microsoft Fabric now supports mirroring for Azure Database for PostgreSQL flexible server instances deployed with Virtual Network (VNET) integration or Private Endpoints. This enhancement broadens the scope of Fabric’s real-time data replication capabilities, enabling secure and seamless analytics on transactional data, even within network-isolated environments. Previously, mirroring was only available for flexible server instances with public endpoint access. With this update, organizations can now replicate data from Azure Database for PostgreSQL hosted in secure, private networks, without compromising on data security, compliance, or performance. This is particularly valuable for enterprise customers who rely on VNETs and Private Endpoints for database connectivity from isolated networks. For more details visit fabric mirroring with private networking support blog. Agentic Web with NLWeb and PostgreSQL We’re excited to announce that NLWeb (Natural Language Web), Microsoft’s open project for natural language interfaces on websites now supports PostgreSQL. With this enhancement, developers can leverage PostgreSQL and NLWeb to transform any website into an AI-powered application or Model Context Protocol (MCP) server. This integration allows organizations to utilize a familiar, robust database as the foundation for conversational AI experiences, streamlining deployment and maximizing data security and scalability. For more details, read Agentic web with NLWeb and PostgreSQL blog. PostgreSQL for VS Code extension enhancements PostgreSQL for VS Code extension is rolling out new updates to improve your experience with this extension. We are introducing key connections, authentication, and usability improvements. Here’s what we improved: SSH connections - You can now set up SSH tunneling directly in the Advanced Connection options, making it easier to securely connect to private networks without leaving VS Code. Clearer authentication setup - A new “No Password” option eliminates guesswork when setting up connections that don’t require credentials. Entra ID fixes - Improved default username handling, token refresh, and clearer error feedback for failed connections. Array and character rendering - Unicode and PostgreSQL arrays now display more reliably and consistently. Azure Portal flow - Reuses existing connection profiles to avoid duplicates when launching from the portal. Don’t forget to update to the latest version in the Marketplace to take advantage of these enhancements and visit our GitHub to learn more about this month’s release. Improved Maintenance Workflow for Stopped Instances We’ve improved how scheduled maintenance is handled for stopped or disabled PostgreSQL servers. Maintenance is now applied only when the server is restarted - either manually or through the 7-day auto-restart rather than forcing a restart during the scheduled maintenance window. This change reduces unnecessary disruptions and gives you more control over when updates are applied. You may notice a slightly longer restart time (5–8 minutes) if maintenance is pending. For more information, refer Applying Maintenance on Stopped/Disabled Instances. Azure Postgres Learning Bytes 🎓 Set Up HA Health Status Monitoring Alerts This section will talk about setting up HA health status monitoring alerts using Azure Portal. These alerts can be used to effectively monitor the HA health states for your server. To monitor the health of your High Availability (HA) setup: Navigate to Azure portal and select your Azure Database for PostgreSQL flexible server instance. Create an Alert Rule Go to Monitoring > Alerts > Create Alert Rule Scope: Select your PostgreSQL Flexible Server Condition: Choose the signal from the drop down (CPU percentage, storage percentage etc.) Logic: Define when the alert should trigger Action Group: Specify where the alert should be sent (email, webhook, etc.) Add tags Click on “Review + Create” Verify the Alert Check the Alerts tab in Azure Monitor to confirm the alert has been triggered. For deeper insight into resource health: Go to Azure Portal > Search for Service Health > Select Resource Health. Choose Azure Database for PostgreSQL Flexible Server from the dropdown. Review the health status of your server. For more information, check out the HA Health status monitoring documentation guide. Conclusion That’s a wrap for our July 2025 feature updates! Thanks for being part of our journey to make Azure Database for PostgreSQL better with every release. We’re always working to improve, and your feedback helps us do that. 💬 Got ideas, questions, or suggestions? We’d love to hear from you: https://aka.ms/pgfeedback 📢 Want to stay on top of Azure Database for PostgreSQL updates? Follow us here for the latest announcements, feature releases, and best practices: Azure Database for PostgreSQL Blog Stay tuned for more updates in our next blog!Book of Archimedes, Copilot and SharePoint Agents
1. Introduction The Book of Archimedes is a single PDF that contains all posts in the Microsoft Graph Data Connect for SharePoint blog. This includes 40 articles and nearly 400 pages, which is handy for searching for specific keywords quickly across the many articles. The PDF is provided as an attachment to the main MGDC for SharePoint article at https://aka.ms/SharePointData. You can also download it directly from Book of Archimedes. 2. Using the Book with Copilot Beyond searching inside the PDF, you can feed the Book of Archimedes as grounding to your favorite AI tool to get answers to your questions about MGDC for SharePoint. Let's look at an example. You can use this with Copilot or any AI tool that accepts attached files. In my case, I used https://copilot.cloud.microsoft/ to access my work Copilot, the secure and compliant Copilot integrated with my enterprise account. I start with the “+” button and then the “add content” button. Then I used the up-arrow icon to “upload from this device” and selected the local copy of the Book of Archimedes I downloaded earlier. After that, I added my question as a prompt. I tried “What is Project Archimedes?” I got a summary of Microsoft Graph Data Connect for SharePoint, including key scenarios. From there, I could ask any question. If the book contains the answer, Copilot will find it for you. Project Archimedes is the early codename for Microsoft Graph Data Connect for SharePoint. This project aims to deliver rich data assets to OneDrive and SharePoint tenants, enabling them to run their own analytics, derive insights from their data, and understand how they use these products. The data is transferred to an Azure account owned by the tenant, where tools like Azure Synapse, Power BI, or Microsoft Fabric can be used to transform this data into insightful reports and dashboards [1]. Key Scenarios of Project Archimedes: Security: Understanding permissions in SharePoint and OneDrive tenants to ensure content is properly protected. Capacity: Understanding site lifecycle, ownership, and storage used by SharePoint sites and OneDrives. Sync Health: Ensuring users are properly using OneDrive for Business to protect their files by synchronizing them with the cloud [1]. Datasets Provided: Sites: Information about SharePoint sites. Groups: Details about SharePoint groups. Permissions: Information about sharing permissions. Files: Data about files stored in SharePoint and OneDrive. File Actions: Details about actions performed on files. Sync Health: Information about devices running OneDrive Sync. Sync Errors: Details about errors encountered by OneDrive Sync clients [1]. Example Use Cases: Security Scenario: Answering questions about oversharing, external sharing, sensitive data sharing, and permissions. Capacity Scenario: Tracking storage usage, site lifecycle, and identifying large or inactive sites. Sync Health Scenario: Monitoring device health, folder backup status, and sync errors [1]. For more detailed information, you can refer to the Book of Archimedes which contains comprehensive guides, FAQs, and step-by-step instructions related to Microsoft Graph Data Connect for SharePoint [1]. [1]: Book of Archimedes.pdf The more impressive capabilities of Copilot are shown when you ask for something that is not just a direct quote from the Book. For instance, I asked about pricing for a specific scenario: "If a tenant has 1,000 SharePoint sites, how much would it cost to get the SharePoint Sites and SharePoint permissions for that tenant using MGDC?" To estimate the cost of getting the SharePoint Sites and SharePoint Permissions datasets for a tenant using Microsoft Graph Data Connect (MGDC), you can follow these guidelines: Pricing Information: SharePoint Sites and Permissions: The price to pull 1,000 objects from the available MGDC for SharePoint datasets (Sites, Groups, and Permissions) in the US is $0.75, plus the cost for infrastructure like Azure Storage, Azure Data Factory, or Azure Synapse [1]. SharePoint Files: This dataset is billed at $0.75 per 50,000 objects due to its typical high volume [1]. Estimating Costs: Number of Objects: Sites: The number of objects in your SharePoint Sites dataset will be equal to the number of sites in your tenant. Permissions: The average number of SharePoint permissions per site is around 61 [1]. Cost Calculation: Example Calculation: For a tenant with 1,000 sites: Sites Dataset Cost: $0.75 Permissions Dataset Cost: $45.75 Total Cost: $0.75 + $45.75 = $46.50 Additional Costs: Azure Storage: Costs for storing the data in Azure Storage. Azure Synapse: Costs for running pipelines to move the data. For more precise estimates, you can sample the dataset to get a total object count without pulling the entire dataset [1]. [1]: Book of Archimedes.pdf Copilot will also answer questions in other languages. You just ask the question in whatever language you want, and it gets detected… Here’s an example using Brazilian Portuguese. I asked "Quais sĂŁo os datasets que fazem parte do cenário de segurança?" Os datasets que fazem parte do cenário de segurança no Project Archimedes sĂŁo: Sites: Informações sobre os sites do SharePoint. Permissions: Informações sobre as permissões de compartilhamento. Groups: Detalhes sobre os grupos do SharePoint. Esses datasets ajudam a entender se o conteĂşdo está devidamente protegido, respondendo a perguntas como: Está ocorrendo compartilhamento excessivo? Está ocorrendo compartilhamento externo? Dados sensĂveis estĂŁo sendo compartilhados? Quanto compartilhamento ocorre por rĂłtulo de sensibilidade? Dados sensĂveis sĂŁo compartilhados com usuários externos? Quais domĂnios externos estĂŁo sendo compartilhados? Quais sites foram mais compartilhados? Quais nĂveis de compartilhamento estĂŁo sendo usados? Quais permissões um usuário especĂfico possui? Quais extensões de arquivo sĂŁo mais compartilhadas? Quanto compartilhamento ocorre no nĂvel de Web, Pasta, Lista ou Arquivo? Esses datasets sĂŁo fundamentais para garantir a segurança e a conformidade dos dados dentro do ambiente do SharePoint e OneDrive [1]. [1]: Book of Archimedes.pdf 3. Using the Book to create a SharePoint agent You can also use the book to create a SharePoint agent. This will make it easy to ask questions about Microsoft Graph Data Connect for SharePoint without having to upload the PDF every time. To start, upload the Book of Archimedes to a SharePoint document library. Next, select the file and use the option to “create an agent”. That’s it. Your agent is created, and you can start using it immediately. The agent shows up in the document library as a file with the “.agent” extension. You can simply open that file in SharePoint to run the agent. Once you open the agent, it offers you a text box to ask questions. Here is the agent response to “What are the main questions about SharePoint capacity that MGDC for SharePoint can answer?” The Book of Archimedes provides detailed answers to several key questions about SharePoint capacity using Microsoft Graph Data Connect (MGDC). Here are the main questions it addresses: Key Questions about SharePoint Capacity: How much storage is being used by SharePoint sites? This includes understanding the total size of the latest versions of files, previous versions, metadata size, and deleted files in the recycle bin 1. What are the different storage sizes reported for a SharePoint site? Storage Used: Includes all storage, metadata, previous versions, and recycle bins. Total Size: Includes metadata and previous versions but excludes recycle bins. Metadata Size: Storage used by file metadata. Total File Stream Size: Size of the latest versions of files. Previous Versions Size: Size of previous versions of files. Recycle Bin Size: Size of deleted files in the recycle bins 1. How can administrators check the amount of storage being used by SharePoint sites? SharePoint client UX: Viewing storage while using SharePoint as a site user or Site Collection administrator. PowerShell cmdlets: Using command-line tools to query site storage information. SharePoint Admin Center reports: Viewing usage reports in the Admin Center. Microsoft Graph Data Connect: Pulling detailed datasets for SharePoint sites and OneDrives 1. How can administrators create test sites to understand storage reporting tools? Creating different types of test sites (empty site, site with files, site with deleted files, site with previous versions) and analyzing how storage sizes are reported 1. How can administrators estimate Azure costs for MGDC usage? Estimating the number of objects (sites, groups, permissions, files) and understanding the billing rates for different datasets 1. How can administrators use MGDC to run detailed analysis of SharePoint and OneDrive storage metrics? Using detailed data in MGDC to analyze storage metrics and understand the impact of metadata, versions, and deleted files 1. Tools and Templates: Capacity Template: Includes instructions, ARM template, Azure Synapse pipeline template, and Power BI template to help administrators use MGDC datasets for capacity analysis 1. Conclusion: The Book of Archimedes provides comprehensive guidance on leveraging MGDC to gather, store, and analyze SharePoint data, ensuring effective data management and security. It is a valuable resource for administrators and developers working with SharePoint and OneDrive data using MGDC 1. Would you like more specific information on any of these questions or tools? 1: <File>Book of Archimedes</File> As we did with Copilot, you can also ask any question on a topic addressed in the book. You can also use languages other than English. You can experiment with editing the agent to rename it, change the description, add more sources, adjust its behavior, offer sample starter prompts, include specific instructions or even customize with Copilot Studio. Just use the option to "edit the agent". You can also share the agent just like you share any file in SharePoint. You can learn more about SharePoint agents in this YouTube video by Vesa Juvonen: https://www.youtube.com/watch?v=pYvK76SVEv4 4. Conclusion I hope you enjoy using the Book of Archimedes as grounding for your AI tools. As usual, remember that AI tools may make mistakes and you should always double-check the answers you receive. There is also a chance that a particular AI tool might not be able to handle a large document like the Book of Archimedes, currently weighing in at around 10MB.
