Ollama on HTTPS for SQL Server
Here is a quick procedure to deploy an Ubuntu container with Ollama and expose its API over HTTPS. The goal is to allow a fast deployment, even for those unfamiliar with Docker or Language Models, making it easy to set up an offline platform for generating embeddings and using Small Language Models This is particularly useful when testing SQL Server 2025 for fully on-premises environment use cases, since SQL Server only allows access to HTTPS endpoints. However, HTTP remains open for testing purposes. Please note that this example is CPU-based, as deploying with (integrated) GPU support involves additional, less straightforward steps. This example is provided solely to illustrate the concept, is not intended for production use, and comes without any guarantee of performance or security. Prerequisites To continue, you need to have Docker Desktop, WSL and SQL Server 2025 (currently Release Candidate 1) Docker Desktop Install WSL | Microsoft Learn SQL Server 2025 Preview | Microsoft Evaluation Center Create a Dockerfile First, create a working directory. In this example, C:\Docker\Ollama will be used. Simply create a file named Dockerfile (without an extension) and paste the following content into it. FROM ubuntu:25.10 RUN apt update && apt install -y curl gnupg2 ca-certificates lsb-release apt-transport-https software-properties-common unzip nano openssl net-tools RUN curl -fsSL https://ollama.com/install.sh | bash RUN curl -1sLf 'https://dl.cloudsmith.io/public/caddy/stable/gpg.key' | gpg --dearmor -o /usr/share/keyrings/caddy-stable-archive-keyring.gpg RUN curl -1sLf 'https://dl.cloudsmith.io/public/caddy/stable/debian.deb.txt' | tee /etc/apt/sources.list.d/caddy-stable.list RUN apt update && apt install -y caddy RUN mkdir -p /etc/caddy/certs RUN cat > /etc/caddy/certs/san.cnf <<EOF [req] default_bits = 2048 prompt = no default_md = sha256 req_extensions = req_ext distinguished_name = dn [dn] CN = 127.0.0.1 [req_ext] subjectAltName = @alt_names [alt_names] IP.1 = 127.0.0.1 DNS.1 = localhost EOF RUN openssl req -x509 -nodes -days 365 -newkey rsa:2048 -keyout /etc/caddy/certs/localhost.key -out /etc/caddy/certs/localhost.crt -config /etc/caddy/certs/san.cnf -extensions req_ext RUN echo "https://:443 {\n tls /etc/caddy/certs/localhost.crt /etc/caddy/certs/localhost.key\n reverse_proxy localhost:11434\n}" >> /etc/caddy/Caddyfile RUN echo "#!/bin/bash" > /usr/local/bin/entrypoint.sh && \ echo "set -e" >> /usr/local/bin/entrypoint.sh && \ echo "OLLAMA_HOST=0.0.0.0 ollama serve >> /var/log/ollama.log 2>&1 &" >> /usr/local/bin/entrypoint.sh && \ echo "caddy run --config /etc/caddy/Caddyfile --adapter caddyfile >> /var/log/caddy.log 2>&1 &" >> /usr/local/bin/entrypoint.sh && \ echo "tail -f /var/log/ollama.log /var/log/caddy.log" >> /usr/local/bin/entrypoint.sh && \ chmod 755 /usr/local/bin/entrypoint.sh ENTRYPOINT ["/usr/local/bin/entrypoint.sh"] For your information, this file allows the creation of an image based on Ubuntu 25.10 and includes: Ollama, for running the models Caddy, for the reverse proxy Creation of a certificate for the HTTPS endpoint on localhost Create the container After opening a Powershell terminal, execute the following commands: cd C:\Docker\Ollama #Build the image from the Dockerfile. docker build -t ollama-https . #Create a container based on the image ollama-https docker run --name ollama-https -d -it -p 443:443 -p 11434:11434 ollama-https #Copy the certificate created into the current Windows directory docker cp ollama-https:/etc/caddy/certs/localhost.crt . # Install the certificate in Trusted Root Certification Authorities Import-Certificate -FilePath "localhost.crt" -CertStoreLocation "Cert:\LocalMachine\Root" #Check Https (wget https://localhost).Content #Check Http (wget http://localhost:11434).Content Ollama is now running With a browser, connect to https://localhost Retrieve Models No model is retrieved when the image is created, as this depends on each use case, and for some models, the size can be substantial. Here’s a quick example for pulling an embedding model, Nomic, and a small language model, Phi3. Ollama Search docker exec ollama-https ollama pull nomic-embed-text docker exec ollama-https ollama pull phi3:mini A quick example with SQL Server 2025 A quick demonstration using the WideWorldImporters database (Wide World Importers sample database) use [master] GO ALTER DATABASE WideWorldImporters SET COMPATIBILITY_LEVEL = 170 WITH ROLLBACK IMMEDIATE GO DBCC TRACEON(466, 474, 13981, -1) GO Note: With RC1, you can use the PREVIEW_FEATURES database-scoped configuration T-SQL Declare an external model for embeddings. use [WideWorldImporters] GO CREATE EXTERNAL MODEL NomicLocal AUTHORIZATION dbo WITH ( LOCATION = 'https://localhost/api/embed', API_FORMAT = 'ollama', MODEL_TYPE = EMBEDDINGS, MODEL = 'nomic-embed-text' ) to enable semantic search capabilities on StockItems, we will create a dedicated table to store embeddings (no chunking in this example) along with a vector index optimized for cosine similarity use [WideWorldImporters] GO CREATE TABLE [Warehouse].[StockItemsEmbedding](StockItemEmbeddingID int identity (1,1) PRIMARY KEY, StockItemId int, SearchDetails nvarchar(max), Embedding vector(768)) GO INSERT INTO [Warehouse].[StockItemsEmbedding] SELECT si.StockItemID, si.SearchDetails, AI_GENERATE_EMBEDDINGS(si.SearchDetails USE MODEL NomicLocal) /* Generate embeddings from declared external model */ FROM [Warehouse].[StockItems] si GO /* Check */ SELECT * FROM [Warehouse].[StockItemsEmbedding] GO CREATE VECTOR INDEX IXV_1 ON [Warehouse].[StockItemsEmbedding] (Embedding) WITH (METRIC = 'cosine', TYPE = 'DiskANN') GO /* User Input */ DECLARE @UserInput varchar(max) = 'Which product is best suited for shipping small items?' /* and Generate embeddings for user input */ DECLARE @UserInputV vector(768) = AI_GENERATE_EMBEDDINGS(@UserInput USE MODEL NomicLocal) DECLARE @ModelInput nvarchar(max) DECLARE AS NVARCHAR (MAX) DECLARE nvarchar(max) /* Similarity Search on StockItems and Model Input creation*/ SELECT @ModelInput = STRING_AGG('ProductDetails: ' + sie.SearchDetails + 'UnitPrice: ' + CAST(si.UnitPrice AS nvarchar(max)), ' \n\n') FROM VECTOR_SEARCH( TABLE = [Warehouse].[StockItemsEmbedding] as sie, COLUMN = Embedding, SIMILAR_TO = @UserInputV, METRIC = 'cosine', TOP_N = 10 ) JOIN [Warehouse].[StockItems] si ON si.StockItemId = sie.StockItemId /* Generate payload for response generation */ SELECT = '{"model": "phi3:mini", "stream": false, "prompt":"You are acting as a customer advisor responsible for recommending the most suitable products based on customer needs, providing clear and personalized suggestions. Question : ' + @UserInput + '\n\nList of Items : ' + @ModelInput + '"}'; EXECUTE sp_invoke_external_rest_endpoint @url = 'https://localhost/api/generate', @method = 'POST', = , @timeout = 230, = OUTPUT; PRINT JSON_VALUE(@response, '$.result.response') LangChain You can also have a try with LangChain. Same demo with a small difference, there is no vector index created on the vector store table. The table has been modified, but only for demonstration purposes. Reference: SQLServer | 🦜️🔗 LangChain # PREREQ #sudo apt-get update && sudo apt-get install -y unixodbc # sudo apt-get update # sudo apt-get install -y curl gnupg2 # curl https://packages.microsoft.com/keys/microsoft.asc | sudo apt-key add - # curl https://packages.microsoft.com/config/debian/11/prod.list | sudo tee /etc/apt/sources.list.d/mssql-release.list # sudo apt-get update # sudo ACCEPT_EULA=Y apt-get install -y msodbcsql18 # pip3 install langchain langchain-sqlserver langchain-ollama langchain-community import pyodbc from langchain_sqlserver import SQLServer_VectorStore from langchain_ollama import OllamaEmbeddings from langchain_ollama import ChatOllama from langchain.schema import Document from langchain_community.vectorstores.utils import DistanceStrategy #Prompt for testing _USER_INPUT = 'Which product is best suited for shipping small items?' ############### Params ########################################## print("\033[93mSetting up variables...\033[0m") _SQL_DRIVER = "ODBC Driver 18 for SQL Server" _SQL_SERVER = "localhost\\SQL2K25" _SQL_DATABASE = "WideWorldImporters" _SQL_USERNAME = "lc" _SQL_PASSWORD = "lc" _SQL_TRUST_CERT = "yes" _SQL_VECTOR_STORE_TABLE = "StockItem_VectorStore" # Table name for vector storage _MODIFY_TABLE_TO_USE_SQL_VECTOR_INDEX = True #As vector index not considered currently in langchain and structure does not match vector index requirements _CONNECTION_STRING = f"Driver={{{_SQL_DRIVER}}};Server={_SQL_SERVER};Database={_SQL_DATABASE};UID={_SQL_USERNAME};PWD={_SQL_PASSWORD};TrustServerCertificate={_SQL_TRUST_CERT}" _OLLAMA_API_URL = "https://localhost" _OLLAMA_EMBEDDING_MODEL = "nomic-embed-text:latest" _OLLAMA_EMBEDDING_VECTOR_SIZE = 768 _OLLAMA_SLM_MODEL = "phi3:mini" # Model for SLM queries ################################################################### #Define Ollama embeddings embeddings = OllamaEmbeddings( model=_OLLAMA_EMBEDDING_MODEL, base_url=_OLLAMA_API_URL ) conn = pyodbc.connect(_CONNECTION_STRING) cursor = conn.cursor() #Drop embeddings table if it exists print("\033[93mDropping existing vector store table if it exists...\033[0m") cursor.execute(f"DROP TABLE IF EXISTS Warehouse.{_SQL_VECTOR_STORE_TABLE};") print("\033[93mConnecting to SQL Server and fetching data...\033[0m") cursor.execute("SELECT StockItemId, SearchDetails, UnitPrice FROM Warehouse.StockItems;") rows = cursor.fetchall() print(f"\033[93mFound {len(rows)} records to process\033[0m") # Create documents from the fetched data documents = [ Document( page_content=row.SearchDetails, metadata={ "StockItemId": row.StockItemId, "UnitPrice": float(row.UnitPrice) # Convert Decimal to float } ) for row in rows ] conn.commit() #Creating vector store print("\033[93mCreating vector store...\033[0m") vector_store = SQLServer_VectorStore( connection_string=_CONNECTION_STRING, distance_strategy=DistanceStrategy.COSINE, # If not provided, defaults to COSINE embedding_function=embeddings, embedding_length=_OLLAMA_EMBEDDING_VECTOR_SIZE, db_schema = "Warehouse", table_name=_SQL_VECTOR_STORE_TABLE ) print("\033[93mAdding to vector store...\033[0m") try: vector_store.add_documents(documents) print("\033[93mSuccessfully added to vector store!\033[0m") except Exception as e: print(f"\033[91mError adding documents: {e}\033[0m") #Vector index not yet integrated in SQL Server VectorStore (drop auto-created nonclustered PK and generating int clustered PK if (_MODIFY_TABLE_TO_USE_SQL_VECTOR_INDEX): print("\033[93mModifying structure to create vector index...\033[0m") cursor.execute("DECLARE @AutoCreatedPK sysname, @SQL nvarchar(max);" f"SELECT @AutoCreatedPK = name FROM sys.key_constraints WHERE type = 'PK' AND parent_object_id = object_id('Warehouse.{_SQL_VECTOR_STORE_TABLE}');" f"SELECT @SQL = 'ALTER TABLE Warehouse.{_SQL_VECTOR_STORE_TABLE} DROP CONSTRAINT ' + @AutoCreatedPK + ';'" "EXEC sp_executesql @SQL;" f"ALTER TABLE Warehouse.{_SQL_VECTOR_STORE_TABLE} ADD Alt_Id int identity(1,1);" f"ALTER TABLE Warehouse.{_SQL_VECTOR_STORE_TABLE} ADD CONSTRAINT PK_{_SQL_VECTOR_STORE_TABLE} PRIMARY KEY (Alt_Id);") conn.commit() print("\033[93mCreating vector index...\033[0m") cursor.execute(f"CREATE VECTOR INDEX IV_{_SQL_VECTOR_STORE_TABLE} ON [Warehouse].[{_SQL_VECTOR_STORE_TABLE}] (embeddings) WITH (METRIC = 'cosine', TYPE = 'DiskANN');") conn.commit() #Generate prompt then answer print(f"\033[92mUser Input: {_USER_INPUT}\033[0m") context = [ { "Item": doc.page_content, "UnitPrice": doc.metadata.get("UnitPrice", None) } for doc in vector_store.similarity_search(_USER_INPUT, k=3) ] llm = ChatOllama(model=_OLLAMA_SLM_MODEL,base_url=_OLLAMA_API_URL) prompt = ( f"You are acting as a customer advisor responsible for recommending the most suitable products based on customer needs, providing clear and personalized suggestions" f"Context: {context}\n\nQuestion: {_USER_INPUT}\n\n") response = llm.invoke(prompt) print(f"\033[36m{response.content}\033[0m") Note : If using devcontainer with VSCode add "runArgs": [ "--network=host" ] to devcontainer.json to allow connections to “localhost”. Import and install the previously created certificat docker cp C:\Docker\Ollama\localhost.crt <devcontainer name>:/usr/local/share/ca-certificates/localhost.crt docker exec <devcontainer name> "update-ca-certificates" Disclaimer The sample scripts are not supported under any Microsoft standard support program or service. The sample scripts are provided AS IS without warranty of any kind. Microsoft further disclaims all implied warranties including, without limitation, any implied warranties of merchantability or of fitness for a particular purpose. The entire risk arising out of the use or performance of the sample scripts and documentation remains with you. In no event shall Microsoft, its authors, or anyone else involved in the creation, production, or delivery of the scripts be liable for any damages whatsoever (including, without limitation, damages for loss of business profits, business interruption, loss of business information, or other pecuniary loss) arising out of the use of or inability to use the sample scripts or documentation, even if Microsoft has been advised of the possibility of such damages.
Creating Azure SQL VM with same name as VM
Hi, Currently we have a resource group, which contains a Virtual Machine and SQL Virtual Machine (and a few other resources). The VM and SQL VM has the same name: I want to move this resource group (and its resources) to another subscription. We tried using Resource Mover, but we couldn't as there are backups. I tried the steps in the following link: https://petri.com/copy-azure-vm-using-managed-disk-snapshots/ I was successful in moving 5 of the 6 resources to the new subscription, but was unable to move the SQL virtual machine: I tried to create a SQL virtual machine, but it says I can't create one with the same name: I found that in order to create a VM and SQL VM's with the same name, in the above image, I have to choose an image that has SQL Server and Windows. But this doesn't allow me to use the original managed disk (it only has an OS disk) and it also creates a couple of more disks, which are not in the original resource group. I was wondering if there are recommendations on how to create a SQL VM that has the same name as the VM in the same resource group and are also linked to each other. Jason
SSMS 21/22 Error Upload BACPAC file to Azure Storage
Hello All In my SSMS 20, I can use "Export Data-tier Application" to export an BACPAC file of Azure SQL database and upload to Azure storage in the same machine, the SSMS 21 gives error message when doing the same export, it created the BACPAC files but failed on the last step, "Uploading BACPAC file to Microsoft Azure Storage", The error message is "Could not load file or assembly 'System.IO.Hashing, Version=6.0.0.0, Culture=neutral, PublicKeyToken=cc7b13ffcd2ddd51' or one of its dependencies. The system cannot find the file specified. (Azure.Storage.Blobs)" I tried the fresh installation of SSMS 21 in a brand-new machine (Windows 11), same issue, Can anyone advice? Thanks
Setting up SQL Managed Instance Link to an Availability Group (Updated September 2025)
On a recent case, a customer was trying to set up SQL Managed Instance Link to partner with an on premise Always On Availability Group (AG). Using the public documentation will work, but there are some differences required to ensure a failover does not break the connection. Please note that Managed Instance Link can only be created with an availability group with a single database. This post will be using steps from the following documents. Prepare your environment for a link - Azure SQL Managed Instance Configure link with scripts - Azure SQL Managed Instance The steps to set this up are below Create a database master key on the AG nodes Enabling trace flags on the AG nodes (Optional) Testing network connectivity between SQL Managed Instance and the AG Create certificates on the AG nodes Import AG certificate public keys to SQL Managed Instance Import the certificate public key of the SQL Managed Instance to AG nodes Import Azure-trusted root certificate authority keys to AG nodes Alter the mirroring endpoint on AG nodes Create a distributed availability group on AG Set up the managed Instance Link Create a database master key Firstly, a master encryption key is required on all nodes of the AG if it does not already exist. The script below will not return any rows if it does not exist. -- Run on SQL Server USE master; GO SELECT * FROM sys.symmetric_keys WHERE name LIKE '%DatabaseMasterKey%'; If no rows are returned, the following query can be used. Keep a note of the passwords in a confidential and secure place. -- Run on SQL Server -- Create a master key USE master; GO CREATE MASTER KEY ENCRYPTION BY PASSWORD = '<strong_password>'; Enabling trace flags on AG nodes (Optional) To optimise the performance of the link, we recommend enabling the trace flags T1800 and T9567 on all nodes. Instructions on this are here and will require a restart of the service. Testing network connectivity between SQL Managed Instance and the AG Instructions on how to run the connectivity tests can be found here, and can be done by SSMS GUI or T-SQL. For these tests, the SQL Managed Instance will need to be able to connect to the Mirror endpoint using the IP of the availability group. The SQL Managed Instance IPs can can change (for example during maintenance). For that reason NSG and firewall rules should allow access to ports 5022 and 11000-11999 for the whole subnet range of the SQL Managed Instance. Create certificates on AG nodes The below query will need to be run on all AG nodes. Pay particular attention to the @cert_expiry_date variable to ensure it is a date in the future. It will need to be replaced after expiry. -- Create the SQL Server certificate for the instance link USE MASTER -- Customize SQL Server certificate expiration date by adjusting the date below DECLARE @cert_expiry_date AS varchar(max)='03/30/2025' -- Build the query to generate the certificate DECLARE @sqlserver_certificate_name NVARCHAR(MAX) = N'Cert_' + @@servername + N'_endpoint' DECLARE @sqlserver_certificate_subject NVARCHAR(MAX) = N'Certificate for ' + @sqlserver_certificate_name DECLARE @create_sqlserver_certificate_command NVARCHAR(MAX) = N'CREATE CERTIFICATE [' + @sqlserver_certificate_name + '] ' + char (13) + ' WITH SUBJECT = ''' + @sqlserver_certificate_subject + ''',' + char (13) + ' EXPIRY_DATE = '''+ @cert_expiry_date + ''''+ char (13) IF NOT EXISTS (SELECT name from sys.certificates WHERE name = @sqlserver_certificate_name) BEGIN PRINT (@create_sqlserver_certificate_command) -- Execute the query to create SQL Server certificate for the instance link EXEC sp_executesql @stmt = @create_sqlserver_certificate_command END ELSE PRINT 'Certificate ' + @sqlserver_certificate_name + ' already exists.' GO Import AG certificate public keys to SQL Managed Instance The public keys of the AG certificates need to be imported into the SQL Managed Instance. The below query will return the data required for the next step. -- Run on SQL Server -- Show the name and the public key of generated SQL Server certificate USE MASTER GO DECLARE @sqlserver_certificate_name NVARCHAR(MAX) = N'Cert_' + @@servername + N'_endpoint' DECLARE @PUBLICKEYENC VARBINARY(MAX) = CERTENCODED(CERT_ID(@sqlserver_certificate_name)); SELECT @sqlserver_certificate_name as 'SQLServerCertName' SELECT @PUBLICKEYENC AS SQLServerPublicKey; Example result The next step will need to be run in PowerShell and can be run through Azure Cloud Shell. Below is an example script to log in to Azure. # Run in Azure Cloud Shell (select PowerShell console) # Enter your Azure subscription ID $SubscriptionID = "<subscriptionid>" # Login to Azure and select subscription ID if ((Get-AzContext ) -eq $null) { echo "Logging to Azure subscription" Login-AzAccount } Select-AzSubscription -SubscriptionName $SubscriptionID Replace the values of $CertificateName, $PublicKeyEncoded and $ManagedInstanceName and then run this. # Run in Azure Cloud Shell (select PowerShell console) # =============================================================================== # POWERSHELL SCRIPT TO IMPORT SQL SERVER PUBLIC CERTIFICATE TO SQL MANAGED INSTANCE # ===== Enter user variables here ==== # Enter the name for the server SQLServerCertName certificate – for example, "Cert_sqlserver1_endpoint" $CertificateName = "<sqlservercertname>" # Insert the certificate public key blob that you got from SQL Server – for example, "0x1234567..." $PublicKeyEncoded = "<sqlserverpublickey>" # Enter your managed instance short name – for example, "sqlmi" $ManagedInstanceName = "<managedinstancename>" # ==== Do not customize the below cmdlets==== # Find out the resource group name $ResourceGroup = (Get-AzSqlInstance -InstanceName $ManagedInstanceName).ResourceGroupName # Upload the public key of the authentication certificate from SQL Server to Azure. New-AzSqlInstanceServerTrustCertificate -ResourceGroupName $ResourceGroup -InstanceName $ManagedInstanceName -Name $CertificateName -PublicKey $PublicKeyEncoded Repeat this step for all AG node values. Import the certificate public key of SQL Managed Instance to AG nodes Using the same PowerShell session, run this script to get the public key of the SQL Managed Instance certificate, replacing the value of the variable $ManagedInstanceName. # Run in Azure Cloud Shell (select PowerShell console) # =============================================================================== # POWERSHELL SCRIPT TO EXPORT MANAGED INSTANCE PUBLIC CERTIFICATE # ===== Enter user variables here ==== # Enter your managed instance short name – for example, "sqlmi" $ManagedInstanceName = "<managedinstancename>" # ==== Do not customize the following cmdlet ==== # Find out the resource group name $ResourceGroup = (Get-AzSqlInstance -InstanceName $ManagedInstanceName).ResourceGroupName # Fetch the public key of the authentication certificate from Managed Instance. Outputs a binary key in the property PublicKey. Get-AzSqlInstanceEndpointCertificate -ResourceGroupName $ResourceGroup -InstanceName $ManagedInstanceName -EndpointType "DATABASE_MIRRORING" | out-string</managedinstancename> On all nodes of the AG run the following query, replacing the certificate name and the value of the PublicKey with the output from the previous step. -- Run on SQL Server USE MASTER CREATE CERTIFICATE [<managedinstancefqdn>] FROM BINARY = <publickey></publickey></managedinstancefqdn> Import Azure-trusted root certificate authority keys to AG nodes Use the steps here to import the Microsoft PKI root-authority certificate and DigiCert PKI root-authority certificate onto all nodes of the AG. Alter the mirroring endpoint on AG nodes The mirroring endpoint on the AG nodes will also need to be updated to allow the Managed Instance to authenticate with the AG using the newly created certificate. This can be done by navigating to Server Objects > Endpoints > Database Mirroring. Right click on the endpoint and select Script Endpoint as > CREATE To > New Query Editor Window. Change CREATE ENDPOINT to ALTER ENDPOINT and add this command after AUTHENTICATION = WINDOWS NEGOTIATE CERTIFICATE, changing the cert_name value. CERTIFICATE [cert_name] Once updated, execute the query. For multiple Availability groups on the same instance, the next section would need to be repeated for each one. Create a distributed availability group on the AG (running against the primary server) Use this script to set up the distributed availability group, updating the sections in angle brackets (<>). The SQLServerIP will need to be the IP of the listener of the availability group. -- Run on SQL Server -- Create a distributed availability group for the availability group and database -- ManagedInstanceName example: 'sqlmi1' -- ManagedInstanceFQDN example: 'sqlmi1.73d19f36a420a.database.windows.net' USE MASTER CREATE AVAILABILITY GROUP [<dagname>] WITH (DISTRIBUTED) AVAILABILITY GROUP ON N'<agnameonsqlserver>' WITH ( LISTENER_URL = 'TCP://<sqlserverip>:<endpointport>', AVAILABILITY_MODE = ASYNCHRONOUS_COMMIT, FAILOVER_MODE = MANUAL, SEEDING_MODE = AUTOMATIC, SESSION_TIMEOUT = 20 ), N'<agnameonsqlmi>' WITH ( LISTENER_URL = 'tcp://<managedinstancefqdn>:5022;Server=[<managedinstancename>]', AVAILABILITY_MODE = ASYNCHRONOUS_COMMIT, FAILOVER_MODE = MANUAL, SEEDING_MODE = AUTOMATIC ); GO</managedinstancename></managedinstancefqdn></agnameonsqlmi></endpointport></sqlserverip></agnameonsqlserver></dagname> Set up the managed Instance Link The final step is to set up the link, the script for this is here. Please ensure that the $SQLServerIP is the IP of the AG listener and not the IP of the primary node. Once this is executed, the MI Link should be up and running and failing over to another node on the AG will not stop MI Link from syncing. Disclaimer Please note that products and options presented in this article are subject to change. This article reflects MI Link and the documentation in September 2025. I hope this article was helpful for you, please feel free to share your feedback in the comments section.
SQL Server 2022 Express Install Issues
I am a non tech savvy student trying to install SQL Server 2022 Express for class and I am running into issues, looking for help. It gets all the way through the install process and gives me "Unable to install SQL Server (setup.exe) Exit code (Decimal): -2061893606Error description: Wait in the Database Engine recovery handle Failed. Check the SQL Server error log for potential causes" and C:\Program Files\Microsoft SQL Server\160\Setup Bootstrap\Log\20250903_162628 I have fully uninstalled anything related to SQL and reinstalled multiple times with no success. I reset windows, no luck. Any help would be appreciated.Using Copilot (GPT-5) to turn schema into SQL and write queries
This article shows a few ways you can use Copilot to help with Microsoft Graph Data Connect for SharePoint. This includes turning a schema into a SQL CREATE TABLE statement and summarizing data from that. Make sure to use the Copilot option to use GPT-5 for best results. Scenario 1 This first scenario just builds a CREATE TABLE statement from the dataset schema definition in markdown notation. I provide a few instructions on how to handle the flattening of the objects. Me: Given the schema at this URL: https://github.com/microsoftgraph/dataconnect-solutions/blob/main/Datasets/data-connect-dataset-sharepointsites.md, give me a CREATE TABLE statement for a SQL Server. Just include the single SQL command in the output. Each column should have a comment with a short description. Don't include any information about keys or constraints. This dataset is flattened. One column in the table for every row, except those of type object. Column names to be flattened with a prefix. Use an underline to separate the prefix. Copilot: CREATE TABLE SharePointSites ( ptenant NVARCHAR(255) -- Id of the tenant ,Id NVARCHAR(255) -- GUID of the site ,Url NVARCHAR(2048) -- URL for the site ,ArchiveState NVARCHAR(50) -- Archive state of the site: None, Archiving, Archived, or Reactivating ,SiteArchivedBy NVARCHAR(255) -- Who archived the site, null if not archived ,SiteArchivedTime DATETIME -- When the site was archived, null if not archived ,RootWeb_Id NVARCHAR(255) -- Root web id ,RootWeb_Title NVARCHAR(512) -- Root web title ,RootWeb_WebTemplate NVARCHAR(255) -- Root web template name ,RootWeb_WebTemplateId INT -- Root web template id ,RootWeb_Configuration INT -- Root web template configuration id ,RootWeb_LastItemModifiedDate DATETIME -- Date when an item in the root web was last modified ,WebCount BIGINT -- Number of webs (subsites) in the site ,StorageQuota BIGINT -- Total storage in bytes allowed for this site ,StorageUsed BIGINT -- Total storage in bytes used by this site ,StorageMetrics_MetadataSize BIGINT -- Total metadata size for the site in bytes ,StorageMetrics_TotalFileCount BIGINT -- Total number of files for the site ,StorageMetrics_TotalFileStreamSize BIGINT -- Total size of latest version of files in bytes ,StorageMetrics_AdditionalFileStreamSize BIGINT -- Total size of additional file streams in bytes ,StorageMetrics_TotalSize BIGINT -- Total size of all files for the site in bytes ,GroupId NVARCHAR(255) -- Id of the group associated with this site ,GeoLocation NVARCHAR(50) -- Geographic region where the data is stored ,IsInRecycleBin BIT -- Indicates if the site is in the recycle bin ,RecycleBinItemCount BIGINT -- Number of items in the recycle bin ,RecycleBinItemSize BIGINT -- Size of items in the recycle bin ,SecondStageRecycleBinStorageUsage BIGINT -- Size of items in the second stage recycle bin ,IsTeamsConnectedSite BIT -- Indicates if the site is connected to Teams ,IsTeamsChannelSite BIT -- Indicates if the site is a channel site ,TeamsChannelType NVARCHAR(50) -- Type of channel if site is a Teams channel site ,IsHubSite BIT -- Indicates if the site is associated with a hub site ,HubSiteId NVARCHAR(255) -- Id of the hub site for this site ,IsCommunicationSite BIT -- Indicates if the site is a communication site ,IsOneDrive BIT -- Indicates if the site is a OneDrive ,BlockAccessFromUnmanagedDevices BIT -- Site blocks access from unmanaged devices ,BlockDownloadOfAllFilesOnUnmanagedDevices BIT -- Site blocks download of all files from unmanaged devices ,BlockDownloadOfViewableFilesOnUnmanagedDevices BIT -- Site blocks download of viewable files from unmanaged devices ,ShareByEmailEnabled BIT -- Site enables share by e-mail ,ShareByLinkEnabled BIT -- Site enables share by link ,IsExternalSharingEnabled BIT -- Indicates if external sharing is enabled ,SiteConnectedToPrivateGroup BIT -- Indicates if site is connected to a Private Group ,Privacy NVARCHAR(50) -- Privacy of the site: Private or Public ,SensitivityLabelInfo_Id NVARCHAR(255) -- Id of the Sensitivity Label for the site ,SensitivityLabelInfo_DisplayName NVARCHAR(255) -- Display name of the Sensitivity Label for the site ,Classification NVARCHAR(255) -- Classification of the site ,IBMode NVARCHAR(50) -- Information Barriers Mode ,IBSegments NVARCHAR(MAX) -- List of organization segments if IB mode is Explicit ,Owner_AadObjectId NVARCHAR(255) -- AAD Object Id of the owner ,Owner_Email NVARCHAR(320) -- Email of the owner ,Owner_UPN NVARCHAR(320) -- User Principal Name of the owner ,Owner_Name NVARCHAR(255) -- Name of the owner ,SecondaryContact_AadObjectId NVARCHAR(255) -- AAD Object Id of the secondary contact ,SecondaryContact_Email NVARCHAR(320) -- Email of the secondary contact ,SecondaryContact_UPN NVARCHAR(320) -- User Principal Name of the secondary contact ,SecondaryContact_Name NVARCHAR(255) -- Name of the secondary contact ,ReadLocked BIT -- Whether the site is locked for read access ,ReadOnly BIT -- Whether the site is in read-only mode ,CreatedTime DATETIME -- When the site was created (UTC) ,LastSecurityModifiedDate DATETIME -- When security on the site was last changed (UTC) ,LastUserAccessDate DATETIME -- Last access by a real user (UTC) ,LastContentChange DATETIME -- When the site contents were last changed (UTC) ,SnapshotDate DATETIME -- When this site information was captured (UTC) ,Operation NVARCHAR(50) -- Extraction mode of this row ); Scenario 2 Now I use the CREATE TABLE as the base to ask for a SELECT statement. Me: Give me a list of sites that have more than 5GB of files. Give me a single SQL statement using the tables described below. <create table statements included here> Copilot: SELECT Id AS SiteId, Url AS SiteUrl, RootWeb_Title AS SiteTitle, StorageMetrics_TotalSize AS TotalSizeInBytes, CAST(StorageMetrics_TotalSize / (1024.0 * 1024 * 1024) AS DECIMAL(10,2)) AS TotalSizeInGB FROM SharePointSites WHERE StorageMetrics_TotalSize > (5 * 1024 * 1024 * 1024) ORDER BY StorageMetrics_TotalSize DESC; Note: Interesting choice of columns and order, without any specific prompting to that effect. Scenario 3 Now for a more challenging scenario using two tables and a more complex requirement. Me: Given the tables below, write a SELECT statement to give me a list of sites with the name of the site, the total storage size and the top 3 file extensions by size. <create table statements for Sites and Files included here> Copilot: WITH ExtensionTotals AS ( SELECT f.SiteId, f.Extension, SUM(f.SizeInBytes) AS TotalSize FROM SharePointFiles f WHERE f.Extension IS NOT NULL GROUP BY f.SiteId, f.Extension ), RankedExtensions AS ( SELECT et.SiteId, et.Extension, et.TotalSize, ROW_NUMBER() OVER (PARTITION BY et.SiteId ORDER BY et.TotalSize DESC) AS rn FROM ExtensionTotals et ), TopExtensions AS ( SELECT SiteId, STRING_AGG(Extension + ' (' + CAST(TotalSize AS VARCHAR(20)) + ')', ', ') WITHIN GROUP (ORDER BY TotalSize DESC) AS Top3Extensions FROM RankedExtensions WHERE rn <= 3 GROUP BY SiteId ) SELECT s.RootWeb_Title AS SiteName, s.StorageMetrics_TotalSize AS TotalStorageSize, te.Top3Extensions FROM SharePointSites s LEFT JOIN TopExtensions te ON s.Id = te.SiteId ORDER BY s.StorageMetrics_TotalSize DESC; Notes: Scenario is nicely handled, using both the Files and Sites tables. Complex aggregation is coded correctly. Scenario 4 In this one, I skip the step of using a SQL CREATE TABLE statement and go directly from the markdown for the two schemas (Sites and Files) to a SQL SELECT statement. I also let GPT-5 add his comments and notes this time, to make sure it's thinking correctly... Me: Consider a SQL table for SharePoint Sites based on the schema at https://github.com/microsoftgraph/dataconnect-solutions/blob/main/Datasets/data-connect-dataset-sharepointsites.md - This dataset is flattened. There is one column in the SQL table for every row, except those of type object. Column names are flattened with a prefix. Column names use an underline to separate the prefix. Also consider a SQL table for SharePoint Files based on the schema at https://github.com/microsoftgraph/dataconnect-solutions/blob/main/Datasets/data-connect-dataset-sharepointfiles.md - Use the same assumptions as the previous one. Now write a SELECT statement to give me a list of sites with the name of the site, the total storage size and the top 3 file extensions by size. Copilot: Got it — you want to join the flattened SharePoint Sites table with the flattened SharePoint Files table, aggregate storage usage, and then find the top 3 file extensions by size for each site. Here’s a SQL example that works with the flattened column naming convention you described: WITH FileSizeByExtension AS ( SELECT f.SiteId, f.Extension, SUM(f.SizeInBytes) AS TotalExtensionSize FROM SharePointFiles f GROUP BY f.SiteId, f.Extension ), RankedExtensions AS ( SELECT SiteId, Extension, TotalExtensionSize, ROW_NUMBER() OVER (PARTITION BY SiteId ORDER BY TotalExtensionSize DESC) AS rn FROM FileSizeByExtension ), Top3Extensions AS ( SELECT SiteId, STRING_AGG(Extension, ', ' ORDER BY TotalExtensionSize DESC) AS TopExtensions FROM RankedExtensions WHERE rn <= 3 GROUP BY SiteId ) SELECT s.RootWeb_Title AS SiteName, s.StorageMetrics_TotalSize AS TotalStorageBytes, t.TopExtensions FROM SharePointSites s LEFT JOIN Top3Extensions t ON s.Id = t.SiteId ORDER BY s.StorageMetrics_TotalSize DESC; How it works FileSizeByExtension: Groups files by SiteId and Extension to sum their sizes. RankedExtensions: Uses ROW_NUMBER() to rank extensions by size within each site. Top3Extensions: Filters to the top 3 per site and concatenates them into a comma-separated list. Final SELECT: Joins back to the Sites table to get the site name and total storage size. Notes RootWeb_Title comes from flattening the RootWeb object in the Sites dataset. StorageMetrics_TotalSize is the flattened column for total site storage (excluding recycle bin). STRING_AGG works in SQL Server 2017+, Azure SQL, and some other RDBMS. If your SQL dialect doesn’t support it, you’d need a different aggregation method. This query orders sites by total storage size so the largest sites appear first. Note: Nicely done in one prompt with the proper explanations. Conclusion I hope these examples help you see the potential of getting Copilot's help with your queries. This is one more reason to load your MGDC for SharePoint tables directly into Microsoft Fabric, where you can run SQL queries against tables in the OneLake...To call a VBA script from a T-SQL procedure
I have the following (unusual) task: I need my T-SQL procedure to somehow call a VBA script. The VBA should copy all content of a certain sheet of an input Excel file into a certain sheet of an output Excel file. The physical full path of the input Excel file is available only in the T-SQL procedure. Therefore, the procedure should somehow pass the file path into the VBA script. How can I do that?
adding computed column to MS SQL
would like to check how to add a computed column with the following requirement Column value will be C-yyyyMMdd-0001 where date will be from the CreatedDate column in the same table. 0001 is an auto-incremental value based on when the record is inserted on the same day eg, the first record added on 23/08/2025, the computed column will be C-20250823-0001. As the table may already contain existing data, a SQL script may also be necessary to update this new column with the correct value.
