Alright folks – we’re going to dive into how you can leverage Azure Cognitive Services with PowerShell to not only set up AI services but also to interact with them. Let’s go!<\/p>\n\n\n\n
Before we begin, ensure you have the following:<\/p>\n\n\n\n
Install-Module -Name Az -AllowClobber<\/code> in your PowerShell session.<\/li>\n<\/ul>\n\n\n\nUse Connect-AZAccount to get into your subscription, then run this to create a new RG and Cognitive Services resource:<\/p>\n\n\n\n
$resourceGroupName = "<YourResourceGroupName>"\n$location = "EastUS"\n$cognitiveServicesName = "<YourCognitiveServicesName>"\n\n# Create a resource group if you haven't already\nNew-AzResourceGroup -Name $resourceGroupName -Location $location\n\n# Create Cognitive Services account\nNew-AzCognitiveServicesAccount -Name $cognitiveServicesName -ResourceGroupName $resourceGroupName -Type "CognitiveServices" -Location $location -SkuName "S0"\n<\/pre><\/div>\n\n\n\nIt’s that simple! <\/p>\n\n\n\n
To interact with Cognitive Services, you’ll need the access keys. Retrieve them with:<\/p>\n\n\n\n
$key = (Get-AzCognitiveServicesAccountKey -ResourceGroupName $resourceGroupName -Name $cognitiveServicesName).Key1\n<\/pre><\/div>\n\n\n\n<\/p>\n\n\n\n
With your Cognitive Services resource set up and your access keys in hand, you can now interact with various cognitive services. Let’s explore a couple of examples:<\/p>\n\n\n\n
Text Analytics<\/h5>\n\n\n\n
To analyze text for sentiment, language, or key phrases, you’ll use the Text Analytics API. Here’s a basic example to detect the language of a given text:<\/p>\n\n\n\n
$text = "Hello, world!"\n$uri = "https:\/\/<YourCognitiveServicesName>.cognitiveservices.azure.com\/text\/analytics\/v3.1\/languages"\n\n$body = @{\n documents = @(\n @{\n id = "1"\n text = $text\n }\n )\n} | ConvertTo-Json\n\n$response = Invoke-RestMethod -Uri $uri -Method Post -Body $body -Headers @{\n "Ocp-Apim-Subscription-Key" = $key\n "Content-Type" = "application\/json"\n}\n\n$response.documents.languages | Format-Table -Property name, confidenceScore<\/pre><\/div>\n\n\n\nSo this code will try and determine the language of the text submitted. The output might look like this:<\/p>\n\n\n\n
Name ConfidenceScore\n---- ---------------\nEnglish 0.99\n<\/pre><\/div>\n\n\n\nLet’s try computer vision now:<\/p>\n\n\n\n
Computer Vision<\/h5>\n\n\n\n
Azure’s Computer Vision service can analyze images and extract information about visual content. Here’s how you can use PowerShell to send an image to the Computer Vision API for analysis:<\/p>\n\n\n\n
$imageUrl = "<YourImageUrl>"\n$uri = "https:\/\/<YourCognitiveServicesName>.cognitiveservices.azure.com\/vision\/v3.1\/analyze?visualFeatures=Description"\n\n$body = @{\n url = $imageUrl\n} | ConvertTo-Json\n\n$response = Invoke-RestMethod -Uri $uri -Method Post -Body $body -Headers @{\n "Ocp-Apim-Subscription-Key" = $key\n "Content-Type" = "application\/json"\n}\n\n$response.description.captions | Format-Table -Property text, confidence\n<\/pre><\/div>\n\n\n\nThis code is trying to describe the image, so the output might look like this – pardon the bad word wrap:<\/p>\n\n\n\n
Text Confidence\n---- ----------\nA scenic view of a mountain range under a clear blue sky 0.98\n<\/pre><\/div>\n\n\n\nTo learn more about Cognitive Services – check out the Docs<\/a>!<\/p>\n\n\n\n<\/p>\n","protected":false},"excerpt":{"rendered":"
Alright folks – we’re going to dive into how you can leverage Azure Cognitive Services with PowerShell to not only set up AI services but also to interact with them. Let’s go! Prerequisites Before we begin, ensure you have the following: Use Connect-AZAccount to get into your subscription, then run this to create a new … Continue reading “Setting Up and Accessing Azure Cognitive Services with PowerShell”<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[26,4,16],"class_list":["post-663","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-ai","tag-azure","tag-powershell"],"_links":{"self":[{"href":"https:\/\/draith.com\/index.php?rest_route=\/wp\/v2\/posts\/663","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/draith.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/draith.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/draith.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/draith.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=663"}],"version-history":[{"count":1,"href":"https:\/\/draith.com\/index.php?rest_route=\/wp\/v2\/posts\/663\/revisions"}],"predecessor-version":[{"id":664,"href":"https:\/\/draith.com\/index.php?rest_route=\/wp\/v2\/posts\/663\/revisions\/664"}],"wp:attachment":[{"href":"https:\/\/draith.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=663"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/draith.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=663"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/draith.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=663"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}