Azure Search with OCR without multi-service cognitive services?

Question

I want to create an Azure Search resource with OCR feature.

As far as i know, if you want to create OCRed documents you need to attach key to multi-service cognitive service:

"cognitiveServices": {
    "@odata.type": "#Microsoft.Azure.Search.CognitiveServicesByKey",
    "description": "xyz",
    "key": "xyz"
  },

But in my case, multi-service resource won't work because everyting will work under VNET and multi-service CCS not supporting that.

My question is, how to enrich documents in Azure Search with OCR wihtout using multi-service cognitive service? I know that i can create custom skill that will communicate with Computer Vision in Azure but i want to avoid writing too much code. Are there any possibilities?

Answer 1

We can attach Azure cognitive services resource to a skillset in azure cognitive search. The procedure is explained in the below link document.

The multi-service resource refers to "Cognitive Services" as the offering, rather than independent services, with access granted through a single API key. This key is specified in a skill set and allows Microsoft to charge you for using these APIs:

• Computer Vision (Which you don't want to implement) Link
• Language Services Link
• Translator Link

These operations can be implemented using:

• Azure Portal (This is suggestable approach for the current requirement)
• REST API
• .NET SDK