Get started with information extraction in Microsoft Foundry

Azure Content Understanding provides multi-modal analysis of documents, audio files, video, and images to extract information.

In this exercise, you will use Azure Content Understanding in Foundry, Microsoft’s platform for creating intelligent applications, to extract information from invoices. Then you will try out using Azure Content Understanding in Foundry Tools with the REST API.

This exercise takes approximately 40 minutes.

Note: This exercise utilizes the classic Foundry portal experience. If you are using the new Foundry portal, you need to toggle back to classic.

Create a Microsoft Foundry project for content understanding

1. In a web browser, open Microsoft Foundry at https://ai.azure.com and sign in using your Azure credentials. Close any tips or quick start panes that are opened the first time you sign in, and if necessary use the Foundry logo at the top left to navigate to the home page, which looks similar to the following image (close the Help pane if it’s open):

   

2. Scroll to the bottom of the page, and select the Explore Azure AI Services tile.

   

3. On the Azure AI Services page, select Try Content Understanding.

   

4. In the Content Understanding page, select Create a project to start. Then in the Create project dialog, select the recommended resource type (Foundry resource):

   

5. On the Next page, enter a valid name for your project. Then Select Advanced options and specify the following settings:
   • Foundry resource: A valid name for your Foundry resource
   • Subscription: Your Azure subscription
   • Resource group: Create or select a resource group
   • Region: Select one of the following locations*:
     • West US
     • Sweden Central
     • Australia East

   *At the time of writing, Content Understanding is supported in these regions.

   

6. Select Create. Wait for the set up process to complete. It may take a few minutes.

Extract information from an invoice in Foundry portal (classic)

1. On the Content Understanding page, select the Try it out tab, and then select the Invoice Data Extraction tile.

   

   A sample invoice is provided.

2. Select the sample invoice and use the Run analysis button to extract information from it. When analysis is complete, view the results.

   

3. Download contoso-invoice-1.pdf from https://raw.githubusercontent.com/MicrosoftLearning/mslearn-ai-fundamentals/refs/heads/main/data/content-understanding/contoso-invoice-1.pdf.

4. In Foundry, use the Browse for files link to upload the contoso-invoice-1.pdf document you downloaded previously, and run analysis on that file.

   

   Note that the Content Understanding analyzer is able to extract information from this invoice, even though it is formatted diffferently from the sample.

5. In the pane on the right where the extracted fields are displayed, view the Result tab to see the JSON response that would be sent to a client application. A developer would write code to process this response and utilize the extracted fields.

   

   Developers can use the REST API to build an app that submits a document for analysis using a POST operation. For example, the following cUrl command could be used to analyze an invoice:

   curl -i -X POST "{endpoint}/contentunderstanding/analyzers/{analyzerId}:analyze?api-version=2025-11-01" \
      -H "Ocp-Apim-Subscription-Key: {key}" \
      -H "Content-Type: application/json" \
      -d '{
            "inputs":[
              {
                "url": "https://{url_path}/invoice.png"
              }          
            ]
          }'
   

   The analysis is performed asynchronously, so the response includes an id value that can be used to poll for the results:

   {
      "id": {resultId},
      "status": "Running",
      "result": {
        "analyzerId": {analyzerId},
        "apiVersion": "2025-11-01",
        "createdAt": "YYYY-MM-DDTHH:MM:SSZ",
        "warnings": [],
        "contents": []
      }
    }
   

   To retrieve the results using the ID, the client must submit a GET request:

   curl -i -X GET "{endpoint}/contentunderstanding/analyzerResults/{resultId}?api-version=2025-11-01" \
      -H "Ocp-Apim-Subscription-Key: {key}"
   

   Clean up

If you’ve finished working with the Content Understanding service, you should delete the resources you have created in this exercise to avoid incurring unnecessary Azure costs.

• In the Azure portal, delete the resource group you created in this exercise.