Merge pull request #53956 from GraemeMalcolm/main

Updates to vision modules

Author: JamesJBarnett

learn-pr/wwl-data-ai/analyze-images-with-content-understanding/includes/3-analyze-images-with-content-understanding.md

@@ -63,26 +63,48 @@ Here's an example schema for analyzing product images:
 
 ## Analyze an image
 
-To analyze an image using Content Understanding, submit a POST request to the analyze endpoint with your analyzer ID and the image URL or file:
+To analyze an image using Content Understanding, you can use the Python SDK, which you can install using `pip` like this:
 
 ```bash
-curl -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://example.url/product-image.jpg"
-          }
-        ]
-      }'
+pip install azure-ai-contentunderstanding
 ```
 
-The response includes a result ID that you use to retrieve the analysis results once processing completes.
-
-## Understand the response
+To submit a request to the analyze endpoint with your analyzer ID and the image URL or file, you can use code similar to this example:
+
+```python
+from azure.ai.contentunderstanding import ContentUnderstandingClient
+from azure.ai.contentunderstanding.models import AnalysisInput, AnalysisResult
+from azure.core.credentials import AzureKeyCredential # for key-based authentication
+from azure.identity import DefaultAzureCredential # for Entra ID authentication
+
+# Get a client
+credential = AzureKeyCredential(key)
+client = ContentUnderstandingClient(endpoint={FOUNDRY_ENDPOINT},
+                                    credential={KEY_OR_IDENTITY},
+                                    api_version="2025-11-01")
+
+# Analyze an image file
+with open("my_image.png", "rb") as f:
+            file_bytes = f.read()
+
+try:
+    poller = client.begin_analyze(
+        analyzer_id={ANALYSER_ID},
+        inputs=[AnalysisInput(data=file_bytes)],
+    )
+    # Get results asynchronously from poller
+    result: AnalysisResult = poller.result()
+
+    # Display results
+    result_str = json.dumps(result.as_dict(), indent=2)
+    ret_lines = result_str.splitlines()
+
+except Exception as ex:
+    print(f"[Unexpected Error]: {ex}")
+    sys.exit(1)
+```
 
-When analysis completes, the response includes:
+When analysis completes, the results include the extracted content:
 
 - **markdown**: A text representation of the image content, useful for search and RAG scenarios
 - **fields**: Extracted field values matching your schema, each with a confidence score
@@ -134,4 +156,4 @@ Use confidence scores to build automation workflows that route low-confidence ex
 - **Single focus**: Images with one clear subject yield better results than cluttered scenes
 - **Consistent orientation**: Upright images are processed more reliably than rotated ones
 
-Content Understanding's image analysis capabilities enable you to transform visual content into structured, actionable data for document processing, inventory management, quality inspection, and many other business scenarios.
+Content Understanding's image analysis capabilities enable you to transform visual content into structured, actionable data for document processing, inventory management, quality inspection, and many other business scenarios.

learn-pr/wwl-data-ai/analyze-images-with-content-understanding/includes/4-exercise.md

@@ -1,8 +1,8 @@
-In this exercise, you'll use Azure Content Understanding to analyze images. You start by exploring the prebuilt image analyzer in the Microsoft Foundry portal to see how Content Understanding extracts information from images. Then, you create a Python application that uses the Content Understanding API to analyze images programmatically and extract structured data.
+In this exercise, you'll use Azure Content Understanding to analyze images. First, you create a custom image analyzer in the Microsoft Foundry portal. Then, you create a Python application that uses the Content Understanding API to analyze images programmatically and extract structured data.
 
 > [!NOTE]
 > To complete this exercise, you need an Azure subscription. If you don't have one, you can [sign up for a free account](https://azure.microsoft.com/pricing/purchase-options/azure-account?cid=msft_learn), which includes credits for the first 30 days.
 
 Launch the exercise and follow the instructions.
 
-[![Button to launch exercise.](../media/launch-exercise.png)](https://go.microsoft.com/fwlink/?linkid=2356120&azure-portal=true)
+[![Button to launch exercise.](../media/launch-exercise.png)](https://go.microsoft.com/fwlink/?linkid=2356972&azure-portal=true)

learn-pr/wwl-data-ai/generate-images-azure-openai/1-introduction.yml

@@ -6,11 +6,10 @@ metadata:
   description: Overview of image generation models
   author: ivorb
   ms.author: berryivor
-  ms.date: 05/08/2025
+  ms.date: 03/24/2026
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
 durationInMinutes: 1
 content: |
   [!include[](includes/1-introduction.md)]
-

learn-pr/wwl-data-ai/generate-images-azure-openai/2-what-is-dall-e.yml

@@ -6,11 +6,10 @@ metadata:
   description: Explore what image-generation models are.
   author: ivorb
   ms.author: berryivor
-  ms.date: 05/08/2025
+  ms.date: 03/24/2026
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
 durationInMinutes: 2
 content: |
   [!include[](includes/2-what-is-dall-e.md)]
-

learn-pr/wwl-data-ai/generate-images-azure-openai/3-dall-e-in-openai-studio.yml

@@ -6,12 +6,10 @@ metadata:
   description: Use the Images playground in Microsoft Foundry portal to explore image generation models.
   author: ivorb
   ms.author: berryivor
-  ms.date: 05/08/2025
+  ms.date: 03/24/2026
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
 durationInMinutes: 3
 content: |
   [!include[](includes/3-dall-e-in-openai-studio.md)]
-
-

learn-pr/wwl-data-ai/generate-images-azure-openai/4-dall-e-rest-api.yml

@@ -6,11 +6,10 @@ metadata:
   description: Use APIs and SDKs to consume image generation models.
   author: ivorb
   ms.author: berryivor
-  ms.date: 05/08/2025
+  ms.date: 03/24/2026
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
 durationInMinutes: 3
 content: |
   [!include[](includes/4-dall-e-rest-api.md)]
-

learn-pr/wwl-data-ai/generate-images-azure-openai/5-exercise-use-dall-e.yml

@@ -6,12 +6,10 @@ metadata:
   description: Hands-on exercise to use an image generation model in Microsoft Foundry.
   author: ivorb
   ms.author: berryivor
-  ms.date: 05/08/2025
+  ms.date: 03/24/2026
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
 durationInMinutes: 20
 content: |
   [!include[](includes/5-exercise-use-dall-e.md)]
-
-

learn-pr/wwl-data-ai/generate-images-azure-openai/6-knowledge-check.yml

@@ -6,7 +6,7 @@ metadata:
   description: Check your knowledge of image generation models.
   author: ivorb
   ms.author: berryivor
-  ms.date: 04/29/2025
+  ms.date: 03/24/2026
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
@@ -15,39 +15,25 @@ durationInMinutes: 3
 content: |
 quiz:
   questions:
-  - content: "You want to use a model in Microsoft Foundry to generate images. Which model should you use?"
-    choices:
-    - content: "DALL-E"
-      isCorrect: true
-      explanation: "The DALL-E model is used to generate images based on natural language prompts."
-    - content: "GPT-4o"
-      isCorrect: false
-      explanation: "The GPT 4o model is used to generate natural language text."
-    - content: "text-embedding-ada-002"
-      isCorrect: false
-      explanation: "The text-embedding-ada-002 model is used to generate embeddings (vectors that represent text tokens)."
-  - content: "Which playground in Microsoft Foundry portal should you use to test an image-generation model?"
-    choices:
-    - content: "Agents"
-      isCorrect: false
-      explanation: "The Agents playground is used to test AI agents."
-    - content: "Chat"
-      isCorrect: false
-      explanation: "The Chat playground is used to explore natural language generation models."
-    - content: "Images"
-      isCorrect: true
-      explanation: "The Images playground is used to explore image generation models."
-  - content: "In a REST request to generate images, what does the **n** parameter indicate?"
-    choices:
-    - content: "The description of the desired image."
-      isCorrect: false
-      explanation: "The image description is provided in the **prompt** parameter."
-    - content: "The number of images to be generated"
-      isCorrect: true
-      explanation: "The number of images to be generated is specified in the **n** parameter."
-    - content: "The size of the image to be generated"
-      isCorrect: false
-      explanation: "The size of the desired image is specified in the **size** parameter"
- 
-
-
+    - content: "You want to find a model in Microsoft Foundry to generate images. Which inference task should you filter by?"
+      choices:
+        - content: "Text to image"
+          isCorrect: true
+          explanation: "Text to image models generate images based on natural language prompts."
+        - content: "Image to text"
+          isCorrect: false
+          explanation: "Image to text models generate natural language descriptions based on images."
+        - content: "Embeddings"
+          isCorrect: false
+          explanation: "Embedding models generate vector representations of text or other data, not images."
+    - content: "Which OpenAI API can you use with image-generation models?"
+      choices:
+        - content: "Video"
+          isCorrect: false
+          explanation: "The Video API is used for video-generation tasks, not image generation."
+        - content: "Image"
+          isCorrect: true
+          explanation: "The Image API is used for image-generation tasks."
+        - content: "Graphics"
+          isCorrect: false
+          explanation: "There is no OpenAI Graphics API."

learn-pr/wwl-data-ai/generate-images-azure-openai/7-summary.yml

@@ -6,11 +6,10 @@ metadata:
   description: Summarize what you've learned about image generation models
   author: ivorb
   ms.author: berryivor
-  ms.date: 05/08/2025
+  ms.date: 03/24/2026
   ms.topic: unit
   ms.collection:
     - wwl-ai-copilot
 durationInMinutes: 1
 content: |
   [!include[](includes/7-summary.md)]
-

learn-pr/wwl-data-ai/generate-images-azure-openai/includes/1-introduction.md

@@ -1,10 +1,9 @@
 With Microsoft Foundry, you can use language models to generate content based on natural language prompts. Often the generated content is in the form of natural language text, but increasingly, models can generate other kinds of content.
 
-For example, the OpenAI DALL-E image generation model can create original graphical content based on a description of a desired image.
+For example, the OpenAI *gpt-image-1* model can create original graphical content based on a description of a desired image.
 
 ![Diagram of a prompt requesting a model to create an image.](../media/image-generation.png)
 
 The ability to use AI to generate graphics has many applications; including the creation of illustrations or photorealistic images for articles or marketing collateral, generation of unique product or company logos, or any scenario where a desired image can be described.
 
 In this module, you'll learn how to develop an application that uses generative AI to generate original images.
-