address PR feedback

Author: mrbullwinkle

articles/ai-services/openai/how-to/evaluations.md

@@ -5,6 +5,7 @@ description: Learn how to use evaluations with Azure OpenAI
 manager: nitinme
 ms.service: azure-ai-openai
 ms.topic: how-to
+ms.custom: references_regions
 ms.date: 11/10/2024
 author: mrbullwinkle
 ms.author: mbullwin
@@ -124,13 +125,13 @@ Testing criteria is used to assess the effectiveness of each output generated by
 
     You'll see the first three lines of the file as a preview:
 
-    :::image type="content" source="../media/how-to/evaluations/preview.png" alt-text="Screenshot that shows a preview of an uploaded evaluation file" lightbox="../media/how-to/evaluations/preview.png":::
+    :::image type="content" source="../media/how-to/evaluations/preview.png" alt-text="Screenshot that shows a preview of an uploaded evaluation file." lightbox="../media/how-to/evaluations/preview.png":::
 
 5. Select the toggle for **Generate responses**. Select `{{item.input}}` from the dropdown. This will inject the input fields from our evaluation file into individual prompts for a new model run that we want to able to compare against our evaluation dataset. The model will take that input and generate its own unique outputs which in this case will be stored in a variable called `{{sample.output_text}}`. We'll then use that sample output text later as part of our testing criteria. Alternatively you could provide your own custom system message and individual message examples manually.
 
 6. Select which model you want to generate responses based on your evaluation. If you don't have a model you can create one. For the purpose of this example we're using a standard deployment of `gpt-4o-mini`.
 
-    :::image type="content" source="../media/how-to/evaluations/item-input.png" alt-text="Screenshot of the generate responses UX with a model selected." lightbox="../media/how-to/evaluations/item-input.png":::
+    :::image type="content" source="../media/how-to/evaluations/item-input.png" alt-text="Screenshot of the UX for generating model responses with a model selected." lightbox="../media/how-to/evaluations/item-input.png":::
 
     The settings/sprocket symbol controls the basic parameters that are passed to the model. Only the following parameters are supported at this time:
 
@@ -144,7 +145,7 @@ Testing criteria is used to assess the effectiveness of each output generated by
 
 8. Select **Semantic Similarity** >  Under **Compare** add `{{item.output}}` under **With** add ``{{sample.output_text}}``. This will take the original reference output from your evaluation `.jsonl` file and compare it against the output that will be generated by giving the model prompts based on your ``{{item.input}}``.
 
-    :::image type="content" source="../media/how-to/evaluations/semantic-similarity-config.png" alt-text="Screenshot of the semantic similarity UX config" lightbox="../media/how-to/evaluations/semantic-similarity-config.png":::
+    :::image type="content" source="../media/how-to/evaluations/semantic-similarity-config.png" alt-text="Screenshot of the semantic similarity UX config." lightbox="../media/how-to/evaluations/semantic-similarity-config.png":::
 
 9. Select **Add** > at this point you can either add additional testing criteria or you select Create to initiate the evaluation job run.
 
@@ -156,7 +157,7 @@ Testing criteria is used to assess the effectiveness of each output generated by
 
     :::image type="content" source="../media/how-to/evaluations/test-complete.png" alt-text="Screenshot of a completed semantic similarity test with mix of pass and failures." lightbox="../media/how-to/evaluations/test-complete.png":::
 
-12. For semantic similarity **View output details** contains a JSON representation that you can copy/paste of the your passing tests.
+12. For semantic similarity **View output details** contains a JSON representation that you can copy/paste of your passing tests.
 
     :::image type="content" source="../media/how-to/evaluations/output-details.png" alt-text="Screenshot of the evaluation status UX with output details." lightbox="../media/how-to/evaluations/output-details.png":::
 
@@ -253,13 +254,13 @@ Verifies if the output is valid JSON or XML.
 
 Ensures the output follows the specified structure.
 
-:::image type="content" source="../media/how-to/evaluations/matches-schema.png" alt-text="Screenshot of the matches schema testing criteria" lightbox="../media/how-to/evaluations/matches-schema.png":::
+:::image type="content" source="../media/how-to/evaluations/matches-schema.png" alt-text="Screenshot of the matches schema testing criteria." lightbox="../media/how-to/evaluations/matches-schema.png":::
 
 ### Criteria match
 
 Assess if model's response matches your criteria. Grade: Pass or Fail.
 
-:::image type="content" source="../media/how-to/evaluations/criteria-match.png" alt-text="Screenshot of the matches criteria test" lightbox="../media/how-to/evaluations/criteria-match.png":::
+:::image type="content" source="../media/how-to/evaluations/criteria-match.png" alt-text="Screenshot of the matches criteria test." lightbox="../media/how-to/evaluations/criteria-match.png":::
 
 You can view the prompt text that is used as part of this testing criteria by selecting the dropdown next to the prompt. The current prompt text is: