fix: nit

Author: santiagxf

articles/ai-foundry/model-inference/includes/use-structured-outputs/python.md

@@ -239,24 +239,72 @@ except ValidationError as e:
     print(f"Validation error: {e}")
 ```
 
-## Structured outputs in images
+### Specifying an schema
 
-You can use structured outputs with multi-modal models to extract information from data like images. Let's consider the following chart:
+There are some limitations that models may place in schemas definitions. Such limitations may vary per-model. **We recommend reviewing the documentation from the model provider** to verify that your schemas are valid.
 
-:::image type="content" source="../../media/use-structured-outputs/example_graph_treecover.png" alt-text="An example image showing a chart with the annual loss in thousand square kilometers of global tree cover across different climate zones." lightbox="../../media/use-structured-outputs/example_graph_treecover.png":::
+The following guidelines applies to the majority of models:
+
+#### Optional fields
 
-Let's load this image:
+Some models may require all the fields to be in the `required` section of the schema. If you need to use optional fields, use unions with null types to express that a given field can be optional.
 
 ```python
-from azure.ai.inference.models import ImageContentItem, ImageUrl
+from pydantic import BaseModel
+from typing import Literal, Union
 
-image_graph = ImageUrl.load(
-    image_file="example_graph_treecover.png",
-    image_format="png"
-)
+class Issue(BaseModel, extra="forbid"):
+    title: str
+    description: str
+    type: Literal["Bug", "Feature", "Documentation", "Regression"]
+    operating_system: Union[str, None]
 ```
 
-Let's define a generic schema that can be use to encode the information contained in a chart. We use [Pyndatic objects](#use-pydantic-objects) as described before.
+#### Nested types
+
+Models may support indicating nesting types. You can compose complex structures as needed:
+
+```python
+from pydantic import BaseModel
+from typing import Literal
+
+class Project(BaseModel, extra="forbid"):
+    name: str
+    owner: str
+
+class Issue(BaseModel, extra="forbid"):
+    title: str
+    description: str
+    type: Literal["Bug", "Feature", "Documentation", "Regression"]
+    operating_system: str
+    project: Project
+```
+
+Nested types also include recursive definition of types:
+
+```python
+from pydantic import BaseModel
+from typing import Literal, List
+
+class Issue(BaseModel, extra="forbid"):
+    title: str
+    description: str
+    type: Literal["Bug", "Feature", "Documentation", "Regression"]
+    operating_system: str
+    related_issues: List[Issue]
+```
+
+Verify the level of nesting supported by the model you are working with.
+
+## Structured outputs in images
+
+You can use structured outputs with multi-modal models to extract information from data like images. 
+
+Let's consider the following chart:
+
+:::image type="content" source="../../media/use-structured-outputs/example_graph_treecover.png" alt-text="An example image showing a chart with the annual loss in thousand square kilometers of global tree cover across different climate zones." lightbox="../../media/use-structured-outputs/example_graph_treecover.png":::
+
+We can define a generic schema that can be use to encode the information contained in the chart and then use it for further analysis. We use [Pyndatic objects](#use-pydantic-objects) as described before.
 
 ```python
 from pydantic import BaseModel
@@ -275,7 +323,18 @@ class Graph(BaseModel):
     data: list[DataPoint]
 ```
 
-Let's use structured outputs to extract the information:
+We can load the image as follows to pass it to the model:
+
+```python
+from azure.ai.inference.models import ImageContentItem, ImageUrl
+
+image_graph = ImageUrl.load(
+    image_file="example_graph_treecover.png",
+    image_format="png"
+)
+```
+
+Use structured outputs to extract the information:
 
 ```python
 response = client.complete(
@@ -297,7 +356,7 @@ response = client.complete(
 )
 ```
 
-Let's check the outputs:
+It's always a good practice to validate the outputs and schemas:
 
 ```python
 import json
@@ -340,7 +399,7 @@ print(json.dumps(json_response_message, indent=4))
 }
 ```
 
-Let's use `matplotlib` and try to plot the data:
+We can see how much information the model was able to capture by plotting the data using `matplotlib`:
 
 ```python
 import matplotlib.pyplot as plt
@@ -372,59 +431,4 @@ plt.show()
 
 :::image type="content" source="../../media/use-structured-outputs/graph_treecover_plot.png" alt-text="The resulting plot of the data contained in the structured output generated by the model." lightbox="../../media/use-structured-outputs/graph_treecover_plot.png":::
 
-
-### Supported schemas
-
-There are some limitations that models may place in how schemas are defined. When using structure outputs, consider the following limitations. Notice that limitations may vary per model.
-
-#### Optional fields
-
-Some models may require all the fields to be in the `required` section of the schema. If you need to use optional fields, use unions with null types to express that a given field can be optional.
-
-```python
-from pydantic import BaseModel
-from typing import Literal, Union
-
-class Issue(BaseModel, extra="forbid"):
-    title: str
-    description: str
-    type: Literal["Bug", "Feature", "Documentation", "Regression"]
-    operating_system: Union[str, None]
-```
-
-#### Nested types
-
-Models may support indicating nesting types. You can compose complex structures as needed:
-
-```python
-from pydantic import BaseModel
-from typing import Literal
-
-class Project(BaseModel, extra="forbid"):
-    name: str
-    owner: str
-
-class Issue(BaseModel, extra="forbid"):
-    title: str
-    description: str
-    type: Literal["Bug", "Feature", "Documentation", "Regression"]
-    operating_system: str
-    project: Project
-```
-
-Nested types also include recursive definition of types:
-
-```python
-from pydantic import BaseModel
-from typing import Literal, List
-
-class Issue(BaseModel, extra="forbid"):
-    title: str
-    description: str
-    type: Literal["Bug", "Feature", "Documentation", "Regression"]
-    operating_system: str
-    related_issues: List[Issue]
-```
-
-
-[!INCLUDE [supported-schemas](supported-schemas.md)]
+While the information is not perfect, we can see the model was able to capture a good amount of information from the original chart.