You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-foundry/how-to/develop/trace-application.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -19,7 +19,7 @@ This article explains how to implement tracing for AI applications using OpenAI
19
19
20
20
## Prerequisites
21
21
22
-
Ensure you have the following:
22
+
You need the following to complete this tutorial:
23
23
24
24
* An Azure AI Foundry project created.
25
25
@@ -28,7 +28,7 @@ Ensure you have the following:
28
28
29
29
## Enable tracing in your project
30
30
31
-
Azure AI Foundry stores traces in Azure Application Insight resources using OpenTelemetry. By default, new Azure AI Foundry resources don't provision these resources. You can connect them to an existing Azure Application Insights resource or create a new one from within the project. You only need to do this once per each Azure AI Foundry resource.
31
+
Azure AI Foundry stores traces in Azure Application Insight resources using OpenTelemetry. By default, new Azure AI Foundry resources don't provision these resources. You can connect them to an existing Azure Application Insights resource or create a new one from within the project. You do such configuration once per each Azure AI Foundry resource.
32
32
33
33
The following steps show how to configure:
34
34
@@ -52,13 +52,13 @@ The following steps show how to configure:
52
52
2. By default, the new resource is created in the same resource group where the Azure AI Foundry resource was created. Use the **Advance settings** option to configure a different resource group or subscription.
53
53
54
54
> [!TIP]
55
-
> To create a new Azure Application Insight resource, you also need contributor role to the resource group you have selected (or the default one).
55
+
> To create a new Azure Application Insight resource, you also need contributor role to the resource group you selected (or the default one).
56
56
57
57
3. Select **Create** to create the resource and connect it to the Azure AI Foundry resource.
58
58
59
59
4. Once the connection is configured, you are ready to use tracing in this project.
60
60
61
-
5. Go to the landing page of your project and copy the project's endpoint URI. You'll need it later in the tutorial.
61
+
5. Go to the landing page of your project and copy the project's endpoint URI. You need it later in the tutorial.
62
62
63
63
:::image type="content" source="../../media/how-to/projects/fdp-project-overview.png" alt-text="A screenshot showing how to copy the project endpoint URI." lightbox="../../media/how-to/projects/fdp-project-overview.png":::
64
64
@@ -68,7 +68,7 @@ The following steps show how to configure:
68
68
69
69
## Instrument the OpenAI SDK
70
70
71
-
If you are using the OpenAI SDK to develop intelligent applications you can instrument it so traces are sent to Azure AI Foundry. Follow these steps:
71
+
When developing using the OpenAI SDK you can instrument your code so traces are sent to Azure AI Foundry. Follow these steps:
72
72
73
73
1. Install `azure-ai-projects`, `azure-monitor-opentelemetry`, and `opentelemetry-instrumentation-openai-v2` in your environment. The following example uses `pip`:
74
74
@@ -167,7 +167,7 @@ If you are using the OpenAI SDK to develop intelligent applications you can inst
167
167
return responses
168
168
```
169
169
170
-
1. Then, traces will look as follows:
170
+
1. Traces look as follows:
171
171
172
172
:::image type="content" source="../../media/how-to/develop/trace-application/tracing-display-decorator.png" alt-text="A screenshot showing how a method using a decorator is displayed in the trace." lightbox="../../media/how-to/develop/trace-application/tracing-display-decorator.png":::
0 commit comments