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
Tracing is a powerful tool that offers developers an in-depth understanding of the execution process of their generative AI applications. It provides a detailed view of the execution flow, including the inputs and outputs of each node within the application. This essential information proves critical while debugging complex applications or optimizing performance.
18
+
Tracing is a powerful tool that offers developers an in-depth understanding of the execution process of their generative AI applications. It provides a detailed view of the execution flow of the application. This essential information proves critical while debugging complex applications or optimizing performance.
19
19
20
20
Tracing with the Azure AI Inference SDK offers enhanced visibility and simplified troubleshooting for LLM-based applications, effectively supporting development, iteration, and production monitoring. Tracing follows the OpenTelemetry semantic conventions, capturing and visualizing the internal execution details of any AI application, enhancing the overall development experience.
Copy file name to clipboardExpand all lines: articles/ai-studio/how-to/develop/visualize-traces.md
+11-31Lines changed: 11 additions & 31 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -24,21 +24,16 @@ To enable traces locally, you have two options:
24
24
1. Using **Prompty**, you can trace your application with the **Azure AI Inference SDK**, which offers enhanced visibility and simplified troubleshooting for LLM-based applications. This method follows the OpenTelemetry specification, capturing and visualizing the internal execution details of any AI application, thereby enhancing the overall development experience. To learn more, see [Debugging Prompty](https://prompty.ai/docs/getting-started/debugging-prompty).
25
25
2.**Aspire Dashboard** : A free & open-source OpenTelemetry dashboard for deep insights into your apps on your local development machine. To learn more, see [Aspire Dashboard](https://aspiredashboard.com/#start).
26
26
27
-
## View your traces in Azure AI Studio
27
+
## View your traces in Azure AI Foundry portal
28
28
29
-
Before you can log to Azure AI Studio, attach an Application Insights resource to your project.
29
+
Before you can log to Azure AI Foundry portal, attach an Application Insights resource to your project.
30
30
31
-
1. Navigate to your project in [Azure AI Studio](https://ai.azure.com/).
31
+
1. Navigate to your project in [Azure AI Foundry portal](https://ai.azure.com/).
32
32
1. Select the **Tracing** page on the left hand side.
33
33
1. Select **Create New** to attach a new Application Insights resource to your project.
34
34
1. Supply a name and select **Create**.
35
35
36
-
(Screenshot or gif placeholder - here)
37
-
38
-
After creating and connecting your Application Insights resource, grab the connection string from **Manage data source**. You'll need to provide this connection string to log traces here.
39
-
40
-
(Screenshot or gif placeholder - here)
41
-
:::image type="content" source="../../media/how-to/tracing/" alt-text="Screenshot of [ADD LINK TEXT]." lightbox="../../media/how-to/tracing/":::
36
+
:::image type="content" source="../../media/how-to/trace/visualize/tracing-setup-overview.gif" alt-text="Animation of going to tracing and creating an Application Insight resource." lightbox="../../media/how-to/trace/visualize/tracing-setup-overview.gif":::
42
37
43
38
Next, install the `opentelemetry` SDK:
44
39
@@ -84,45 +79,30 @@ Select the link and begin viewing traces in Azure AI Studio!
84
79
85
80
In your project, you can filter your traces as you see fit.
86
81
87
-
(Placeholder for gif/pic)
88
-
:::image type="content" source="../../media/how-to/tracing/" alt-text="Screenshot of [ADD LINK TEXT]." lightbox="../../media/how-to/tracing/":::
89
-
90
82
By selecting a trace, I can step through each span and identify issues while observing how my application is responding.
91
83
92
-
(Placeholder for gif/pic)
93
-
:::image type="content" source="../../media/how-to/tracing/" alt-text="Screenshot of [ADD LINK TEXT]." lightbox="../../media/how-to/tracing/":::
84
+
:::image type="content" source="../../media/how-to/trace/visualize/debug-filter-tracing.gif" alt-text="Animation of filtering traces in the portal." lightbox="../../media/how-to/trace/visualize/debug-filter-tracing.gif":::
94
85
95
86
### Update your attached Application Insights resource
96
87
97
88
To update the Application Insights resource that is attached to your project, go to **Manage data source** and **Edit** to switch to a new Application Insights resource.
98
89
99
-
(Placeholder for gif/pic)
100
-
:::image type="content" source="../../media/how-to/tracing/" alt-text="Screenshot of [ADD LINK TEXT]." lightbox="../../media/how-to/tracing/":::
90
+
:::image type="content" source="../../media/how-to/trace/visualize/tracing-manage-data-source.png" alt-text="Screenshot of manage data sources pop-up highlighting the edit button." lightbox="../../media/how-to/trace/visualize/tracing-manage-data-source.png":::
101
91
102
92
## View your traces in Azure Monitor
103
93
104
-
If you logged traces using the previous code snippet, then you're all set to view your traces in Azure Monitor Application Insights. You can open in Application Insights from **Manage data source** and use the **Transaction Search** to further investigate.
94
+
If you logged traces using the previous code snippet, then you're all set to view your traces in Azure Monitor Application Insights. You can open in Application Insights from **Manage data source** and use the **End-to-end transaction details view** to further investigate.
105
95
106
-
(Placeholder for gif/pic)
107
-
:::image type="content" source="../../media/how-to/tracing/" alt-text="Screenshot of [ADD LINK TEXT]." lightbox="../../media/how-to/tracing/":::
108
-
109
-
Refer to [Azure Monitor OpenTelemetry documentation](/azure/azure-monitor/app/opentelemetry-enable) for more details on how to send Azure AI Inference traces to Azure Monitor and create Azure Monitor resource.
96
+
For more information on how to send Azure AI Inference traces to Azure Monitor and create Azure Monitor resource, see [Azure Monitor OpenTelemetry documentation](/azure/azure-monitor/app/opentelemetry-enable).
110
97
111
98
### View your generative AI spans and traces
112
99
113
-
From Azure AI studio project, you can also open your custom dashboard that will provide you with insights specifically to help you monitor your generative AI application.
114
-
115
-
(Placeholder for gif/pic)
116
-
:::image type="content" source="../../media/how-to/tracing/" alt-text="Screenshot of [ADD LINK TEXT]." lightbox="../../media/how-to/tracing/":::
117
-
118
-
In this Azure Workbook, you can view your Gen AI spans and jump into the extensive **Transaction search** view to deep dive and investigate.
100
+
From Azure AI studio project, you can also open your custom dashboard that provides you with insights specifically to help you monitor your generative AI application.
119
101
120
-
(Placeholder for gif/pic)
121
-
:::image type="content" source="../../media/how-to/tracing/" alt-text="Screenshot of [ADD LINK TEXT]." lightbox="../../media/how-to/tracing/":::
102
+
In this Azure Workbook, you can view your Gen AI spans and jump into the Azure Monitor **End-to-end transaction details view** view to deep dive and investigate.
122
103
123
104
Learn more about using this workbook to monitor your application, see [Azure Workbook documentation](/azure/azure-monitor/visualize/workbooks-create-workbook).
124
105
125
106
## Related content
126
107
127
-
-
128
-
-
108
+
-[Trace your application with Azure AI Inference SDK](./develop/trace-local-sdk.md)
0 commit comments