Skip to content

Commit 82a7333

Browse files
authored
Merge pull request #1827 from mrbullwinkle/mrb_12_04_2024_update_image
[Azure OpenAI] Image update
2 parents cfd4117 + 4b7e583 commit 82a7333

File tree

3 files changed

+5
-2
lines changed

3 files changed

+5
-2
lines changed

articles/ai-services/openai/how-to/business-continuity-disaster-recovery.md

Lines changed: 5 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -59,7 +59,8 @@ By default, the Azure OpenAI service provides a [default SLA](https://www.micros
5959

6060
The additional benefit of this architecture is that it allows you to stack Standard deployments with Provisioned Deployments so that you can dial in your preferred level of performance and resiliency. This allows you to use PTU for your baseline demand across workloads and leverage pay-as-you-go for spikes in traffic.
6161

62-
:::image type="content" source="../how-to/media/disaster-recovery/recovery.jpg" alt-text="Failover architectural diagram." lightbox="../how-to/media/disaster-recovery/recovery.jpg":::
62+
:::image type="content" source="../how-to/media/disaster-recovery/scaling.jpg" alt-text="Provisioned scaling diagram." lightbox="../how-to/media/disaster-recovery/scaling.jpg":::
63+
6364

6465
## Supporting Infrastructure
6566

@@ -70,9 +71,11 @@ The infrastructure that supports the Azure OpenAI architecture needs to be consi
7071
Organizations consuming the service through the Microsoft public backbone should consider the following design elements:
7172

7273
1. The Generative AI Gateway should be deployed in manner that ensures it's available in the event of an Azure regional outage. If using APIM (Azure API Management), this can be done by deploying separate APIM instances in multiple regions or using the [multi-region gateway feature of APIM](/azure/api-management/api-management-howto-deploy-multi-region).
74+
7375
1. A public global server load balancer should be used to load balance across the multiple Generative AI Gateway instances in either an active/active or active/passive manner. [Azure FrontDoor](/azure/traffic-manager/traffic-manager-routing-methods) can be used to fulfill this role depending on the organization’s requirements.
7476

75-
:::image type="content" source="../how-to/media/disaster-recovery/scaling.jpg" alt-text="Provisioned scaling diagram." lightbox="../how-to/media/disaster-recovery/scaling.jpg":::
77+
:::image type="content" source="../how-to/media/disaster-recovery/recovery.png" alt-text="Failover architectural diagram." lightbox="../how-to/media/disaster-recovery/recovery.png":::
78+
7679

7780
### Designing for consumption through the private networking
7881

Binary file not shown.
206 KB
Loading

0 commit comments

Comments
 (0)