Skip to content

Commit 80c85ec

Browse files
committed
add precision about discovery mode
1 parent d740cc3 commit 80c85ec

File tree

2 files changed

+7
-0
lines changed

2 files changed

+7
-0
lines changed

pages/public_cloud/ai_machine_learning/endpoints_guide_01_getting_started/guide.en-gb.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,7 @@ It explains how to obtain an access key, access AI models, and interact with AI
2424
## Requirements
2525

2626
- A [Public Cloud project](/links/public-cloud/public-cloud) in your OVHcloud account
27+
- A payment method defined on your Public Cloud project. **Access keys created from Public Cloud projects in Discovery mode (without a payment method) cannot use the service**.
2728

2829
## Instructions
2930

pages/public_cloud/ai_machine_learning/endpoints_guide_03_troubleshooting/guide.en-gb.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -57,6 +57,12 @@ If you exceed these rate limits, you will receive a 429 error code. In this case
5757

5858
Alternatively, please **[reach out to us to discuss increasing your limits](https://help.ovhcloud.com/csm?id=csm_get_help )** if you require higher usage.
5959

60+
### When using AI Endpoints, I am facing "Resource tag 'discovery' is forbidden"
61+
62+
This error occurs when you are trying to use AI Endpoints with an access key that was created from a Public Cloud project in **Discovery mode**, which doesn't have a payment method.
63+
64+
To resolve this error, add a payment method to your Public Cloud project and try again.
65+
6066
### I am experiencing slow response times when using some of the AI Endpoints models. What is causing this delay?
6167

6268
The delay you are experiencing could be due to the fact that the model you are using has been decommissioned. In most cases, we redirect decommissioned models to updated versions (for example, from llama 3.0 to llama 3.1) to ensure that they still answer requests. However, we add a 10-second delay before the model responds to signal to users that the model is no longer in active use.

0 commit comments

Comments
 (0)