diff --git a/Images/readme_deployment/Control_Model_TPM000.png b/Images/readme_deployment/Control_Model_TPM000.png index 07eb11a8..01f1777d 100644 Binary files a/Images/readme_deployment/Control_Model_TPM000.png and b/Images/readme_deployment/Control_Model_TPM000.png differ diff --git a/Images/readme_deployment/Control_Model_TPM001.png b/Images/readme_deployment/Control_Model_TPM001.png index 1e5b25e5..53fba65a 100644 Binary files a/Images/readme_deployment/Control_Model_TPM001.png and b/Images/readme_deployment/Control_Model_TPM001.png differ diff --git a/README.DEPLOYMENT.md b/README.DEPLOYMENT.md index ffc185a0..49c91739 100644 --- a/README.DEPLOYMENT.md +++ b/README.DEPLOYMENT.md @@ -116,7 +116,7 @@ You will be prompted for the following parameters with this Screen : ### Manual Deployment Steps: **Create Content Filter** - Please follow below steps -> * Navigate to Azure AI Studio +> * Navigate to project in Azure OpenAI, then go to Azure AI Foundry, select Safety + security > * Click on Create Content Filter and set the filters to a high threshold for the following categories: ``` Hate, Sexual, Self-harm, Violence @@ -138,7 +138,7 @@ Don't miss this Url information. This is the application's endpoint URL and it s > **Capacity Note:** > * The deployment script creates models with a setting of 1 token per minute (TPM) rate limit. -> * Faster performance can be achieved by increasing the TPM limit with Azure OpenAI Studio. +> * Faster performance can be achieved by increasing the TPM limit with Azure AI Foundry. > * Capacity varies for [regional quota limits](https://learn.microsoft.com/en-us/azure/ai-services/openai/quotas-limits#regional-quota-limits) as well as for [provisioned throughput](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/provisioned-throughput). > * As a starting point, we recommend the following quota threshold be set up for this service run. @@ -151,7 +151,7 @@ Don't miss this Url information. This is the application's endpoint URL and it s > **⚠️ Warning:** **Insufficient quota can cause failures during the upload process.** Please ensure you have the recommended capacity or request for additional capacity before start uploading the files. -1. Browse to Azure OpenAI Studio and select **each of the 2 models** within the `Deployments` menu: +1. Browse to the project in Azure AI Foundry, and select **each of the 2 models** within the `Deployments` menu: Select Model 2. Increase the TPM value for **each model** for faster report generation: