Merge pull request #529 from microsoft/update-model-capacity-similar-to-bicep

fix: update model capacity similar to bicep

Author: Roopan-Microsoft

.github/workflows/deploy-KMGeneric.yml

@@ -40,8 +40,8 @@ jobs:
           export AZURE_TENANT_ID=${{ secrets.AZURE_TENANT_ID }}
           export AZURE_CLIENT_SECRET=${{ secrets.AZURE_CLIENT_SECRET }}
           export AZURE_SUBSCRIPTION_ID="${{ secrets.AZURE_SUBSCRIPTION_ID }}"
-          export GPT_MIN_CAPACITY="150"
-          export TEXT_EMBEDDING_MIN_CAPACITY="80"
+          export GPT_MIN_CAPACITY=${{ env.GPT_MIN_CAPACITY }}
+          export TEXT_EMBEDDING_MIN_CAPACITY=${{ env.TEXT_EMBEDDING_MIN_CAPACITY }}
           export AZURE_REGIONS="${{ vars.AZURE_REGIONS_KM }}"
           chmod +x infra/scripts/checkquota_km.sh
           if ! infra/scripts/checkquota_km.sh; then

documents/QuotaCheck.md

@@ -10,7 +10,7 @@ azd auth login
 
 ### 📌 Default Models & Capacities:
 ```
-gpt-4o:30, gpt-4o-mini:30, gpt-4:30, text-embedding-ada-002:80
+gpt-4o:150, gpt-4o-mini:150, gpt-4:150, text-embedding-ada-002:80
 ```
 ### 📌 Default Regions:
 ```
@@ -36,19 +36,19 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc
    ```
 ✔️ Check specific model(s) in default regions:
   ```
-  ./quota_check_params.sh --models gpt-4o:30,text-embedding-ada-002:80
+  ./quota_check_params.sh --models gpt-4o:150,text-embedding-ada-002:80
   ```
 ✔️ Check default models in specific region(s):
   ```
 ./quota_check_params.sh --regions eastus,westus
   ```
 ✔️ Passing Both models and regions:  
   ```
-  ./quota_check_params.sh --models gpt-4o:30 --regions eastus,westus2
+  ./quota_check_params.sh --models gpt-4o:150 --regions eastus,westus2
   ```
 ✔️ All parameters combined:
   ```
- ./quota_check_params.sh --models gpt-4:30,text-embedding-ada-002:80 --regions eastus,westus --verbose
+ ./quota_check_params.sh --models gpt-4:150,text-embedding-ada-002:80 --regions eastus,westus --verbose
   ```
 
 ### **Sample Output**

infra/scripts/quota_check_params.sh

@@ -47,7 +47,7 @@ log_verbose() {
 }
 
 # Default Models and Capacities (Comma-separated in "model:capacity" format)
-DEFAULT_MODEL_CAPACITY="gpt-4o:30,gpt-4o-mini:30,gpt-4:30,text-embedding-ada-002:80"
+DEFAULT_MODEL_CAPACITY="gpt-4o:150,gpt-4o-mini:150,gpt-4:150,text-embedding-ada-002:80"
 
 # Convert the comma-separated string into an array
 IFS=',' read -r -a MODEL_CAPACITY_PAIRS <<< "$DEFAULT_MODEL_CAPACITY"