fix: updated model capacity minimum to 200

.github/workflows/CAdeploy.yml

@@ -10,8 +10,8 @@ on:
     - cron: '0 6,18 * * *'  # Runs at 6:00 AM and 6:00 PM GMT
 
 env:
-  GPT_MIN_CAPACITY: 250
-  TEXT_EMBEDDING_MIN_CAPACITY: 40
+  GPT_MIN_CAPACITY: 200
+  TEXT_EMBEDDING_MIN_CAPACITY: 80
   BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
 jobs:

docs/QuotaCheck.md

@@ -11,7 +11,7 @@ azd auth login
 
 ### 📌 Default Models & Capacities:
 ```
-gpt-4o-mini:30, text-embedding-ada-002:80
+gpt-4o-mini:200, text-embedding-ada-002:80
 ```
 ### 📌 Default Regions:
 ```
@@ -37,19 +37,19 @@ eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southc
    ```
 ✔️ Check specific model(s) in default regions:
   ```
-  ./quota_check_params.sh --models gpt-4o-mini:30,text-embedding-ada-002:80
+  ./quota_check_params.sh --models gpt-4o-mini:200,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-mini:30 --regions eastus,westus2
+  ./quota_check_params.sh --models gpt-4o-mini:200 --regions eastus,westus2
   ```
 ✔️ All parameters combined:
   ```
- ./quota_check_params.sh --models gpt-4o-mini:30,text-embedding-ada-002:80 --regions eastus,westus --verbose
+ ./quota_check_params.sh --models gpt-4o-mini:200,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-mini:30,text-embedding-ada-002:80"
+DEFAULT_MODEL_CAPACITY="gpt-4o-mini:200,text-embedding-ada-002:80"
 
 # Convert the comma-separated string into an array
 IFS=',' read -r -a MODEL_CAPACITY_PAIRS <<< "$DEFAULT_MODEL_CAPACITY"