|
1 | 1 | ## Check Quota Availability Before Deployment |
2 | 2 |
|
3 | | -Before deploying the accelerator, **ensure sufficient quota availability** for the required model. |
4 | | -Use one of the following scripts based on your needs: |
| 3 | +Before deploying the accelerator, **ensure sufficient quota availability** for the required model. |
| 4 | +> **We recommend increasing the capacity to 100k tokens for optimal performance.** |
5 | 5 |
|
6 | | -- **`quota_check_params.sh`** → If you **know the model and capacity** required. |
7 | | -- **`quota_check_all_regions.sh`** → If you **want to check available capacity across all regions** for supported models. |
| 6 | +### Login if you have not done so already |
| 7 | +``` |
| 8 | +azd auth login |
| 9 | +``` |
| 10 | + |
| 11 | + |
| 12 | +### Login if you have not done so already |
| 13 | +``` |
| 14 | +azd auth login |
| 15 | +``` |
| 16 | + |
| 17 | +### 📌 Default Models & Capacities: |
| 18 | +``` |
| 19 | +gpt-4o:30, gpt-4o-mini:30, gpt-4:30, text-embedding-ada-002:80 |
| 20 | +``` |
| 21 | +### 📌 Default Regions: |
| 22 | +``` |
| 23 | +eastus, uksouth, eastus2, northcentralus, swedencentral, westus, westus2, southcentralus, canadacentral |
| 24 | +``` |
| 25 | +### Usage Scenarios: |
| 26 | +- No parameters passed → Default models and capacities will be checked in default regions. |
| 27 | +- Only model(s) provided → The script will check for those models in the default regions. |
| 28 | +- Only region(s) provided → The script will check default models in the specified regions. |
| 29 | +- Both models and regions provided → The script will check those models in the specified regions. |
| 30 | +- `--verbose` passed → Enables detailed logging output for debugging and traceability. |
| 31 | + |
| 32 | +### **Input Formats** |
| 33 | +> Use the --models, --regions, and --verbose options for parameter handling: |
| 34 | +
|
| 35 | +✔️ Run without parameters to check default models & regions without verbose logging: |
| 36 | + ``` |
| 37 | + ./quota_check_params.sh |
| 38 | + ``` |
| 39 | +✔️ Enable verbose logging: |
| 40 | + ``` |
| 41 | + ./quota_check_params.sh --verbose |
| 42 | + ``` |
| 43 | +✔️ Check specific model(s) in default regions: |
| 44 | + ``` |
| 45 | + ./quota_check_params.sh --models gpt-4o:30,text-embedding-ada-002:80 |
| 46 | + ``` |
| 47 | +✔️ Check default models in specific region(s): |
| 48 | + ``` |
| 49 | +./quota_check_params.sh --regions eastus,westus |
| 50 | + ``` |
| 51 | +✔️ Passing Both models and regions: |
| 52 | + ``` |
| 53 | + ./quota_check_params.sh --models gpt-4o:30 --regions eastus,westus2 |
| 54 | + ``` |
| 55 | +✔️ All parameters combined: |
| 56 | + ``` |
| 57 | + ./quota_check_params.sh --models gpt-4:30,text-embedding-ada-002:80 --regions eastus,westus --verbose |
| 58 | + ``` |
| 59 | + |
| 60 | +### **Sample Output** |
| 61 | +The final table lists regions with available quota. You can select any of these regions for deployment. |
| 62 | + |
| 63 | + |
8 | 64 |
|
9 | 65 | --- |
10 | | -## **If using Azure Portal and Cloud Shell** |
| 66 | +### **If using Azure Portal and Cloud Shell** |
11 | 67 |
|
12 | 68 | 1. Navigate to the [Azure Portal](https://portal.azure.com). |
13 | 69 | 2. Click on **Azure Cloud Shell** in the top right navigation menu. |
14 | 70 | 3. Run the appropriate command based on your requirement: |
15 | 71 |
|
16 | | - **To check quota for a specific model and capacity:** |
| 72 | + **To check quota for the deployment** |
17 | 73 |
|
18 | 74 | ```sh |
19 | 75 | curl -L -o quota_check_params.sh "https://raw.githubusercontent.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator/main/infra/scripts/quota_check_params.sh" |
20 | 76 | chmod +x quota_check_params.sh |
21 | | - ./quota_check_params.sh <model_name:capacity> [<model_region>] (e.g., gpt-4o-mini:30,text-embedding-ada-002:20 eastus) |
| 77 | + ./quota_check_params.sh |
22 | 78 | ``` |
23 | | - |
24 | | - **To check available quota across all regions for supported models:** |
25 | | - |
26 | | - ```sh |
27 | | - curl -L -o quota_check_all_regions.sh "https://raw.githubusercontent.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator/main/infra/scripts/quota_check_all_regions.sh" |
28 | | - chmod +x quota_check_all_regions.sh |
29 | | - ./quota_check_all_regions.sh |
| 79 | + - Refer to [Input Formats](#input-formats) for detailed commands. |
| 80 | + |
| 81 | +### **If using VS Code or Codespaces** |
| 82 | +1. Open the terminal in VS Code or Codespaces. |
| 83 | +2. If you're using VS Code, click the dropdown on the right side of the terminal window, and select `Git Bash`. |
| 84 | +  |
| 85 | +3. Navigate to the `scripts` folder where the script files are located and make the script as executable: |
| 86 | + ```sh |
| 87 | + cd infra/scripts |
| 88 | + chmod +x quota_check_params.sh |
30 | 89 | ``` |
31 | | - |
32 | | -## **If using VS Code or Codespaces** |
33 | | - |
34 | | -1. Run the appropriate script based on your requirement: |
| 90 | +4. Run the appropriate script based on your requirement: |
35 | 91 |
|
36 | | - **To check quota for a specific model and capacity:** |
| 92 | + **To check quota for the deployment** |
37 | 93 |
|
38 | 94 | ```sh |
39 | | - ./quota_check_params.sh <model_name:capacity> [<model_region>] (e.g., gpt-4o-mini:30,text-embedding-ada-002:20 eastus) |
| 95 | + ./quota_check_params.sh |
40 | 96 | ``` |
| 97 | + - Refer to [Input Formats](#input-formats) for detailed commands. |
41 | 98 |
|
42 | | - **To check available quota across all regions for supported models:** |
43 | | - |
44 | | - ```sh |
45 | | - ./quota_check_all_regions.sh |
46 | | - ``` |
47 | | -2. If you see the error `_bash: az: command not found_`, install Azure CLI: |
| 99 | +5. If you see the error `_bash: az: command not found_`, install Azure CLI: |
48 | 100 |
|
49 | 101 | ```sh |
50 | 102 | curl -sL https://aka.ms/InstallAzureCLIDeb | sudo bash |
51 | 103 | az login |
52 | 104 | ``` |
53 | | -3. Rerun the script after installing Azure CLI. |
54 | | - |
55 | | - **Parameters** |
56 | | - - `<model_name:capacity>`: The name and required capacity for each model, in the format model_name:capacity (**e.g., gpt-4o-mini:30,text-embedding-ada-002:20**). |
57 | | - - `[<model_region>] (optional)`: The Azure region to check first. If not provided, all supported regions will be checked (**e.g., eastus**). |
| 105 | +6. Rerun the script after installing Azure CLI. |
0 commit comments