Using MaaS with AI Gateway

To enable MaaS to leverage AI Gateway features (such as Rate Limiting, Model Caching, etc.), follow these steps:

Step 1: Access the AI Gateway interface on the GreenNode Console via: http://aigateway.console.vngcloud.vn/arrow-up-right

Step 2: In the left-hand menu, select AI Gateway, then click the Create an AI Gateway button.

Step 3: On the Create New Gateway screen, fill in the following information:

  • AI Gateway Name: Provide a memorable name for your gateway. The name must contain only a–z, A–Z, 0–9, underscore (_) or hyphen (-), and be between 5 and 50 characters.

  • Model Provider:

    • Select OpenAI Compatible as the AI model provider.

    • Model Type: Select the Model Type (refer to MaaSarrow-up-right in the AI Platform portal).

    • Model Endpoint: Enter the model URL (refer to MaaSarrow-up-right in the AI Platform portal).

    • Authentication info:

      • header_name: Enter Authorization.

      • header_value: Enter the MaaS API Key (created in the AI Platform Portal arrow-up-right).

  • Gateway Config: By default, the system enables the Authenticated Gateway feature.

Step 4: Click Create an AI Gateway. Your AI Gateway will be initialized and ready to use.

Step 5: After the AI Gateway is created, generate a Token to call the API.

Step 6: After creating the token, you can configure specific rate limits for each token based on your needs

Step 7: In the Providers & Model section, locate the AI model you configured. Click the Curl command icon to get a sample request.

Step 8: Copy the displayed curl command and execute it on your local machine (via Terminal or Command Prompt).

Example:

Note:

  • Replace {AUTHENTICATION_TOKEN} with the token created in Step 5.

Last updated