...

• base_url: The base url of the API (requried).

• model: The AI model to be used (required).

• api_token: The security secure API token to be used.

• max_token: The max token prompt tokens allowed to be send sent (defaults to 800 if missing)

• custom_headers: KeyOptional key-value pairs to be passed along as HTTP headers on any request. This is handy for example in case basic authentication or any other additional header setting is required.

...

In case you would like to integrate OpenAI as additional AI backend for example, you could use these settings in your secret of type secret-text:

{
  "base_url": "https://api.openai.com/v1",
  "model": "gpt-3.5-turbo",
  "api_token": "your_token",
  "max_token": 800
} 

Replace your_token by the API token you can generate on the OpenAI website.

Use the secret in your AI commands

In any of the AI commands you , if no secret is specified, the default AI backend is used. You can refer to the configured a different AI backend, by using its secret namein the AI command.

Lets assume the OpenAI secret from above was added under a secret with name openai-secret, then to prompt it this OpenAI backlend from inside your pipeline you can do something like this:

...