How should the header be configured in the generative AI custom LLM Transformer?

[Perry4]

I configured a generic large language model (LLM) connector, but for the Authorization part in the header, I have to either set it as a fixed value or use a script to query. I believe that after the authentication has been configured, there should no longer be a need to query the apikey in the AI custom LLM Transformer. Could you please tell me exactly how to configure it so that I don't need to use a script to obtain the API key?

my generative AI custom LLM Transformer request transformer :

(function(inputs) {

    /* write code here to construct the request body and any custom headers needed using the inputs object.

    inputs structure: {

        prompt_data: object,

        request_data: object

    } */

    var requestData = inputs.request_data;

    var promptData = inputs.prompt_data;

    var prompt = promptData.prompt;

    var model = promptData.model;

    // construct body using the inputs    

    var body = {

        "model": model,

        "messages": [{

            "role": "user",

            "content": prompt

        }],

        "stream": false

    };

    var apikey = "Bearer ";

    var provider = new sn_cc.ConnectionInfoProvider();

    // Replace 'MyExternalServiceAPI' with the actual ID of your Connection & Credential Alias

    var connectionInfo = provider.getConnectionInfo('XXXXXX');

    if (connectionInfo) {

        // Access the API key securely

        apiKey = apikey + connectionInfo.getCredentialAttribute('api_key');

        var headers = {

            "Authorization": apiKey,

            "Content-Type": "application/json"

        };

        return {

            body: body,

            headers: headers

        };

    } else {

        gs.error('Connection & Credential Alias not found or invalid.');

    }

})(inputs);