OpenAI #FtJob: Retrieve

// GraalJS standard mode Script Script (engine type: 3)
// cf. 'engine type: 2': "GraalJS Nashorn compatible mode" (renamed from "GraalJS" at 20230526)


//////// START "main()" /////////////////////////////////////////////////////////////////

main();
function main(){ 

////// == Config Retrieving / 工程コンフィグの参照 ==
const strAuthzSetting     = configs.get( "AuthzConfU1" );             /// REQUIRED
  engine.log( " AutomatedTask Config: Authz Setting: " + strAuthzSetting );
const strOrgId            = configs.get( "StrConfU2" );               // NotRequired
  engine.log( " AutomatedTask Config: OpenAI-Organization: " + strOrgId );
const strJobId            = configs.get( "StrConfA1" );               /// REQUIRED
  if( strJobId          === "" ){
    throw new Error( "\n AutomatedTask ConfigError:" +
                     " Config {A1: Job Id} must be non-empty string \n" );
  }
const strPocketStatus     = configs.getObject( "SelectConfB1" );      // NotRequired
const strPocketModelId    = configs.getObject( "SelectConfB2" );      /// REQUIRED
const strPocketEventTsv   = configs.getObject( "SelectConfB3" );      // NotRequired
const strPocketResultIds  = configs.getObject( "SelectConfB4" );      // NotRequired



////// == Data Retrieving / ワークフローデータの参照 ==
// (Nothing. Retrieved via Expression Language in Config Retrieving)



////// == Calculating / 演算 ==

//// OpenAI API > Documentation > API REFERENCE > Fine-tunes > Retrieve fine-tune
//// https://platform.openai.com/docs/api-reference/fine-tunes/retrieve

/// prepare request1
let request1Uri = "https://api.openai.com/v1/fine-tunes/" + strJobId;
let request1 = httpClient.begin(); // HttpRequestWrapper
    request1 = request1.authSetting( strAuthzSetting ); // with "Authorization: Bearer XX"
    if ( strOrgId !== "" ){
      request1 = request1.header( "OpenAI-Organization", strOrgId );
    }

/// try request1
const response1     = request1.get( request1Uri ); // HttpResponseWrapper
engine.log( " AutomatedTask ApiRequest1 Start: " + request1Uri );
const response1Code = response1.getStatusCode() + ""; // JavaNum to string
const response1Body = response1.getResponseAsString();
engine.log( " AutomatedTask ApiResponse1 Status: " + response1Code );
if( response1Code !== "200"){
  throw new Error( "\n AutomatedTask UnexpectedResponseError: " +
                    response1Code + "\n" + response1Body + "\n" );
}

/* engine.log( response1Body ); // debug
{
  "object": "fine-tune",
  "id": "ft-lN1WPLOp8rtoalbMG5Nctc0T",
  "hyperparams": {
    "n_epochs": 4,
    "batch_size": null,
    "prompt_loss_weight": 0.01,
    "learning_rate_multiplier": null
  },
  "organization_id": "org-xxxxxyyyyyzzzzzXXXXXYYYY",
  "model": "curie",
  "training_files": [
    {
      "object": "file",
      "id": "file-rM8tP15b9pZ2tJSLZEfUl7fG",
      "purpose": "fine-tune",
      "filename": "training-data-questetra-bpm-suite-assistant.jsonl",
      "bytes": 6823,
      "created_at": 1690249576,
      "status": "processed",
      "status_details": null
    }
  ],
  "validation_files": [],
  "result_files": [],
  "created_at": 1690354635,
  "updated_at": 1690354635,
  "status": "pending",
  "fine_tuned_model": null,
  "events": [
    {
      "object": "fine-tune-event",
      "level": "info",
      "message": "Created fine-tune: ft-lN1WPLOp8rtoalbMG5Nctc0T",
      "created_at": 1690354635
    }
  ]
}
*/

/// parse response1
const response1Obj = JSON.parse( response1Body );
engine.log( " AutomatedTask OpenAI #retrieved " );

let arrEvents = [];
for ( let i = 0; i < response1Obj.events.length; i++ ) {
  const dateTmp = new Date ( response1Obj.events[i].created_at * 1000 );
  arrEvents.push ( 
    dateTmp.toISOString() + '\t' +
    response1Obj.events[i].level + '\t' +
    response1Obj.events[i].message
  );
}

let arrResultIds = [];
let numResultFiles = response1Obj?.result_files.length ?? 0;
for ( let i = 0; i < numResultFiles; i++ ) {
  arrResultIds.push (
    response1Obj.result_files[i].id
  );
}


////// == Data Updating / ワークフローデータへの代入 ==
if( strPocketStatus !== null ){
  engine.setData( strPocketStatus, response1Obj.status + "" );
}
if( strPocketModelId !== null ){
  engine.setData( strPocketModelId, response1Obj.fine_tuned_model + "" );
}
if( strPocketEventTsv !== null ){
  engine.setData( strPocketEventTsv, arrEvents.join('\n') );
}
if( strPocketResultIds !== null ){
  engine.setData( strPocketResultIds, arrResultIds.join('\n') );
}


} //////// END "main()" /////////////////////////////////////////////////////////////////



/*
Notes:
- This "Automated Step" will retrieve the fine-tune job by FtJob ID.
    - Example of FtJob ID: "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
- If you place this "Automated Step" in the Workflow diagram, the request will be automatically sent every time the process token arrives.
    - A request is automatically sent to the OpenAI API server. (REST API)
    - The response from the OpenAI API server is automatically parsed.

APPENDIX
- To activate a Workflow App that includes this Automated Step, "HTTP Authz Setting" is required
    - Obtain a "Secret API Key" in advance.
    - Set the key as the communication token in "Token Fixed Value"


Notes-ja:
- この［自動工程］は、FtJob IDでファインチューンJob（微調整ジョブ）を参照します。
    - Example of FtJob ID: "ft-AF1WoRqd3aJAHsqc9NY7iL8F"
- この［自動工程］をワークフロー図に配置すれば、案件が到達する度にリクエストが自動送信されます。
    - OpenAI API サーバに対してリクエストが自動送出されます。（REST API通信）
    - OpenAI API サーバからのレスポンスが自動保存解析されます。

APPENDIX-ja
- この［アドオン自動工程］を含むワークフローアプリを運用するには［HTTP 認証設定］が必要です。
    - あらかじめ "Secret API Key" を取得しておいてください。
    - "Secret API Key" を通信トークンとしてセットします。［トークン直接指定］
*/