{"id":143855,"date":"2023-03-20T11:30:54","date_gmt":"2023-03-20T02:30:54","guid":{"rendered":"https:\/\/support.questetra.com\/?p=143855"},"modified":"2023-08-10T13:24:25","modified_gmt":"2023-08-10T04:24:25","slug":"openai-chat-start-202303","status":"publish","type":"post","link":"https:\/\/support.questetra.com\/en\/addons\/openai-chat-start-202303\/","title":{"rendered":"OpenAI #Chat: Start"},"content":{"rendered":"\n

OpenAI: Chat, Start<\/strong><\/h4>\n\n\n\n

OpenAI: Chat, \u958b\u59cb<\/a><\/p>\n\n\n\n

Starts a conversation with the OpenAI API (ChatGPT). The MODEL used is “gpt-4” by default (configurable). A response (COMPLETION) to an instruction question (PROMPT) is automatically obtained.<\/p>\n\n\n\n

\"Auto<\/figure>\n\n\n\n
\n
Configs for this Auto Step<\/summary>
\n
\n
AuthzConfU<\/dt>
U: Select HTTP_Authz Setting (Secret API Key as “Fixed Value”) *<\/span><\/dd>\n
StrConfM<\/dt>
M: Set MODEL Name (default “gpt-4”)#{EL}<\/sup><\/span><\/dd>\n
StrConfA1<\/dt>
A1: Set Request Message PROMPT *<\/span>#{EL}<\/sup><\/span><\/dd>\n
SelectConfB1<\/dt>
B1: Select STRING that stores Response COMPLETION (update) *<\/span><\/dd>\n
SelectConfC1<\/dt>
C1: Select NUMERIC that stores PROMPT Tokens (update)<\/dd>\n
SelectConfC2<\/dt>
C2: Select NUMERIC that stores COMPLETION Tokens (update)<\/dd>\n
SelectConfC3<\/dt>
C3: Select NUMERIC that stores Total Tokens (update)<\/dd>\n\n<\/dl>\n<\/div><\/details><\/div>\n<\/div>\n\n\n\n
\n
Script (click to open)<\/summary>
\n
\/\/ GraalJS Script (engine type: 2)\n\n\/\/\/\/\/\/\/\/ START "main()" \/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\n\nmain();\nfunction main(){ \n\n\/\/\/\/\/\/ == Config Retrieving \/ \u5de5\u7a0b\u30b3\u30f3\u30d5\u30a3\u30b0\u306e\u53c2\u7167 ==\nconst strAuthzSetting   = configs.get( "AuthzConfU" );       \/\/\/ REQUIRED\n  engine.log( " AutomatedTask Config: Authz Setting: " + strAuthzSetting );\nconst strModel          = configs.get( "StrConfM" ) !== "" ? \/\/ NotRequired\n                          configs.get( "StrConfM" ) : "gpt-4"; \/\/ (default)\n  engine.log( " AutomatedTask Config: OpenAI Model: " + strModel );\nconst strPrompt         = configs.get( "StrConfA1" );        \/\/\/ REQUIRED\n  if( strPrompt       === "" ){\n    throw new Error( "\\n AutomatedTask ConfigError:" +\n                     " Config {A1: Prompt} must be non-empty \\n" );\n  }\nconst strPocketCompletion       = configs.getObject( "SelectConfB1" ); \/\/\/ REQUIRED\nconst numPocketPromptTokens     = configs.getObject( "SelectConfC1" ); \/\/ NotRequired\nconst numPocketCompletionTokens = configs.getObject( "SelectConfC2" ); \/\/ NotRequired\nconst numPocketTotalTokens      = configs.getObject( "SelectConfC3" ); \/\/ NotRequired\n\n\n\/\/\/\/\/\/ == Data Retrieving \/ \u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30c7\u30fc\u30bf\u306e\u53c2\u7167 ==\n\/\/ (Nothing. Retrieved via Expression Language in Config Retrieving)\n\n\n\/\/\/\/\/\/ == Calculating \/ \u6f14\u7b97 ==\n\n\/\/\/\/ OpenAI API > Documentation > API REFERENCE > CHAT\n\/\/\/\/ https:\/\/platform.openai.com\/docs\/api-reference\/chat\n\n\/\/\/ prepare json\nlet strJson = {};\n    strJson.model = strModel;\n    strJson.messages = [];\n    strJson.messages[0] = {};\n    strJson.messages[0].role = "user";\n    strJson.messages[0].content = strPrompt;\n\n\/\/\/ prepare request1\nlet request1Uri = "https:\/\/api.openai.com\/v1\/chat\/completions";\nlet request1 = httpClient.begin(); \/\/ HttpRequestWrapper\n    request1 = request1.authSetting( strAuthzSetting ); \/\/ with "Authorization: Bearer XX"\n    request1 = request1.body( JSON.stringify( strJson ), "application\/json" );\n\n\/\/\/ try request1\nconst response1     = request1.post( request1Uri ); \/\/ HttpResponseWrapper\nengine.log( " AutomatedTask ApiRequest1 Start: " + request1Uri );\nconst response1Code = response1.getStatusCode() + ""; \/\/ JavaNum to string\nconst response1Body = response1.getResponseAsString();\nengine.log( " AutomatedTask ApiResponse1 Status: " + response1Code );\nif( response1Code !== "200"){\n  throw new Error( "\\n AutomatedTask UnexpectedResponseError: " +\n                    response1Code + "\\n" + response1Body + "\\n" );\n}\n\n\/\/\/ parse response1\nengine.log( response1Body ); \/\/ debug\n\/* engine.log( response1Body ); \/\/ debug\n{\n  "id":"chatcmpl-6pttfxxxxxmzOKmyyyyy9A2gIwwww",\n  "object":"chat.completion",\n  "created":1677827615,\n  "model":"gpt-3.5-turbo-0301",\n  "usage":{\n    "prompt_tokens":41,\n    "completion_tokens":424,\n    "total_tokens":465\n  },\n  "choices":[{\n    "message":{\n      "role":"assistant",\n      "content":"\\n\\n\u4eac\u90fd\u306e\u826f\u3055\u306f\u3001\u6570\u3048\u5207\u308c\u306a\u3044\u307b\u3069\u305f\u304f\u3055\u3093\u3042\u308a\u307e\u3059\u304c...\\n\\n\u6e05\u6c34\u5bfa\u306f..."\n    },\n    "finish_reason":null,\n    "index":0\n  }]\n}\n*\/\nconst response1Obj = JSON.parse( response1Body );\n\n\n\/\/\/\/\/\/ == Data Updating \/ \u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30c7\u30fc\u30bf\u3078\u306e\u4ee3\u5165 ==\n\nif( strPocketCompletion !== null ){\n  engine.setData( strPocketCompletion,\n                  response1Obj.choices[0].message.content ?? ""\n                );\n}\nif( numPocketPromptTokens !== null ){\n  engine.setData( numPocketPromptTokens, new java.math.BigDecimal(\n                  response1Obj.usage.prompt_tokens ?? 0\n                ));\n}\nif( numPocketCompletionTokens !== null ){\n  engine.setData( numPocketCompletionTokens, new java.math.BigDecimal(\n                  response1Obj.usage.completion_tokens ?? 0\n                ));\n}\nif( numPocketTotalTokens !== null ){\n  engine.setData( numPocketTotalTokens, new java.math.BigDecimal(\n                  response1Obj.usage.total_tokens ?? 0\n                ));\n}\n\/\/ "??": Nullish coalescing operator (ES11)\n\/\/ https:\/\/developer.mozilla.org\/docs\/Web\/JavaScript\/Reference\/Operators\/Nullish_coalescing\n\n} \/\/\/\/\/\/\/\/ END "main()" \/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\n\n\n\/*\nNotes:\n- If you place this "Automated Step" in the Workflow diagram,\n    - the request will be automatically sent every time the process token arrives.\n    - A request is automatically sent to the OpenAI API server. (REST API)\n    - The response from the OpenAI API server is automatically parsed.\n    - You can incorporate "AI assistance" into your business processes.\n- About "OpenAI API"\n    - https:\/\/platform.openai.com\/docs\/introduction\/overview\n    - The OpenAI API can be applied to virtually any task that involves understanding or generating natural language or code.\n    - For example, if you give the API the prompt, "Write a tagline for an ice cream shop",\n        - it will return a completion like "We serve up smiles with every scoop!"\n- API key is required to use the OpenAI API.\n    - Obtain the API key to be used in advance.\n- Configurable MODEL names:\n    - https:\/\/platform.openai.com\/docs\/models\/model-endpoint-compatibility\n\nAPPENDIX\n- Header for developers belonging to multiple organizations is not supported (as of 202303)\n    - `OpenAI-Organization`\n- Requests with context are not supported.\n    - You cannot set the flow of conversation in this auto-step.\n    - Use "OpenAI: Chat, Interact with Parameters" instead.\n        - https:\/\/support.questetra.com\/addons\/openai-chat-interact-with-parameters-2023\/\n- To activate the Workflow App including this "Add-on automated Step", "HTTP Authorization Setting" is required.\n    - Set "Secret API Key" as communication token. (Token Fixed Value)\n- Older versions\n    - https:\/\/support.questetra.com\/addons\/openai-chat-start-2023\/\n        - Compatible.\n        - Overwrite to update "Add-on Service Task".\n        - No need for re-release of "Workflow App"\n- If access to the latest Model is restricted, 404 error ("That model does not exist")\n    - Even if the latest Model is released by OpenAI, it is not open to all developers.\n- An error may occur depending on the timing.\n    - 429 error ("Too Many Requests")\n    - Timeout script error 'java.util.concurrent.TimeoutException'\n\nNotes-ja:\n- \u3053\u306e\uff3b\u81ea\u52d5\u5de5\u7a0b\uff3d\u3092\u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u56f3\u306b\u914d\u7f6e\u3059\u308c\u3070\u3001\u6848\u4ef6\u304c\u5230\u9054\u3059\u308b\u5ea6\u306b\u30ea\u30af\u30a8\u30b9\u30c8\u304c\u81ea\u52d5\u9001\u4fe1\u3055\u308c\u307e\u3059\u3002\n    - OpenAI API \u30b5\u30fc\u30d0\u306b\u5bfe\u3057\u3066\u30ea\u30af\u30a8\u30b9\u30c8\u304c\u81ea\u52d5\u9001\u51fa\u3055\u308c\u307e\u3059\u3002\uff08REST API\u901a\u4fe1\uff09\n    - OpenAI API \u30b5\u30fc\u30d0\u304b\u3089\u306e\u30ec\u30b9\u30dd\u30f3\u30b9\u304c\u81ea\u52d5\u89e3\u6790\u3055\u308c\u307e\u3059\u3002\n    - "AI \u306b\u3088\u308b\u652f\u63f4" \u3092\u696d\u52d9\u30d7\u30ed\u30bb\u30b9\u306b\u7d44\u307f\u8fbc\u3080\u3053\u3068\u304c\u51fa\u6765\u307e\u3059\u3002\n- "OpenAI API" \u3068\u306f\n    - https:\/\/platform.openai.com\/docs\/introduction\/overview\n    - OpenAI API \u306f\u3001\u81ea\u7136\u8a00\u8a9e\u3084\u30b3\u30fc\u30c9\u3092\u7406\u89e3\u3057\u3001\u81ea\u7136\u8a00\u8a9e\u3084\u30b3\u30fc\u30c9\u3092\u751f\u6210\u3057\u307e\u3059\u3002\u3042\u3089\u3086\u308b\u4ed5\u4e8b\u306b\u9069\u7528\u53ef\u80fd\u3067\u3059\u3002\n    - \u305f\u3068\u3048\u3070\u3001\u300c\u30a2\u30a4\u30b9\u30af\u30ea\u30fc\u30e0\u5c4b\u306e\u30ad\u30e3\u30c3\u30c1\u30d5\u30ec\u30fc\u30ba\u3092\u66f8\u3044\u3066\u300d\u3068\u3044\u3046\u30d7\u30ed\u30f3\u30d7\u30c8\uff08Prompt\uff09\u3092\u4e0e\u3048\u308b\u3068\u3001\n        - \u300c\u5168\u3066\u306e\u30b9\u30af\u30fc\u30d7\u3092\u7b11\u9854\u3067\uff01\u300d\u3068\u3044\u3063\u305f\u5fdc\u7b54\uff08Completion\uff09\u304c\u8fd4\u3055\u308c\u307e\u3059\u3002 (\u2190Questetra\u793e\u306b\u3088\u308b\u610f\u8a33)\n- OpenAI API \u306e\u5229\u7528\u306b\u306f API key \u304c\u5fc5\u8981\u3067\u3059\u3002\n    - \u3042\u3089\u304b\u3058\u3081 "Secret API Key" \u3092\u53d6\u5f97\u3057\u3066\u304a\u3044\u3066\u304f\u3060\u3055\u3044\u3002\n- \u8a2d\u5b9a\u53ef\u80fd\u306a\u30e2\u30c7\u30eb\u540d:\n    - https:\/\/platform.openai.com\/docs\/models\/model-endpoint-compatibility\n\n\nAPPENDIX-ja\n- Older versions\n    - https:\/\/support.questetra.com\/ja\/addons\/openai-chat-start-2023\/\n        - \u4e92\u63db\u6027\u3042\u308a\u307e\u3059\u3002\n        - \uff3b\u30a2\u30c9\u30aa\u30f3\u30b5\u30fc\u30d3\u30b9\u30bf\u30b9\u30af\uff3d\u3092\u4e0a\u66f8\u304d\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u3057\u3066\u304f\u3060\u3055\u3044\u3002\n        - \uff3b\u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30a2\u30d7\u30ea\uff3d\u306e\u66f4\u65b0\u30ea\u30ea\u30fc\u30b9\u306f\u3001\u5fc5\u305a\u3057\u3082\u5fc5\u8981\u3067\u306f\u3042\u308a\u307e\u305b\u3093\u3002\n            - \u30e2\u30c7\u30eb\uff08AI\u30a8\u30f3\u30b8\u30f3\uff09\u3092\u5909\u66f4\u3059\u308b\u3053\u3068\u304c\u51fa\u6765\u308b\u3088\u3046\u306b\u306a\u308a\u307e\u3057\u305f\u3002\n- \u8907\u6570\u7d44\u7e54\u306b\u6240\u5c5e\u3059\u308b\u958b\u767a\u8005\u5411\u3051\u306e\u30d8\u30c3\u30c0\u306b\u306f\u672a\u5bfe\u5fdc\u3067\u3059\uff08202303\u6642\u70b9\uff09\n    - `OpenAI-Organization`\n- \u6587\u8108\u3092\u4f7f\u3063\u305f\u30ea\u30af\u30a8\u30b9\u30c8\u306b\u306f\u672a\u5bfe\u5fdc\u3067\u3059\u3002\n    - \u3053\u306e\u81ea\u52d5\u5de5\u7a0b\u3067\u306f\u4f1a\u8a71\u306e\u6d41\u308c\u3092\u8a2d\u5b9a\u3059\u308b\u3053\u3068\u306f\u3067\u304d\u307e\u305b\u3093\u3002\n    - \u4ee3\u308f\u308a\u306b\u300eOpenAI: Chat, \u30d1\u30e9\u30e1\u30fc\u30bf\u4ed8\u304d\u5bfe\u8a71\u300f\u3092\u5229\u7528\u3057\u3066\u304f\u3060\u3055\u3044\u3002\n        - https:\/\/support.questetra.com\/ja\/addons\/openai-chat-interact-with-parameters-2023\/\n- \u3053\u306e\uff3b\u30a2\u30c9\u30aa\u30f3\u81ea\u52d5\u5de5\u7a0b\uff3d\u3092\u542b\u3080\u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30a2\u30d7\u30ea\u3092\u904b\u7528\u3059\u308b\u306b\u306f\uff3bHTTP \u8a8d\u8a3c\u8a2d\u5b9a\uff3d\u304c\u5fc5\u8981\u3067\u3059\u3002\n    - "Secret API Key" \u3092\u901a\u4fe1\u30c8\u30fc\u30af\u30f3\u3068\u3057\u3066\u30bb\u30c3\u30c8\u3057\u307e\u3059\u3002\uff3b\u30c8\u30fc\u30af\u30f3\u76f4\u63a5\u6307\u5b9a\uff3d\n- \u6700\u65b0Model\u3078\u306e\u30a2\u30af\u30bb\u30b9\u304c\u5236\u9650\u3055\u308c\u3066\u3044\u308b\u5834\u5408\u3001404\u30a8\u30e9\u30fc\uff08"That model does not exist"\uff09\n    - \u6700\u65b0Model\u304c\u767a\u8868\u3055\u308c\u3066\u3082\u3001\u5168\u3066\u306e\u958b\u767a\u8005\u30a2\u30ab\u30a6\u30f3\u30c8\u304c\u30a2\u30af\u30bb\u30b9\u3067\u304d\u308b\u8a33\u3067\u306f\u3042\u308a\u307e\u305b\u3093\u3002\n    - eg. `GPT-4 is currently in a limited beta and only accessible to those who have been granted access.`\n    - eg. `AutomatedTask UnexpectedResponseError: 404 { "error": { "message": "That model does not exist",`\n- \u30bf\u30a4\u30df\u30f3\u30b0\u306b\u3088\u3063\u3066\u3001\u30a8\u30e9\u30fc\u306b\u306a\u308b\u5834\u5408\u304c\u3042\u308a\u307e\u3059\u3002\n    - 429\u30a8\u30e9\u30fc\uff08"Too Many Requests"\uff09\n    - Timeout \u30b9\u30af\u30ea\u30d7\u30c8\u30a8\u30e9\u30fc 'java.util.concurrent.TimeoutException'\n*\/\n\n<\/code><\/pre><\/div>\n<\/div><\/details><\/div>\n<\/div>\n\n\n\n
Download<\/span><\/h3>\n\n\n\n