{"id":154395,"date":"2023-11-10T16:33:40","date_gmt":"2023-11-10T07:33:40","guid":{"rendered":"https:\/\/support.questetra.com\/?p=154395"},"modified":"2023-11-10T16:33:42","modified_gmt":"2023-11-10T07:33:42","slug":"openai-chat-answer-text-prompt-202311","status":"publish","type":"post","link":"https:\/\/support.questetra.com\/ja\/addons\/openai-chat-answer-text-prompt-202311\/","title":{"rendered":"OpenAI #Chat: Text\u30d7\u30ed\u30f3\u30d7\u30c8\u306b\u56de\u7b54"},"content":{"rendered":"\n

OpenAI #Chat: Text\u30d7\u30ed\u30f3\u30d7\u30c8\u306b\u56de\u7b54<\/strong><\/h4>\n\n\n\n

translate<\/span> OpenAI #Chat: Answer Text Prompt<\/a><\/p>\n\n\n\n

Text Prompt \u306b\u5bfe\u3059\u308b\u56de\u7b54\u6587\u3092\u751f\u6210\u3057\u307e\u3059\u3002\u30c7\u30d5\u30a9\u30eb\u30c8\u3067\u306f “gpt-4-1106-preview MODEL” \u306b\u30a2\u30af\u30bb\u30b9\u3057\u3066\u751f\u6210\u3057\u307e\u3059\uff08\u4efb\u610f\u306e MODEL \u306b\u5909\u66f4\u53ef\uff09\u3002\u4f1a\u8a71\u3092\u59cb\u3081\u308b\u305f\u3081\u306e Text Prompt \u306f “system\u30e1\u30c3\u30bb\u30fc\u30b8” \u3068 “user\u30e1\u30c3\u30bb\u30fc\u30b8” \u306b\u5206\u3051\u3066\u5b9a\u7fa9\u3057\u307e\u3059\u3002\u4e00\u822c\u7684\u306b\u306f “system\u30e1\u30c3\u30bb\u30fc\u30b8” \u306b\u306f\u56de\u7b54\u30eb\u30fc\u30eb\u3084\u56de\u7b54\u30ad\u30e3\u30e9\u30af\u30bf\u30fc\u306e\u6027\u683c\u306a\u3069\u304c\u8a2d\u5b9a\u3055\u308c\u3001”user\u30e1\u30c3\u30bb\u30fc\u30b8” \u306b\u306f\u8cea\u554f\u6587\u304c\u8a2d\u5b9a\u3055\u308c\u307e\u3059\u3002\u8907\u6570\u56de\u7b54\u6587\u306e\u30ea\u30af\u30a8\u30b9\u30c8\u3082\u53ef\u80fd\u3067\u3059\u3002<\/p>\n\n\n\n

\"Auto<\/figure>\n\n\n\n
\n
Configs for this Auto Step<\/summary>
\n
\n
AuthzConfU1<\/dt>
U1: HTTP\u8a8d\u8a3c\u8a2d\u5b9a\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08Secret API Key \uff20\u30c8\u30fc\u30af\u30f3\u76f4\u63a5\u6307\u5b9a\uff09 *<\/span><\/dd>\n
StrConfA1<\/dt>
A1: SYSTEM Message Prompt\u3092\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044#{EL}<\/sup><\/span><\/dd>\n
StrConfA2<\/dt>
A2: USER Message Prompt\u3092\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044#{EL}<\/sup><\/span><\/dd>\n
StrConfB1<\/dt>
B1: \u30ec\u30b9\u30dd\u30f3\u30b9\u6570\u3092\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044 (default 1 upto 4)#{EL}<\/sup><\/span><\/dd>\n
SelectConfC1<\/dt>
C1: \u30ec\u30b9\u30dd\u30f3\u30b9\uff11\u304c\u683c\u7d0d\u3055\u308c\u308b\u6587\u5b57\u5217\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09 *<\/span><\/dd>\n
SelectConfC2<\/dt>
C2: \u30ec\u30b9\u30dd\u30f3\u30b9\uff12\u304c\u683c\u7d0d\u3055\u308c\u308b\u6587\u5b57\u5217\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09<\/dd>\n
SelectConfC3<\/dt>
C3: \u30ec\u30b9\u30dd\u30f3\u30b9\uff13\u304c\u683c\u7d0d\u3055\u308c\u308b\u6587\u5b57\u5217\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09<\/dd>\n
SelectConfC4<\/dt>
C4: \u30ec\u30b9\u30dd\u30f3\u30b9\uff14\u304c\u683c\u7d0d\u3055\u308c\u308b\u6587\u5b57\u5217\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09<\/dd>\n<\/div>\n
StrConfM<\/dt>
M: \u30e2\u30c7\u30eb\u540d\uff08AI\u30a8\u30f3\u30b8\u30f3\u540d\uff09\u3092\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044 (default “gpt-4-1106-preview”)#{EL}<\/sup><\/span><\/dd>\n
StrConfU2<\/dt>
U2: OpenAI Organization ID \u3092\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044\uff08”org-xxxx”\uff09#{EL}<\/sup><\/span><\/dd>\n
StrConfU3<\/dt>
U3: \u76e3\u8996\u3084\u691c\u77e5\u306e\u305f\u3081\u306e End-User ID \u3092\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044\uff08”user123456″\uff09#{EL}<\/sup><\/span><\/dd>\n
StrConfB2<\/dt>
B2: Response \u30c8\u30fc\u30af\u30f3\u306e\u8a31\u5bb9\u91cf\u3092\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044 (default 4095)#{EL}<\/sup><\/span><\/dd>\n
StrConfB3<\/dt>
B3: \u751f\u6210\u4e2d\u65ad\u6587\u5b57\u5217\u3092\u5404\u884c\u306b\u5206\u3051\u3066\u30bb\u30c3\u30c8\u3057\u3066\u304f\u3060\u3055\u3044 (eg “.” “\u3002”)#{EL}<\/sup><\/span><\/dd>\n
SelectConfD1<\/dt>
D1: PROMPT \u30c8\u30fc\u30af\u30f3\u6570\u304c\u683c\u7d0d\u3055\u308c\u308b\u6570\u5024\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09<\/dd>\n
SelectConfD2<\/dt>
D2: COMPLETION \u30c8\u30fc\u30af\u30f3\u6570\u304c\u683c\u7d0d\u3055\u308c\u308b\u6570\u5024\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09<\/dd>\n
SelectConfD3<\/dt>
D3: \u5408\u8a08\u30c8\u30fc\u30af\u30f3\u6570\u304c\u683c\u7d0d\u3055\u308c\u308b\u6570\u5024\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09<\/dd>\n
SelectConfD4<\/dt>
D4: \u751f\u6210\u7d42\u4e86\u7406\u7531\u304c\u683c\u7d0d\u3055\u308c\u308b\u6587\u5b57\u5217\u578b\u30c7\u30fc\u30bf\u9805\u76ee\u3092\u9078\u629e\u3057\u3066\u304f\u3060\u3055\u3044\uff08\u66f4\u65b0\uff09<\/dd>\n<\/div>\n\n<\/dl>\n<\/div><\/details><\/div>\n<\/div>\n\n\n\n
\n
Script (click to open)<\/summary>
\n
\/\/ Script Example of Business Process Automation\n\/\/ for 'engine type: 3' ("GraalJS standard mode")\n\/\/ cf. 'engine type: 2' ("GraalJS Nashorn compatible mode") (renamed from "GraalJS" at 20230526)\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      ( "AuthzConfU1" );  \/\/\/ REQUIRED\n  engine.log( " AutomatedTask Config: Authz Setting: " + strAuthzSetting );\nconst strOrgId                  = configs.get      ( "StrConfU2" );    \/\/ NotRequired\n  engine.log( " AutomatedTask Config: OpenAI-Organization: " + strOrgId );\nconst strEndUserId              = configs.get      ( "StrConfU3" ) !== "" ?  \/\/ NotRequired\n                                  configs.get      ( "StrConfU3" ) :\n                                  "m" + processInstance.getProcessModelInfoId().toString(); \/\/ (default)\n  engine.log( " AutomatedTask Config: End User IDs: " + strEndUserId );\n\nconst strModel                  = configs.get      ( "StrConfM" ) !== "" ?   \/\/ NotRequired\n                                  configs.get      ( "StrConfM" ) : "gpt-4-1106-preview"; \/\/ (default)\n  engine.log( " AutomatedTask Config: OpenAI Model: " + strModel );\n\nconst strSystemMsg              = configs.get      ( "StrConfA1" );    \/\/ NotRequired\nconst strUserMsg                = configs.get      ( "StrConfA2" );    \/\/ NotRequired\n  if( strUserMsg === "" && strSystemMsg    === ""){\n    throw new Error( "\\n AutomatedTask ConfigError:" +\n                     " Config {A1:SystemMsg} or {A2:UserMsg} required \\n" );\n  }\nconst strChoises                = configs.get      ( "StrConfB1" );    \/\/ NotRequired\nconst numChoises                = isNaN(parseInt(strChoises,10)) ?\n                                  1 : parseInt(strChoises,10);\nconst strLimit                  = configs.get      ( "StrConfB2" );    \/\/ NotRequired\nconst numLimit                  = isNaN(parseInt(strLimit,10)) ?\n                                  4095 : parseInt(strLimit,10);\nconst strStops                  = configs.get      ( "StrConfB3" );    \/\/ NotRequired\nconst arrStops                  = strStops !== "" ?\n                                  strStops.split("\\n") : null;\n\nconst strPocketResponse1        = configs.getObject( "SelectConfC1" ); \/\/\/ REQUIRED\nconst strPocketResponse2        = configs.getObject( "SelectConfC2" ); \/\/ NotRequired\nconst strPocketResponse3        = configs.getObject( "SelectConfC3" ); \/\/ NotRequired\nconst strPocketResponse4        = configs.getObject( "SelectConfC4" ); \/\/ NotRequired\nconst numPocketPromptTokens     = configs.getObject( "SelectConfD1" ); \/\/ NotRequired\nconst numPocketCompletionTokens = configs.getObject( "SelectConfD2" ); \/\/ NotRequired\nconst numPocketTotalTokens      = configs.getObject( "SelectConfD3" ); \/\/ NotRequired\nconst strPocketFinishReasons    = configs.getObject( "SelectConfD4" ); \/\/ NotRequired\n\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.user  = strEndUserId;\n    \/\/  strJson.response_format = {};\n    \/\/  strJson.response_format.type = "json_object"; \/\/ valid JSON mode\n    \/\/  To Make response_content JSON ('json' required in Request Msg)\n    strJson.n          = numChoises;\n    strJson.max_tokens = numLimit;\n    if ( arrStops !== null ){\n      strJson.stop = [];\n      \/\/ Up to 4 sequences where the API will stop generating further tokens.\n      const numMaxSeq = 4;\n      for ( let i = 0; i < arrStops.length && i < numMaxSeq; i++ ){\n        if ( arrStops[i] === "- - -" ){\n          strJson.stop.push ( "\\n" );\n        }else{\n          strJson.stop.push ( arrStops[i] );\n        }\n      }\n    }\n    strJson.messages = [];\n    if ( strSystemMsg !=="" ) {\n      let objSystemMsg = {};\n          objSystemMsg.role = "system";\n          objSystemMsg.content = strSystemMsg;\n      strJson.messages.push ( objSystemMsg );\n    }\n    if ( strUserMsg !=="" ) {\n      let objUserMsg = {};\n          objUserMsg.role = "user";\n          objUserMsg.content = strUserMsg;\n      strJson.messages.push ( objUserMsg );\n    }\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    if ( strOrgId !== "" ){\n      request1 = request1.header( "OpenAI-Organization", strOrgId );\n    }\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\n\/\/\/ parse response1\n\/* engine.log( response1Body ); \/\/ debug\n{\n  "id": "chatcmpl-8JF1v1NheMIZfeX2AcBjKunKUMN8p",\n  "object": "chat.completion",\n  "created": 1699596699,\n  "model": "gpt-4-1106-preview",\n  "choices": [\n    {\n      "index": 0,\n      "message": {\n        "role": "assistant",\n        "content": "\u304a\u5ba2\u69d8\u3001\u3053\u306e\u8a71\u984c\u306b\u3064 ... ... "\n      },\n      "finish_reason": "stop"\n    },\n    {\n      "index": 1,\n      "message": {\n        "role": "assistant",\n        "content": "\u3053\u306e\u5ea6\u306e\u65b0\u805e\u8a18\u4e8b\u306b\u95a2\u3057 ... ... "\n      },\n      "finish_reason": "stop"\n    }\n  ],\n  "usage": {\n    "prompt_tokens": 1678,\n    "completion_tokens": 1401,\n    "total_tokens": 3079\n  },\n  "system_fingerprint": "fp_a24b4d720c"\n}\n*\/\nconst response1Obj = JSON.parse( response1Body );\n\nlet arrFinishReasons = [];\nfor ( let i = 0; i < response1Obj.choices.length; i++ ){\n  arrFinishReasons.push ( response1Obj.choices[i].finish_reason );\n}\n\n\n\/\/\/\/\/\/ == Data Updating \/ \u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30c7\u30fc\u30bf\u3078\u306e\u4ee3\u5165 ==\n\nif( strPocketResponse1 !== null ){\n  engine.setData( strPocketResponse1,\n                  response1Obj.choices[0]?.message.content ?? ""\n                );  \/\/ optional chaining - nullish coalescing\n}\nif( strPocketResponse2 !== null ){\n  engine.setData( strPocketResponse2, response1Obj.choices[1]?.message.content ?? "" );\n}\nif( strPocketResponse3 !== null ){\n  engine.setData( strPocketResponse3, response1Obj.choices[2]?.message.content ?? "" );\n}\nif( strPocketResponse4 !== null ){\n  engine.setData( strPocketResponse4, response1Obj.choices[3]?.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\nif( strPocketFinishReasons !== null ){\n  engine.setData( strPocketFinishReasons, arrFinishReasons.join('\\n') );\n}\n\n} \/\/\/\/\/\/\/\/ END "main()" \/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\n\n\n\/*\nNotes:\n- This [Automated Step] obtains the Text Response via OpenAI API (Chat endpoint).\n    - Up to 4 Text can be genarated (default: 1)\n- If place this [Automated Atep] in the workflow diagram, communication will occur every time a process arrives.\n    - Request from the Questetra BPM Suite server to the OpenAI server.\n    - Analyzes the response from the OpenAI server and stores the necessary information.\n- [HTTP Authz Settings] is required for workflow apps that include this [Automated Step].\n    - An API key is required to use OpenAI API. Please obtain an API key in advance.\n        - https:\/\/platform.openai.com\/api-keys\n    - Set 'Secret API Key' as communication token. [HTTP Authz Settings] > [Token Fixed Value]\n- Model endpoint compatibility (as of Nov 2023)\n    - `gpt-4` (dated model releases)\n    - `gpt-4-1106-preview`\n    - `gpt-4-32k` (dated model releases)\n    - `gpt-3.5-turbo` (dated model releases)\n    - `gpt-3.5-turbo-16k` (dated model releases)\n    - fine-tuned versions of `gpt-3.5-turbo`\n    - see: https:\/\/platform.openai.com\/docs\/models\/model-endpoint-compatibility (\/v1\/chat\/completions)\n- GPT-4 Turbo with 128K context\n    - `gpt-4-1106-preview`: a preview of the next generation of GPT-4 (GPT-4 Turbo)\n        - the first version of GPT-4 in March 2023 (available to all developers in July 2023)\n    - has knowledge of world events up to April 2023.\n        - CEO Altman, "We will try to never let it get that out of date again." \n    - has a 128k context window so it can fit the equivalent of more than 300 pages of text in a single prompt.\n    - at a 3x cheaper price for input tokens and a 2x cheaper price for output tokens compared to GPT-4.\n\nAPPENDIX\n- Large amount of allowable response sentences to be generated may exceed the system limit.\n    - Generation will be aborted if the allowable amount is reached.\n        - `"finish_reason":"length",`\n        - If a large number is set for "Number of Responses," the response is more likely to be interrupted.\n    - For English, one word or symbol often counts as one token.\n        - For average English, it is about 1 token for 4 characters.\n        - In Japanese, a single character may be divided into multiple tokens.\n        - In the case of average Japanese, a single character is about one token.\n    - You can check the approximate number of word tokens at tokenizer.\n        - https:\/\/platform.openai.com\/tokenizer\n- Stop Sequences can be set up to four (invalid after the fifth line)\n    - If set `\\t` or other characters, they will be escaped.\n    - To set a newline code (`\\n`), set `- - -`. (experimental)\n        - The response will always be a single line.\n- Note that the workflow app ID is automatically assigned to the `user` parameter of the OpenAI API. (experimental)\n    - `processInstance.getProcessModelInfoId()`\n- In settings that refer to numeric type data, be careful not to mix in digit separators.\n    - The formatting function `#sformat` is useful. (Java String.format)\n    - e.g. `#{#sformat("%1.1f", #q_numeric)}` (rounded to one decimal place)\n    - "R2272: Output of Strings via EL"\n        - https:\/\/questetra.zendesk.com\/hc\/ja\/articles\/360024292872-R2272-Output-of-Strings-via-EL-syntax\n- If the number of responses is set to more than one, "Finish Reasons" will be in multiple lines.\n     - If multiple lines are expected, set the data item to be stored as a multiline string.\n\nNotes-ja:\n- \u3053\u306e\uff3b\u81ea\u52d5\u5de5\u7a0b\uff3d\u306f\u3001OpenAI API \uff08Chat \u30a8\u30f3\u30c9\u30dd\u30a4\u30f3\u30c8\uff09\u3092\u901a\u3058\u3066\u3001\u56de\u7b54\u6587\u7ae0\u3092\u53d6\u5f97\u3057\u307e\u3059\u3002\n    - \u3053\u306e\uff3b\u81ea\u52d5\u5de5\u7a0b\uff3d\u3067\u751f\u6210\u3067\u304d\u308b\u6587\u7ae0\u306f\u6700\u59274\u3064\u3067\u3059\u3002\uff08\u30c7\u30d5\u30a9\u30eb\u30c8\uff1a\uff11\uff09\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\u5230\u9054\u306e\u5ea6\u306b\u901a\u4fe1\u304c\u767a\u751f\u3057\u307e\u3059\u3002\n    - Questetra BPM Suite \u30b5\u30fc\u30d0\u304b\u3089 OpenAI \u30b5\u30fc\u30d0\u306b\u5bfe\u3057\u3066\u30ea\u30af\u30a8\u30b9\u30c8\u3057\u307e\u3059\u3002\n    - OpenAI \u30b5\u30fc\u30d0\u304b\u3089\u306e\u30ec\u30b9\u30dd\u30f3\u30b9\u3092\u89e3\u6790\u3057\u3001\u5fc5\u8981\u60c5\u5831\u3092\u683c\u7d0d\u3057\u307e\u3059\u3002\n- \u3053\u306e\uff3b\u81ea\u52d5\u5de5\u7a0b\uff3d\u3092\u542b\u3080\u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30a2\u30d7\u30ea\u306b\u306f\u3001\uff3bHTTP \u8a8d\u8a3c\u8a2d\u5b9a\uff3d\u304c\u5fc5\u8981\u3067\u3059\u3002\n    - OpenAI API \u306e\u5229\u7528\u306b\u306f API key \u304c\u5fc5\u8981\u3067\u3059\u3002\u3042\u3089\u304b\u3058\u3081 API Key \u3092\u53d6\u5f97\u3057\u3066\u304a\u3044\u3066\u304f\u3060\u3055\u3044\u3002\n        - https:\/\/platform.openai.com\/api-keys\n    - 'Secret API Key' \u3092\u901a\u4fe1\u30c8\u30fc\u30af\u30f3\u3068\u3057\u3066\u30bb\u30c3\u30c8\u3057\u307e\u3059\u3002\uff3bHTTP \u8a8d\u8a3c\u8a2d\u5b9a\uff3d\uff1e\uff3b\u30c8\u30fc\u30af\u30f3\u76f4\u63a5\u6307\u5b9a\uff3d\n- \u5bfe\u5fdc MODEL (2023\u5e7411\u6708\u73fe\u5728)\n    - `gpt-4` (dated model releases)\n    - `gpt-4-1106-preview`\n    - `gpt-4-32k` (dated model releases)\n    - `gpt-3.5-turbo` (dated model releases)\n    - `gpt-3.5-turbo-16k` (dated model releases)\n    - fine-tuned versions of `gpt-3.5-turbo`\n    - see: https:\/\/platform.openai.com\/docs\/models\/model-endpoint-compatibility (\/v1\/chat\/completions)\n- 128K \u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u3092\u5099\u3048\u305f GPT-4 Turbo \u3068\u306f\uff1f\n    - `gpt-4-1106-preview`: \u6b21\u4e16\u4ee3 GPT-4 (GPT-4 Turbo) \u306e\u30d7\u30ec\u30d3\u30e5\u30fc\u7248\n        - GPT-4 \u306e\u521d\u7248\u306f 2023\u5e743\u6708\u30ea\u30ea\u30fc\u30b9 (2023\u5e747\u6708\u306b\u5168\u958b\u767a\u8005\u304c\u5229\u7528\u53ef\u80fd)\n    - 2023\u5e744\u6708\u307e\u3067\u306e\u51fa\u6765\u4e8b\u306b\u77e5\u8b58\u304c\u3042\u308b\u3002\n        - \u30a2\u30eb\u30c8\u30de\u30f3CEO\u3001\u300c2\u5ea6\u3068\u6642\u4ee3\u9045\u308c\u306b\u306a\u3089\u306a\u3044\u3088\u3046\u306b\u3059\u308b\u300d\n    - 128k \u30b3\u30f3\u30c6\u30ad\u30b9\u30c8\u3067\u3001300\u30da\u30fc\u30b8\u3092\u8d85\u3048\u308b\u30c6\u30ad\u30b9\u30c8\u306b\u76f8\u5f53\u3059\u308b\u60c5\u5831\u30921\u30d7\u30ed\u30f3\u30d7\u30c8\u306b\u53ce\u7d0d\u53ef\u3002\n    - GPT-4 \u3068\u6bd4\u8f03\u3057\u3066\u3001\u5165\u529b\u30c8\u30fc\u30af\u30f3\u4fa1\u683c\u304c3\u500d\u3001\u51fa\u529b\u30c8\u30fc\u30af\u30f3\u306e\u4fa1\u683c\u304c2\u500d\u3001\u5b89\u304f\u306a\u3063\u305f\u3002\n\nAPPENDIX-ja\n- \u30ec\u30b9\u30dd\u30f3\u30b9\u6587\u306e\u751f\u6210\u8a31\u5bb9\u91cf\u3092\u5927\u304d\u304f\u8a2d\u5b9a\u3057\u305f\u5834\u5408\u3001\u30b7\u30b9\u30c6\u30e0\u5236\u9650\u3092\u8d85\u3048\u308b\u53ef\u80fd\u6027\u304c\u3042\u308a\u307e\u3059\u3002\n    - \u6587\u7ae0\u306e\u9014\u4e2d\u3067\u3042\u3063\u3066\u3082\u8a31\u5bb9\u91cf\u306b\u5230\u9054\u3059\u308c\u3070\u751f\u6210\u304c\u4e2d\u65ad\u3055\u308c\u307e\u3059\u3002\n        - `"finish_reason":"length",`\n        - "\u30ec\u30b9\u30dd\u30f3\u30b9\u6570" \u306b\u5927\u304d\u306a\u6570\u5b57\u3092\u30bb\u30c3\u30c8\u3059\u308b\u3068\u3001\u30ec\u30b9\u30dd\u30f3\u30b9\u4e2d\u65ad\u306e\u53ef\u80fd\u6027\u304c\u9ad8\u304f\u306a\u308a\u307e\u3059\u3002\n    - \u82f1\u8a9e\u306e\u5834\u5408\u3001\u5358\u8a9e\u3084\u8a18\u53f7\u3054\u3068\u306b1\u30c8\u30fc\u30af\u30f3\u306b\u306a\u308a\u307e\u3059\u3002\n        - \u5e73\u5747\u7684\u306a\u82f1\u8a9e\u306e\u5834\u5408\u30014\u6587\u5b57\u30671\u30c8\u30fc\u30af\u30f3\u7a0b\u5ea6\u306b\u306a\u308a\u307e\u3059\u3002\n        - \u65e5\u672c\u8a9e\u306e\u5834\u5408\u30011\u6587\u5b57\u304c\u8907\u6570\u30c8\u30fc\u30af\u30f3\u306b\u5206\u5272\u3055\u308c\u308b\u3053\u3068\u3082\u3042\u308a\u307e\u3059\u3002\n        - \u5e73\u5747\u7684\u306a\u65e5\u672c\u8a9e\u306e\u5834\u5408\u30011\u6587\u5b57\u30671\u30c8\u30fc\u30af\u30f3\u7a0b\u5ea6\u306b\u306a\u308a\u307e\u3059\u3002\n    - \u30ef\u30fc\u30c9\u30c8\u30fc\u30af\u30f3\u6570\u306e\u76ee\u5b89\u306f tokenizer \u306b\u3066\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002\n        - https:\/\/platform.openai.com\/tokenizer\n- "\u4e2d\u65ad\u6587\u5b57\u5217" \u3068\u3057\u3066\u30bb\u30c3\u30c8\u3067\u304d\u308b\u6587\u7bc0\u306f\uff14\u3064\u307e\u3067\u3067\u3059\u3002\uff085\u884c\u76ee\u4ee5\u964d\u306f\u7121\u52b9\uff09\n    - "\u4e2d\u65ad\u6587\u5b57\u5217" \u306b `\\t` \u7b49\u3092\u8a2d\u5b9a\u3057\u305f\u5834\u5408\u3001\u30a8\u30b9\u30b1\u30fc\u30d7\u51e6\u7406\u3055\u308c\u307e\u3059\u3002\n    - "\u4e2d\u65ad\u6587\u5b57\u5217" \u306b\u6539\u884c\u30b3\u30fc\u30c9\uff08`\\n`\uff09\u3092\u30bb\u30c3\u30c8\u3057\u305f\u3044\u5834\u5408\u3001`- - -` \u3092\u30bb\u30c3\u30c8\u3057\u307e\u3059\u3002\uff08\u8a66\u9a13\u7684\uff09\n        - \u30ec\u30b9\u30dd\u30f3\u30b9\u306f\u5e38\u306b\u4e00\u884c\u306b\u306a\u308a\u307e\u3059\u3002\n- \u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u30a2\u30d7\u30eaID\u304c\u3001OpenAI API \u306e `user` \u30d1\u30e9\u30e1\u30fc\u30bf\u306b\u81ea\u52d5\u7684\u306b\u4ee3\u5165\u3055\u308c\u307e\u3059\u3002\uff08\u8a66\u9a13\u7684\uff09\n    - `processInstance.getProcessModelInfoId()`\n- \u6570\u5024\u578b\u30c7\u30fc\u30bf\u3092\u53c2\u7167\u3059\u308b\u8a2d\u5b9a\u3067\u306f\u3001\u6841\u533a\u5207\u308a\u6587\u5b57\u304c\u6df7\u5165\u3057\u306a\u3044\u3088\u3046\u306b\u6ce8\u610f\u3057\u3066\u304f\u3060\u3055\u3044\u3002\n    - \u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u95a2\u6570 `#sformat` \u3092\u4f7f\u3046\u3068\u4fbf\u5229\u3067\u3059\u3002\uff08Java String.format\uff09\n    - e.g. `#{#sformat("%1.1f", #q_numeric)}` \uff08\u5c0f\u6570\u7b2c\u4e00\u4f4d\u307e\u3067\u56db\u6368\u4e94\u5165\uff09\n    - "R2272: \u6587\u5b57\u5217\u3068\u3057\u3066\u306e\u51fa\u529b"\n        - https:\/\/questetra.zendesk.com\/hc\/ja\/articles\/360024292872-R2272\n- \u30ec\u30b9\u30dd\u30f3\u30b9\u6570\u306e\u8a2d\u5b9a\u304c\u8907\u6570\u306e\u5834\u5408\u3001"\u751f\u6210\u7d42\u4e86\u7406\u7531" \u304c\u8907\u6570\u884c\u306b\u306a\u308a\u307e\u3059\u3002\n    - \u8907\u6570\u884c\u304c\u60f3\u5b9a\u3055\u308c\u308b\u5834\u5408\u3001\u683c\u7d0d\u3059\u308b\u30c7\u30fc\u30bf\u9805\u76ee\u306f\u8907\u6570\u884c\u6587\u5b57\u5217\u3092\u8a2d\u5b9a\u3057\u3066\u304f\u3060\u3055\u3044\u3002\n*\/\n\n<\/code><\/pre><\/div>\n<\/div><\/details><\/div>\n<\/div>\n\n\n\n
Download<\/span><\/h3>\n\n\n\n