@promptbook/node 0.61.0-28 → 0.61.0-30

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/esm/index.es.js CHANGED
@@ -654,7 +654,7 @@ function forEachAsync(array, options, callbackfunction) {
654
654
  });
655
655
  }
656
656
 
657
- var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.61.0-27",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n- Make pieces of information concise, clear, and easy to understand\n- One piece of information should be approximately 1 paragraph\n- Divide the paragraphs by markdown horizontal lines ---\n- Omit irrelevant information\n- Group redundant information\n- Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}",dependentParameterNames:["knowledgeContent"],resultingParameterName:"knowledgePieces"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-27",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.61.0-27",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n- Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}",dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-27",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.61.0-27",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced content creator, write best title for the document.\n\n# Rules\n\n- Write just title, nothing else\n- Title should be concise and clear\n- Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}",expectations:{words:{min:1,max:8}},dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-27",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.61.0-27",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"make-model-requirements",title:"Make modelRequirements",modelRequirements:{modelVariant:"CHAT",modelName:"gpt-4-turbo"},content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Sample\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n### Option `modelName`\n\nPick from the following models:\n\n- {availableModelNames}\n\n### Option `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Option `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n- `0.1`: Low temperature, extremely conservative and deterministic\n- `0.5`: Medium temperature, balanced between conservative and creative\n- `1.0`: High temperature, creative and bit random\n- `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n- `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}",expectFormat:"JSON",dependentParameterNames:["availableModelNames","personaDescription"],resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-27",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
657
+ var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.61.0-29",parameters:[{name:"knowledgeContent",description:"Markdown document content",isInput:true,isOutput:false},{name:"knowledgePieces",description:"The knowledge JSON object",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, extract the important knowledge from the document.\n\n# Rules\n\n- Make pieces of information concise, clear, and easy to understand\n- One piece of information should be approximately 1 paragraph\n- Divide the paragraphs by markdown horizontal lines ---\n- Omit irrelevant information\n- Group redundant information\n- Write just extracted information, nothing else\n\n# The document\n\nTake information from this document:\n\n> {knowledgeContent}",dependentParameterNames:["knowledgeContent"],resultingParameterName:"knowledgePieces"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-29",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-from-markdown.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-keywords.ptbk.md",promptbookVersion:"0.61.0-29",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"keywords",description:"Keywords separated by comma",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced data researcher, detect the important keywords in the document.\n\n# Rules\n\n- Write just keywords separated by comma\n\n# The document\n\nTake information from this document:\n\n> {knowledgePieceContent}",dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"keywords"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-29",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-keywords.ptbk.md"},{title:"Prepare Title",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-title.ptbk.md",promptbookVersion:"0.61.0-29",parameters:[{name:"knowledgePieceContent",description:"The content",isInput:true,isOutput:false},{name:"title",description:"The title of the document",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"knowledge",title:"Knowledge",modelRequirements:{modelVariant:"CHAT",modelName:"claude-3-opus-20240229"},content:"You are experienced content creator, write best title for the document.\n\n# Rules\n\n- Write just title, nothing else\n- Title should be concise and clear\n- Write maximum 5 words for the title\n\n# The document\n\n> {knowledgePieceContent}",expectations:{words:{min:1,max:8}},dependentParameterNames:["knowledgePieceContent"],resultingParameterName:"title"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-29",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-knowledge-title.ptbk.md"},{title:"Prepare Keywords",pipelineUrl:"https://promptbook.studio/promptbook/prepare-persona.ptbk.md",promptbookVersion:"0.61.0-29",parameters:[{name:"availableModelNames",description:"List of available model names separated by comma (,)",isInput:true,isOutput:false},{name:"personaDescription",description:"Description of the persona",isInput:true,isOutput:false},{name:"modelRequirements",description:"Specific requirements for the model",isInput:false,isOutput:true}],promptTemplates:[{blockType:"PROMPT_TEMPLATE",name:"make-model-requirements",title:"Make modelRequirements",modelRequirements:{modelVariant:"CHAT",modelName:"gpt-4-turbo"},content:"You are experienced AI engineer, you need to create virtual assistant.\nWrite\n\n## Sample\n\n```json\n{\n\"modelName\": \"gpt-4o\",\n\"systemMessage\": \"You are experienced AI engineer and helpfull assistant.\",\n\"temperature\": 0.7\n}\n```\n\n## Instructions\n\n### Option `modelName`\n\nPick from the following models:\n\n- {availableModelNames}\n\n### Option `systemMessage`\n\nThe system message is used to communicate instructions or provide context to the model at the beginning of a conversation. It is displayed in a different format compared to user messages, helping the model understand its role in the conversation. The system message typically guides the model's behavior, sets the tone, or specifies desired output from the model. By utilizing the system message effectively, users can steer the model towards generating more accurate and relevant responses.\n\nFor example:\n\n> You are an experienced AI engineer and helpful assistant.\n\n> You are a friendly and knowledgeable chatbot.\n\n### Option `temperature`\n\nThe sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.\n\nYou can pick a value between 0 and 2. For example:\n\n- `0.1`: Low temperature, extremely conservative and deterministic\n- `0.5`: Medium temperature, balanced between conservative and creative\n- `1.0`: High temperature, creative and bit random\n- `1.5`: Very high temperature, extremely creative and often chaotic and unpredictable\n- `2.0`: Maximum temperature, completely random and unpredictable, for some extreme creative use cases\n\n# The assistant\n\nTake this description of the persona:\n\n> {personaDescription}",expectFormat:"JSON",dependentParameterNames:["availableModelNames","personaDescription"],resultingParameterName:"modelRequirements"}],knowledgeSources:[],knowledgePieces:[],personas:[],preparations:[{id:1,promptbookVersion:"0.61.0-29",modelUsage:{price:{value:0},input:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}},output:{tokensCount:{value:0},charactersCount:{value:0},wordsCount:{value:0},sentencesCount:{value:0},linesCount:{value:0},paragraphsCount:{value:0},pagesCount:{value:0}}}}],sourceFile:"./promptbook-collection/prepare-persona.ptbk.md"}];
658
658
 
659
659
  /**
660
660
  * This error indicates that the promptbook in a markdown format cannot be parsed into a valid promptbook object
@@ -2268,7 +2268,7 @@ function union() {
2268
2268
  /**
2269
2269
  * The version of the Promptbook library
2270
2270
  */
2271
- var PROMPTBOOK_VERSION = '0.61.0-27';
2271
+ var PROMPTBOOK_VERSION = '0.61.0-29';
2272
2272
  // TODO: !!!! List here all the versions and annotate + put into script
2273
2273
 
2274
2274
  /**
@@ -2389,17 +2389,16 @@ function checkExpectations(expectations, value) {
2389
2389
  */
2390
2390
  function createPipelineExecutor(options) {
2391
2391
  var _this = this;
2392
- var rawPipeline = options.pipeline, tools = options.tools, _a = options.settings, settings = _a === void 0 ? {} : _a;
2393
- var _b = settings.maxExecutionAttempts, maxExecutionAttempts = _b === void 0 ? MAX_EXECUTION_ATTEMPTS : _b, _c = settings.maxParallelCount, maxParallelCount = _c === void 0 ? MAX_PARALLEL_COUNT : _c, _d = settings.isVerbose, isVerbose = _d === void 0 ? false : _d;
2394
- validatePipeline(rawPipeline);
2392
+ var pipeline = options.pipeline, tools = options.tools, _a = options.settings, settings = _a === void 0 ? {} : _a;
2393
+ var _b = settings.maxExecutionAttempts, maxExecutionAttempts = _b === void 0 ? MAX_EXECUTION_ATTEMPTS : _b, _c = settings.maxParallelCount, maxParallelCount = _c === void 0 ? MAX_PARALLEL_COUNT : _c, _d = settings.isVerbose, isVerbose = _d === void 0 ? false : _d, _e = settings.isNotPreparedWarningSupressed, isNotPreparedWarningSupressed = _e === void 0 ? false : _e;
2394
+ validatePipeline(pipeline);
2395
2395
  var llmTools = joinLlmExecutionTools.apply(void 0, __spreadArray([], __read(arrayableToArray(tools.llm)), false));
2396
- var pipeline;
2397
- if (isPipelinePrepared(rawPipeline)) {
2398
- pipeline = rawPipeline;
2396
+ var preparedPipeline;
2397
+ if (isPipelinePrepared(pipeline)) {
2398
+ preparedPipeline = pipeline;
2399
2399
  }
2400
- else {
2401
- // TODO: !!!!! This should be maybe warning in report
2402
- console.warn(spaceTrim$1("\n Pipeline ".concat(rawPipeline.pipelineUrl || rawPipeline.sourceFile || rawPipeline.title, " is not prepared\n\n ").concat(rawPipeline.sourceFile, "\n\n It will be prepared ad-hoc before the first execution\n But it is recommended to prepare the pipeline during collection preparation\n\n @see more at https://ptbk.io/prepare-pipeline\n ")));
2400
+ else if (isNotPreparedWarningSupressed !== true) {
2401
+ console.warn(spaceTrim$1("\n Pipeline ".concat(pipeline.pipelineUrl || pipeline.sourceFile || pipeline.title, " is not prepared\n\n ").concat(pipeline.sourceFile, "\n\n It will be prepared ad-hoc before the first execution and **returned as `preparedPipeline` in `PipelineExecutorResult`**\n But it is recommended to prepare the pipeline during collection preparation\n\n @see more at https://ptbk.io/prepare-pipeline\n ")));
2403
2402
  }
2404
2403
  var pipelineExecutor = function (inputParameters, onProgress) { return __awaiter(_this, void 0, void 0, function () {
2405
2404
  // TODO: !!! Extract to separate functions and files - ALL FUNCTIONS BELOW
@@ -2416,9 +2415,9 @@ function createPipelineExecutor(options) {
2416
2415
  template) {
2417
2416
  return __awaiter(this, void 0, void 0, function () {
2418
2417
  return __generator(this, function (_a) {
2419
- // TODO: [♨] Implement Better - use real index and keyword search
2418
+ // TODO: [♨] Implement Better - use real index and keyword search from `template` and {samples}
2420
2419
  TODO_USE(template);
2421
- return [2 /*return*/, pipeline.knowledgePieces.map(function (_a) {
2420
+ return [2 /*return*/, preparedPipeline.knowledgePieces.map(function (_a) {
2422
2421
  var content = _a.content;
2423
2422
  return "- ".concat(content);
2424
2423
  }).join('\n')];
@@ -2491,7 +2490,7 @@ function createPipelineExecutor(options) {
2491
2490
  case 0:
2492
2491
  name = "pipeline-executor-frame-".concat(currentTemplate.name);
2493
2492
  title = currentTemplate.title;
2494
- priority = pipeline.promptTemplates.length - pipeline.promptTemplates.indexOf(currentTemplate);
2493
+ priority = preparedPipeline.promptTemplates.length - preparedPipeline.promptTemplates.indexOf(currentTemplate);
2495
2494
  if (!onProgress /* <- [3] */) return [3 /*break*/, 2]; /* <- [3] */
2496
2495
  return [4 /*yield*/, onProgress({
2497
2496
  name: name,
@@ -2595,13 +2594,13 @@ function createPipelineExecutor(options) {
2595
2594
  case 7:
2596
2595
  prompt = {
2597
2596
  title: currentTemplate.title,
2598
- pipelineUrl: "".concat(pipeline.pipelineUrl
2599
- ? pipeline.pipelineUrl
2597
+ pipelineUrl: "".concat(preparedPipeline.pipelineUrl
2598
+ ? preparedPipeline.pipelineUrl
2600
2599
  : 'anonymous' /* <- TODO: [🧠] How to deal with anonymous pipelines, do here some auto-url like SHA-256 based ad-hoc identifier? */, "#").concat(currentTemplate.name),
2601
2600
  parameters: parameters,
2602
2601
  content: preparedContent,
2603
2602
  modelRequirements: currentTemplate.modelRequirements,
2604
- expectations: __assign(__assign({}, (pipeline.personas.find(function (_a) {
2603
+ expectations: __assign(__assign({}, (preparedPipeline.personas.find(function (_a) {
2605
2604
  var name = _a.name;
2606
2605
  return name === currentTemplate.personaName;
2607
2606
  }) || {})), currentTemplate.expectations),
@@ -2893,7 +2892,7 @@ function createPipelineExecutor(options) {
2893
2892
  ) {
2894
2893
  // TODO: [🧠] Maybe put other blockTypes into report
2895
2894
  executionReport.promptExecutions.push({
2896
- prompt: __assign(__assign({ '!!! All information': null }, prompt), { '!!! Wanted information': null, title: currentTemplate.title /* <- Note: If title in pipeline contains emojis, pass it innto report */, content: prompt.content, modelRequirements: prompt.modelRequirements, expectations: prompt.expectations, expectFormat: prompt.expectFormat }),
2895
+ prompt: __assign({}, prompt),
2897
2896
  result: result || undefined,
2898
2897
  error: expectError || undefined,
2899
2898
  });
@@ -2934,7 +2933,7 @@ function createPipelineExecutor(options) {
2934
2933
  var outputParameters = {};
2935
2934
  try {
2936
2935
  // Note: Filter ONLY output parameters
2937
- for (var _b = __values(pipeline.parameters.filter(function (_a) {
2936
+ for (var _b = __values(preparedPipeline.parameters.filter(function (_a) {
2938
2937
  var isOutput = _a.isOutput;
2939
2938
  return isOutput;
2940
2939
  })), _c = _b.next(); !_c.done; _c = _b.next()) {
@@ -2961,29 +2960,29 @@ function createPipelineExecutor(options) {
2961
2960
  return __generator(this, function (_g) {
2962
2961
  switch (_g.label) {
2963
2962
  case 0:
2964
- if (!(pipeline === undefined)) return [3 /*break*/, 2];
2965
- return [4 /*yield*/, preparePipeline(rawPipeline, {
2963
+ if (!(preparedPipeline === undefined)) return [3 /*break*/, 2];
2964
+ return [4 /*yield*/, preparePipeline(pipeline, {
2966
2965
  llmTools: llmTools,
2967
2966
  isVerbose: isVerbose,
2968
2967
  maxParallelCount: maxParallelCount,
2969
2968
  })];
2970
2969
  case 1:
2971
- pipeline = _g.sent();
2970
+ preparedPipeline = _g.sent();
2972
2971
  _g.label = 2;
2973
2972
  case 2:
2974
2973
  errors = [];
2975
2974
  warnings = [];
2976
2975
  executionReport = {
2977
- pipelineUrl: pipeline.pipelineUrl,
2978
- title: pipeline.title,
2976
+ pipelineUrl: preparedPipeline.pipelineUrl,
2977
+ title: preparedPipeline.title,
2979
2978
  promptbookUsedVersion: PROMPTBOOK_VERSION,
2980
- promptbookRequestedVersion: pipeline.promptbookVersion,
2981
- description: pipeline.description,
2979
+ promptbookRequestedVersion: preparedPipeline.promptbookVersion,
2980
+ description: preparedPipeline.description,
2982
2981
  promptExecutions: [],
2983
2982
  };
2984
2983
  try {
2985
2984
  // Note: Check that all input input parameters are defined
2986
- for (_a = __values(pipeline.parameters.filter(function (_a) {
2985
+ for (_a = __values(preparedPipeline.parameters.filter(function (_a) {
2987
2986
  var isInput = _a.isInput;
2988
2987
  return isInput;
2989
2988
  })), _b = _a.next(); !_b.done; _b = _a.next()) {
@@ -2998,6 +2997,7 @@ function createPipelineExecutor(options) {
2998
2997
  executionReport: executionReport,
2999
2998
  outputParameters: {},
3000
2999
  usage: ZERO_USAGE,
3000
+ preparedPipeline: preparedPipeline,
3001
3001
  })];
3002
3002
  }
3003
3003
  }
@@ -3010,7 +3010,7 @@ function createPipelineExecutor(options) {
3010
3010
  finally { if (e_1) throw e_1.error; }
3011
3011
  }
3012
3012
  _loop_1 = function (parameterName) {
3013
- var parameter = pipeline.parameters.find(function (_a) {
3013
+ var parameter = preparedPipeline.parameters.find(function (_a) {
3014
3014
  var name = _a.name;
3015
3015
  return name === parameterName;
3016
3016
  });
@@ -3027,6 +3027,7 @@ function createPipelineExecutor(options) {
3027
3027
  executionReport: executionReport,
3028
3028
  outputParameters: {},
3029
3029
  usage: ZERO_USAGE,
3030
+ preparedPipeline: preparedPipeline,
3030
3031
  }) };
3031
3032
  }
3032
3033
  };
@@ -3050,7 +3051,7 @@ function createPipelineExecutor(options) {
3050
3051
  _g.label = 3;
3051
3052
  case 3:
3052
3053
  _g.trys.push([3, 8, , 9]);
3053
- resovedParameterNames_1 = pipeline.parameters
3054
+ resovedParameterNames_1 = preparedPipeline.parameters
3054
3055
  .filter(function (_a) {
3055
3056
  var isInput = _a.isInput;
3056
3057
  return isInput;
@@ -3059,7 +3060,7 @@ function createPipelineExecutor(options) {
3059
3060
  var name = _a.name;
3060
3061
  return name;
3061
3062
  });
3062
- unresovedTemplates_1 = __spreadArray([], __read(pipeline.promptTemplates), false);
3063
+ unresovedTemplates_1 = __spreadArray([], __read(preparedPipeline.promptTemplates), false);
3063
3064
  resolving_1 = [];
3064
3065
  loopLimit = LOOP_LIMIT;
3065
3066
  _loop_2 = function () {
@@ -3136,6 +3137,7 @@ function createPipelineExecutor(options) {
3136
3137
  usage: usage_1,
3137
3138
  executionReport: executionReport,
3138
3139
  outputParameters: outputParameters_1,
3140
+ preparedPipeline: preparedPipeline,
3139
3141
  })];
3140
3142
  case 9:
3141
3143
  usage = addUsage.apply(void 0, __spreadArray([], __read(executionReport.promptExecutions.map(function (_a) {
@@ -3150,6 +3152,7 @@ function createPipelineExecutor(options) {
3150
3152
  usage: usage,
3151
3153
  executionReport: executionReport,
3152
3154
  outputParameters: outputParameters,
3155
+ preparedPipeline: preparedPipeline,
3153
3156
  })];
3154
3157
  }
3155
3158
  });
@@ -3157,8 +3160,6 @@ function createPipelineExecutor(options) {
3157
3160
  return pipelineExecutor;
3158
3161
  }
3159
3162
  /**
3160
- * TODO: !!!!! return `preparedPipeline` from execution
3161
- * TODO: !!!!! `isNotPreparedWarningSupressed`
3162
3163
  * TODO: Use isVerbose here (not only pass to `preparePipeline`)
3163
3164
  * TODO: [🪂] Use maxParallelCount here (not only pass to `preparePipeline`)
3164
3165
  * TODO: [♈] Probbably move expectations from templates to parameters
@@ -3218,6 +3219,7 @@ function prepareKnowledgeFromMarkdown(knowledgeContent /* <- TODO: [🖖] (?mayb
3218
3219
  outputParameters = result.outputParameters;
3219
3220
  knowledgePiecesRaw = outputParameters.knowledgePieces;
3220
3221
  knowledgeTextPieces = (knowledgePiecesRaw || '').split('\n---\n');
3222
+ // <- TODO: !!!!! Smarter split and filter out empty pieces
3221
3223
  if (isVerbose) {
3222
3224
  console.info('knowledgeTextPieces:', knowledgeTextPieces);
3223
3225
  }