@promptbook/core 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
@@ -1517,7 +1517,7 @@ function forEachAsync(array, options, callbackfunction) {
1517
1517
  });
1518
1518
  }
1519
1519
 
1520
- 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"}];
1520
+ 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"}];
1521
1521
 
1522
1522
  var defaultDiacriticsRemovalMap = [
1523
1523
  {
@@ -2522,7 +2522,7 @@ function union() {
2522
2522
  /**
2523
2523
  * The version of the Promptbook library
2524
2524
  */
2525
- var PROMPTBOOK_VERSION = '0.61.0-27';
2525
+ var PROMPTBOOK_VERSION = '0.61.0-29';
2526
2526
  // TODO: !!!! List here all the versions and annotate + put into script
2527
2527
 
2528
2528
  /**
@@ -2664,17 +2664,16 @@ function isPassingExpectations(expectations, value) {
2664
2664
  */
2665
2665
  function createPipelineExecutor(options) {
2666
2666
  var _this = this;
2667
- var rawPipeline = options.pipeline, tools = options.tools, _a = options.settings, settings = _a === void 0 ? {} : _a;
2668
- 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;
2669
- validatePipeline(rawPipeline);
2667
+ var pipeline = options.pipeline, tools = options.tools, _a = options.settings, settings = _a === void 0 ? {} : _a;
2668
+ 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;
2669
+ validatePipeline(pipeline);
2670
2670
  var llmTools = joinLlmExecutionTools.apply(void 0, __spreadArray([], __read(arrayableToArray(tools.llm)), false));
2671
- var pipeline;
2672
- if (isPipelinePrepared(rawPipeline)) {
2673
- pipeline = rawPipeline;
2671
+ var preparedPipeline;
2672
+ if (isPipelinePrepared(pipeline)) {
2673
+ preparedPipeline = pipeline;
2674
2674
  }
2675
- else {
2676
- // TODO: !!!!! This should be maybe warning in report
2677
- 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 ")));
2675
+ else if (isNotPreparedWarningSupressed !== true) {
2676
+ 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 ")));
2678
2677
  }
2679
2678
  var pipelineExecutor = function (inputParameters, onProgress) { return __awaiter(_this, void 0, void 0, function () {
2680
2679
  // TODO: !!! Extract to separate functions and files - ALL FUNCTIONS BELOW
@@ -2691,9 +2690,9 @@ function createPipelineExecutor(options) {
2691
2690
  template) {
2692
2691
  return __awaiter(this, void 0, void 0, function () {
2693
2692
  return __generator(this, function (_a) {
2694
- // TODO: [♨] Implement Better - use real index and keyword search
2693
+ // TODO: [♨] Implement Better - use real index and keyword search from `template` and {samples}
2695
2694
  TODO_USE(template);
2696
- return [2 /*return*/, pipeline.knowledgePieces.map(function (_a) {
2695
+ return [2 /*return*/, preparedPipeline.knowledgePieces.map(function (_a) {
2697
2696
  var content = _a.content;
2698
2697
  return "- ".concat(content);
2699
2698
  }).join('\n')];
@@ -2766,7 +2765,7 @@ function createPipelineExecutor(options) {
2766
2765
  case 0:
2767
2766
  name = "pipeline-executor-frame-".concat(currentTemplate.name);
2768
2767
  title = currentTemplate.title;
2769
- priority = pipeline.promptTemplates.length - pipeline.promptTemplates.indexOf(currentTemplate);
2768
+ priority = preparedPipeline.promptTemplates.length - preparedPipeline.promptTemplates.indexOf(currentTemplate);
2770
2769
  if (!onProgress /* <- [3] */) return [3 /*break*/, 2]; /* <- [3] */
2771
2770
  return [4 /*yield*/, onProgress({
2772
2771
  name: name,
@@ -2870,13 +2869,13 @@ function createPipelineExecutor(options) {
2870
2869
  case 7:
2871
2870
  prompt = {
2872
2871
  title: currentTemplate.title,
2873
- pipelineUrl: "".concat(pipeline.pipelineUrl
2874
- ? pipeline.pipelineUrl
2872
+ pipelineUrl: "".concat(preparedPipeline.pipelineUrl
2873
+ ? preparedPipeline.pipelineUrl
2875
2874
  : 'anonymous' /* <- TODO: [🧠] How to deal with anonymous pipelines, do here some auto-url like SHA-256 based ad-hoc identifier? */, "#").concat(currentTemplate.name),
2876
2875
  parameters: parameters,
2877
2876
  content: preparedContent,
2878
2877
  modelRequirements: currentTemplate.modelRequirements,
2879
- expectations: __assign(__assign({}, (pipeline.personas.find(function (_a) {
2878
+ expectations: __assign(__assign({}, (preparedPipeline.personas.find(function (_a) {
2880
2879
  var name = _a.name;
2881
2880
  return name === currentTemplate.personaName;
2882
2881
  }) || {})), currentTemplate.expectations),
@@ -3168,7 +3167,7 @@ function createPipelineExecutor(options) {
3168
3167
  ) {
3169
3168
  // TODO: [🧠] Maybe put other blockTypes into report
3170
3169
  executionReport.promptExecutions.push({
3171
- 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 }),
3170
+ prompt: __assign({}, prompt),
3172
3171
  result: result || undefined,
3173
3172
  error: expectError || undefined,
3174
3173
  });
@@ -3209,7 +3208,7 @@ function createPipelineExecutor(options) {
3209
3208
  var outputParameters = {};
3210
3209
  try {
3211
3210
  // Note: Filter ONLY output parameters
3212
- for (var _b = __values(pipeline.parameters.filter(function (_a) {
3211
+ for (var _b = __values(preparedPipeline.parameters.filter(function (_a) {
3213
3212
  var isOutput = _a.isOutput;
3214
3213
  return isOutput;
3215
3214
  })), _c = _b.next(); !_c.done; _c = _b.next()) {
@@ -3236,29 +3235,29 @@ function createPipelineExecutor(options) {
3236
3235
  return __generator(this, function (_g) {
3237
3236
  switch (_g.label) {
3238
3237
  case 0:
3239
- if (!(pipeline === undefined)) return [3 /*break*/, 2];
3240
- return [4 /*yield*/, preparePipeline(rawPipeline, {
3238
+ if (!(preparedPipeline === undefined)) return [3 /*break*/, 2];
3239
+ return [4 /*yield*/, preparePipeline(pipeline, {
3241
3240
  llmTools: llmTools,
3242
3241
  isVerbose: isVerbose,
3243
3242
  maxParallelCount: maxParallelCount,
3244
3243
  })];
3245
3244
  case 1:
3246
- pipeline = _g.sent();
3245
+ preparedPipeline = _g.sent();
3247
3246
  _g.label = 2;
3248
3247
  case 2:
3249
3248
  errors = [];
3250
3249
  warnings = [];
3251
3250
  executionReport = {
3252
- pipelineUrl: pipeline.pipelineUrl,
3253
- title: pipeline.title,
3251
+ pipelineUrl: preparedPipeline.pipelineUrl,
3252
+ title: preparedPipeline.title,
3254
3253
  promptbookUsedVersion: PROMPTBOOK_VERSION,
3255
- promptbookRequestedVersion: pipeline.promptbookVersion,
3256
- description: pipeline.description,
3254
+ promptbookRequestedVersion: preparedPipeline.promptbookVersion,
3255
+ description: preparedPipeline.description,
3257
3256
  promptExecutions: [],
3258
3257
  };
3259
3258
  try {
3260
3259
  // Note: Check that all input input parameters are defined
3261
- for (_a = __values(pipeline.parameters.filter(function (_a) {
3260
+ for (_a = __values(preparedPipeline.parameters.filter(function (_a) {
3262
3261
  var isInput = _a.isInput;
3263
3262
  return isInput;
3264
3263
  })), _b = _a.next(); !_b.done; _b = _a.next()) {
@@ -3273,6 +3272,7 @@ function createPipelineExecutor(options) {
3273
3272
  executionReport: executionReport,
3274
3273
  outputParameters: {},
3275
3274
  usage: ZERO_USAGE,
3275
+ preparedPipeline: preparedPipeline,
3276
3276
  })];
3277
3277
  }
3278
3278
  }
@@ -3285,7 +3285,7 @@ function createPipelineExecutor(options) {
3285
3285
  finally { if (e_1) throw e_1.error; }
3286
3286
  }
3287
3287
  _loop_1 = function (parameterName) {
3288
- var parameter = pipeline.parameters.find(function (_a) {
3288
+ var parameter = preparedPipeline.parameters.find(function (_a) {
3289
3289
  var name = _a.name;
3290
3290
  return name === parameterName;
3291
3291
  });
@@ -3302,6 +3302,7 @@ function createPipelineExecutor(options) {
3302
3302
  executionReport: executionReport,
3303
3303
  outputParameters: {},
3304
3304
  usage: ZERO_USAGE,
3305
+ preparedPipeline: preparedPipeline,
3305
3306
  }) };
3306
3307
  }
3307
3308
  };
@@ -3325,7 +3326,7 @@ function createPipelineExecutor(options) {
3325
3326
  _g.label = 3;
3326
3327
  case 3:
3327
3328
  _g.trys.push([3, 8, , 9]);
3328
- resovedParameterNames_1 = pipeline.parameters
3329
+ resovedParameterNames_1 = preparedPipeline.parameters
3329
3330
  .filter(function (_a) {
3330
3331
  var isInput = _a.isInput;
3331
3332
  return isInput;
@@ -3334,7 +3335,7 @@ function createPipelineExecutor(options) {
3334
3335
  var name = _a.name;
3335
3336
  return name;
3336
3337
  });
3337
- unresovedTemplates_1 = __spreadArray([], __read(pipeline.promptTemplates), false);
3338
+ unresovedTemplates_1 = __spreadArray([], __read(preparedPipeline.promptTemplates), false);
3338
3339
  resolving_1 = [];
3339
3340
  loopLimit = LOOP_LIMIT;
3340
3341
  _loop_2 = function () {
@@ -3411,6 +3412,7 @@ function createPipelineExecutor(options) {
3411
3412
  usage: usage_1,
3412
3413
  executionReport: executionReport,
3413
3414
  outputParameters: outputParameters_1,
3415
+ preparedPipeline: preparedPipeline,
3414
3416
  })];
3415
3417
  case 9:
3416
3418
  usage = addUsage.apply(void 0, __spreadArray([], __read(executionReport.promptExecutions.map(function (_a) {
@@ -3425,6 +3427,7 @@ function createPipelineExecutor(options) {
3425
3427
  usage: usage,
3426
3428
  executionReport: executionReport,
3427
3429
  outputParameters: outputParameters,
3430
+ preparedPipeline: preparedPipeline,
3428
3431
  })];
3429
3432
  }
3430
3433
  });
@@ -3432,8 +3435,6 @@ function createPipelineExecutor(options) {
3432
3435
  return pipelineExecutor;
3433
3436
  }
3434
3437
  /**
3435
- * TODO: !!!!! return `preparedPipeline` from execution
3436
- * TODO: !!!!! `isNotPreparedWarningSupressed`
3437
3438
  * TODO: Use isVerbose here (not only pass to `preparePipeline`)
3438
3439
  * TODO: [🪂] Use maxParallelCount here (not only pass to `preparePipeline`)
3439
3440
  * TODO: [♈] Probbably move expectations from templates to parameters
@@ -3493,6 +3494,7 @@ function prepareKnowledgeFromMarkdown(knowledgeContent /* <- TODO: [🖖] (?mayb
3493
3494
  outputParameters = result.outputParameters;
3494
3495
  knowledgePiecesRaw = outputParameters.knowledgePieces;
3495
3496
  knowledgeTextPieces = (knowledgePiecesRaw || '').split('\n---\n');
3497
+ // <- TODO: !!!!! Smarter split and filter out empty pieces
3496
3498
  if (isVerbose) {
3497
3499
  console.info('knowledgeTextPieces:', knowledgeTextPieces);
3498
3500
  }