@promptbook/core 0.61.0 → 0.62.0-1

package/esm/index.es.js

@@ -387,7 +387,8 @@ function promptTemplateParameterJsonToString(promptTemplateParameterJson) {
 /**
  * TODO: !!!! Implement new features and commands into `promptTemplateParameterJsonToString`
  * TODO: [🧠] Is there a way to auto-detect missing features in pipelineJsonToString
- * TODO: Escape all
+ * TODO: [🏛] Maybe make some markdown builder
+ * TODO: [🏛] Escape all
  */
 
 /**
@@ -1517,7 +1518,7 @@ function forEachAsync(array, options, callbackfunction) {
     });
 }
 
-var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.61.0-30",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:"0.61.0-30",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:"0.61.0-30",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:"0.61.0-30",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:"0.61.0-30",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:"0.61.0-30",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:"0.61.0-30",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:"0.61.0-30",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"}];
+var PipelineCollection = [{title:"Prepare Knowledge from Markdown",pipelineUrl:"https://promptbook.studio/promptbook/prepare-knowledge-from-markdown.ptbk.md",promptbookVersion:"0.62.0-0",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:"0.62.0-0",usage:{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:"0.62.0-0",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:"0.62.0-0",usage:{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:"0.62.0-0",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:"0.62.0-0",usage:{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:"0.62.0-0",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:"0.62.0-0",usage:{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"}];
 
 var defaultDiacriticsRemovalMap = [
     {
@@ -2287,6 +2288,9 @@ function joinLlmExecutionTools() {
     }
     return new (MultipleLlmExecutionTools.bind.apply(MultipleLlmExecutionTools, __spreadArray([void 0], __read(llmExecutionTools), false)))();
 }
+/**
+ * TODO: [👷‍♂️] @@@ Manual about construction of llmTools
+ */
 
 /**
  * Determine if the pipeline is fully prepared
@@ -2522,7 +2526,7 @@ function union() {
 /**
  * The version of the Promptbook library
  */
-var PROMPTBOOK_VERSION = '0.61.0-30';
+var PROMPTBOOK_VERSION = '0.62.0-0';
 // TODO: !!!! List here all the versions and annotate + put into script
 
 /**
@@ -3436,6 +3440,7 @@ function createPipelineExecutor(options) {
 }
 /**
  * TODO: Use isVerbose here (not only pass to `preparePipeline`)
+ * TODO: [🧠] Use here `countTotalUsage` and put preparation and prepared pipiline to report
  * TODO: [🪂] Use maxParallelCount here (not only pass to `preparePipeline`)
  * TODO: [♈] Probbably move expectations from templates to parameters
  * TODO: [🧠] When not meet expectations in PROMPT_DIALOG, make some way to tell the user
@@ -3644,6 +3649,86 @@ TODO: [🧊] This is how it can look in future
  *       [ ] One piece can have multiple sources
  */
 
+/**
+ * Intercepts LLM tools and counts total usage of the tools
+ *
+ * @param llmTools LLM tools to be intercepted with usage counting
+ * @returns LLM tools with same functionality with added total cost counting
+ */
+function countTotalUsage(llmTools) {
+    var _this = this;
+    var totalUsage = ZERO_USAGE;
+    var proxyTools = {
+        get title() {
+            // TODO: [🧠] Maybe put here some suffix
+            return llmTools.title;
+        },
+        get description() {
+            // TODO: [🧠] Maybe put here some suffix
+            return llmTools.description;
+        },
+        listModels: function () {
+            return /* not await */ llmTools.listModels();
+        },
+        getTotalUsage: function () {
+            // <- Note: [🥫] Not using getter `get totalUsage` but `getTotalUsage` to allow this object to be proxied
+            return totalUsage;
+        },
+    };
+    if (llmTools.callChatModel !== undefined) {
+        proxyTools.callChatModel = function (prompt) { return __awaiter(_this, void 0, void 0, function () {
+            var promptResult;
+            return __generator(this, function (_a) {
+                switch (_a.label) {
+                    case 0: return [4 /*yield*/, llmTools.callChatModel(prompt)];
+                    case 1:
+                        promptResult = _a.sent();
+                        totalUsage = addUsage(totalUsage, promptResult.usage);
+                        return [2 /*return*/, promptResult];
+                }
+            });
+        }); };
+    }
+    if (llmTools.callCompletionModel !== undefined) {
+        proxyTools.callCompletionModel = function (prompt) { return __awaiter(_this, void 0, void 0, function () {
+            var promptResult;
+            return __generator(this, function (_a) {
+                switch (_a.label) {
+                    case 0: return [4 /*yield*/, llmTools.callCompletionModel(prompt)];
+                    case 1:
+                        promptResult = _a.sent();
+                        totalUsage = addUsage(totalUsage, promptResult.usage);
+                        return [2 /*return*/, promptResult];
+                }
+            });
+        }); };
+    }
+    if (llmTools.callEmbeddingModel !== undefined) {
+        proxyTools.callEmbeddingModel = function (prompt) { return __awaiter(_this, void 0, void 0, function () {
+            var promptResult;
+            return __generator(this, function (_a) {
+                switch (_a.label) {
+                    case 0: return [4 /*yield*/, llmTools.callEmbeddingModel(prompt)];
+                    case 1:
+                        promptResult = _a.sent();
+                        totalUsage = addUsage(totalUsage, promptResult.usage);
+                        return [2 /*return*/, promptResult];
+                }
+            });
+        }); };
+    }
+    // <- Note: [🤖]
+    return proxyTools;
+}
+/**
+ * TODO: [🔼] !!! Export via `@promptbookcore/`
+ * TODO: [🧠][💸] Maybe make some common abstraction `interceptLlmTools` and use here (or use javascript Proxy?)
+ * TODO: [🧠] Is there some meaningfull way how to test this util
+ * TODO: [🧠][🌯] Maybe a way how to hide ability to `get totalUsage`
+ *     > const [llmToolsWithUsage,getUsage] = countTotalUsage(llmTools);
+ * TODO: [👷‍♂️] @@@ Manual about construction of llmTools
+ */
+
 /**
  * Prepares the persona for the pipeline
  *
@@ -3767,23 +3852,24 @@ function prepareTemplates(pipeline, options) {
  */
 function preparePipeline(pipeline, options) {
     return __awaiter(this, void 0, void 0, function () {
-        var _a, maxParallelCount, parameters, promptTemplates, 
+        var llmTools, _a, maxParallelCount, _b, isVerbose, parameters, promptTemplates, 
         /*
         <- TODO: [🧠][0] `promptbookVersion` */
         knowledgeSources /*
         <- TODO: [🧊] `knowledgePieces` */, personas /*
-        <- TODO: [🧊] `preparations` */, currentPreparation, preparations, preparedPersonas, knowledgeSourcesPrepared, partialknowledgePiecesPrepared, knowledgePiecesPrepared, promptTemplatesPrepared /* TODO: parameters: parametersPrepared*/;
+        <- TODO: [🧊] `preparations` */, llmToolsWithUsage, currentPreparation, preparations, preparedPersonas, knowledgeSourcesPrepared, partialknowledgePiecesPrepared, knowledgePiecesPrepared, promptTemplatesPrepared /* TODO: parameters: parametersPrepared*/;
         var _this = this;
-        return __generator(this, function (_b) {
-            switch (_b.label) {
+        return __generator(this, function (_c) {
+            switch (_c.label) {
                 case 0:
-                    _a = options.maxParallelCount, maxParallelCount = _a === void 0 ? MAX_PARALLEL_COUNT : _a;
+                    llmTools = options.llmTools, _a = options.maxParallelCount, maxParallelCount = _a === void 0 ? MAX_PARALLEL_COUNT : _a, _b = options.isVerbose, isVerbose = _b === void 0 ? false : _b;
                     parameters = pipeline.parameters, promptTemplates = pipeline.promptTemplates, knowledgeSources = pipeline.knowledgeSources, personas = pipeline.personas;
+                    llmToolsWithUsage = countTotalUsage(llmTools);
                     currentPreparation = {
                         id: 1,
                         // TODO: [🍥]> date: $currentDate(),
                         promptbookVersion: PROMPTBOOK_VERSION,
-                        modelUsage: ZERO_USAGE,
+                        usage: ZERO_USAGE,
                     };
                     preparations = [
                         // ...preparations
@@ -3795,7 +3881,11 @@ function preparePipeline(pipeline, options) {
                             var modelRequirements, preparedPersona;
                             return __generator(this, function (_a) {
                                 switch (_a.label) {
-                                    case 0: return [4 /*yield*/, preparePersona(persona.description, options)];
+                                    case 0: return [4 /*yield*/, preparePersona(persona.description, {
+                                            llmTools: llmToolsWithUsage,
+                                            maxParallelCount: maxParallelCount /* <- TODO:  [🪂] */,
+                                            isVerbose: isVerbose,
+                                        })];
                                     case 1:
                                         modelRequirements = _a.sent();
                                         preparedPersona = __assign(__assign({}, persona), { modelRequirements: modelRequirements, preparationIds: [/* TODO: [🧊] -> */ currentPreparation.id] });
@@ -3805,20 +3895,30 @@ function preparePipeline(pipeline, options) {
                             });
                         }); })];
                 case 1:
-                    _b.sent();
+                    _c.sent();
                     knowledgeSourcesPrepared = knowledgeSources.map(function (source) { return (__assign(__assign({}, source), { preparationIds: [/* TODO: [🧊] -> */ currentPreparation.id] })); });
-                    return [4 /*yield*/, prepareKnowledgePieces(knowledgeSources /* <- TODO: [🧊] {knowledgeSources, knowledgePieces} */, options)];
+                    return [4 /*yield*/, prepareKnowledgePieces(knowledgeSources /* <- TODO: [🧊] {knowledgeSources, knowledgePieces} */, {
+                            llmTools: llmToolsWithUsage,
+                            maxParallelCount: maxParallelCount /* <- TODO:  [🪂] */,
+                            isVerbose: isVerbose,
+                        })];
                 case 2:
-                    partialknowledgePiecesPrepared = _b.sent();
+                    partialknowledgePiecesPrepared = _c.sent();
                     knowledgePiecesPrepared = partialknowledgePiecesPrepared.map(function (piece) { return (__assign(__assign({}, piece), { preparationIds: [/* TODO: [🧊] -> */ currentPreparation.id] })); });
                     return [4 /*yield*/, prepareTemplates({
                             parameters: parameters,
                             promptTemplates: promptTemplates,
                             knowledgePiecesCount: knowledgePiecesPrepared.length,
-                        }, options)];
+                        }, {
+                            llmTools: llmToolsWithUsage,
+                            maxParallelCount: maxParallelCount /* <- TODO:  [🪂] */,
+                            isVerbose: isVerbose,
+                        })];
                 case 3:
-                    promptTemplatesPrepared = (_b.sent()).promptTemplatesPrepared;
+                    promptTemplatesPrepared = (_c.sent()).promptTemplatesPrepared;
                     // ----- /Templates preparation -----
+                    // Note: Count total usage
+                    currentPreparation.usage = llmToolsWithUsage.getTotalUsage();
                     return [2 /*return*/, __assign(__assign({}, pipeline), { promptTemplates: promptTemplatesPrepared, knowledgeSources: knowledgeSourcesPrepared, knowledgePieces: knowledgePiecesPrepared, personas: preparedPersonas, preparations: preparations })];
             }
         });
@@ -3829,7 +3929,6 @@ function preparePipeline(pipeline, options) {
  * TODO: Write tests for `preparePipeline`
  * TODO: [🏏] Leverage the batch API and build queues @see https://platform.openai.com/docs/guides/batch
  * TODO: [🧊] In future one preparation can take data from previous preparation and save tokens and time
- * TODO: [🎐] !!!!! Use here countTotalUsage
  * TODO: [🛠] Actions, instruments (and maybe knowledge) => Functions and tools
  */
 
@@ -6029,6 +6128,29 @@ function usageToWorktime(usage) {
     return uncertainNumber;
 }
 
+/**
+ * Function `usageToHuman` will take usage and convert it to human readable report
+ */
+function usageToHuman(usage) {
+    var report = 'Usage:';
+    var uncertainNumberToHuman = function (_a) {
+        var value = _a.value, isUncertain = _a.isUncertain;
+        return "".concat(isUncertain ? 'approximately ' : '').concat(Math.round(value * 100) / 100);
+    };
+    report += '\n' + "- Cost ".concat(uncertainNumberToHuman(usage.price), " USD");
+    report += '\n' + "- Saved ".concat(uncertainNumberToHuman(usageToWorktime(usage)), " hours of human time");
+    return spaceTrim(report);
+}
+/**
+ * TODO: Use "$1" not "1 USD"
+ * TODO: Use markdown formatting like "Cost approximately **$1**"
+ * TODO: Report in minutes, seconds, days NOT 0.1 hours
+ * TODO: [🧠] Maybe make from `uncertainNumberToHuman` separate exported utility
+ * TODO: When negligible usage, report "Negligible" or just don't report it
+ * TODO: [🧠] Maybe use "~" instead of "approximately"
+ * TODO: [🏛] Maybe make some markdown builder
+ */
+
 /**
  * Delagates the user interaction to a async callback function
  * You need to provide your own implementation of this callback function and its bind to UI.
@@ -6407,5 +6529,5 @@ function executionReportJsonToString(executionReportJson, options) {
  * TODO: [🧠] Allow to filter out some parts of the report by options
  */
 
-export { BlockTypes, CallbackInterfaceTools, CollectionError, ExecutionReportStringOptionsDefaults, ExpectError, NotFoundError, PROMPTBOOK_VERSION, ParsingError, PipelineExecutionError, PipelineLogicError, RESERVED_PARAMETER_NAMES, ReferenceError$1 as ReferenceError, SimplePromptInterfaceTools, UnexpectedError, VersionMismatchError, addUsage, assertsExecutionSuccessful, checkExpectations, collectionToJson, createCollectionFromJson, createCollectionFromPromise, createCollectionFromUrl, createPipelineExecutor, createSubcollection, embeddingVectorToString, executionReportJsonToString, isPassingExpectations, joinLlmExecutionTools, pipelineJsonToString, pipelineStringToJson, pipelineStringToJsonSync, prepareKnowledgeFromMarkdown, preparePipeline, prettifyPipelineString, stringifyPipelineJson, unpreparePipeline, usageToWorktime, validatePipeline };
+export { BlockTypes, CallbackInterfaceTools, CollectionError, ExecutionReportStringOptionsDefaults, ExpectError, NotFoundError, PROMPTBOOK_VERSION, ParsingError, PipelineExecutionError, PipelineLogicError, RESERVED_PARAMETER_NAMES, ReferenceError$1 as ReferenceError, SimplePromptInterfaceTools, UnexpectedError, VersionMismatchError, addUsage, assertsExecutionSuccessful, checkExpectations, collectionToJson, createCollectionFromJson, createCollectionFromPromise, createCollectionFromUrl, createPipelineExecutor, createSubcollection, embeddingVectorToString, executionReportJsonToString, isPassingExpectations, joinLlmExecutionTools, pipelineJsonToString, pipelineStringToJson, pipelineStringToJsonSync, prepareKnowledgeFromMarkdown, preparePipeline, prettifyPipelineString, stringifyPipelineJson, unpreparePipeline, usageToHuman, usageToWorktime, validatePipeline };
 //# sourceMappingURL=index.es.js.map